id
int64 0
37.9k
| prompt
listlengths 2
2
| completion
listlengths 1
1
| Label
stringclasses 3
values |
|---|---|---|---|
0
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nStarling on the heart. Facsimile reprints including the Linacre Lecture on the Law of the Heart\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
1
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nSwift's half-way house.\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
2
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nA medieval glorification of disease and death.\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
3
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nSome lesser known Irish physicians.\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
4
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe life of Charles Ledger (1818–1905): alpacas and quinine\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
5
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\n\"Matrix and the pain thereof\": a sixteenth-century gynaecological essay.\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
6
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe culture of pain\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
7
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThomas Willis 1621–1675: his life and work\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
8
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nHistory of pain\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
9
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nPancreatic organotherapy for diabetes, 1889-1921.\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
10
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe puzzle of pain\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
11
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe London Lock: a charitable hospital for venereal disease 1746–1952\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
12
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe great pox: the French disease in Renaissance Europe\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
13
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe secret malady: venereal disease in eighteenth-century Britain and France\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
14
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nHistorical aspects of American trypanosomiasis (Chagas' disease)\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
15
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nDeciphering global epidemics: analytical approaches to the disease records of world cities, 1888–1912\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
16
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nIn the land of pain\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
17
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nScience review: Natriuretic peptides in critical illness\n\n**Article Abstract:**\n\nThe present review will cover the mechanisms of release and the potential pathophysiological role of different natriuretic peptides in critically ill patients. By focusing on the cardiovascular system, possible implications of natriuretic peptides for diagnosis and treatment will be presented. In critical illness such as sepsis, trauma or major surgery, systemic hypotension and an intrinsic myocardial dysfunction occur. Impairment of the cardiovascular system contributes to poor prognosis in severe human sepsis. Natriuretic peptides have emerged as valuable marker substances to detect left ventricular dysfunction in congestive heart failure of different origins. Increased plasma levels of circulating natriuretic peptides, atrial natriuretic peptide, N-terminal pro-atrial natriuretic peptide, brain natriuretic peptide and its N-terminal moiety N-terminal pro-brain natriuretic peptide have also been found in critically ill patients. All of these peptides have been reported to reflect left ventricular dysfunction in these patients. The increased wall stress of the cardiac atria and ventricles is followed by the release of these natriuretic peptides. Furthermore, the release of atrial natriuretic peptide and brain natriuretic peptide might be triggered by members of the IL-6-related family and endotoxin in the critically ill. Apart from the vasoactive actions of circulating natriuretic peptides and their broad effects on the renal system, anti-ischemic properties and immunological functions have been reported for atrial natriuretic peptide. The early onset and rapid reversibility of left ventricular impairment in patients with good prognosis associated with a remarkably augmented plasma concentration of circulating natriuretic peptides suggest a possible role of these hormones in the monitoring of therapy success and the estimation of prognosis in the critically ill.\n\n**Article Body:**\n\nIntroduction\nCritical illness, such as sepsis, trauma and major surgery, is accompanied by an activation of the immune system and mediator cells; that is, macrophages elaborating soluble inflammatory products such as cytokines and vasoactive compounds. Acting in a complex network of mediator and cell to cell interactions, inflammatory response in the most severe clinical scenario evolves in multiple organ failure and death [\n1\n]. Sepsis is defined by the presence of an infective agent in combination with typical clinical and laboratory findings of infection [\n2\n], although an infective organism is found in fewer than 50% of cases [\n3\n]. It has been increasingly recognized that sepsis represents only one example of a systemic inflammatory response syndrome (SIRS) that can be triggered not only by infection, but also by noninfective disorders such as trauma or major surgery [\n4\n,\n5\n].\nAdditive therapy strategies could not substantially lower the mortality of sepsis and SIRS during the past 15 years [\n6\n]; mortality remained as high as 30–50%, accounting for at least 225,000 deaths annually alone in the United States [\n7\n,\n8\n]. In a recent large clinical trial, however, recombinant human activated protein C, a compound with anticoagulant and anti-inflammatory properties, has been found to reduce mortality in patients with severe sepsis [\n9\n].\nThe cardiovascular system in sepsis and SIRS\nThe cardiovascular system is a major target in patients with sepsis or SIRS, and depressed functions of this system might directly influence outcome [\n10\n]. Thus, in the 40% of patients with sepsis who develop cardiovascular impairment, mortality rises to 70–90%, a percentage with only marginal changes in recent years [\n11\n]. Peripheral vasodilatation typically manifests as a systemic hypotension, hypo-responsive to pressor agents, and an intrinsic myocardial dysfunction commonly masked by a concomitant elevation in cardiac index can be observed in these patients [\n10\n]. Most severe alterations of the cardiovascular system were frequently seen in patients with septic shock. The mechanisms of myocardial depression in human septic shock involve a complex network of vasoactive, Ca\n2+\n-regulative and inflammatory mediators [\n12\n-\n15\n].\nMyocardial depression and outcome in septic shock\nSurvivors of septic shock were found to have a decreased systolic function to an ejection fraction of about 33% and an increase in left ventricular end-diastolic diameter. These changes are of rapid onset and are reversible in survivors within several days. In contrast, in nonsurvivors a progressive myocardial depression early in the disease course has been observed [\n16\n]. It has further been shown using trans-oesophageal echocardiography that, apart from left ventricular systolic dysfunction, left ventricular diastolic dysfunction may also occur in patients with septic shock [\n17\n]. The significance of diastolic dysfunction in sepsis and septic shock has not yet been elucidated.\nThe natriuretic peptide system\nThe family of natriuretic peptides (NP) comprises at least eight structurally related amino acid peptides stored as three different prohormones: 126 amino acid atrial natriuretic peptide (ANP) prohormone, 108 amino acid brain natriuretic peptide (BNP) prohormone, and 126 amino acid C-type natriuretic peptide (CNP) prohormone [\n18\n].\nThe ANP prohormone is synthesized mainly within the atrial myocytes and in a variety of other tissues [\n19\n]. The prohormone consisting of 126 amino acids contains several peptides with blood pressure lowering properties, natriuretic properties, diuretic properties and/or kaliuretic properties [\n20\n]. These peptide hormones, numbered by their amino acid sequences beginning at the N-terminal end of the ANP prohormone, consist of the first 30 amino acids of the prohormone (i.e. proANP 1–30; long-acting natriuretic peptide), amino acids 31–67 (i.e. proANP 31–67; vessel dilator), amino acids 79–98 (proANP 79–98; kaliuretic peptide) and amino acids 99–126 (ANP) [\n20\n]. The ANP prohormone processing is different within the kidney, resulting in an additional four amino acids added to the N-terminus of ANP (i.e. proANP 95–126; urodilatin) [\n21\n].\nBNP, so named because of its initial isolation from the porcine brain [\n22\n], has subsequently shown to be 10-fold more abundant in the heart than in the brain [\n23\n]. BNP is processed within the human heart to form 32 amino acid BNP, consisting of amino acids 77–108 of its 108 amino acid prohormone, and an N-terminal proBNP peptide (amino acids 1–76; NT-proBNP), both of which circulate in humans [\n24\n].\nCNP was originally found in the brain [\n25\n] and has been subsequently suggested to be present also within the heart [\n26\n]. In fact, CNP has been detected in human coronary arteries [\n27\n] and in the peripheral circulation in endothelial cells of human veins and arteries at various sites [\n28\n]. Two CNP molecules, 22 and 53 amino acids in length, have been identified within the circulation [\n25\n,\n26\n]. The 22 amino acid form predominates in plasma and is more potent than the 53 amino acid form [\n26\n]. CNP lacks a significant natriuretic function [\n29\n], and serves as a regulator of vascular tone [\n30\n,\n31\n] and growth [\n32\n,\n33\n] in a paracrine or autocrine fashion.\nActions of circulating NP\nApart from blood pressure lowering properties, natriuretic, diuretic and/or kaliuretic properties of the NP originating from the ANP prohormone [\n20\n] and from BNP, inhibition of the renin–angiotensin system, sympathetic outflow, and vascular smooth muscle and endothelial cell proliferation have been attributed to NP [\n34\n]. Furthermore, a link of ANP to the immune system has been suggested [\n35\n], and a receptor-mediated modulation of macrophage function [\n36\n-\n38\n] and priming of polymophonuclear neutrophils [\n39\n] have been observed. Priming of neutrophils in endotoxemia is one of the earliest alterations of these cells in the course of activation, preceding expression of adhesion molecules and respiratory burst triggered by inflammatory mediators (i.e. tumor necrosis factor alpha and complement cascade) [\n40\n]. Whether NT-proBNP has biological effects on its own is currently unknown. The function of dendroaspis natriuretic peptide, the most recent addition to the family of NP first isolated from the venom of the green mamba, in humans still remains unclear [\n41\n]. Atrial and ventricular volume expansion and pressure overload are an adequate stimulus for secretion of circulating natriuretic peptides deriving from ANP and BNP pro-hormones, respectively [\n42\n,\n43\n].\nReceptors of NP\nMost biological effects of ANP and BNP are mediated by a guanylate cyclase coupled cell surface receptor, the A-receptor (NPR-A) [\n44\n]. Long-acting natriuretic peptide and vessel dilator have distinct receptors separate from the ANP receptors [\n45\n]. The natriuretic effects of the long-acting natriuretic peptide and the vessel dilator have a different mechanism of action from ANP, in that they inhibit renal Na\n+\n-K\n+\n-ATPase secondary to their ability to enhance the synthesis of prostaglandin E\n2 \n[\n46\n,\n47\n], which ANP does not do [\n46\n,\n47\n].\nCNP is a specific ligand for the B-receptor (NPR-B), another guanylate cyclase coupled NP receptor [\n48\n]. The third NP receptor, the so-called NP clearance receptor (NPR-C), binds ANP, BNP and CNP. Apart from a major role in the clearance of NP in the whole body [\n48\n], an increasing number of reports describe that several effects of ANP are mediated via the NPR-C receptor [\n49\n]. Stimulation of the NPR-C seems to be related to a G-protein coupled inhibition of adenylate cyclase [\n50\n]. Apart from binding to the NPRs, NP are cleared also through proteolysis by peptidases, the most closely studied being neutral endopeptidase 24.11. Renal excretion is currently regarded as the main clearance mechanism for NT-proBNP, but this topic awaits further study. All three subtypes of natriuretic peptide receptors (i.e. NPR-A, NPR-B and NPR-C) have been demonstrated to be expressed in diverse tissues including the renal system and the animal and human hearts [\n51\n].\nNP in ischemia-reperfusion\nIn recent years it has been increasingly recognized that the functions of the NP are not restricted to the regulation of volume homeostasis. For instance, protective actions of ANP against ischemia-reperfusion injury on whole organs have been described first in the kidney [\n52\n] and in the liver [\n53\n]. This effect of ANP has been attributed to an antagonism of catecholamine-mediated renal vasoconstriction [\n52\n], a cGMP-mediated direct cytoprotective action on hepatocytes [\n54\n] and a regulation of Kupffer cell function [\n55\n], respectively. Protective actions against hypoxia and ischemia have also been described for ANP and urodilatin at the heart [\n56\n]. Since tissue hypoxia due to a deterioration of oxygen utilization has been suspected in patients with sepsis [\n57\n], antihypoxic and/or anti-ischemic effects of ANP at the cellular level might be important also in primarily nonischemic diseases such as sepsis. Apart from potential direct anti-ischemic actions, the cardiac NP have received close attention as cardiovascular markers. Following acute myocardial infarction, plasma levels of ANP, N-terminal proANP, vessel dilator, long-acting natriuretic peptide, BNP and NT-proBNP have been found to be increased in patients suffering from myocardial infarction [\n58\n-\n62\n]. BNP measured between 1 and 4 days after an ST-segment elevation myocardial infarction provides long-term prognostic information [\n58\n,\n63\n] independent of left ventricular ejection fraction [\n64\n]. Predictive information for use of risk stratification has been provided for BNP in the whole spectrum of acute coronary syndromes including patients with nonpersistent ST-segment elevation [\n65\n]. N-terminal proANP has also been reported to be an independent predictor of long-term prognosis in humans when measured 3–16 days after infarction [\n66\n]. A prognostic value for long-term prognosis after acute myocardial infarction [\n67\n,\n68\n] and short-term prognosis after treatment with primary percutaneous coronary intervention have also been described for NT-proBNP [\n69\n].\nNP and left ventricular dysfunction\nIncreased plasma levels of circulating NP have been described in patients with congestive heart failure, and a direct proportion assigned to the severity of congestive heart failure as classified by the symptomatic New York Heart Association has been reported for vessel dilator, for long-acting natriuretic peptide, for BNP and for NT-proBNP [\n70\n-\n73\n]. N-terminal proANP and BNP have been reported to be more sensitive indicators of systolic left ventricular dysfunction [\n74\n-\n76\n].\nN-terminal proANP has been reported to identify patients with asymptomatic left ventricular dysfunction with a sensitivity and specificity of more than 90% [\n75\n]. For vessel dilator as the only peptide (including ANP, BNP, NT-proBNP, etc.), 100% sensitivity and 100% specificity have been reported in differentiating persons with mild congestive heart failure from healthy individuals [\n71\n]. N-terminal proANP has also been reported to be an independent predictor of the development of congestive heart failure and of cardiovascular mortality [\n66\n].\nBNP and NT-proBNP have been shown to be useful markers for prognosis in patients with asymptomatic left ventricular dysfunction and different degrees of congestive heart failure [\n76\n-\n78\n]. The major site of synthesis and release of BNP, the cardiac ventricles, and BNP's rapid upregulation by gene expression followed by a remarkably augmented plasma concentration exceeding that of ANP in severe cases [\n79\n], make this peptide not only especially suitable to estimate the severity of disease in patients with left ventricular dysfunction [\n70\n], but may also help guide the treatment of systolic left ventricular impairment in the future [\n80\n].\nNP and pulmonary disease\nIn the urgent care setting it is often difficult to distinguish between cardiac and pulmonary causes of dyspnea. Physical signs, routine laboratory tests, electrocardiograms and chest films are not diagnostically consistent in differentiating heart failure from other disease, such as pulmonary disease [\n81\n]. Rapid testing of BNP and NT-proBNP has been reported to differentiate pulmonary etiologies from cardiac etiologies of dyspnea [\n82\n-\n84\n]. Some types of pulmonary disease, such as cor pulmonale, pulmonary embolism and lung cancer, however, are also associated with elevated natriuretic peptide levels, but not generally to the same extent as those in patients with acute left ventricular dysfunction. BNP levels in the intermediate range from 100 to 500 pg/ml have been reported to be attributable to causes other than congestive heart failure [\n85\n].\nIncreased plasma levels of NP (i.e. ANP [\n86\n], N-terminal proANP [\n87\n] and BNP [\n88\n]) have also been found in patients with acute respiratory distress syndrome (ARDS). Acute cor pulmonale as a consequence of increased pulmonary vascular resistance occurs in up to 60% of patients with ARDS submitted to conventional mechanical ventilation [\n89\n]. An increase of pulmonary vascular resistance observed in ARDS may lead to right ventricular overload and decreased right ventricular output in presence of impaired right ventricular contractility [\n90\n,\n91\n]. BNP levels secreted by the right ventricular myocardium are said not to exceed 300–600 pg/ml [\n82\n]. However, there might be a considerable overlap of patients with increased BNP due to ARDS and patients with primary symptomatic congestive heart failure, where BNP levels have to reach more than 500 pg/ml to ensure the diagnosis with a probability greater than 95% [\n92\n].\nIn support of this concept, elevated values reported for ANP [\n86\n], N-terminal proANP [\n87\n], BNP [\n88\n] and NT-proBNP [\n93\n] in patients with acute lung injury and/or sepsis are well in the range found in patients with severe heart failure. These data suggest at least for BNP a limited value of intermediate BNP values for the discrimination of primary pulmonary disease (i.e. ARDS) or cardiac disease. Sufficient data for other NP are still lacking. In contrast, a BNP cutoff value of 100 pg/ml measured at admission of patients presenting in the emergency department has been reported to have a strong negative predictive value for congestive heart failure in acute dyspneic patients [\n73\n]. Nevertheless, a BNP cutoff value of 80 pg/ml was not able to exclude patients with 'flash' pulmonary edema [\n94\n]. Pulmonary edema and heart failure are often found in patients (who are frequently old) with diastolic dysfunction and a preserved systolic left ventricular ejection fraction [\n95\n]. BNP might be useful in establishing the diagnosis of (concomitant) diastolic dysfunction [\n96\n], which is common in the elderly population with pulmonary disease. However, although it could be confirmed by other investigators that patients in the presence of diastolic dysfunction had higher BNP levels compared with healthy controls, in terms of absolute values symptomatic patients with mild diastolic heart failure might have BNP levels in the normal range [\n97\n].\nBecause of the overlap of BNP levels in the lower and intermediate concentration, to date, the diagnostic value of BNP in this concentration range seems to be poor. The major role of BNP is thus still the separation of symptomatic patients without congestive heart failure. Taking into consideration the poor prognosis and higher readmission rate in heart failure patients with increased levels of BNP (values >500 pg/ml) [\n92\n], BNP and possibly further NP might have a place in monitoring therapy success in the future. In this regard, BNP might be of value also in patients with ARDS, where a lack of BNP decrease has been related to prognosis [\n88\n].\nNP in the critically ill\nRelation to endotoxin and proinflammatory cytokines\nHemodynamic changes typically seen in sepsis and septic shock (i.e. reduced ejection fraction in presence of an increased diastolic volume and pressure of both ventricles, and an increase in pulmonary arterial pressure [\n10\n,\n98\n]) might explain increased plasma levels of circulating NP derived from both ventricles of the heart in those patients. ANP has consistently been shown to increase in plasma during hyperdynamic ovine endotoxemia associated with right ventricular distension due to pulmonary hypertension, and in acute respiratory failure associated with sepsis related to pulmonary arterial and occlusion pressures [\n86\n,\n99\n-\n101\n]. Furthermore, a diminished pulmonary uptake in the case of a reduced organ perfusion might contribute to the elevation in plasma levels of ANP in sepsis. The lung is a major clearance organ of ANP besides the liver, the kidney and the peripheral and splanchnic circulation [\n102\n,\n103\n].\nPlasma BNP has also been described as increased in animal models dealing with endotoxemia [\n104\n]. However, it has been questioned whether BNP expression and secretion in endotoxemia is solely explained upon cardiac overloading due to alterations of the cardiovascular system. A direct upregulation of the BNP gene by lipopolysaccharide, not mediated by other cytokines and independent from mechanical loading in endotoxemia, has recently been described in rats [\n104\n]. In fact, increased plasma levels of endotoxin have also been found in other conditions accompanied with increased BNP plasma levels (i.e. congestive heart failure) [\n105\n], and endotoxin exerts deleterious effects on cardiac performance itself [\n106\n,\n107\n]. Based on these findings, one might speculate that endotoxin itself contributes to left ventricular dysfunction and modulates BNP expression and secretion in addition to elevated ventricular wall stress in endotoxemia in man.\nApart from endotoxin, proinflammatory cytokines stimulated in different forms of heart failure and dramatically increased in sepsis and septic shock might also contribute to ANP and BNP secretion from the heart. \nIn vitro \nstudies have shown an enhanced gene expression of BNP and prepro-ANP, the precursor form of circulating ANPs, following stimulation of cultured cardiomyocytes with IL-1β [\n108\n,\n109\n]. Increased secretion of both ANP and BNP following stimulation with members of the IL-6-related family (i.e. cardiotrophin-1) has recently been reported in cultured cardiomyocytes [\n110\n]. In heart failure, cardiotrophin-1 and IL-6 levels increase [\n111\n,\n112\n], and cosecretion of IL-6 and ANP as well as of cardiotrophin-1 and pro-BNP has been reported [\n111\n,\n113\n].\nIn human septic shock, ANP is related to IL-6 rather than to the altered hemodynamics of these patients [\n114\n]. In septic shock, IL-6 levels exceed those in ischemic or severe congestive heart failure more than 100-fold [\n114\n,\n115\n], and the relation between ANP and IL-6 seems to be rather specific since no association between ANP and other inflammatory mediators of septic shock (i.e. soluble tumor necrosis factor receptors) could be observed [\n114\n]. These findings argue for a possible role for members of the IL-6-related family in the modulation of both NP (ANP and BNP) in patients suffering from ventricular impairment in septic shock.\nEstimation of disease severity and prognosis\nA negative relationship between heart function indices and elevated plasma levels of ANP [\n116\n], N-terminal pro-ANP [\n87\n] and, recently, for BNP [\n117\n] and NT-proBNP [\n93\n] has been reported in human septic shock. These findings suggest that these peptides might reflect myocardial dysfunction as described in congestive heart failure in septic shock as well. The relative value of ANP compared with BNP in recognition of myocardial depression, severity of disease and outcome prediction has been prospectively evaluated in human septic shock [\n114\n]. In this study, cardiac impairment was reflected by plasma BNP rather than by ANP [\n114\n]. Interestingly, neither ANP nor BNP was related to the severity of disease judged by the Acute Pathophysiology and Acute Chronic Health Evaluation (APACHE) II score [\n114\n], and neither ANP nor BNP was able to differentiate survivors from nonsurvivors [\n114\n]. Although these results should be interpreted cautiously because of the relatively small number of patients included, the finding of a lack of value for prediction of the severity of disease judged by the APACHE II score and estimation of mortality is in good agreement with former results in critically ill patients with a medium degree of severity of illness [\n118\n]. Thus, in patients with trauma or different kinds of surgery, neither ANP nor BNP were useful for either estimation of disease severity or outcome prediction [\n118\n].\nIn summary, BNP and to a minor degree ANP are associated with the degree of cardiac impairment in septic shock. BNP might therefore be the more suitable and valuable marker to monitor therapy success. Actually, however, there is no convincing evidence to establish a role of NP in estimation of disease severity. Further studies are needed to clarify a feasible role of NP in outcome prediction in human septic shock.\nCNP in sepsis and inflammatory response\nAlthough CNP is known to be a local regulator of vascular tone and growth, CNP can be detected in human circulation [\n119\n]. In contrast to other members of the natriuretic peptide family, however, the plasma concentration of CNP is not altered in heart disease such as congestive heart failure [\n119\n]. So far, sepsis and further septic shock is the only condition where sharply increased plasma levels of CNP have been observed [\n119\n]. Tumor necrosis factor alpha, inducible nitric oxide synthase and endotoxin, mediators all shown to be increased in sepsis, are potent stimulators of CNP from endothelial cells and might contribute to elevated plasma levels of this peptide in sepsis [\n119\n]. Furthermore, macrophages represent a source for and a target of CNP [\n120\n]. In these mediator cells of inflammation, endotoxin has been shown to induce CNP [\n121\n], and a B-receptor-mediated inhibition of inducible nitric oxide synthase has been described [\n122\n].\nAt the level of the vascular wall, CNP seems to act predominantly at the vein [\n123\n]. It has been suspected that increased concentrations of CNP might contribute to venous pooling by vasodilative action on the vein in septic shock [\n123\n].\nConclusion\nCirculating NP such as ANP, peptides derived from the N-terminal prohormone, BNP and its N-terminal moiety NT-proBNP reflect a decreased left ventricular function in patients with congestive heart failure, and play a role in risk stratification in the whole spectrum of acute coronary syndromes. Tissue hypoxia and impairment of left ventricular function are often found in critically ill patients. NP such as ANP, N-terminal proANP, BNP and NT-proBNP seem useful to detect myocardial dysfunction early in the clinical course of the critically ill. Myocardial dysfunction has been shown to be associated with poor outcome in the critically ill, and reversibility of cardiac impairment in patients with good prognosis has been described. First results suggest a possible role of circulating NP in monitoring of therapy success in septic shock and perhaps in acute lung injury associated with sepsis. Future studies are needed to confirm a prognostic value of these natriuretic peptides in the critically ill.\nCompeting interests\nNone declared.\nAbbreviations\nANP = atrial natriuretic peptide; ARDS = acute respiratory distress syndrome; BNP = brain natriuretic peptide; CNP = C-type natriuretic peptide; IL = interleukin; NP = natriuretic peptides; NPR = natriuretic peptide receptor; NT-proBNP = N-terminal proBNP; SIRS = systemic inflammatory response syndrome.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
18
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nRoundtable debate: Controversies in the management of the septic patient – desperately seeking consensus\n\n**Article Abstract:**\n\nDespite continuous advances in technologic and pharmacologic management, the mortality rate from septic shock remains high. Care of patients with sepsis includes measures to support the circulatory system and treat the underlying infection. There is a substantial body of knowledge indicating that fluid resuscitation, vasopressors, and antibiotics accomplish these goals. Recent clinical trials have provided new information on the addition of individual adjuvant therapies. Consensus on how current therapies should be prescribed is lacking. We present the reasoning and preferences of a group of intensivists who met to discuss the management of an actual case. The focus is on management, with emphasis on the criteria by which treatment decisions are made. It is clear from the discussion that there are areas where there is agreement and areas where opinions diverge. This presentation is intended to show how experienced intensivists apply clinical science to their practice of critical care medicine.\n\n**Article Body:**\n\nIntroduction\nDespite continuous advances in technologic and pharmacologic management, the mortality rate from septic shock remains high. Each year in the USA there are an estimated 400,000 cases of sepsis, resulting in more than 100,000 deaths annually [\n1\n]. The hemodynamic derangements of septic shock are characterized by arterial hypotension, peripheral vasodilatation, hypovolemia from capillary leakage, and the development of myocardial depression. An excessive inflammatory response typifies the initial stages of infection and contributes to the progression to organ failure. Progression to septic shock represents failure of the circulatory system to maintain adequate delivery of oxygen and other nutrients to tissues, causing cellular and then organ dysfunction (Task force of the American College of Critical Care Medicine and Society of Critical Care Medicine [\n2\n]). The ultimate goals of therapy for shock are to restore effective tissue perfusion, to normalize cellular metabolism, and to preserve and restore tissue function.\nCare of patients with sepsis includes measures to support the circulatory system and treat the underlying infection. Although there is a substantial body of knowledge indicating that fluid resuscitation, vasopressors, and antibiotics accomplish these goals, consensus on how they should be prescribed is lacking. Recent clinical trials have provided new information on the addition of individual adjuvant therapies, including adrenal supplementation therapy, tight glucose control, and drotrecogin alpha (activated) to standard therapies. These therapies are effective with statistical certainty in their respective study populations, but they do not provide insights into potential synergistic or antagonistic interactions, making it challenging to determine which combination of treatments, if any, is best for a given patient. It is the reasoning that clinicians use to process this information and synthesize individual care plans that is the focus of this commentary.\nWe present the reasoning and preferences of a group of intensivists who met to discuss the management of an actual case. Throughout this presentation, the focus is on management, with emphasis on the points of discussion of the criteria by which treatment decision are made. It is clear from the discussion that there are areas where there is agreement and areas where opinions diverge. Participants support their opinions with literature citations and provide a perspective on how clinical practice can be distinct from participation in a clinical trial.\nCase presentation part 1\nThe patient is a 56-year-old male who awoke the morning of admission with nausea, shortness of breath, and diaphoresis. Over the previous 2 days he had noted a productive cough, associated with midline chest pain, shaking chills, and three to four episodes of watery diarrhea. He had no abdominal pain and no swelling or pain in the legs. Over the past 3 months he had lost 30 lb (approximately 13.6 kg) in weight and he had recently sought medical attention for left shoulder pain. A bone scan was reportedly negative. He had no known drug allergies and took no medications. Family history was unremarkable. He was a former smoker, of less than 20 pack-years, having stopped about 3 years previously, and he denied alcohol or illicit drug use. He had worked as a dry cleaner for the past 30 years.\nPhysical examination in the emergency department (ED) revealed a temperature of 97°F (36.1°C), a heart rate of 180 beats/min, and blood pressure of 120/60 mmHg. His respirations were labored at 26 breaths/min, and oxygen saturation was 89% on 4 l nasal cannulae oxygen. During the examination he had an episode of coffee ground emesis. He was put on a nonrebreather mask, and his oxygen saturation increased to 98%. Breath sounds were diminished in the right upper lung zones. His stool was hemoccult positive. Initial laboratory study findings are summarized in Table \n1\n.\nDr A \nAs we stand at the bedside, reviewing the admission laboratory findings and waiting impatiently for a chest radiograph, let us try and put these findings together. First of all, this patient presents with an acute illness with fever, chills, a cough that is productive of purulent sputum, and 3 days of watery diarrhea. At first thought this sounds like community-acquired pneumonia (CAP), possibly with an atypical pathogen. Perhaps the diarrhea is a red herring. Weight loss and left shoulder pain in a 53-year-old former smoker raises concern for lung cancer with possible postobstructive pneumonia, and we shall look for signs of volume loss or chest wall metastasis on the chest radiograph. This patient also has evidence of severe sepsis, with a left shift, and tachycardia. He has signs of impending organ failures with renal dysfunction, a creatinine level of 1.9 mg/dl, metabolic acidosis, a coagulopathy with an elevated prothrombin time and D-dimer, and low platelets that could signal early disseminated intravascular coagulation (DIC). He has respiratory failure, with an A–a gradient over 500. He is probably hemoconcentrated, and clinically we would expect him to be hypovolemic from diarrhea, high insensible losses, and poor oral intake. My immediate therapeutic concern is the tachycardia, the nature of the cardiac rhythm, and the possibility of myocardial ischemia.\nDr D \nI might disagree with you that this patient has severe sepsis. What if, after 2 or 3 l saline, his blood pressure, heart rate, and creatinine normalize? I think this illustrates one of the greatest triage challenges in this area, and that is differentiating infection with sepsis from another very common scenario – infection with dehydration and hypovolemia. I think the most important point is not to confuse sepsis with hypovolemia from any cause, including hemorrhage.\nDr B \nThe firsts steps in the care of patients like this should be very systematic. Once the tachycardia was assessed and assuming the chest readiograph confirms pneumonia, I would initiate prompt antibiotic therapy based on the most likely type(s) of infection; ensure adequate hemodynamic and respiratory support; try to identify the source of infection; identify and ascertain the extent of his organ dysfunction; and, based on that, develop an overall treatment plan.\nDr C \nI agree – we need to treat this suspected infection. Although a chest radiograph is not initially available, there is a strong clinical suspicion for pneumonia, as a source of major infection, and empiric antibiotic coverage should be started. When the differential diagnosis includes a central nervous system infection, there is never a question in regard to early antibiotic coverage, and in fact antibiotics are started within a window of 6–8 hours. Data for most infections, especially pneumonia, have the same window of opportunity in regard to mortality. Animal models of septic shock also indicate that mortality can directly relate to time delay in antibiotics. If there is any delay in the work up, including a delay in obtaining a chest radiograph, then empiric treatment for CAP with ceftriaxone and azithromycin should be initiated.\nCase presentation part 2\nThe patient was given 2 l of normal saline and a chest radiograph was obtained. He was given a total of 18 mg adenosine with no response; and then 2.5 mg intravenous verapamil in three doses, with a decrease in heart rate to 110 beats/min. Atrial fibrillation was diagnosed. His blood pressure fell with these interventions. The chest radiograph showed a dense opacity in the right-upper lobe with patchy opacities in the right-lower lobe, the lingula, and left-upper lobe. There were no clear air bronchograms or lateral shift to suggest lobar collapse (Fig. \n1\n).\nDr B \nThere are now additional diagnostic data available, and clinically important interventions have been done that raise important considerations. The additional radiographic information addresses the concerns raised about the 30 lb weight loss and any chronic process that may be acutely infected. There is no clear evidence of an endobronchial lesion or airway obstruction. This, along with the history of a recent negative bone scan, makes cancer less likely. Active tuberculosis is possible, and sputum should be sent for appropriate studies. With the complaint of midsternal pleuritic chest pain, there is concern of pericardial involvement. However, there are no suggestive changes on the ECG, and the heart size looks normal, somewhat narrow, and probably under-filled, which is consistent with hypovolemia.\nDr A \nDo we need to consider any other diagnostic tests for CAP in a patient with severe sepsis?\nDr C \nIt can be very helpful in cases like this to have blood and sputum cultures. It is usually possible to get a set of blood cultures in patients like this, prior to starting antibiotics. Although they do not have a high yield, they can play an important role in the treatment of the infection by identifying possible sources and unusual or resistant organisms. They can also help to identify high-risk patients.\nDr B \nThe purist's goal is to try to establish a bacteriologic diagnosis, but the realization is that one must initially treat broadly because no single test has the sensitivity and specificity to allow one to treat narrowly. Regardless, the coverage we use includes coverage for almost every possible bacteriologic pathogen. Knowing that this patient is from the community, we do not need to consider double Gram-negative coverage, even in a septic patient. If a patient is from the community but has recently been hospitalized, is immunosuppressed, is being treated with steroids, or has structural lung disease, such as bronchiectasis, then we would consider alternative or additional antibiotic coverage to cover for \nPseudomonas \nspp. or other resistant Gram-negative rods. For the time being there is no indication to change either the azithromycin or ceftriaxone. I agree that to try to obtain a bacteriologic diagnosis, we use blood, urine and sputum cultures, if available, and might perform bronchoscopy once the patient is hemodynamically stable.\nDr C \nGetting back to the ECG, the patient has a narrow complex tachycardia with a rate of 190 beats/min with 2–3 mm ST-segment depressions across the precordium. Should the heart rate be directly controlled? Could the patient be having a myocardial infarction or is he simply volume depleted? I am concerned about using adenosine before adequately addressing the patient's volume status. The initial approach should be to volume replete him aggressively and see whether the hemodynamics improve, and then address any persistent tachycardia only after he is volume replete. In this case, rate controlling agents may not be the first line of therapy, given a strong suspicion for sepsis. One question that comes up is, what if he is ischemic and you start volume resuscitating him? Is he going to go into heart failure? Does that matter? This should not be an issue. If the need arises then support him with invasive or noninvasive ventilation and get him through this. Regardless of the cause of the tachycardia, fluid load this patient.\nDr A \nWould there be any indication to treat him for an acute coronary syndrome with aspirin or heparin at this point? Would there be a problem with starting heparin in this man if one felt he truly had a coronary basis of ischemia versus demand ischemia? It is likely that this represents demand related ischemia, as opposed to an unstable coronary syndrome. This is a 55-year-old man. The ECG shows a narrow complex tachycardia at 190 beats/min with ST-segment depressions in V\n3\n–V\n5\n. Creatine phosphokinase and troponin levels were all initially normal. Is there a down side to giving aspirin? Aspirin is not going to be of much value, if you think this is demand-related ischemia. It does complicate the decision making for drotrecogin alpha (activated) should he develop severe sepsis. There is also the concern that he is having gastrointestinal bleeding. There is reluctance to go after his ischemia in a big way until we get his rate controlled. If ECG changes persist after control of heart rate, then we might consider aspirin. If heparin is started then it can easily be discontinued.\nDr B \nI agree that aspirin may complicate the decision making, should you want to give a new agent like drotrecogin alpha (activated). Patients receiving aspirin or other antiplatelet agents were excluded from the PROWESS (Recombinant Human Activated Protein C Worldwide Evaluation in Severe Sepsis) trial, and so its safety in the presence of antiplatelet agents is unclear. If you think the patient is more at risk for death from severe sepsis than from demand ischemia, then your attention should be directed toward the interventions that are most likely to give the patient benefit. Because this patient had no prior history of coronary disease, and because demand related ischemia is more likely than an acute coronary syndrome that may benefit from aspirin, the risk/benefit moves one step toward sepsis interventions rather than acute myocardial infarction interventions.\nCoronary flow is upregulated in sepsis [\n3\n-\n5\n]. It is actually unusual for patients to develop myocardial ischemia.\nCase presentation part 3\nThe patient was admitted to the general medical floor. He was still tachycardic at 110 beats/min in sinus rhythm, and ST-segment changes had resolved. He was described as being cold and clammy. His systolic blood pressure was now in the 90s. He was given an additional 3 l normal saline, resulting in a blood pressure of 110/60 mmHg. He was increasingly tired, and his breathing became more labored. He received ceftriaxone and azithromycin. The patient subsequently required orotracheal intubation with a #8 endotracheal tube. He was given fentanyl, propofol, and midazolam for intubation. Eight hours after presenting in the ED, he was transferred to the intensive care unit (ICU). A chest radiograph following intubation showed progression of the right-upper lobe process. The heart rate was 106 beats/min, and blood pressure was 94/47 mmHg with a mean arterial pressure (MAP) of 60 mmHg. Oxygen saturations were 96% on 100% oxygen. An additional 3 l normal saline was given, for a total of about 6.5 l (Fig. \n2\n).\nDr A \nWhat is interesting in this case is that, in the ED, when you have someone who already has single organ failure and some borderline findings that make you suspect he is on his way to multiorgan failure, should this patient automatically be an ICU admission? We argue this frequently because, if you volume resuscitate this patient in the ED and he turns around in the ED, the tachycardia goes away, the ST segments normalize, his respiratory distress gets better, and he either goes to an ICU or a regular floor bed. This becomes a very important triage question. This patient is a great example of someone who has the potential to crash very hard, and if you intervene right away with early therapy you may be able to reverse at least what we see as early organ dysfunction and prevent multiorgan failure. This man could have gone straight to the ICU, and we could have figured all this out there, rather than try to get him floor ready. The other thing is that if you send him to the ICU, he could spend 24 hours there and then be ready to go to the floor; instead he ended up coming to the ICU for a week.\nCase presentation part 4\nTwo hours later, the patient was agitated on the ventilator and had frequent high peak airway pressure alarms; the oxygen saturations were stable. The blood pressure had been trending downward, with systolic in the high 70s, MAP in the 50s, and urine output under 20 cc/hour. His sodium was 137 mmol/l, potassium 3.2 mmol/l, chloride 118 mmol/l, carbon dioxide 17.8 mmol/l, blood urea nitrogen 18 mg/dl, and creatinine 1.1 mg/dl, the latter representing an improvement. The glucose was 170 mg/dl, phosphate was down to 1.4 mg/dl, and albumin was 1.3 g/dl. The white cell count was 6500/mm\n3\nwith 15% bands; platelets were 56,000/mm\n3\n. The hematocrit was down to 28.4%. Cardiac enzymes were within normal limits. The arterial blood gases on 50% inspired fractional oxygen (FiO\n2\n) were as follows: pH 7.46, partial carbon dioxide tension (PCO\n2\n) 24 mmHg, and partial oxygen tension (PO\n2\n) 99 mmHg. Central venous pressure (CVP) was 14 cmH\n2\nO. Central venous PO\n2 \nwas 39 mmHg. Lactate was 5.6 mg/dl. Norepinephrine (noradrenaline) was being started (Fig. \n3\n).\nDr D \nResuscitation is clearly ongoing, and appropriate endpoints have not yet been reached. The patient is hypotensive, in spite of 8–10 l crystalloid. He has not received any blood, and pressors are being started. He was just intubated and heavily sedated. The chest radiograph needs to be checked for anything that could have a negative hemodynamic impact, such as a pneumothorax or other mechanical reasons for shock.\nDr A \nHow do we judge the completeness of his volume resuscitation?\nDr B \nClinical indices should be the first guide to the appropriateness of volume resuscitation. Clinical markers that were originally deranged can be followed, looking for improvement. Regardless, many of these patients may go on to develop organ failure. A threshold is often reached at which volume is given to the point that the presumption is that the patient is intravascularly replete. How is that point defined in the patient with organ failure? It depends, in part, on the age of the patient and cardiac function. If the patient is young or left ventricular function is known from a previous echocardiogram, then a central venous line with CVP and central venous oxygenation (scVO\n2\n) monitoring may be adequate. Alternatively, if cardiac function is not known or there is a suspicion of compromise, especially in an elderly patient, or if a large volume of fluid has been given without improvement, then invasive monitoring with a pulmonary artery (PA) line would be a consideration. When do you decide that enough fluid has been given? When is it time to hang a pressor or an inotrope? Initial volume resuscitation should be between 8 and 10 l, but after that how do you decide if that is enough or if are they leaking into the third space?\nDr A \nAdequacy of volume resuscitation is a big picture issue, and I never rely on a single variable. Multiple parameters are considered, including the hemodynamic measurements of heart rate, blood pressure, urine output, skin perfusion, and mentation. If these measures do not improve with aggressive volume expansion, then a PA line is considered. This suggests that it takes an experienced intensivist to judge fluid requirements. How does the resident or nonintensivist do it? As part of the protocol for early goal-directed therapy, pressors are used to keep the MAP about 60 or the systolic pressure above 90. Fluids are given to raise the CVP to between 10 and 12. The central venous oxygen saturation is pushed up with dobutamine and/or red cells. If these goals are not achieved within a reasonable time frame, then consider what additional information can be obtained from the PA catheter. The reason why the PA catheter trials have been so inconclusive is because there have been such varying goals or protocols associated with their use. If we could figure out the best protocol to resuscitate people, then we might be able to use the PA line as a guide and perhaps show benefit over non-PA-guided protocols.\nDr D \nThis raises the question as to when pressors should be started. The preference is not to hang vasopressors early in the resuscitation. If the patient is not adequately volume resuscitated, then splanchnic blood flow could be compromised by pressors. Conversely, we cannot allow a patient to remain hypotensive while striving to achieve volume resuscitation goals. Although the preference is to refrain from giving vasopressors before adequate volume resuscitation, sometimes we have to maintain an adequate blood pressure. In patients who are on pressors, should target goals be adjusted? It is likely that a higher central venous pressure is required in patients who are on pressors. A patient who has a CVP of 12 or 15, but who requires significant doses of vasopressors to maintain adequate MAP, might really need a CVP of 25.\nDr B \nWhen resuscitating a septic patient, there is a need, if we have not achieved our therapeutic goal, to double check the status of the left ventricle. We should not make an assumption in the septic patient that left ventricular function is normal. Many of these patients, perhaps even this one, have pulmonary vascular alterations in which there is a disconnect between the left and right side. They can have elevated CVPs in the presence of a low wedge. In this setting the PA catheter may give us additional useful information that CVP does not. An important point is not to fall into the trap of searching for the one best number. There is no one best number. Generally, there is a lot of information being generated for each patient, and it is important to look at all this information, especially the stroke volume or cardiac output for given CVP or wedge values, and how all these variables change, or do not change, after fluid boluses. Noninvasive estimates of preload and cardiac function can also be obtained. We all want to be reassured that we have given enough, but not too much, volume. If more fluid is given, and whatever index of cardiac function is being followed does not change, then we're probably close to adequate fluid resuscitation. That said, we have no idea whether this is the right construct, even though we all seem to agree on it. It may be that a strategy that favors norepinephrine, vasopressin, and/or inotropes allowing for less fluid resuscitation produces better outcomes than one that favors aggressive fluid resuscitation aimed at optimizing cardiac output and minimizing vasopressors. One recent study of elective surgical patients [\n6\n] showed superior outcomes with a severely restricted perioperative fluid management strategy. We need much better studies in this area.\nCase presentation part 5\nHe received over 10 l isotonic crystalloid, and his initial CVP was around 6 mmHg. He received additional volume as a combination of crystalloid and colloid; the resulting CVP was 15 mmHg.\nDr A \nIs it possible to be more efficient in the resuscitation? Do colloids make a difference in resuscitation?\nDr D \nColloids make a difference in the sense that we can volume resuscitate much more quickly. We also add oncotic pressure, which hopefully keeps more crystalloid intravascularly, and the total volume of fluid is less. If the issue is one of timing, then the more aggressively you achieve your end-diastolic volume goals, the better.\nDr C \nInadequate preload in sepsis and septic shock is multifactorial and can be related to venodilation, fever and fluid losses, and diffuse capillary leak. Vascular dysfunction presumably results from damage to underlying endothelium and likely results in compromised endothelial barrier function. Larger colloids are more likely to stay in the intravascular space. This, in combination with widespread inflammatory activation, explains one of the challenges of fluid therapy – capillary leak and formation of edema. This also plays a role in the requirement for large volume resuscitation. Restoration of adequate circulatory volume is necessary to permit adequate tissue perfusion, but it may not be sufficient on its own to correct microvascular abnormalities associated with sepsis.\nDr A \nThe literature does not support a benefit of one colloid over the other, or colloids over crystalloids. So the question is, you know you can give 10 l crystalloid or you can give 2.5 l colloid, so why wouldn't you just give 2.5 l? It is faster, with the same gauge intravenous line. Many intensivists would generally use 100% crystalloid, and many of us would look for reasons to give blood. If the hemoglobin is below 10, then packed red blood cells would be reasonable.\nDr B \nFor the most part I would use crystalloid as a first-line agent. Some of us would consider using both starch and blood, depending on the hemoglobin. As far as a specific approach, once I have reached a point where the patient has received over 6–10 l crystalloid, there is a desire to give something that is going to stay intravascular and provide more volume expansion with less total volume. At this point, I would start using colloid and, especially knowing his hemoglobin is where it is, I would probably give him starch. The bottom line is that most of us agree that the quantity and timing of whatever you pick is much more important than the fluid you pick.\nDr A \nWould anybody transfuse this patient with a hematocrit of 28.4?\nDr C \nKnowing he has a hematocrit that was 43 when he came in is important. He has had close to 10 l of crystalloid. Based on the protocol of Rivers and coworkers [\n7\n], initial volume resuscitation was given to get the CVP to 8–12. scVO\n2 \nis then examined. If the scVO\n2 \nis under 70, then either dobutamine or red cells (to get to a hematocrit of 30) are given to achieve a scVO\n2 \nabove 70%. It is not entirely clear why the patients assigned to early goal-directed therapy in the Rivers study did better. The data suggest that it was not necessarily because they got blood but rather the timing of how much fluid they received. At the end of 72 hours, both groups received the same amount of fluid but it was frontloaded in the early goal-directed therapy group, potentially having only to do with the aggressiveness of resuscitation. However, the protocol group did receive more blood (64% versus 16% transfused) during the first 6 hours.\nDr B \nThere are several studies that show that packed red blood cells may not increase oxygen utilization in sepsis. It is believed their main benefit in a situation like this is as a colloid – one that is very expensive, is of limited supply, and may have a variety of infection risks.\nDr A \nShould we treat this patient with empiric steroids?\nDr D \nThe best current evidence with which to answer this question comes from the randomized controlled trial conducted by Annane and coworkers [\n8\n]. A prior trial suggested that failure to augment serum cortisol by 9 μg/dl after high-dose adrenocorticotropic hormone (ACTH) was a bad prognostic sign and was independent of the pre-ACTH stimulated cortisol value [\n9\n]. The subsequent randomized controlled trial by Annane and coworkers showed benefit from steroids in the ACTH nonresponder patients only. Therefore, a random cortisol without cosyntropin may not help you decide whether to treat relative adrenal insufficiency. On the practical side, in many institutions cortisol results are not available for 2 days. If that were the case, then I would draw a pre- and post-ACTH cortisol and begin hydrocortisone 50 mg every 6 hours until the cortisol results return. I think we all would withdraw steroids if the serum cortisol increased by more than 9 μg/dl following ACTH.\nDr A \nAccording to the study by Annane and coworkers [\n8\n], if the baseline cortisol goes from 55 to 61, then the patient must be treated because they have relative adrenal insufficiency. An argument could be made that if the baseline cortisol is 55, then the patient may not benefit from additional steroids. Of the 299 patients who were studied and the 229 who were said to be adrenally insufficient, we do not know what fraction of those patients truly had a baseline cortisol of 55. In the patients who had an elevated cortisol to start with, it is unclear whether there is really any benefit in steroid replacement.\nDr D \nA cosyntropin stimulation test is easy and safe and is the only clear way, at the present time, to distinguish patients who appear to have an insufficient adrenal response. Because the random cortisol is not a reliable index, the best approach would be to treat the patient with steroid replacement therapy, pending the results of the cosyntropin stimulation test, and withdraw steroids, once those results show a normal response. This assumes that patients who respond are not harmed by 2 days of steroids.\nCase presentation part 6\nTwo hours later the sodium was 135 mmol/l, potassium 4.5 mmol/l, chloride 94 mmol/l, carbon dioxide 17 mmol/l, blood urea nitrogen 21 mg/dl, creatinine 1.8 mg/dl, and glucose 153 mg/dl. An arterial blood gas on 60% FiO\n2 \nrevealed pH 7.33, PCO\n2 \n34 mmHg, and PO\n2 \n70 mmHg, with a central venous oxygen saturation of 66%. The white blood cell count was 32,000/mm\n3 \nwith 32% bands. The platelets had dropped to 28,000/mm\n3\n, and the international normalized ratio was 1.8, with a prothrombin time of 19.5 s and a partial thromboplastin time of 50 s. Urine output had increased to 40 cc/hour.\nDr A \nShould this patient be treated with drotrecogin alpha (activated)?\nDr B \nThis patient has septic shock, organ injury, coagulopathy, and signs of DIC. His platelets are 28,000, which is below the 30,000 cutoff used in the PROWESS trial [\n10\n], but I think this may be exactly the kind of patient who should receive Drotrecogin alpha (activated). In the PROWESS trial DIC was part of the enrollment criteria. Actually, in the subgroup analysis, the DIC patients did better. If there is concern with the platelet count, we can either give platelets if this man had a lot of incisions or previously showed bleeding or forget about the platelet count, give the drotrecogin alpha (activated), and watch him expectantly.\nDr D \nMy understanding of the mechanisms by which this drug works tells me that drotrecogin alpha (activated) works by reversing the underlying pathophysiology in sepsis, and if you can improve this patient rapidly in the first 24 hours with standard therapies, then he is likely to have a better mortality. If you can't, then an intervention with a drug like drotrecogin alpha (activated) makes sense [\n11\n]. The data make a case for early treatment in all respects. Early intervention of almost anything is better than later intervention. Given what we know of the sepsis cascade, the further it rolls on the worse it gets. For most of us who have been sepsis investigators for a long time, the generalized expectation is that the earlier we intervene the better the chances that one can interrupt the sepsis cascade, and so on.\nCase presentation part 7\nOver the next 48 hours the findings on chest radiography improved. A chest computed tomography scan was done and did not reveal an endobronchial lesion. By day 3 the patient was off pressors. Urine output was up and the FiO\n2 \nis down. The patient was awake, alert, and responsive. On the third hospital day he was extubated. The white count was 14,000/mm\n3\nwithout bands. The platelets and prothrombin time normalized, and the creatinine was normalizing (Fig. \n4\n).\nDr A \nThe next question is whether he is clearly getting better. Do we keep the patient in the ICU to complete the full course of drotrecogin alpha (activated) or send him to the floor? Those are two different questions: do we have to complete the full 96-hour infusion and do we keep a patient who no longer requires ICU level care in the unit to complete the treatment?\nDr D \nHere is a man who is off the vent; renal failure and hypotension are resolved. If someone meets every other criterion for leaving the ICU – except for the fact they are receiving drotrecogin alpha (activated) – do you send him out of the ICU on drotrecogin alpha (activated) or stop the infusion early to send him out to the medical floor? If he is this stable, then I would stop the infusion and send him out. I think most would agree that you wouldn't keep the patient in the ICU solely to keep him on drotrecogin alfa (activated) if he is no longer critically ill. However, the much more common question is if he were still intubated, off pressors, looking much better, and one was thinking about extubating, 72 hours into the course, would one continue drotrecogin alpha (activated)? In that case I feel compelled to continue the drug. We don't raise that same question with antibiotics, and in that scenario he would continue to receive antibiotics for the next 7–10 days.\nSummary\nThe analysis and commentary of the care provided to this patient with severe sepsis and septic shock highlight the challenges in assessing and managing critically ill patients. The participants provided their perspectives on the recognition of physiological instability and the definition of severe sepsis and septic shock; at what point a patient should be admitted to the ICU; the importance of early goal-directed resuscitation therapy and the choice of resuscitation fluid; when to consider intravascular monitoring; the use of low-dose corticosteroids and drotrecogin-alpha; and at what point an improving patient should leave the ICU (Table \n2\n).\nIn this case, the assessment of the patient begins with recognition of the signs and symptoms of a serious infection. The participants agreed not only that antibiotic treatment should be given within 8 hours of presentation but also that combination therapy for CAP was appropriate. It was agreed that cultures of blood, urine, and sputum are indicated but should not delay the initiation of antibiotic therapy. Diagnostic bronchoscopy was not recommended while the patient was hemodynamically unstable.\nPatients often present with tachycardia and electrocardiographic abnormalities that may reflect sepsis, infection with vasodilation and hypovolemia (so-called ineffective arterial circulation), or cardiac ischemia. Distinguishing sepsis and an ineffective circulation from an acute coronary syndrome can be challenging. All of the participants agreed that, regardless, the most important effort should be directed toward restoring adequate intravascular volume. Resolution of tachycardia and increased urine flow with fluid resuscitation would suggest that hypovolemia and sepsis were the problems. Although there were differences of opinion regarding the timing of CVP or PA catheter placement, all were in agreement that a CVP or pulmonary capillary wedge pressure in the single digits was inappropriate for this patient. Furthermore, all agreed that the adequacy of volume resuscitation was best determined from cumulative data, including serial hemodynamic measurements, measurements of arterial and central venous oxygenation, and the response to volume infusion.\nBoth the availability and potential risks (although small) of transfusion of red blood cells made their use more restricted. The group agreed that patients with a hematocrit of less than 30 and a mixed or central venous oxygen saturation of less than 70% might benefit from red cell transfusion.\nAdditionally, everyone agreed that patients who are not likely to be harmed by 2 days of steroid replacement with hydrocortisone and fludrocortisone, but continued treatment with steroids should be guided by the results of a cosyntropin stimulation test. All of the participants agreed that this patient with severe sepsis and no contraindications should be treated with drotrecogin-alpha (activated).\nConclusion\nThe Blue Ginger Group has prepared this synthesis of opinion on the optimal treatment of a specific case of severe sepsis in order to share how experienced critical care providers treat their patients. This presentation in not intended to advocate particular treatment algorithms but rather to show how experienced intensivists apply clinical science to their practice of critical care medicine. Applying information provided by clinical trials to practice requires synthetic reasoning, judgment, and knowledge about the patient as well as those patients included in the studies. Even more important than the specific details of this analysis is that we need more high-quality clinical trial data to clarify which treatments or combinations of treatments best help individual patients with severe sepsis.\nCompeting interests\nThe authors declare that they have no competing interests.\nAbbreviations\nACTH = adrenocorticotropic hormone; CAP = community-acquired pneumonia; CVP = central venous pressure; DIC = disseminated intravascular coagulation; ED = emergency department; FiO\n2 \n= fractional inspired oxygen; ICU = intensive care unit; MAP = mean arterial pressure; PA = pulmonary artery; PCO\n2 \n= partial carbon dioxide tension; PO\n2 \n= partial oxygen tension; scVO\n2 \n= central venous oxygenation.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
19
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe paradoxical text 'On the Heart'. II.\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
20
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe family life of Ralph Josselin, a seventeenth century clergyman. An essay in historical anthropology\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
21
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe heart and circulation\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
22
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe ambrosia heart tantra\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
23
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nEnophthalmos Is Not Present in Horner Syndrome\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\nThe case report by Nautiyal et al. [\n1\n] is an instructive reminder that the first episode of an acute painful Horner Syndrome should prompt imaging of the ipsilateral internal carotid artery, since carotid dissection (as well as other conditions, such as high-grade stenosis) needs to be ruled out. Unfortunately, the authors perpetuate the extremely common misconception that enophthalmos accompanies ptosis and miosis in human Horner Syndrome. It is only an illusion of enophthalmos caused by the ptosis. This is evident in the left eye of their patient in Figure 1 of the case report.\nActual measurement with exophthalmometry clearly demonstrates the lack of enophthalmos. As stated by Loewenfeld ([\n2\n], p. 1139), “Animals such as cats, rats, or dogs have enophthalmos on the side of the sympathetic lesion. But in man, the enophthalmos is only apparent. The small palpebral fissure makes the eye look sunken in on the affected side, but the position of the globe in the orbit remains virtually unchanged. This has been found by all workers who have measured the supposed enophthalmos objectively.” Loewenfeld cites four supportive references.\nThompson and Miller ([\n3\n], p. 964) provide four additional references that the enophthalmos “is apparent rather than real.”\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
24
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nEpidemiology of leisure-time physical activity in socio-demographic, lifestyle and psychological characteristics of men and women in Greece: the ATTICA Study\n\n**Article Abstract:**\n\nBackground\nWe aimed to evaluate the prevalence, frequency and type of leisure-time physical activity (LTPA) among adults in Greece, as well as its relationship with socio-demographic, lifestyle and clinical characteristics of these people.\nMethods\nFrom May 2001 to December 2002 we randomly enrolled 1514 men and 1528 women, without any evidence of cardiovascular or any other chronic disease. The sampling was stratified by the age – gender distribution of (census 2001) of the greater area of Athens. Weekly energy expenditure assessed by considering frequency, duration (in minutes) and intensity of sports related physical activity during a usual week.\nResults\n53% of men and 48% of women were classified as physically active. Men were more likely to be active as compared to women (p < 0.05), while the lowest activity rates were observed in 40 to 49 years old participants (p < 0.01). Physically active people had higher occupation skills, were more likely to live in rural areas, to be unmarried, non smokers and they were devoted to a healthier dietary pattern, as compared to sedentary, irrespective of age and sex (all p < 0.05). In addition, the cumulative risk factors score of obesity, hypertension, hypercholesterolemia and diabetes, was inversely associated with activity status (p < 0.001). Finally, physically active men and women were less likely to report depressive symptoms (p < 0.01), after various adjustments were made.\nConclusion\nHalf of the studied population reported physically inactive, indicating that sedentary lifestyle becomes a serious epidemic in Greece. High occupation skills, non-smoking, devotion to a healthier dietary pattern and a better cardiovascular risk factors profile were some of the determinants of physically active people.\n\n**Article Body:**\n\nBackground\nSeveral observational and clinical studies suggest that physical activity substantially reduces the risk of dying of coronary heart disease, stroke, and colon cancer [\n1\n-\n4\n]. It also helps to control weight, contributes to healthy bones, muscles, and joints, reduces falls among older adults, helps to relieve the pain of arthritis, reduces symptoms of anxiety and depression and is associated with fewer hospitalizations, physician visits, and medications [\n3\n]. Despite the proven benefits of physical activity, the National Center for Chronic Disease Prevention and Health Promotion reports that more than one half of American adults do not get enough physical activity to provide health benefits, while 25% of adults are not active at all in their leisure time [\n3\n]. Worldwide, the World Health Organization estimates that over 60% of adults are not active enough to benefit their health [\n4\n]. Moreover, physical activity declines significantly with age, it is generally higher among females, and the overall inactivity trend is worse in poor urban areas. In addition, there are racial and ethnic differences in physical activity rates, particularly among women.\nData regarding the prevalence of physical activity and its association with various characteristics of Greek men and women are lacking. Therefore, the aim of this work is to evaluate the prevalence of leisure-time physical activity (LTPA) and to investigate its association with various socio-demographic, lifestyle and behavioural characteristics of Greek adults.\nMethods\nThe \"ATTICA\" study is a health and nutrition survey, carried out in the province of Attica (including 78% urban and 22% rural areas), where Athens, is a major metropolis. The sampling was random, multistage and based on the city – gender – age distribution of the province of Attica (census of 2001). The study's design anticipates enrolling only one participant per household. The main goals of the ATTICA study were to record the distribution of several blood lipids, inflammatory, oxidation, coagulation, thrombotic and clinical factors and to explore the associations between these factors with several socio-demographic, lifestyle and psychological characteristics of the participants.\nStudy's participants\nFrom May 2001 to August 2002, 4056 inhabitants from the above area were randomly asked to participate in the study. Of those, 3042 agreed to participate (75% participation rate); 1514 of the participants were men (50%, 20–87 years old) and 1528 were women (50%, 20–89 years old). Between 40 – 49 years old there were 48% men and 52% women. The number of the participants was determined by power analysis and chosen to evaluate two-sided differences between the normally distributed investigated parameters and physical activity groups greater than 10%, achieving statistical power > 0.80 at < 0.05 probability level (\nP\n-value). Also, those living in institutions were excluded from the sampling. The participants had no clinical evidence of cardiovascular or any other atherosclerotic disease, as well as chronic viral infections dental problems or any type of surgery in the past week. They also exhibited no signs of cold, flu, or any acute respiratory infection.\nPhysical activity ascertainment\nWe used a translated version of a validated questionnaire [\n5\n] of weekly energy expenditure that assessed: frequency (times per week), duration (in minutes) and intensity of sports related physical activity during a usual week. Intensity was graded in qualitative terms such as: light (expended calories < 4 Kcal/min, i.e. walking slowly, cycling stationary, light stretching etc.), moderate (expended calories 4–7 Kcal/min, i.e. walking briskly, cycling outdoor, swimming moderate effort etc.) and high (expended calories >7 Kcal/min, i.e. walking briskly uphill, long distance running, cycling fast or racing, swimming fast crawl etc.). Participants who did not report any physical activities were defined as sedentary. For the rest, we calculated a combined score by multiplying the weekly frequency, duration and intensity of physical activity. Then we calculated the tertiles of this score, and physically active participants were equally classified into three groups: low physical activity (1\nst \ntertile), medium physical activity (2\nnd \ntertile) and high physical activity (3\nrd \ntertile). Therefore, 1\nst\n, 2\nnd \nand 3\nrd \ntertile included 217 men and 205 women, respectively. We have also recorded the type of exercise, i.e. resistance (i.e. any technique that uses progressive resistance to increase muscular strength) or endurance training. The presence of occupational physical activity was recorded (41% of men and 27% of women reported occupational physical activity at least one time per week, i.e. mainly manual workers like builders, mason, labourer, technicians, etc), but was not taken into account for the analysis due to difficulties in evaluation and standardization. This exclusion may confound our findings, but the large sample size and the randomised procedure for the selection of the participants can spread the subjects who reported occupational exercise equally in both groups of the study.\nAlthough there are some concerns with self-reported physical activity, the introduced evaluation is now considered reliable, valid and has been used by many other similar studies [\n6\n].\nSocio-demographic and behavioural characteristics\nIn addition to the physical activity status, the study's questionnaire included demographic characteristics like age, gender, family status (married, divorced, widowed), financial status (average annual income during the past three years), and occupational status as well as education level. The educational level of the participants (as a proxy of social status) was measured in years of school. Occupation was also recorded and evaluated through a ten-point scale from unskilled – hand workers (lower values) to executive – skilled workers (higher values).\nInformation about smoking habits was collected using a standardized questionnaire developed for the Study. Current smokers were defined as those who smoked at least one cigarette per day. Never smokers those who have never tried a cigarette in their life and former smokers were defined as those who had stopped smoking more than one year previously. In all multivariate statistical analyses cigarette smoking habits were taken into account using the pack-years (cigarette packs per day × years of smoking). However, in order to correct for the amount of nicotine containment in various types of cigarettes smoked (i.e. light, heavy, very heavy), we assigned a weight in each different type of cigarette – pack, using the 0.8 mg/cigarette as the standard.\nConsumption of non-refined cereals and products, vegetables, legumes, fruits, olive oil, dairy products, fish, pulses, nuts, potatoes, eggs, sweets, poultry, red meat and meat products were measured as an average per week during the past year through a validated food – frequency questionnaire (FFQ), from the Department of Nutritional Epidemiology of Athens Medical School [\n7\n]. The frequency of consumption was then quantified approximately in terms of the number of times a month a food was consumed. Alcohol consumption was measured by daily ethanol intake, in wineglasses (100 ml and 12 gr ethanol concentration). Based on the Mediterranean – diet pyramid [\n8\n], we calculated a special diet score ranged from 0 to 55. Higher values of this score indicates adherence to the traditional Mediterranean diet, characterized by moderate consumption of fat and high monounsaturated: saturated fat ratio), while lower values indicate adherence to the \"Westernized\" diet.\nDepressive symptomatology was assessed using a translated and validated version of the Zung Self-Rating Depression Scale (ZDRS) [\n9\n]. The ZDRS is a well known and world-widely used self-rating scale for the measurement of depression. It is a self-reporting instrument and was originally developed in order to assess depression symptoms without the bias of an administrator affecting the results. Higher scores on this scale are indicative of more severe depression [\n9\n]. ZDRS consists of 20 items that cover affective, psychological, and somatic symptoms. The patient specifies the frequency with which the symptom is experienced (that is: a little = 1, some = 2, a good part of the time = 3, or most of the time = 4). A subject with ZDRS score below 50 is considered normal, with a score of 50–59 is considered to suffer from mild depression, with score 60–69 depression is considered moderate, while with a score of 70 or above depression is considered to be severe [\n9\n]. Previous investigations indicate that the ZDRS is a valid and sensitive measure of clinical severity in depressed patients and support its continued use as a research instrument [\n10\n]. Moreover, the sensitivity of the ZDRS was found adequate, and the scale was able to significantly differentiate four severity groups classified on the basis of the global rating.\nBiochemical and clinical measurements\nThe blood samples were collected from the antecubital vein between 8 to 10 a.m., in a sitting position after 12 hours of fasting and avoiding of alcohol. The biochemical evaluation was carried out in the same laboratory that followed the criteria of the World Health Organization Lipid Reference Laboratories. Serum cholesterol was measured using chromatographic enzymic method in a Technicon automatic analyzer RA-1000. The intra and inter-assay coefficients of variation of cholesterol levels did not exceed 5%. Participants with total serum cholesterol levels greater than 200 mg/dl or those taking lipid-lowering agents were classified as hypercholesterolemic and those with blood sugar > 125 mg/dl or the use of antidiabetic medication were classified as diabetic. Arterial blood pressure was measured at end of the physical examination with subject in sitting position for 25–30 minutes. Three measurements were abtained from the right arm (\nELKA using aneroid manometric sphygmometer\n, \nVon Schlieben Co\n, \nWest Germany\n). Patients whose average blood pressure levels were greater or equal to 140/90 mm Hg or taking antihypertensive medication were classified as hypertensives. Body mass index was calculated as weight (in kilograms) divided by standing height (in meters squared). Obesity was defined as body mass index > 29.9 kg/m\n2\n. Also, the investigators of the study recorded a detailed medical history of the participants.\nDetails about the aims and methods of the ATTICA study have been presented elsewhere [\n11\n].\nStatistical analysis\nContinuous variables are presented as mean values ± standard deviation, while categorical variables are presented as absolute and relative frequencies. Associations between categorical variables were tested by the use of contingency tables and the calculation of chi-squared test. Correlations (or partial correlations) between continuous or discrete variables were tested by the calculation of Pearson's \nr \nor Spermans's \nrho \n(for skewed variables) correlation coefficients. Comparisons between normally distributed continuous variables and categorical were performed by the use of Analysis of co-Variance (multi- way ANCOVA), after controlling for homoscedacity, and potential confounders. Kolmogorov-Smirnov criterion was used for the assessment of normality. In the case of asymmetric continuous variables the tested hypotheses were based on the calculation of the Kruskal – Wallis test. Associations between the investigated variables and physical activity levels were tested through fixed effects models, after the adjustment for several potential confounders and its interactions with physical activity status. The assumptions of linearity and homoscedacity were graphically tested by plotting fitted values against standardised residuals. Multiple logistic regression analysis estimated the odds ratio of being at a specific health condition with respect to physical activity status. Deviance residuals evaluated models' goodness of fit. All reported \nP\n-values are based on two-sided tests and compared to a significance level of 5%. However, due to multiple significance comparisons we used the Bonferronni correction in order to account for the increase in Type I error. SPSS 11.0.5 software (SPSS Inc. 2002, Texas, USA) was used for all the statistical calculations.\nResults\nEight hundred and two (53%) of men and 733 (48%) of women were classified as physically active. Table \n1\n presents the age distribution of physical activity in study's participants. Men were more likely to be physically active as compared to women, across all age groups (p = 0.001). The lowest physical activity rates were observed between 40 to 49 years old men and women (p = 0.01). Physically active men were devoted to more intense activities as compared to women (6.96 ± 1.2 vs. 6.23 ± 1.1 kcal/min, p = 0.02). In addition, men used to exercise 3.2 ± 1.7 times per week (for 85 ± 19 min/time) and women 2.7 ± 1.3 times per week (for 42 ± 21 min/time) (p = 0.03). An inverse relationship was observed between age and frequency, intention and time devoted to physical activities (partial \nr \n= -0.23, p = 0.02, \nr \n= -0.34, p = 0.001, and \nr \n= -0.21, p = 0.0001, respectively).\nTable 1\nDistribution of physical activity by age and sex\nPhysically active\nAge group (men / women)\nMen (n = 1514)\nWomen (n = 1528)\n20 – 29 y\n52.2%\n48.0%\n30 – 39 y\n43.1%\n41.0%\n40 – 49 y\n37.1%\n35.1%\n50 – 59 y\n47.3%\n37.5%\n> 60 y\n45.4%\n38.2%\nFurthermore, from physically active participants, 5% of men and 2% of women reported only resistance training, while 7% of men and 12% of women reported only endurance training. Thirty five percent of men and 25% of women reported that they were engaged in organised sports (sport clubs, or football, basketball and volleyball teams, etc.). When we compared participants in organised sports with non-participants, those who participated in organised sports were more often persistent exercisers as compared to those who did not (odds ratio = 11.6 for men, 95% confidence interval 7.2 to 15.1 and 7.9 for women, 95% confidence interval 5.5 to 11.0).\nPhysical activity and socio-demographic characteristics\nTable \n2\n presents social characteristics of the participants by physical activity status. In particular, a positive association was observed between physical activity and occupation skills (unskilled to skilled) in men and in women (both p < 0.05). Moreover, people living in rural areas were more likely to be physically active as compared to people living in urban areas (55% vs. 46%, p = 0.02). Never married participants were more likely to be physically active as compared to married or divorced/widowed (57% vs. 44%, p < 0.001), irrespective of age and sex. No statistically significant associations were found between physical activity levels and other social status indices (education level and annual income).\nTable 2\nSocio – demographic characteristics by physical activity status and sex\nPhysical activity status\nMen\nSedentary\n1\nst\ntertile\n2\nnd\ntertile\n3\nrd\ntertile\nP\nEducation (years of school)\n12 ± 4\n12 ± 4\n13 ± 4\n12 ± 5\n0.18\nAnnual income (× 1000 Euros)\n18,2 ± 3\n16,9 ± 3\n16,2 ± 5\n15,8 ± 5\n0.23\nOccupational status\n⊥ \n(0 – 10)\n5,1 ± 2\n6,1 ± 3*\n6,2 ± 3*\n7,0 ± 5**\n0.02\nWomen\nSedentary\n1\nst\ntertile\n2\nnd\ntertile\n3\nrd\ntertile\nP\nEducation (years of school)\n11 ± 4\n11 ± 3\n13 ± 5\n12 ± 2\n0.36\nAnnual income (× 1000 Euros)\n15,4 ± 7\n15,8 ± 7\n17,7 ± 6\n14,2 ± 6\n0.35\nOccupational status\n⊥ \n(0 – 10)\n4,9 ± 2\n6,5 ± 3**\n6,9 ± 3*\n7,8 ± 3**\n0.01\nVariables are expressed as mean value ± SD\n⊥\nOccupational status is measured in a ten-unit scale where lower values imply unskilled professions and higher values skilled.\nP\n-values of the last column derived from stratified ANCOVA tests, after controlling for age and denote the significance of the association between physical activity status and education, income and occupational status of the participants.\n* \nP \n< 0.05 and ** \nP \n< 0.01 Bonferronni corrected probability values for the comparisons between physical activity groups and sedentary participants.\nPhysical activity, lifestyle and behavioural characteristics\nTable \n3\n illustrates the associations between physical activity and various lifestyle and behavioural characteristics of the participants. Particularly, we observed that physically active participants were less frequent to be active smokers as compared to sedentary. An inverse relationship was found between physical activity and dietary score, which implies that physically active participants showed greater adherence to a healthier dietary pattern, i.e. the Mediterranean diet (higher values of the diet score). In addition, active men and women consumed lower quantities of alcoholic beverages as compared to sedentary. Multivariate analysis (that used physical activity index as an independent variable and diet score as a dependent variable) showed that all the previous associations were independent from age, sex, education and financial status of the participants, as well as region of living (all p's < 0.05).\nTable 3\nBehavioural characteristics by physical activity status and sex\nPhysical activity status\nMen\nSedentary\n1\nst\ntertile\n2\nnd\ntertile\n3\nrd\ntertile\nP\nCurrent smoking\n58%\n54%\n54%\n48%*\n0.01\nAlcohol intake (ml/d)\n280 ± 40\n250 ± 55*\n190 ± 95**\n180 ± 90**\n0.001\nDiet score (0 – 55)\n28 ± 10\n32 ± 25*\n38 ± 23**\n41 ± 22**\n0.001\nZDRS (0 – 100)\n48 ± 23\n41 ± 23\n38 ± 16\n32 ± 17\n< 0.001\nWomen\nSedentary\n1\nst\ntertile\n2\nnd\ntertile\n3\nrd\ntertile\nCurrent smoking\n49%\n44%\n36%**\n29%**\n0.041\nAlcohol intake (ml/d)\n120 ± 40\n110 ± 55\n90 ± 55*\n85 ± 50**\n0.001\nDiet score (0 – 55)\n29 ± 11\n36 ± 22*\n42 ± 19**\n43 ± 21**\n< 0.001\nZDRS (0 – 100)\n52 ± 21\n44 ± 13*\n39 ± 13**\n34 ± 19**\n0.001\nVariables are expressed as mean value ± SD or relative frequencies.\nP\n-values of the last column derived from stratified ANCOVA tests, after controlling for age and denote the significance of the association between physical activity status and smoking, dietary habits and depression status of the participants.\n* \nP \n< 0.05 and ** \nP \n< 0.01 Bonferronni corrected probability values for the comparisons between physical activity groups and sedentary participants.\nAn inverse relationship was observed between physical activity status and ZDRS, which indicates that men and women who used to exercise were less likely to have depressive symptoms as compared to sedentary (standardised beta-coefficient = -0.34, p = < 0.001), irrespective from the effect of various potential confounding factors like age, sex, educational, financial and occupational status. Moreover, participants in the highest tertile of physical activity had 41% lower odds (95% confidence interval 0.35 to 0.9) of having major depressive syndromes (i.e. ZDRS > 60), after controlling for the previous potential confounding factors.\nPhysical activity and clinical characteristics\nAn inverse relationship was observed between body mass index and physical activity score (partial \nr \n= -0.46, p < 0.001), after adjusting for age and sex. Participants in the highest tertile of physical activity had 48% lower odds of being obese (95% confidence interval 0.42 to 0.64), after adjusting for age, sex, smoking habits, blood pressure, total cholesterol and glucose levels. The prevalence of hypertension was 38% in men and 24% in women. Physical activity was also associated with lower odds of being hypertensive (odds ratio = 0.76, 95% confidence interval 0.59 to 0.98), irrespective of age, sex, smoking habits, total cholesterol and glucose levels. Moreover, compared to sedentary, people in the highest tertile of physical activity had on average 15 mm Hg lower systolic (p = 0.02) and 8 mmHg lower diastolic (p = 0.04) blood pressure levels, after adjusting for age, sex, body mass index and diet score. We have also observed that 54% of men and 60% of women had total serum cholesterol levels <200 mg/dl. No association was observed between physical activity and presence of hypercholesterolemia (p = 0.76).\nAfterwards we calculated the cumulative distribution of four major cardiovascular risk factors, i.e. obesity, hypertension, hypercholesterolemia, and diabetes. We observed an inverse relationship between physical activity index and the cumulative score of risk factors (partial \nrho \n= -0.33, p < 0.001), after adjusting for age, sex and smoking habits. Figure \n1\n illustrates the inverse association between activity status and risk factors score in men and women, respectively. Additionally, we may observed that even moderate amounts of physical activity (i.e. second tertile) have a beneficial effect on the cumulative distribution of these cardiovascular risk factors.\nFigure 1\nCumulative distribution of cardiovascular risk factors score by physical activity status.\nDiscussion\nIn this observational study of 3042 adult people from Attica region, Greece, we found that, roughly, one out of two men and women were physically active. Therefore, it could be speculated that, about, 4 million Greek adults are sedentary. In addition, men were more likely to be physically active as compared to women, while the lowest physical activity rates were observed in middle-aged participants (i.e. 40 to 49 years old). A description of the profile of the participants showed that physically active people had higher occupation skills, were more likely to live in rural areas, to be unmarried, to be non smokers and they were devoted to a healthier dietary pattern, as compared to sedentary, irrespective of age and sex. In addition, the cumulative score of four major cardiovascular risk factors, i.e. obesity, hypertension, hypercholesterolemia, and diabetes, was inversely associated with the applied physical activity index. Finally, physically active men and women were less likely to report depressive symptoms.\nPhysical activity and socio-demographic characteristics\nPhysical activity has been related with social status in some, but not all studies. For example, in a population-based sample from Copenhagen [\n12\n], the investigators observed that subjects with the lowest level of education (a proxy of social status) were most frequently physically inactive, as well as heavy smokers, heavy drinkers and obese. In another community health survey of Adelaide [\n13\n] the investigators reported that low physical activity status was strongly associated with low education and reduced mobility, number of social connections and degree of satisfaction with recreation facilities. On the other hand, Tammelin et al. [\n14\n] reported that infrequent participation at young age was associated with physical inactivity at older age, while low social class of the childhood family was associated with physical inactivity in adolescence but not with inactivity at older age. In our study, we observed a positive association of physical activity with some (occupation skills), but not all social status indices (education level and annual income). This may reflect various cultural characteristics of the participants, but it could not be further investigated by the present work.\nWe also found that participants who were devoted in organised sports and members in sports clubs were more frequently persistent exercisers as compared to those who did not. This is in accord to the reports from several other investigators, which observed that participation in organised sports was associated with the stability of physical activity [\n15\n-\n17\n]. Thus, we may suggest that the development of programs to promote participation in organised sports it could be a worthwhile investment for their health and well-being.\nWe observed that men were more likely to be physically active as compared to women, irrespective of age. These gender differences are pronounced in most countries. For example, it has been reported that the proportions of girls exercising actively is approximately half of that of boys among 15-year-olds in Greenland, Lithuania and Greece [\n18\n]. The issue of gender differences is also relevant, when we consider physical activity trends from adolescents to adults. In addition, we found that the gender difference in physical fitness was even higher than the difference in physical activity status, since men were more commonly persistently fit. The aforementioned gender differences have been reported in several studies [\n19\n-\n21\n], and may reflect behavioural and work-related differences, as well as differences in family responsibilities between sexes that could not investigated in this study. However, it should be noted that Barnekow-Bergkvist et al. [\n22\n] reported that, although more men than women participated in sports activities at the age of 16, there was no significant difference at the age of 34.\nRegarding marital status we observed that never married participants were more likely to be physically active as compared to married or divorced/widowed, independent from age and sex of the participants. There are very sparse data in the literature concerning the relationship between marital status and physical activity. In a population-based study of men and women from the US [\n23\n], the investigators observed that the change from a married to a single state did not affect physical activity relative to remaining married, whilst the transition from a single to a married state resulted in significant positive changes in physical activity relative to remaining single. Thus, they concluded that marriage might potentially set the stage for natural changes in physical activity status. Family, work and other social responsibilities, as well as cultural difference may be responsible for the divergence of the results between the present and other studies.\nPhysical activity and depression\nDepression constitutes a worldwide health problem, because is associated with functional impairment in normal life and at work, poor compliance with medical therapy and lifestyle risk factors interventions [\n24\n]. Much discussion has been made regarding the association between depression and physical activity status [\n25\n-\n31\n]. Few population-based studies reported that physical activity was not associated with depression [\n25\n-\n27\n], while other studies reported a protective effect [\n28\n-\n33\n]. For example, the results from the first National Health and Nutrition Examination Survey (NHANES) reported that the risk of depressive symptoms at follow-up were two-fold for women with little or no physical activity compared to women with much or moderate recreational physical activity [\n28\n]. Although it is difficult to compare findings from prospective with cross-sectional studies, we have found similar results with the NHANES since participants in the lowest tertile of physical activity had 1.6-times higher odds of reporting major depressive syndromes. Whether physical activity is associated with depression it is difficult to answered by the present study. Although we provided clear scientific evidence, further research is needed to state cause – effect relationships and to clarify the mechanisms underlying the association between physical activity and depression.\nPhysical activity and clinical characteristics\nFurthermore, we confirmed previous reports concerning an inverse association of physical activity with the prevalence of obesity and hypertension [\n34\n-\n36\n], while no relationship was observed in our, as well as several other studies, regarding physical activity and hypercholesterolemia [\n37\n,\n38\n]. We also found an inverse relationship between presence of leisure time physical activities and the cumulative distribution of four major cardiovascular risk factors (i.e. obesity, hypertension, hypercholesterolemia, and diabetes). We expanded the previous findings by showing that even moderate amounts of physical activity were associated with the frequency of these cardiovascular risk factors levels. It is becoming more apparent that most of the health benefits at a minimal risk are derived from low to moderate intensity physical activities [\n39\n].\nLimitations\nThis is a cross-sectional study that cannot provide causal relationships, but only state hypotheses for future research. Occupational physical activity which was not taken into account in the present study, and misreporting of physical activity status due to self-reports may confound, at least in part, the strength of the observed relationships. Another limitation is that LTPA has been related to a healthier lifestyle habits and consequently to a better health status. For example, adoption of a healthier dietary pattern or reduced smoking habits may be more common among individuals who were devoted to leisure time exercise. Thus, the benefits from LTPA on the prevalence of risk factors (Figure \n1\n) cannot provide causal relationships and may be miss-interpreted at population level. Finally, although we took into account dietary and smoking habits of the participants the influence of the potential confounding effect of these factors cannot entirely be excluded.\nConclusion\nA considerable proportion of the population studied reported physically inactive, indicating that sedentary lifestyle becomes a serious epidemic in Greece, and especially in women. We have also illustrated the socio-demographic profile of people that are physically active and we revealed the relationships between physical activity and various lifestyle behaviors, the presence of depressive symptoms and several metabolic disorders associated with cardiovascular risk. Despite the limitations of the cross-sectional design of the present study, our findings may carry an important public health message, i.e. to inform the community and especially middle-aged, low socio-economic status people living in urban areas, about the benefits derived from physical activity in order to prevent future cardiovascular events and other psychological disorders.\nCompeting interests\nThe author(s) declare that they have no competing interests\nAuthors' contributions\nCP = drafted the paper, was the principal investigator, and had the concept, and design of the study, DBP = wrote the paper, was the principal investigator, and had the concept and design of the study, performed the data analysis, YL = drafted the paper, participated in the clinical evaluation of the participants and CS = drafted the paper.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
25
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nWar Syndromes: The Impact of Culture on Medically Unexplained Symptoms\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\nThe general principle that the experience of combat damages servicemen's long-term physical and mental health is recognized.\n1\n However, controversy has raged over the nature of particular post-combat disorders such as shell shock, disordered action of the heart (DAH), effort syndrome, effects of Agent Orange and, not least, Gulf War syndrome.\n2\n We, among many others, have argued that they should be classified as functional syndromes\n3\n characterized by medically unexplained symptoms,\n4\n which include: fatigue, weakness, sleep difficulties, headache, muscle ache and joint pain, problems with memory, attention and concentration, nausea and other gastro-intestinal symptoms, anxiety, depression, irritability, palpitations, shortness of breath, dizziness, sore throat and dry mouth.\n5\n Despite popular claims to the contrary, no simple biomedical aetiology has been discovered to account for these disorders, hence the term “medically unexplained”.\n6\n Furthermore, they are not easily interpreted using accepted psychiatric classifications. Without demonstrable organic cause, war syndromes have attracted diverse causal explanations, ranging from pressure on the arteries of the chest, constitutional inferiority, toxic exposure, bacterial infection to microscopic cerebral haemorrhage.\nOne area of understandable confusion is the relationship between conventional psychiatric disorders, in particular post-traumatic stress disorder (PTSD), and syndromes characterized by medically unexplained symptoms. This lack of clarity is hardly surprising since both can arise in the context of warfare. PTSD, first recognized as a legitimate psychiatric diagnosis in 1980,\n7\n is defined in psychological terms as a disorder of traumatic memory, featuring nightmares, intrusive recollections and flashbacks (which overlap with the normal ways in which veterans remember their experiences), but also behaviourally since these features lead to avoidance and impaired social interaction. Hence, PTSD is distinct from functional somatic syndromes, such as irritable heart or DAH, which are defined by the presence of multiple, clinically-significant somatic symptoms but do not require overt psychological experiences such as nightmares or avoidant behaviour. However, these somatic disorders are associated, but are not synonymous, with anxiety and depression.\n8\nCulture is an elusive phenomenon but has been defined as “systems of meaning” that “are necessarily the collective property of a group”.\n9\n In essence, it refers to learned patterns of thought and behaviour characteristic of a given population. Culture, perhaps, has its greatest opportunity to influence the form of, and meaning attached to, medical disorders when scientific experiment and clinical investigation have failed to define or identify their aetiology. Functional somatic syndromes, which arise in the context of traumatic experience thereby evoking powerful feelings, may be particularly prone to the impact of such forces.\nEdward Shorter argued that individuals possess a “symptom repertoire”, which is available to both the conscious and unconscious mind for the physical expression of psychological conflict.\n10\n Particular symptoms may appear in specific periods partly as a result of underlying cultural trends. At a societal level, popular health fears alert patients to particular areas of the body and can offer explanations that resonate with widely shared beliefs. Servicemen during the Second World War, for example, may have tended to emphasize gastro-intestinal symptoms because of the general fear of peptic ulcer. Not only would dyspepsia and stomach pain convey a sense of seriousness, they would plausibly gain the attention of a regimental medical officer primed to invalid men who might break down in action. At a professional level, doctors are likely to look for, or to emphasize, symptoms that fall within their specialist area or are considered significant at the time. A gastroenterologist will tend to look for stomach-related symptoms and pay less attention to muscular and joint pains than, say, a rheumatologist.\n11\n Given the rising incidence of peptic ulcer during the 1940s and the risk of death from perforation, physicians paid particular attention to dyspepsia in individuals who might serve in situations without ready access to emergency medical services. The very real difficulties of making an accurate diagnosis, often led to multiple and varied investigations. In the mind of the serviceman, this attention may have reinforced any belief that his gut pain had a life-threatening cause. Thus, the selection of symptoms, the weight that is attached to them and the explanations that follow from both doctors and patients were likely to have been subject to cultural forces.\nFurthermore, it is hypothesized that the form taken by war syndromes was influenced by the evolving nature of combat: not least the effect of new technology on weaponry but also the impact of “modernity” in Weberian terms of the growth and differentiation of bureaucracy; the application of standardization and routine to administrative action; and the employment of experts to define and order such systems.\n12\n The role of the soldier and his place in society plausibly influenced the behaviour of veterans and the explanations offered for such post-combat disorders as they experienced.\nAlthough considerable research has been directed towards the cultural history of PTSD,\n13\n war syndromes have been somewhat neglected. Some studies have assumed that PTSD is, in effect, a modern re-interpretation of popular diagnoses of earlier wars. Dean argued, for example, that the symptoms of PTSD, including flashbacks, can be identified in the accounts of veterans of the American Civil War.\n14\n Indeed, some have argued that railway spine and shell shock were simply PTSD by other names.\n15\n Furthermore, there is a “Whiggish” tendency, notable in the quasi-historical accounts of some contemporary trauma specialists, to assume that PTSD trumps all previous conditions as we move in a steady progression from ignorance to post \nDSM-III\n enlightenment.\nIn this paper we seek to assess the impact of culture on the expression and interpretation of functional somatic syndromes during the Boer War, First and Second World Wars and the Gulf conflict. Medically-unexplained symptoms are explored in their own right and not simply as the putative ancestors of PTSD. We will then compare evidence derived from random samples of servicemen suffering from war syndromes with contemporary accounts in an attempt to understand the form of these disorders.\nMethod\nThe statistical investigation on which this paper is based has already been published and the methodology and results are reiterated in their simplest form to provide a basis for a wider discussion.\n16\n To identify symptom patterns, random samples of veterans diagnosed with post-combat disorders typical of particular conflicts were selected. War pension files were used as the primary source because they contained detailed medical and military reports. The assessment procedure for soldiers did not change greatly over the period, though the criteria were revised. After 1916, awards were no longer based on a veteran's ability to earn a living wage but were granted according to a standardized schedule of injury in which, for example, the loss of two or more limbs entitled a man to a 100 per cent pension.\n17\nSelection of Subjects\nAll the surviving pension files for Boer War veterans, formerly administered by the Royal Hospital, Chelsea, are held at the National Archives (PIN71). An analysis of mortality rates and serial numbers showed that these are not a complete holding. The 6,276 files represent some of the longest-lived or more severe cases. Because the catalogue listed pensioners alphabetically without recording their diagnosis, it was necessary to examine every file. To generate representative samples, consecutive cases were extracted in proportion to their alphabetical distribution by surname. In this way 200 cases of disordered action of the heart (DAH) or valvular disease of the heart (VDH), where subsequent reports and death certificates indicated a functional disorder, were gathered, together with 200 cases of rheumatism (in the absence of organic signs such as inflammation and joint swelling). Whilst surveying the archive, a few pensioners were discovered who had served in Victorian campaigns, notably Afghanistan, Egypt and the Sudan. Twenty-eight of these had functional somatic disorders, which fell into two broad diagnostic groups: cardiac (19), which included “palpitation” and “irritable heart”, and debility (9).\nThe only surviving war pension records from the First World War are held at the National Archives (PIN26). The 22,756 cases in the holding are based on the London Region of the Ministry of Pensions, which under the decentralized system of May 1919 acquired responsibility for South East England.\n18\n The sampling exercise had been undertaken by War Pensions staff, who probably chose the London Region as the largest and most accessible holding. They selected every fiftieth file to create a 2 per cent sample. On this basis, the 22,756 files were extracted from 1,137,800 records. An official report calculated that by March 1930, 1,644,000 pensions or gratuities had been granted to veterans of the First World War,\n19\n which suggests that the London Region represented about 60 per cent of the total number of pensions and gratuities awarded for the conflict. The catalogue, which is organized alphabetically by recipient, was placed into a database and analysed by diagnosis. Using a random-number generator, samples of 200 cases of DAH (to provide a direct comparison with the Boer War) and 200 cases of shell shock, or neurasthenia as it was re-classified in 1917, were selected. The proportions of officers to other ranks for DAH and neurasthenia were adjusted to reflect their distribution within the total population. In addition, a random selection of 167 servicemen who had been gassed without permanent organic injury were included. In total, 305 pensions granted to nurses have survived; all awards for DAH and neurasthenia were included.\nThe task of creating a random sample of servicemen who had been gassed but not suffered long-term physical damage was more complex. A catalogue survey revealed 279 veterans awarded a war pension for the effects of gas or gas poisoning. A systematic examination of these cases indicated that many showed the symptoms of serious exposure to toxic gases with identifiable damage to lungs, skin and eyes. Soldiers who had lesser exposures and no lasting objective signs and yet suffered from unexplained symptoms were often re-categorized by doctors as DAH.\n20\n It was necessary, therefore, to examine all 279 veterans with a pension for gassing to distinguish the organic cases from the functional ones. Approximately 30 per cent proved to have objective signs of toxic exposure and were excluded from the investigation. A further 20 per cent had incomplete or limited medical files and were also excluded. This gave a total of 143 cases. To obtain a sample of significant size, DAH files were selected using a random-number generator to identify veterans who had been gassed. Twenty-four such servicemen were added to the sample in this fashion, bringing the total to 167.\nPension files relating to the Second World War and subsequent conflicts are closed to public inspection and were held by the War Pensions Agency. Ministerial permission was obtained to gather anonymized data from these records. The files are stored chronologically from the time that they were awarded and sub-divided between the three services and between officers and other ranks. The other ranks' files are divided into two groups: those that applied for a pension between 1939 and 1942 and who were assessed on a regional basis (133,500 files), and those that applied between 1942 and 1945 and were assessed centrally (750,000 files). These central files are further divided into two groups: M2 and M6. The M2 series continued chronologically from the old regional centres and covers the years 1943 to 1945. The M6 series was created in 1945 to deal with servicemen released (rather than discharged) from the forces at the end of the war. These soldiers were released rapidly either because of their length of service, because their skills were urgently needed in industry, or on compassionate grounds. The M6 series was discontinued in 1950. In addition, there are 215,000 files in payment, relating to the Second World War. The structure of the archive has important implications for the design of the sample, as different periods of the war saw different groups of servicemen granted pensions. Awards in the first year, for example, were often to elderly territorials or re-enlisted regulars who found active service too stressful. Before the selection and training of troops became carefully controlled, many conscripts were discharged from the forces because their educational, psychological or physical attributes made them unable to cope with the rigours of training.\n21\n The Normandy campaign of 1944 saw many seasoned troops break down, some war-weary after earlier combat in Africa and Italy. To reflect the various changes that occurred to the pension population during the war, files were randomly extracted to equate with the proportions of the archive.\nThree diagnostic groups were chosen: effort syndrome (for comparison with the Boer War and First World War samples of DAH) and psychoneurosis (for comparison with shell shock/neurasthenia). To reflect the change in medical priorities from the heart to the gut, 100 cases of non-ulcer dyspepsia were also randomly selected. Relatively few pensions were awarded for effort syndrome and all cases were included.\nConsiderable problems were encountered in finding awards for psychoneurosis, effort syndrome and dyspepsia from the Korean War and campaign in Malaya in part because troops deployed there represented a small proportion of the UK's armed forces. All cases were included. Although pensions have been granted to veterans of the Gulf War, we were not granted permission to consult these files. Nevertheless, it was important to study a group who believed that their health was damaged by military service. The Ministry of Defence granted access to anonymized case records from the Gulf Veterans' Medical Assessment Programme at St Thomas' Hospital. From their database of 2162 army personnel, a sample of 400 Gulf veterans was selected using a random-number generator.\nMedical notes in war pension files were in most cases detailed and covered the serviceman's history from enlistment until demise; death certificates were often included. Veterans were required to attend regular medical boards to assess their disability and specialist opinions were sought. As a result, symptoms were recorded throughout an individual's military service and after discharge. The long-term nature of the notes allowed cases to be excluded if a serviceman was found to be suffering from an organic disorder or a major mental illness. Prisoners-of-war were not included because of the psychological stress they experienced and the nutritional deficits which many had suffered. The investigation was restricted to members of the British army. A total of 1856 subjects were included drawn from six conflicts and representing ten diagnoses (\nTable 1\n).\nFor each subject biographical and military details were recorded, together with a possible 94 symptoms extracted from medical notes taken during service and, where possible, for a decade after discharge from the forces. The 94 symptoms were then reduced to the 25 most common and the resulting dataset of 1856 soldiers subjected to cluster analysis.\nWith the exception of the Gulf War sample, the evidence for this study was derived from war pension records. In practice, these files had been used to establish whether a veteran was entitled to financial compensation and, if a dispute occurred, could form the subject of an appeal or, more rarely, a court case. As a result, claimants had a vested interest in reporting symptoms and may on occasion have exaggerated their severity and number. By contrast, the examining doctors, who were employed by the Ministry of Pensions, were instructed to test the veracity of these claims and to look for signs of recovery. Pensioners were required to attend an annual board composed of two or more doctors until the disability was regarded as stable. Thereafter assessments were more sporadic unless the veteran believed that his condition had deteriorated. War pension case notes contain inherent bias but we have no evidence to suggest that these competing forces changed in any significant respect over the period of this investigation.\nResults\nThe analysis identified three clusters of post-combat syndromes: a debility cluster (n = 847), a somatic cluster (n = 434) and a neuropsychiatric cluster (n = 575). Although a significant statistical difference was found between the three clusters (\nTable 2\n), there was considerable overlap in the presentation of symptoms. The debility cluster was characterized by fatigue, difficulty completing tasks, shortness of breath and weakness, while rapid heartbeat, tremor, headache, dizziness, pains in joints, difficulty sleeping, changes in weight and anxiety were moderately represented. Psychological and neurological symptoms, such as depression, memory impairment, irritability and poor concentration were notably absent. The somatic cluster was typified by rapid heartbeat, shortness of breath, fatigue and dizziness. Difficulty completing tasks, headache, tremor and anxiety were moderately represented. This symptom cluster was indicative of a functional cardiac syndrome.\nAlthough a range of bodily symptoms (shortness of breath, tremor, pains in joints, back pain, excessive sweating and rapid or irregular heartbeat) were prominent in the neuropsychiatric cluster, it was distinguished from the somatic group by a range of psychological symptoms, including fatigue, headache, depression, anxiety and difficulty sleeping. In addition, difficulty completing tasks, forgetfulness, dizziness, weakness, irritability, poor concentration, jumpiness, changes in personality, nightmares and weight change were moderately represented.\nUsing logistic regression analysis, an underlying association was detected between war (in effect, chronology) and clusters of symptoms. The debility syndrome was largely drawn from veterans of late Victorian campaigns, the Boer War and First World War. The somatic syndrome represented First World War with subsidiary elements from the Boer War and Second World War. The neuropsychiatric cluster was predominantly composed of Second World War and Gulf War servicemen.\nCluster membership was cross-classified against contemporary diagnosis. Because diagnosis tends to follow changes in medical knowledge and cultural developments, the temporal pattern identified in the analysis by war is also apparent from this variable (\nTable 3\n). For example, functional cardiac disorders (palpitation, irritable heart, DAH and effort syndrome) were little understood until the First World War and had been a major cause of discharge from the British army. Cluster one has 57.3 per cent of all functional cardiac disorders cases, cluster two 39.1 per cent and cluster three 3.5 per cent. By comparison, psychological disorders (neurasthenia and psychoneurosis), which became increasingly recognized as the twentieth century progressed, are distributed as follows: cluster one 22.2 per cent, cluster two 10.8 per cent and cluster three 67 per cent.\nThe Medical Expression of War Syndromes\nBoth generic terms, “war syndrome” and “post-combat disorder”, are of recent origin, and somewhat misleading insofar as they have been applied to servicemen who have broken down in training or when deployed to the comparative safety of rear echelons. It is important to distinguish them from what was termed battle exhaustion or combat fatigue and is now known as combat stress reaction. These are the immediate effects of battle and manifested by an inability to function largely because of physical and mental fatigue. Such cases can develop into post-combat disorders if a serviceman fails to recover after a short period of rest and rehabilitation. Because it has only recently been proposed that a common theme runs through these war syndromes,\n22\n each campaign tended to generate its own specific label. To what extent, therefore, do contemporary diagnostic terms, ideas of aetiology and changes in the technology of warfare explain the three clusters that have been identified?\nFocus on the Heart\nSymptoms relating to the heart (palpitation, chest pain and shortness of breath) are prominent in both the debility and somatic clusters, which relate to disorders of the late nineteenth and early twentieth century. Military medicine in this period struggled to explain growing numbers of heart disorders for which no organic cause could be found. A variety of terms were employed, including soldier's heart, irritable heart, palpitation and later disordered action of the heart, reflecting the general confusion. Jacob Da Costa (1833–1900), who had studied the phenomenon during the American Civil War,\n23\n concluded that there was no clear-cut cause, though his analysis of 200 cases (selection criteria were not stated) showed that 38.5 per cent had been subject to “hard field service and excessive marching”, a further 30.5 per cent had previously suffered from diarrhoea.\n24\nCases of palpitation had been recorded by the British army during the Crimea, though discharges became a serious cause for concern in 1864 following a presentation at the Royal United Services Institute by W C Maclean (d. 1898), professor of military medicine at the Army Medical School, Netley. Although Britain was not then at war, these soldiers had broken down either under the rigours of training or when serving overseas, particularly in India. Subsequently, Maclean surveyed 5500 soldiers admitted to the Royal Victoria Hospital, Netley, who had served abroad between 1863 and 1866, and found that almost 10 per cent had been discharged from the forces with a heart disorder.\n25\n Having excluded rheumatism, excessive alcohol consumption, heavy smoking or over-exertion as causes, Maclean considered that the weight and distribution of the soldier's equipment were responsible: “the present accoutrements are highly injurious to the health of infantry soldiers and have a large share in producing many affections of the lungs and heart common among them”.\n26\n He argued that webbing supporting a pack constricted the major blood vessels to and from the heart forcing it to pump excessively hard to maintain circulation. Having reached a similar conclusion, the 1865 War Office inquiry recommended the redesign of equipment affecting the chest.\n27\n The marked differences in incidence between units, Maclean believed, related to illness behaviour: “in well-disciplined regiments the practice of falling out at drill or on the line of march is discouraged, and men will bear and suffer much, rather than incur the imputation of being ‘soft’”.\n28\nA further survey of 1635 cardiac admissions to Netley Hospital between 1863 and 1869 by A B R Myers, assistant surgeon to the Coldstream Guards, found that 1322 (80.9 per cent) were discharged from the forces and only 276 (16.9 per cent) returned to duty.\n29\n Having concluded that heart disorders were “more prevalent in the army than the civil population”, Myers concluded that three factors accounted for this difference: rheumatic fever, Bright's disease and violent manual labour. He too pointed a finger at the soldier's equipment:\nHis waist-belt adds to the constriction below the chest, and his tunic collar above it … and then, to complete the artificial chest case, the knapsack straps supply all that is requisite, whilst the pouch-belt adds its share to the general compression. The chest, thus fixed as it were in a vice, has little or no power of expansion, and the circulation through the heart, lungs and great vessels is proportionately impeded.\n30\nConcern in the UK mounted in 1876 when re-designed equipment failed to prevent new cases of irritable heart. Indeed, the Royal Hospital, Chelsea, awarded some ex-servicemen disability pensions for “palpitation” after the Afghan War of 1879 and the various campaigns in Egypt (1882–89) and the Sudan (1896–97).\n31\n Despite this evidence that there was an association with combat, Surgeon Arthur Davy suggested that the setting-up drill caused an over-expansion of the chest, which in turn produced dilatation of the heart thereby inducing “irritability”.\n32\n Hence, late-nineteenth-century studies of DAH attempted to identify a mechanical pathology, whether hypertrophy, valvular lesion or aortic dilatation, and proposed mechanical causes, commonly an obstruction of the heart's outflow.\n33\n Because there was no effective treatment of these supposed organic conditions, servicemen were simply discharged, while investigators continued to search for ways to prevent new cases.\nDisordered action of the heart was a major cause of invalidity during the South African campaign of 1899–1902. According to official statistics, 3631 servicemen were hospitalized with DAH, and of these 41 per cent were invalided to the UK where they were generally discharged.\n34\n The highest incidence of DAH was reported in orderlies of the Royal Army Medical Corps, explained by the great distances that field units were required to march to support fighting battalions.\n35\n In the latter stages of the war, a large number of small columns were deployed against the Boers so that medical units had long periods of continuous marching to keep up with the widely spread engagements. It was concluded that the prolonged strain of carrying heavy weights and the pressure of straps on the chest had damaged the heart. An official report also argued that “cardiac exhaustion cases were much more frequent among men of volunteer companies than the regulars, probably due to the great difference of their usual daily occupation from the life of a soldier on active service”\n36\n—an observation that would be repeated during the next century. Once a soldier had succumbed to DAH, it was noticed that the symptoms returned if he had to “undergo any extra exertion, or from the excitement or nervousness of going under fire”. These cases also increased in number “if the physical strength of the men cannot be kept up by good and sufficient food and the necessary amount of sleep and rest”.\n37\n Thus, the important connection between battle fatigue and continuous exposure to combat had been observed but its implications not fully understood.\nAlthough heavy smoking was thought to play a contributory part in DAH, the trend from rural to industrial recruits was now identified as a significant cause: “the ill-fed, anaemic, under-sized and somewhat neurotic lads, of which the larger cities produce so plentiful a supply as compared with the sturdy, somewhat lethargic country lad”.\n38\n Indeed, the scandal, much canvassed by politicians and journalists, over the apparently poor physique of potential recruits during the Boer War led to the setting up of the Inter-Departmental Committee on Physical Deterioration in 1904.\n39\n Its report argued that the problem was bound geographically and socially to the poor of the slums and that the principal cause was overcrowding.\n40\n Ironically, it was the widespread nature of shell shock and other war syndromes during the First World War that helped to undermine the traditional distinction between the hereditarily fit and unfit. When officers were found to suffer disproportionately from the disorder, mental illness could no longer be conceived in the restricted realm of degenerates with weak hereditary constitutions.\n41\nAlthough shell shock was the quintessential war syndrome of 1914–18, soldier's heart or DAH did not disappear. Howell has argued that military physicians, under the leadership of Thomas Lewis, re-defined the disorder as “effort syndrome” in a way that was “more consistent both with acute wartime exigencies and with an ongoing transformation of the concept of heart disease from static and anatomical to dynamic and physiological”.\n42\n In the opening phases of the war, for example, the disorder was hypothesized not in terms of improper drill and faulty equipment but as a result of excessive glandular secretions or infectious micro-organisms. Early in 1916, Sir James Mackenzie argued that the privations of trench warfare not only weakened men's constitutions but also provided a suitable habitat for toxic bacteria.\n43\n The net result, he believed, was a state of general exhaustion and that heart abnormalities were not cardiac in origin, but the outcome of injury to the central nervous system.\n44\n This interpretation had parallels in the late-nineteenth-century idea that neurasthenia was a consequence of influenza or typhoid infection. Despite the existence of toxic or post-infective explanatory models, these did not achieve widespread popularity in contrast to the latter part of the twentieth century when they were used to account for the effects of Agent Orange and Gulf War syndrome.\nSpecialist military hospitals were set up in Hampstead and Colchester under Thomas Lewis to research these hypotheses.\n45\n Although he was unable to discover the cause of DAH, Lewis ruled out a number of organic factors, including valvular lesions. By the end of the war, he had identified three possible pathological mechanisms: decreased buffer salts in the blood, an increased leucocyte count, and a difference in urinary constituents (increased calcium and oxalic acid together with decreased urea).\n46\n However, none of these hypotheses were mentioned in the 1940 edition of Lewis's \nThe soldier's heart and the effort syndrome\n, which suggests that further investigation had failed to establish a connection. Lewis did retain his conviction that this was a disorder of functional capacity and that the symptoms represented “exaggerated manifestations of the healthy responses to effort”.\n47\n In his 1917 report, Lewis recommended that terms such as irritable heart and DAH be replaced by “effort syndrome” because they conveyed the “meaning of a primary cardiac disorder”. Graded exercises were used not only to assess the severity of the disorder but as a treatment, soldiers being encouraged at each increment of exertion.\nRheumatism\nDuring the Boer War, rheumatism, or muscle and joint pain associated with fatigue, became prominent causes of invalidity. “Among the symptoms we find prominently,” recalled Anthony Bowlby (1855–1929), a civil surgeon, who had worked at the Portland Hospital in Rondebosch and Bloemfontein during 1900, were “pain, in the form of headache, generally posterior, pains in the neck, pains in the back and limbs, so that these cases are generally sent back as cases of rheumatism; general feebleness of the muscular system amounting to paralysis more or less pronounced”.\n48\n The Boer War saw 24,460 troops admitted to hospital with rheumatic fever or rheumatism, of whom 4305 were evacuated home. Although today rheumatic fever, a disease that can cause heart failure, is differentiated from non-articular rheumatism, a disorder characterized by subjective symptoms (joint pain, stiffness and tenderness), physicians in the nineteenth century were unable or unwilling to draw such a definite distinction.\nA systematic investigation of the war pension files administered by the Royal Hospital, Chelsea, has shown that most veterans who had been awarded a pension for rheumatism showed no objective signs of the disease within a few years of discharge. Dr J W Washbourn, who ran the Imperial Yeomanry Hospital at Pretoria in the latter stages of the war, treated 296 cases of chronic muscular rheumatism (the fourth most common medical disorder there) but was unable to establish a connection with rheumatic fever. At a loss to explain the phenomenon, Washbourn considered that it was the result of “the men's food and especially the want of fresh vegetables”.\n49\n A more common explanation offered by both men and RAMC doctors was that exposure to cold and wet on the veldt was the primary cause of rheumatic pains. Because the cardiac complications of rheumatic fever were then untreatable and often led to invalidity and premature death, pains in muscles and joints were a focus of concern for both patients and doctors.\nShell Shock\nAlthough shell shock has become a synonym for the trauma of trench warfare, no unambiguous definition of the disorder exists.\n50\n The closest attempt was made in the report of the Southborough Committee: “emotional shock, either acute in men with a neuropathic predisposition, or developing slowly as a result of prolonged strain and terrifying experience, the final breakdown being sometimes brought about by some relatively trivial cause. [Or] nervous and mental exhaustion, the result of prolonged strain and hardship”.\n51\n In practice, shell shock was characterized by medically un-explained symptoms: tics, paresis, tremor, contractures, fatigue, headache, sleep difficulties, nightmares, memory loss, poor concentration and general bodily aches and pains. As such, it bore little resemblance to the modern definition of PTSD.\n52\nAs regards causation, it was initially hypothesized that there were two varieties of shell shock: commotional and emotional. Frederick Mott (1853–1926), pathologist to the London County Council asylums, categorized it as a form of “commotio cerebri” with a defined physical aetiology. He suggested that the forces of compression and decompression, resulting from proximity to an explosion, in turn led to microscopic brain haemorrhage.\n53\n He also believed that carbon monoxide released by the blast might lead to cerebral poisoning. When it became apparent that many of those soldiers with the symptoms of shell shock had not been close to an explosion, and some not even in combat, Mott accepted the idea of an emotional category. Such individuals with “an inborn or acquired disposition to emotivity” could become so affected by the stress of battle, or its prospect, to “be rendered unconscious or so dazed as to necessitate them being taken or carried to the clearing station”.\n54\nBy contrast, a psychological interpretation of shell shock came from medical officers who had first-hand experience of war in France. Captain Harold Wiltshire, who until August 1915 had been responsible for the diagnosis of functional psychiatric cases at No. 12 General Hospital in Rouen, observed that:\nGradual psychic exhaustion from continued fear is an important disposing cause of shell shock, particularly in men of neuropathic predisposition. In such subjects it may suffice to cause shell shock \nper se\n. In the vast majority of cases of shell shock, the exciting cause is some special psychic shock. Horrible sights are the most frequent and potent factor in the production of this shock. Losses and the fright of being buried are also important in this respect.\n55\nC S Myers, a medically-qualified psychologist, proposed that functional symptoms, such as loss of memory, partial paralysis or mutism, were expressions of a traumatic experience of which the servicemen could not consciously admit. He believed that an individual had to acquire “volitional control” over memories of these events “if he is to be healed”.\n56\n Almost as soon as shell shock was interpreted as a psychological, rather than a physical, injury, efforts were made to suppress use of the term. Fearing that it would open a floodgate to malingerers and war pension claimants, Sir Arthur Sloggett, Director-General of Medical Services of the British Armies in the Field, ruled in December 1916 that the term was to be discouraged in favour of “Not Yet Diagnosed, Nervous” (NYDN), while strict guidelines were laid down for the clinical management of such cases.\n57\nSpecial “NYDN Centres” were set up about ten miles from the front line in France to treat soldiers by physical methods: rest followed by graduated exercise. If a serviceman failed to respond to treatment and was discharged from the forces, the war pension authorities opted for the diagnosis of neurasthenia, though if heart symptoms predominated a claimant could be re-classified as DAH or effort syndrome. While shell shock disappeared from medical terminology (and was actively proscribed in 1939),\n58\n it gathered strength during the interwar period in popular usage. By comparison, effort syndrome, DAH and, its American variant, neurocirculatory asthenia (NCA), all of which continued to be used in medical literature, did not strike the same cultural chord and gradually fell into disuse as they were superseded by other diagnostic terms.\nIn terms of symptoms, shell shock combined that traditional focus on the heart with a comparatively novel range of neuropsychiatric symptoms. Senses were sometimes affected: men could not hear or see and experienced strange smells, tastes and inexplicable pain. Their physical and mental functioning was also impaired; some could not speak or walk, while their cognitions were affected by nightmares, intrusive thoughts and difficulty concentrating. This was a broader range of symptoms than had been indicated after Victorian campaigns and the Boer War and seemed to express the effects that men felt on their psychological well-being. Indeed, Chris Feudtner had showed how shell shock cases, often volunteers and men with unblemished characters, forced both physicians and the public to begin to question their conception of mental illness as an outcome of constitutional degeneration. “The old dichotomy of sanity and madness simply could not address the questions of the age”.\n59\n A similar conclusion was reached by Ted Bogacz, who argued that the widespread incidence of shell shock “challenged long-held medical opinions about the nature and treatment of mental illness”, while also threatening “a number of traditional moral values”.\n60\nSecond World War: Effort Syndrome and Non-Ulcer Dyspepsia\nFrom being an unexplained form of heart disease to a functional disorder with psychological features, the status of effort syndrome was transformed by three papers published by Paul Wood in the \nBritish Medical Journal\n during 1941.\n61\n By comparing a sample of 175 soldiers admitted to the effort syndrome unit at Mill Hill EMS Hospital with a control population of militiamen, he demonstrated that men with functional cardiac symptoms exhibited a heightened emotional response to stressful activity. Wood concluded that the division into sub-types of effort syndrome (constitutional, induced, post-infective, psychoneurotic and physically fatigued) was “misleading if not meaningless”.\n62\n Effort syndrome, he argued was “an emotional reactive pattern peculiar to psychopathic personalities and to subjects of almost any form of psychoneurosis”.\n63\n Whilst the aftermath of the Second World War did not witness an epidemic of pensions for effort syndrome, Maxwell Jones, Wood's psychiatric collaborator at Mill Hill, observed in 1946 that “there is no reason to assume that the condition has become less common—it is simply that the diagnosis E.S. is out of favour; psychiatrists in this country prefer to classify patients according to their psychiatric disability rather than their effort intolerance”.\n64\nOutwardly, a significant change appeared to have taken place in the physical focus of war syndromes, related not simply to the discrediting of effort syndrome. In 1945, Roy Grinker and John Spiegel observed that “gastrointestinal symptoms flourish in an abundance and variety”, contrasting with “the frequent cardiac syndromes observed in the last war”.\n65\n By 1941 the incidence of non-ulcer dyspepsia had become a “major medical problem” for the UK armed forces.\n66\n In May 1942, digestive disorders accounted for 17 per cent of all discharges for diseases from the army and airforce.\n67\n At first, it was hypothesized that dyspepsia represented a new entity akin to shell shock at the beginning of the First World War; others suggested that it was due to an acute type of peptic ulceration. Yet, studies soon showed that the incidence of ulcer in the civilian population had been growing steadily during the inter-war period and that most servicemen with gastric symptoms had suffered from them before enlistment. These findings led to the conclusion that most cases were of old-standing peptic ulceration, which had broken down under the conditions of active service.\n68\n At a time when diagnostic tools were at best unreliable, gastroenterologists and radiologists tended to err on the side of caution. Estimates of those with peptic ulcer among the large numbers of servicemen suffering from chronic dyspepsia ranged from 89 per cent of 201 cases invalided from France\n69\n to 45.5 per cent of 88 consecutive UK admissions.\n70\n A 1941 study, which included veterans of Dunkirk and the Lofoten raid, found an incidence of 64.2 per cent in 246 servicemen admitted to a military hospital with gastro-intestinal pain. The authors concluded that a change in dietary habits together with the stress of adopting to a new lifestyle were responsible.\n71\n It is interesting that the most obvious explanation, the intense stress of combat, was not explored.\nIn March 1941, H L Tidy, consultant physician to the Royal Military Hospital, Millbank, speaking at a special conference held by the Royal Society of Medicine, identified two potential causes: irregular mealtimes and the heavier nature of army food.\n72\n Psychological factors were excluded because “peptic ulcer and all dyspeptic disturbances were noticeably rare” during the First World War when similar stresses arguably operated. Not everyone agreed with this conclusion. C A Hinds Howell reported 131 cases of “neurotic dyspepsia” in 1941 at a UK military hospital, an increase of 12.4 per cent over the figure for 1940.\n73\n By contrast, he proposed a constitutional explanation:\nThose people of poor personality who in peacetime are only just able to accommodate themselves to their home environment are no longer able to do so when this is changed on enlistment to the discipline of Army environment. Whether it is pure chance that their neurosis is centred on their digestion it is difficult to say.\n74\nAlthough studies conducted at the beginning of the war excluded psychological explanations, increasing contact with patients led to a re-evaluation. An analysis of the social class and lifestyles of peptic-ulcer mortalities led J N Morris and R M Titmuss to conclude that duodenal ulcer was a psychosomatic disorder related to a particular “hypothalamic” type of personality. They considered that the stresses of metropolitan life, rather than nutritional factors, played a key causal role.\n75\nRetrospective studies, based on mortality statistics, established that the war years witnessed an epidemic of peptic ulceration, which rose to a peak prevalence in the-mid 1950s.\n76\n During the Second World War, there was no effective treatment, apart from risky gastrectomy, so that peptic ulcer became “known and feared by the laity as a cause of incapacity and sometimes fatal complications”.\n77\n It was also appreciated that complex investigations could be counterproductive. An editorial in the \nLancet\n for August 1945 observed that “in gastric disorders which come short of actual ulceration army experience has shown that even hospital investigation and the ritual of barium meal examination fix the susceptible soldier's attention increasingly on his stomach and help to perpetuate ‘functional’ symptoms”.\n78\n This suggests that “pure chance” was probably not the explanation for the increase in non-ulcer dyspepsia during the Second World War and that the form taken by conversion disorders were influenced by popular health fears and limitations of medical science.\nUsing the example of hysterical paraplegia, Shorter showed that this disorder was doomed once neurologists had developed accurate neurophysiological methods to distinguish between organic and psychological causation.\n79\n This example suggests that it is unlikely that non-ulcer dyspepsia will ever again be a prominent medically unexplained syndrome. The discovery of histamine H\n2\n-antagonists as an effective treatment of peptic ulcer in 1976,\n80\n subsequent research into the pathological role of Helicobacter pylori and the development of accurate endoscopic techniques have removed any doubt or mystery surrounding stomach disorders.\nWhile cultural forces played an important part in the presentation and recognition of symptoms, they were not the sole factor. It is significant that cluster analysis did not reveal a gastro-intestinal group composed in the main of veterans of the Second World War. Indeed, soldiers diagnosed with non-ulcer dyspepsia are distributed between all three clusters, though to a lesser extent in the neuropsychiatric group. Similarly, ex-servicemen with a diagnosis of shell shock/neurasthenia are not to be found in a single cluster associated with the First World War. Some of them have symptom patterns in common with Gulf War veterans and men who fought in the Boer War. These results suggest that the actual symptom patterns of war syndromes are diverse and less focused on bodily areas than contemporary descriptions and interpretations have suggested. By no means were all sufferers of war syndromes in the First World War troubled by the symptoms of shell shock, and many manifested the traditional cardiac picture of DAH. Effort syndrome endured well into the Second World War when stomach problems and psychological symptoms were thought to dominate post-combat syndromes. It appears therefore that culture may play less of a part in determining symptom patterns than has been suggested. Its main impact may relate to the ways that physicians categorize and interpret functional somatic presentations, and the ways that patients act on and explain their symptoms. Thus, culture can often condition a novel medical explanation that satisfies most of society at a particular time but at the cost of ignoring exceptions and continuities.\nSecond World War: Psyche over Soma\nThe incidence of somatoform disorders, common during the First World War and before, is widely stated to have fallen during the Second World War.\n81\n J A Hadfield, who worked at No. 41 General (Neuropathic) Hospital, regarded “the far greater proportion of anxiety states … as against conversion hysteria (blindness, paralysis etc.)” as “the most striking change” between the two conflicts. Of the 700 servicemen admitted over a period of ten months, he calculated that 53 per cent had a diagnosis of anxiety compared with 24 per cent who had a functional somatic disorder. Hadfield cited the “thousands of ‘shell-shocked’ patients who returned from the Somme and other great battles” as evidence for a greater preponderance of hysteria.\n82\n Without objective measures and statistical analysis of overseas and UK military hospitals, it is impossible to substantiate this claim. However, the epidemic of non-ulcer dyspepsia witnessed during the Second World War suggests that Hadfield overlooked an important category of patients. It is by no means certain that somatoform disorders were displaced by overt psychological presentations, rather it appears that they assumed a different disguise.\nYet Hadfield's view was widely held. An editorial in the \nBritish Medical Journal\n for 30 June 1945 declared:\n“Disordered action of the heart”—a favourite diagnosis in the last war—has given place to “effort syndrome”; and now that that has been shown by Paul Wood, [T.] Lewis, M. Jones and others to be in every respect the equivalent of an anxiety neurosis, it too has lost favour and has become a rare diagnosis. No longer do we talk of “shell shock”: the organic approach has given place to a preference for psychological interpretation.\n83\nMore recently, Joanna Bourke has argued that “unlike the First World War when hysterical reactions greatly outnumbered fear reactions, from 1940 there were epidemics of acute anxiety”.\n84\n This apparent change from physical to psychological symptoms was explained by administrative measures to outlaw diagnoses such as shell shock, the discrediting of effort syndrome and because servicemen were increasingly made aware of unconscious mechanisms in so-called “war neuroses” through education and psychotherapy.\n85\n Hence, it remains conventional wisdom that as psychological enlightenment spread during the twentieth century, psychiatric models for unexplained symptoms gained ascendancy over more intellectually suspect organic claims. To support this contention, it is claimed that hysteria, once common, has now almost vanished from the western world.\n86\n An alternative suggestion is that the former popularity of the diagnosis was a cultural phenomenon, which may be unrelated to real changes in the incidence of hysteria,\n87\n a view supported by common presentation of conversion disorders in neurological, rather than psychiatric, practice.\nGulf War Syndrome: Toxic Exposures\nDuring the Second World War, no post-combat syndrome had been explained in terms of toxic exposure and indeed, apart from men who had been gassed, poisonous substances were not implicated in the First World War or the Boer War. The only exception was perhaps the use of atebrin in South East Asia, as a prophylaxis against malaria, which some Australian troops believed was the cause of impotence, a claim that was to be echoed by Gulf veterans.\n88\n With Vietnam a significant change took place in the attribution of causality. Dioxin (Agent Orange), a defoliant, was sprayed from aircraft over the jungle that provided cover for the Vietcong. Agent Orange derived its name, not from the chemical itself, as was popularly believed, but the colour of the drums in which it was stored. Some veterans suffering from chronic somatic symptoms attributed their illness to the effects of herbicide exposure, while it was also claimed to have been the cause of birth defects in their children.\n89\n Indeed, the Vietnam Veterans Association of Australia suggested that exposure to Agent Orange could have led to a form of “toxic neurasthenia”.\n90\n To date, scientific and epidemiological studies have failed to identify a causal link.\n91\n However, it is noteworthy that the somatic symptoms frequently described by veterans who were exposed to Agent Orange were similar to symptoms commonly associated with other war-related illnesses.\n92\n Exposure to Agent Orange reflected contemporary fears that organic solvents and other chemical compounds could provoke a widespread sensitivity crisis in the body, sometimes involving the immune system. These ideas found civilian expression in sick building syndrome, mercury poisoning syndrome and multiple chemical sensitivities (MCS), autoimmune diseases and dysregulation of immunological processes caused by modern synthetic chemicals.\n93\nDesert Storm syndrome, or Gulf War syndrome as it more popularly became known, has also attracted a range of causal hypotheses, most of which involve exposure to a toxic agent that is unseen or disguised, difficult to detect and potent in its effects.\n94\n Candidates included side effects of multiple vaccinations, smoke from oil-well fires, depleted-uranium shells, chemical and biological warfare, and organophosphate pesticides.\n95\n These explanations reflect powerful cultural themes, and represent civilian concerns translated into a military context. Fears over DU poisoning are related to a general fear of radiation, vaccinations are widely mistrusted as the concern over the MMR has demonstrated, while society's fear of chemical pesticides has, in part, encouraged organic methods of farming.\nThe Changing Nature of Warfare\nThe technology of war and tactical ideas changed dramatically over the period of this study. Troops who fought in the Boer War were often required to march considerable distances to engage the enemy; it was a war of movement without mechanization. Contemporaries believed that the physical exertion involved was, in part, responsible for the various heart disorders encountered. Similarly, shell shock was framed in terms of trench warfare: an expression of the terror felt by men forced to endure passively the effects of artillery bombardment. Although not the subject of this paper, air combat produced its own varieties of post-combat disorder: “flying stress”, “aviation neurasthenia” and later “lack of moral fibre”, which initially were attributed to anoxia, the result of flying in rarified air. The technical nature of modern warfare, and in particular the threat of chemical and biological weapons, is expressed by the symptoms (headache, poor concentration and memory impairment) and explanations surrounding Gulf War syndrome. Not only do the diagnostic labels attached to war syndromes reflect the changing nature of combat, so too do the causal hypotheses advanced by veterans and doctors.\nAn analysis of the military records of servicemen in our study, together with war diaries, revealed that the percentage involved in actual fighting fell over time as the proportion of troops in combat-support roles has risen. Of the Boer War veterans, 77 per cent had been in combat, of the First World War pensioners 73.4 per cent, of the Second World War sample 52 per cent, while only 19.8 per cent of the Gulf War sample had seen action. War syndromes arose therefore not only in servicemen who fought but also in those faced with the prospect of battle.\nAttributions by Servicemen\nHow, then, did servicemen themselves explain their war syndromes? Applicants for a war pension were required to state what they thought was the cause of their disability. In addition, doctors recorded patient statements at subsequent assessments. In the main, there were six categories of explanation that symptoms were: (1) the result of a physical illness acquired while in the army; (2) the result either of a physical injury or the physical strain of campaigning (marching, sleeping on hard ground, completing assault courses); (3) the result of an adverse climate (wet and cold in South Africa) or environment (the heat of the Western Desert or monsoon jungle of Burma); (4) the result of a toxic exposure: either to gas in the First World War or chemical and biological weapons or depleted-uranium ordnance in the Gulf War; (5) the result of psychological stress caused by combat or the prospect of combat; (6) the result of psychological stress caused by distance from family and friends or particular home worries.\nAn analysis of pensioners' explanations suggested that attributions were culturally conditioned and varied across the century tied to prevailing health beliefs and concerns (\nTable 4\n). Boer War servicemen diagnosed with DAH generally believed it to be the result of either physical illness (25.5 per cent) or of physical exertion (24.5 per cent). A different pattern emerged in the First World War with physical exertion accounting for 45.0 per cent of the DAH sample and 42.5 per cent of the neurasthenia group. However, a significant number of the latter (34.0 per cent) attributed their symptoms to the psychological stress of military service. They had, perhaps, been influenced by psychologically-minded physicians and the gradual incursion of psychiatric texts into medical and general literature.\nThe Second World War saw this process continue and 41.0 per cent of the neuropsychiatric sample attributed their symptoms to psychological stress arising from military service and a further 5 per cent to stresses related to their domestic situation. By contrast, 44.0 per cent of the dyspepsia population ascribed their symptoms to the physical exertions of active service, as did 37.3 per cent of the effort syndrome sample. Only 8.3 per cent of the Gulf War sample believed that stress played a causal role, while 34.3 per cent thought that their condition was the result of toxic exposure.\nContemporary attributions made by servicemen broadly correlated with the symptom characteristics of the three groups. In the debility cluster, 61.2 per cent believed that their illness was related either to a physical illness, physical injury/strain, climate or toxic exposure. By comparison, 143 (63.8 per cent) of the 224 who believed the psychological stress of military service was the cause of their illness came from the neuropsychiatric cluster. Equally, only 23 (12.4 per cent) of the 186 who believed that they were suffering from a physical illness were found in this group.\nIssues of Evidence\nOver the period covered by this study, terminology has changed and the same diagnostic term could subtly alter its meaning.\n96\n However, data for this study was derived from contemporaneous accounts and limited to relatively straightforward symptoms such as headache, joint pain, chest pain, fatigue, difficulty sleeping, dizziness, tics, rashes, incontinence or shortness of breath. Some symptoms were verifiable such as palpitations, contractures, or changes in weight by measurement. Others, such as difficulty performing tasks, could be corroborated as police reports and evidence from employers were gathered. Nevertheless, Guenter Risse and John Harley Warner have shown that patient records “hardly provide a simple access to clinical reality” insofar as they reflect “the perceptions and interpretations of contemporary health care providers”.\n97\n They will express the bias of the physician and reflect the culture of the period. As a result, it has to be acknowledged that some symptoms may have been given a different emphasis over the ninety years of this investigation.\nHowever, there were some safeguards against the effects of bias. First, the use of war pension files containing repeated medical investigations sometimes over fifty years and by a number of doctors often with different backgrounds, militated against error or extreme opinions. Secondly, it was in the veteran's interest to describe his symptoms, as the award and level of his pension was based on the severity of his disability. Although this system may have encouraged some patients to exaggerate their illnesses, the pension authorities often required servicemen to provide corroborative evidence. In our study, the benefit of any doubt about the existence of a symptom was always given to the veteran.\nConclusion\nAlthough cultural factors influenced both the report of symptoms by patients and their recognition by doctors, the patterns manifested by war syndromes were not straightforward. Cluster analysis of ten diagnostic varieties of war syndrome did not identify sub-populations with a clear-cut bodily focus related to a particular war. For example, we did not discover a cluster solely characterized by gastro-intestinal symptoms limited to the Second World War, nor did we find a cluster of heart patients confined to the Boer War and the First World War. There was considerable symptom overlap between different formal diagnoses and between the same diagnosis recorded in different conflicts. Soldiers labelled with shell shock were found in both the somatic and neuropsychiatric clusters. Although veterans from the Gulf War were predominantly distributed in the neuropsychiatric cluster, they also fell within the somatic and debility clusters. This finding partly relates to the nature of functional somatic disorders. Because they are characterized by a range of common but non-specific symptoms, doctors were able to categorize them in a variety of ways, often according to their own speciality or interests. Although a specific association between formal diagnosis and symptoms did not exist, a general association between particular wars and clustering was identified. Most soldiers in the debility cluster, for example, were veterans of Victorian campaigns or the Boer War, while the neuropsychiatric cluster mainly contained men from the Second World War or Gulf conflict.\nThe continued presentation of functional somatic symptoms in contemporary medical practice also undermines the claim that psychosomatic causation has been driven to extinction by growing psychological understanding and sophistication.\n98\n A recent study of primary care showed a minimum prevalence figure of 48 per 100,000 for conversion disorders, though the authors believed that this was an understatement of their true incidence.\n99\n It is by no means clear that psychiatric explanations are significantly more acceptable than they were in the past. Furthermore, it has been suggested that the limited number of epidemiological investigations into hysteria has contributed to the impression that this remains a rare phenomenon.\n100\nThe major cultural change to impact on war syndromes in the last quarter of the twentieth century appears to be a general fear of toxins spread as a result of modern industrial life. Of the 218 Gulf War veterans in our study who gave an explanation, 34.3 per cent believed that their condition was caused by some form of poisoning. By contrast, only 1.5 per cent of the effort syndrome sample and 0.5 per cent of the psychoneurosis sample drawn from Second World War veterans thought that toxic exposure was implicated. It is perhaps too early to say what were the key events in raising public consciousness although the thalidomide episode, the publication of \nSilent spring\n (1962)—Rachel Carson's investigation into the hazards of DDT\n101\n—and environmental catastrophes such as Bhopal and Chernobyl attracted considerable media attention. Multiple chemical sensitivities (MCS) or “twentieth century disease” is perhaps the most extreme expression of this theme.\nWhilst infection provided a powerful explanatory model in the first half of the twentieth century (suggested as a cause of rheumatism in the Boer War and DAH during the First World War), the development of effective anti-bacterial agents muted its impact. As a result, rituals of disinfection and measures to prevent contagion have become less prominent. Although the concept of surface violation and the need to maintain hygiene are no longer at the forefront of modern culture, they have been replaced by fears of internal threats to the immune system and the wish to ingest nothing that is not natural or pure.\n102\nIt is often stated that shell shock is the cultural predecessor of PTSD; in essence, the same disorder masquerading under a different name.\n103\n By contrast, our findings suggest that shell shock is one example of a variety of functional somatic disorders that include effort syndrome, irritable heart, the effects of Agent Orange and Gulf War syndrome. In depth, cultural histories of these illnesses have yet to be written, though an attempt was recently made to re-interpret Gulf War syndrome as a modern form of soldier's heart.\n104\n In understanding the true nature of war syndromes, it is important not only to acknowledge the debt to shell shock and the legacy of trauma but also to examine their expression as reflections of contemporary accounts of health and illness beyond the field of PTSD.\nOur findings imply that the pathology of war syndromes is not static. Culture, along with advances in treatments, the discovery of new diseases, new diagnostic tools and the changing nature of warfare, plays a significant role in shaping patterns of symptoms. Paul Lerner and Mark Micale concluded that “national medical culture; political, legal, and economic factors; race, class, and gender—these are only a handful of the determining influences in the history of psychological trauma”.\n105\n There is no single way for human beings to respond to the terrifying events of war. Ian Hacking has suggested that transient psychological disorders are not only shaped by changing culture but that they provide a form of release that is not available elsewhere in the society in which they thrive.\n106\n This would explain why functional somatic disorders remain relatively common and continue to evoke strong feelings in veterans. We suggest that war syndromes are an important phase in the evolving picture of man's reaction to adversity.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
26
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nCerebral infarction in diabetes: Clinical pattern, stroke subtypes, and predictors of in-hospital mortality\n\n**Article Abstract:**\n\nBackground\nTo compare the characteristics and prognostic features of ischemic stroke in patients with diabetes and without diabetes, and to determine the independent predictors of in-hospital mortality in people with diabetes and ischemic stroke.\nMethods\nDiabetes was diagnosed in 393 (21.3%) of 1,840 consecutive patients with cerebral infarction included in a prospective stroke registry over a 12-year period. Demographic characteristics, cardiovascular risk factors, clinical events, stroke subtypes, neuroimaging data, and outcome in ischemic stroke patients with and without diabetes were compared. Predictors of in-hospital mortality in diabetic patients with ischemic stroke were assessed by multivariate analysis.\nResults\nPeople with diabetes compared to people without diabetes presented more frequently atherothrombotic stroke (41.2% vs 27%) and lacunar infarction (35.1% vs 23.9%) (\nP \n< 0.01). The in-hospital mortality in ischemic stroke patients with diabetes was 12.5% and 14.6% in those without (\nP \n= NS). Ischemic heart disease, hyperlipidemia, subacute onset, 85 years old or more, atherothrombotic and lacunar infarcts, and thalamic topography were independently associated with ischemic stroke in patients with diabetes, whereas predictors of in-hospital mortality included the patient's age, decreased consciousness, chronic nephropathy, congestive heart failure and atrial fibrillation\nConclusion\nIschemic stroke in people with diabetes showed a different clinical pattern from those without diabetes, with atherothrombotic stroke and lacunar infarcts being more frequent. Clinical factors indicative of the severity of ischemic stroke available at onset have a predominant influence upon in-hospital mortality and may help clinicians to assess prognosis more accurately.\n\n**Article Body:**\n\nBackground\nDiabetes mellitus is a well-established independent risk factor for ischemic stroke [\n1\n]. Additionally, diabetes is the cerebrovascular risk factor associated with greater in-hospital mortality both in patients with ischemic stroke [\n2\n-\n5\n] and intracerebral hemorrhage [\n6\n]. However, little is known regarding the clinical pattern, outcome, and predictors of early mortality after an ischemic stroke in people with diabetes. To improve our knowledge of ischemic stroke in diabetes, we carried out a clinical study of patients with diabetes and cerebral infarction collected from an hospital-based stroke registry with the following objectives: 1) to compare demographic data, clinical variables, stroke subtypes, and prognostic features of ischemic stroke in patients with diabetes and without diabetes; and 2) to determine the independent predictors of in-hospital mortality in people with diabetes and ischemic stroke.\nMethods\nStudy population\nBetween January 1986 and December 1997, data of 2,500 acute stroke patients admitted consecutively to the Department of Neurology of Sagrat Cor-Hospital of Barcelona, Spain were collected prospectively in a stroke registry.[\n7\n] Our institution is an acute care 350-bed university-affiliated hospital in the city of Barcelona and serves an urban population of approximately 250,000 people. The large majority of people are Caucasian. All patients with cerebrovascular disease are initially attended to in the emergency department and are then admitted to the Department of Neurology, which has 25 beds and acute stroke unit. Intensive care unit beds are also available. Patients are chosen for admission to the Department of Neurology if the reason for consultation is an acute cerebrovascular event occurring independently of the presence or absence of severe concomitant medical problems. Patients with transient ischemic attack (TIA) or reversible neurologic deficits who are evaluated on an outpatient basis are routinely referred to the emergency department for assessment and included in the registry. Thus, the proportion of patients experiencing minor strokes who are not treated at the hospital is negligible. Subtypes of stroke were classified according to the Cerebrovascular Study Group of the Spanish Neurological Society [\n8\n], which is similar to the National Institute of Neurological Disorders and Stroke Classification [\n9\n] and has been used by our group in previous studies [\n2\n,\n10\n,\n11\n]. Subtypes of cerebrovascular accident included transient ischemic attack (TIA), atherothrombotic stroke (n = 553), lacunar stroke (n = 484), cardioembolic infarction (n = 468), infarction of undetermined origin (n = 248), infarction of unusual cause (n = 87), intracerebral hemorrhage, subarachnoid hemorrhage, spontaneous subdural hematoma, and spontaneous epidural hematoma. For the purpose of this study, the group of 1,840 patients with cerebral infarction was selected.\nAll patients were admitted to the hospital within 48 hours of onset of symptoms. On admission, demographic characteristics, salient features of clinical and neurological examination and results of laboratory tests (blood cell count, biochemical profile, serum electrolytes, and urinalysis), chest radiography, and twelve-lead electrocardiography were recorded. Neurological examination was performed on a daily basis. In all diabetic patients, brain computed tomography scan was performed within this first week of hospital admission. Cardiac investigations included electrocardiogram in 100% (\nn \n= 393) of patients and echocardiography in 32% (\nn \n= 125). Carotid investigations consisted of Doppler and/or angio-magnetic resonance imaging in 63.9% (\nn \n= 251) of patients, arterial digital angiography in 7% (n = 28), and conventional angiography 6.5% (\nn \n= 25). Lumbar puncture was performed in 2% of cases. As used in previous studies [\n2\n,\n6\n], diabetic patients were those with known diabetes, treated with either insulin or oral hypoglycemic agents or not treated, whatever the plasma glucose level at stroke onset. Patients with post-stroke repeated fasting plasma glucose levels >7.8 mmol/L (140 mg/dL) were enrolled in accordance with the World Health Organization diagnostic criteria for diabetes used in 1993 [\n12\n]. Patients with reactive hyperglycemia were excluded. Serum determination of HbA1c was performed in doubtful cases to diagnose previous diabetes.\nFor each patient, demographic data (age and sex), vascular risk factors, clinical features, neuroimaging findings, and outcome were recorded. Anamnestic findings consisted of history of hypertension, myocardial infarction or angina, rheumatic heart disease, congestive heart failure, atrial fibrillation, smoking, alcohol abuse, intermittent claudication, TIA, previous cerebral infarction, hyperlipidemia, chronic nephropathy, cirrhosis or chronic liver disease, chronic obstructive pulmonary disease (COPD), and age of 85 years or older. Clinical variables, dichotomized as present versus absent, included sudden onset of symptoms (< 60 min), acute onset (1–24 hours), and subacute onset (> 24 hours); headache; dizziness; seizures; nausea or vomiting; altered consciousness; limb weakness; sensory symptoms; aphasia or dysarthria; ataxia; cranial nerve palsy; and presence of lacunar syndrome (pure motor hemiparesis, pure sensory stroke, sensorimotor stroke, ataxic hemiparesis, and dysarthria-clumsy hand) [\n13\n,\n14\n]. Topographic diagnoses based on data on neuroimaging variables also dichotomized as present versus absent, included middle cerebral, posterior cerebral, anterior cerebral artery involvement, and basilar and vertebral artery involvement, and frontal, parietal, temporal, occipital lobes, internal capsule, basal ganglia, thalamus, midbrain, and pons location. Outcome variables included infectious complications and cardiac, respiratory, and vascular events. Causes of death were analyzed according to criteria of Silver et al. [\n15\n]. The degree of clinical disability at hospital discharge was evaluated according to the scale recommended by the Ad Hoc Committee [\n16\n] and the modified Rankin Scale [\n17\n].\nStatistical analysis\nUnivariate analysis for each variable in relation to vital status at discharge (alive, dead) as well as differences in the frequency of demographic characteristics, vascular risk factors, clinical events, neuroimaging data, and outcome between ischemic stroke patients with and without diabetes were assessed with the Student's \nt \ntest and the chi-square test (χ\n2\n) (with Yate's correction when necessary), and the analysis of variance. Statistical significance was set at \nP \n< 0.05. Variables associated with ischemic stroke in patients with diabetes in the univariate analysis were subjected to multivariate analysis with a logistic regression procedure and forward stepwise selection if \nP \n< 0.10. Ischemic stroke in diabetic patients coded as absent = 0, present = 1, was the dependent variable. A first predictive model was based on demographic variables and vascular risk factors (total 8 variables). In addition to these variables, clinical features and ischemic stroke subtypes, --dichotomized as present versus absent--, were included in a second model (total 17 variables). In addition to these variables, neuroimaging data, --also dichotomized as present versus absent--, were included in a third model (total 22 variables). In all cases, the level of significance to remain in the model was 0.15. The tolerance level was established as 0.0001. The maximum likelihood approach was used to estimate weights of the logistic parameters. Odds ratio (OR) and 95% confidence intervals (CI) were calculated from the beta coefficients and standard errors. The hypothesis that the logistic model adequately fits the data was tested by means of the goodness-of-fit χ\n2 \ntest [\n18\n]. The area under the receiver operating characteristics (ROC) curve for each predictive model was calculated [\n19\n]. Cox proportional-hazards models were used to estimate the relative risk of (RR) mortality (with discharge alive for hospital as the censoring event and death in hospital as the event of interest) after adjusting for age, sex, cerebrovascular risk factors and clinical findings, both in the group of diabetic and non-diabetic stroke patients. Data are expressed as RR and 95% confidence intervals (CIs). The SPSS-PC+ [\n20\n] and BMDP [\n21\n] computer programs were used for statistical analysis.\nResults\nDiabetes was identified in 393 (21.3%) of the 1,840 ischemic stroke patients. A total of 51.4% of patients were men. The mean age of diabetic patients with ischemic stroke was 73.6 ± 9.8 years. Cardiovascular risk factors included hypertension in 53.2% of cases atrial fibrillation in 26.4%, hyperlipidemia in 15.3%, ischemic heart disease in 18.6%, chronic nephropathy in 4.8%, and congestive heart failure in 2.7%. The frequency of stroke subtypes was as follows: atherothrombotic infarction in 41.2% of patients, lacunar infarction in 35.1%, presumed cardioembolic stroke in 18.6%, infarction of unknown etiology in 4.3%, and infarction of unusual cause in 0.8%. The in-hospital mortality was rate was 12.5% (\nn \n= 50). Causes of death included cerebral herniation in 17 patients, cardiac events in 11, respiratory events in 10, sepsis in 4, sudden death in 1, and unknown cause in 7. Symptom-free at hospital discharge was observed in 18.1% of patients. The median hospital stay was 13 days (interquartile range 8–21).\nDifferential features between people with and without diabetes with ischemic stroke patients are shown in Table \n1\n. Patients with diabetes compared to patients without diabetes (\nn \n= 1,447) were more likely to have ischemic heart disease, previous cerebral infarction, peripheral vascular disease, hyperlipidemia, subacute stroke onset, atherothrombotic and lacunar infarctions, and thalamus, pons and cerebral posterior artery involvement. On the other hand, they were less likely to be 85 years or older and to have valvular heart disease, sudden stroke onset, seizures, cardioembolic infraction, stroke of unusual cause, stroke of unknown etiology, and parietal and temporal lobe involvement. There were no differences in medications used for the treatment of patients (patients with diabetes vs patients without diabetes) antiplatelets 84.5% vs 85.4%, anticoagulants at therapeutic doses (15.5% vs. 14.6%), antibiotic therapy (14.5% vs 12.6%), and other medical treatments (96% vs 94%). After multivariate analysis (Table \n2\n), ischemic heart disease, hyperlipidemia, atherothrombotic and lacunar infarcts, subacute onset and thalamic infarcts were independently associated with diabetes in patients with ischemic stroke. Age of 85 years or older was inversely associated.\nTable 1\nResults of univariate analysis in diabetic patients with cerebral infarction as compared with patients with cerebral infarction without diabetes mellitus\nVariable\nPatients with diabetes (\nn \n= 393)\nPatients without diabetes (\nn \n= 1,447)\nP \nvalue\nMen\n202 (51.4)\n724 (50)\n0.6313\nAge, years, mean (SD)\n73.6 (9.8)\n74 (12.7)\n0.4945\nAge, 85 year or more\n49 (12.5)\n254 (17.6)\n0.0159\nCardiovascular risk factors\n Valvular heart disease\n19 (4.8)\n111 (7.7)\n0.0517\n Ischemic heart disease\n73 (18.6)\n193 (13.3)\n0.0088\n Previous cerebral infarction\n77 (19.6)\n223 (15.4)\n0.0466\n Peripheral vascular disease\n39 (9.9)\n103 (7.1)\n0.0646\n Hypelipidemia\n89 (22.6)\n241 (16.7)\n0.0060\nClinical findings\n Sudden onset\n183 (46.3)\n764 (52.8)\n0.0225\n Subacute onset (days)\n40 (10.2)\n90 (6.2)\n0.0066\n Seizures\n3 (0.8)\n31 (2.1)\n0.0718\n Lacunar syndrome\n156 (39.7)\n349 (27.2)\n<0.0001\nIschemic stroke subtypes\n Atherothrombotic\n162 (41.2)\n391 (27)\n<0.0001\n Cardioembolic\n73 (18.6)\n395 (27.3)\n0.0004\n Lacunar infarct\n138 (35.1)\n346 (23.9)\n<0.001\n Unusual etiology\n3 (0.8)\n84 (5.8)\n<0.0001\n Unknown cause\n17 (4.3)\n231 (16)\n<0.0001\nLocalization of cerebral infarction\n Parietal\n74 (18.8)\n339 (23.4)\n0.0527\n Temporal\n79 (20.1)\n380 (26.3)\n0.0123\n Thalamus\n44 (11.2)\n88 (6.1)\n0.0005\n Pons\n30 (7.6)\n71 (4.9)\n0.0353\n Cerebral posterior involvement\n52 (13.2)\n128 (8.8)\n0.0095\nOutcome\n Symptom free at discharge\n71 (18.1)\n272 (18.8)\n0.4324\n Hospital stay, days, median (interquartile range)\n13 (8 to 21)\n12 (8 to 21)\n0.9752\n In-hospital death\n50 (12.5)\n211 (14.6)\n0.3488\nData as number and percentages in parenthesis except for the mean (SD) age and length of hospitalization.\nTable 2\nIndependent factors associated with diabetes in patients with ischemic stroke.\nLogistic regression models\nβ\nSE (β)\nOdds ratio (95% CI)\nDemographic, and vascular risk factors *\n Ischemic heart disease\n0.386\n0.152\n1.47 (1.09–1.98)\n Hyperlipidemia\n0.354\n0.141\n1.42 (1.08–1.88)\n 85 years old or more\n-0.351\n0.169\n0.70 (0.50–0.98)\nDemographic, vascular risk factors, clinical variables and ischemic stroke subtypes\n†\n Atherothrombotic infarct\n1.910\n0.250\n6.75 (4.14–11.02)\n Lacunar infarct\n1.900\n0.254\n6.68 (4.07–10.99)\n Subacute onset (days)\n0.590\n0.213\n1.80 (1.19–2.74)\n 85 years old or more\n-0.391\n0.172\n0.68 (0.48–0.95)\nDemographic, vascular risk factors, clinical variables and neuroimaging data\n‡\n Atherothrombotic\n1.929\n0.250\n6.88 (4.21–11.24)\n Lacunar infarct\n1.848\n0.255\n6.35 (3.85–10.46)\n Subacute onset (days)\n0.601\n0.213\n1.82 (1.20–2.77)\n Thalamic topography\n0.557\n0.204\n1.74 (1.17–2.61)\n 85 years old or more\n-0.381\n0.172\n0.683 (0.49–0.96)\n* β = -1.381, SE (β) = 0.074, goodness of fit χ\n2 \n= 0.434, \ndf \n= 3, \nP \n= 0.933. Area under the ROC curve = 0.563, sensitivity 28%, specificity 81%, correctly classified 67%.\n† \nβ = -2.802, SE (β) = 0.235, goodness of fit χ\n2 \n= 2.133, \ndf \n= 4, \nP \n= 0.711. Area under the ROC curve = 0.663, sensitivity 29%, specificity 88%, correctly classified 55%.\n‡ \nβ = -2.847, SE (β) = 0.236, goodness of fit χ\n2 \n= 3.151, \ndf \n= 5, \nP \n= 0.677. Area under the ROC curve = 0.671, sensitivity 30%, specificity 50%, correctly classified 42%.\nThe characteristics of ischemic stroke patients with diabetes according to vital status at discharge are shown in Table \n3\n. Patients who died (\nn \n= 50) compared to those who were discharged alive from the hospital (\nn \n= 343) had a significantly higher occurrence of the following variables: age 85 years or older, atrial fibrillation, congestive heart disease, chronic kidney disease, sudden and acute stroke onset, seizures, decreased consciousness, limb weakness, sensory deficit, hemianopia, atherothrombotic stroke, cardioembolic infarction, parietal, temporal, internal capsule, mesencephalon and pons topography, basilar and middle cerebral artery involvement, and cardiac, respiratory, urinary, digestive and infectious complications.\nTable 3\nResults of univariate analysis in 393 diabetic patients with cerebral infarction according to vital status at discharge\nVariable\nDead (\nn \n= 50)\nAlive (\nn \n= 343)\nP \nvalue\nMen\n18 (36)\n184 (53.6)\n0.0197\nAge, years, mean (SD)\n78.4 (7.2)\n72.9 (9.9\n0.0002\nAge, 85 years or more\n13 (26)\n36 (10.5)\n0.0019\nCardiovascular risk factors\n Atrial fibrillation\n26 (52)\n78 (22.7)\n<0.0001\n Congestive heart disease\n6 (12)\n13 (3.8)\n0.0296\n Chronic nephropathy\n4 (8)\n7 (2)\n0.0389\nClinical findings\n Sudden onset\n32 (64)\n150 (43.7)\n0.0072\n Acute onset (hours)\n11 (22)\n122 (35.6)\n0.0582\n Seizures\n2 (4)\n1 (0.3)\n0.0518\n Decreased consciousness\n31 (62)\n29 (8.5)\n<0.0001\n Limb weakness\n48 (96)\n249 (72.6)\n0.0003\n Sensory symptoms\n33 (66)\n130 (37.9)\n0.0002\n Hemianopia\n17 (34)\n54 (15.7)\n0.0017\n Lacunar syndrome\n0\n156 (45.5)\n<0.0001\nIschemic stroke subtypes\n Atherothrombotic\n29 (58)\n1333 (38.8)\n0.0988\n Cardioembolic\n19 (38)\n54 (15.7)\n0.0016\n Lacunar infarct\n0\n138 (40.2)\n<0.0001\n Unusual etiology\n0\n3 (0.9)\n1.0000\n Unknown cause\n2 (4)\n15 (4.4)\n1.0000\nLocalization of cerebral infarction\n Parietal\n24 (48)\n50 (14.6)\n<0.0001\n Temporal\n22 (44)\n57 (16.6)\n0.0001\n Internal capsule\n4 (8)\n77 (22.4)\n0.0183\n Mesencephalon\n4 (8)\n1 (0.3)\n<0.0001\n Pons\n8 (16)\n22 (6.4)\n0.0171\n Middle cerebral artery involvement\n31 (62)\n166 (48.4)\n0.0723\n Basilar artery involvement\n9 (18)\n23 /6.7)\n0.0142\nOutcome\n Respiratory complications\n19 (38)\n19 (5.5)\n<0.0001\n Digestive complications\n4 (8)\n5 (1.5)\n0.0172\n Urinary infections\n9 (18)\n30 (8.7)\n0.0732\n Cardiac complications\n15 (30)\n8 (2.3)\n<0.0001\n Infectious complications\n16 (32)\n33 (9.6)\n<0.0001\n Hospital stay, days, median (interquartile range)\n13 (8 to 21)\n12 (8 to 21)\n0.9752\nData as number and percentages in parenthesis except for median (interquartile range) for hospitalization.\nThe relative risk for mortality in the groups of diabetic and non-diabetic ischemic stroke patients is shown in Table \n4\n. Congestive heart disease, atrial fibrillation, decreased consciousness, and age were significantly adversely associated with outcome after acute ischemic stroke in both diabetic and non-diabetic ischemic stroke patients. Chronic nephropathy was a predictor of in-hospital mortality for the group of diabetic ischemic stroke patients, whereas limb weakness, nausea/vomiting, and seizures were predictors of in-hospital mortality for the group of non-diabetic stroke patients.\nTable 4\nRisk for in-hospital mortality in ischemic stroke patients with diabetes and without diabetes. Cox's proportional hazards model.\nPredictors of death\nHazard ratio\nP \nvalue\n95% CI\nDiabetic stroke patients\n Demographic variables and vascular risk factors (model 1)\n Chronic nephropathy\n5.78\n0.001\n1.99–16.80\n Congestive heart disease\n2.52\n0.045\n1.02–6.23\n Atrial fibrillation\n2.39\n0.003\n1.36–4.20\n Age\n1.06\n0.002\n1.02–1.10\n Demographic variables, vascular risk factors, clinical variables, and stroke subtypes (model 2)\n Decreased consciousness\n5.16\n0.000\n2.82–9.42\n Congestive heart disease\n4.08\n0.002\n1.65–10.09\n Chronic nephropathy\n3.27\n0.036\n1.08–9.89\n Atrial fibrillation\n2.41\n0.002\n1.38–4.23\nNon-diabetic stroke patients\n Demographic variables and vascular risk factors (model 1)\n Congestive heart disease\n2.00\n0.001\n1.35–2.96\n Atrial fibrillation\n1.83\n0.000\n1.38–2.43\n Ischemic heart disease\n1.74\n0.002\n1.23–2.58\n Age\n1.04\n0.000\n1.03–1.06\n Demographic variables, vascular risk factors, clinical variables, and stroke subtypes (model 2)\n Decreased consciousness\n4.58\n0.000\n3.39–6.19\n Limb weakness\n1.93\n0.038\n1.04–3.59\n Nausea/vomiting\n1.79\n0.009\n1.16–2.76\n Seizures\n1.75\n0.047\n1.01–3.03\n Congestive heart disease\n1.74\n0.006\n1.17–2.59\n Ischemic heart disease\n1.72\n0.003\n1.02–1.80\n Atrial fibrillation\n1.35\n0.039\n1.02–1.80\n Age\n1.03\n0.000\n1.02–1.05\nDiscussion\nIn this hospital-based study of 1,840 consecutive patients with acute ischemic stroke, the prevalence of diabetes was 21%, a figure similar to that reported in the studies of Megherbi et al. [\n22\n] and Jorgensen et al. [\n4\n] and higher than the prevalence of diabetes in the Spanish population (6–7%) [\n23\n]. This may be explained by a stronger disposition to stroke in the diabetic patient, because diabetes mellitus is associated with accelerated atherogenesis [\n24\n] and also due to the fact that diabetic stroke patients have more often other cerebrovascular risk factors as, in our study, hyperlipidemia and ischemic heart disease, which in turn were independent predictors of ischemic stroke in the diabetic population as previously reported by others [\n25\n,\n26\n]. The present results are consistent with the study of Lehto et al. [\n25\n] in which hyperlipidemia was a strong predictor of stroke in middle-aged patients with non-insulin-dependent diabetes, probably because lipid abnormalities have been shown to be associated with cerebral atherosclerosis [\n1\n,\n24\n].\nWith regard to data of our study in comparison to previous works [\n3\n-\n5\n,\n22\n,\n26\n-\n31\n], Table \n5\n shows that there are only two previous studies [\n29\n,\n31\n] similar to ours. In the study of Kiers et al. [\n29\n], however, stroke subtypes are differentiated according to topography (cortical, lacunar, striatocapsular, brainstem/cerebellar) and in the study of Hamidon and Raymond [\n31\n] according to vascular topography (anterior, middle, and posterior artery involvement) and not according to cause (cardioembolic, atherothrombotic, lacunar, unusual etiology, undetermined cause) as in our report. In these two previous studies 50 and 90 patients were included as compared with 393 in our study. A strength of the present study is that predictors of in-hospital mortality in patients with diabetes and ischemic stroke were determined using logistic regression analysis, but a limitation is that a follow-up survival analysis is lacking. On the other hand, with a lower cut-point for the definition of hypertension (BP > 130/85 mm Hg), the prevalence of hypertension would have been probably substantially greater.\nTable 5\nIschemic stroke and diabetes. Series reported in the literature\n1st author, year\nNo. patients with ischemic stroke and diabetes\nType of study\nIschemic stroke subtypes\nPredictors of in-hospital death\nFollow-up survival analysis\nAsplund [27], 1980\n53\nRetrospective\nNo\nNo\nNo\nOppenheimer [5], 1985\n14\nRetrospective\nNo\nNo\nNo\nLithner [26], 1988\n75\nRetrospective\nNo\nNo\nNo\nWoo [28], 1990\n47\nCross-sectional\nYes\nNo\nNo\nOlsson [3], 1990\n121\nProspective\nNo\nNo\nYes (0–10 yr)\nKiers [29], 1992\n50\nProspective\nYes\nYes\nNo\nJorgensen [4], 1994\n233\nProspective, community-based stroke registry\nNo\nYes\nNo\nWeir [30], 1997\n61\nProspective\nNo\nNo\nYes (3 mo)\nMegherbi [22], 2003\n937\nProspective multicenter\nNo\nNo\nYes (3 mo)\nHamidon [31], 2003\n90\nProspective\nNo\nYes\nNo\nPresent series, 2004\n393\nProspective, hospital.-based stroke registry\nYes\nYes\nNo\nIschemic heart disease was another independent predictor of ischemic stroke in diabetic patients. It could suggest that diabetic patients have concurrent vascular lesions in the heart and the brain due to widespread atherosclerotic disease. In the study of Manson et al. [\n32\n], maturity-onset clinical diabetes was a independent risk factor for coronary heart disease.\nSubacute stroke onset (> 24 hours) was found to be a predictive clinical factor in diabetic ischemic stroke. This may be because thrombotic occlusion usually is gradual, and thrombotic infarcts show more frequently a fluctuating or progressive clinical course [\n33\n]. In contrast, sudden stroke onset is more characteristic of cardioembolic infarction and was observed in 83% of cases in the series of Bogousslavsky et al. [\n34\n] and in 79% of patients reported by Mohr et al. [\n35\n].\nIn our diabetic group, the distribution of pathological subtypes of ischemic stroke showed a higher occurrence of atherothrombotic and lacunar infarctions compared to nondiabetic ischemic stroke patients. Atherothrombotic infarcts were the most frequent stroke subtype (41.2%). This high frequency may be related to the increased susceptibility to atherosclerosis and the accelerated atherogenesis associated with diabetes mellitus.[\n1\n,\n24\n] Other authors found that diabetes was more frequently associated with angiographically demonstrated extracranial atherosclerotic carotid artery occlusion and atherosclerotic occlusive disease of the basilar artery, with a strong association between diabetes and carotid artery intimal-medial thickness [\n1\n,\n24\n]. The fact that we observed more lacunar infarcts in diabetic patients has been reported by our group in a previous study[\n2\n] and has been also observed in another recent series [\n22\n]. Diabetes can cause small vessel arteriolopathy, especially in the retina, kidney and brain (mainly in thalamus, internal capsule and pons topography) [\n36\n,\n37\n]. In a classical autopsy study of cerebrovascular accident in diabetes mellitus, Alex et al. [\n38\n] found that small vessel cerebral disease was present about 2.5 times more frequent in diabetes.\nAt discharge, the case fatality rate in the two groups of diabetic and nondiabetic ischemic stroke patients was comparable (12.5% and 14.6%, respectively). In our opinion, the increased occurrence of lacunar infarcts in diabetic patients, with a known good prognosis [\n36\n,\n37\n] (0% of in-hospital mortality in our study), may account for the lack of differences in early mortality. Functional recovery after lacunar infarcts as well as survival has been found to be favorable [\n38\n-\n40\n] and in a recent study [\n41\n], lacunar stroke had an odds ratio of 3.1 for an excellent outcome at 3 months.\nIn the multivariate analysis, independent clinical factors related to in-hospital mortality in diabetic patients with ischemic stroke were age, atrial fibrillation, congestive heart failure, chronic nephropathy and altered consciousness. Baseline plasma glucose level, which is a variable associated with poor outcome in stroke was not assessed. In the present study, like others [\n42\n], decreased consciousness and age were important clinical predictors of early mortality. In the study of Hamidon and Raymond [\n31\n], middle cerebral artery territory infarct and poor conscious level were independent predictors of mortality. Atrial fibrillation was another major aggravating factor in this population. Atrial fibrillation increases the risk of early recurrent stroke substantially and patients with atrial fibrillation may have larger infarcts [\n43\n]. In addition, atrial fibrillation may be a cause of more severe handicap through more severe motor or sensory deficits. Diabetic patients who died also tended to show a more severe neurological impairment at onset, characterized by a predominance of motor deficit and decreased consciousness, which is similar to results of the study of Olsson et al. [\n3\n]. The presence of congestive heart failure was another significant prognostic factor. This finding is similar to other studies [\n44\n,\n45\n] who reported a high mortality among patients with embolic stroke and ischemic heart diseases or congestive heart failure. Our results agree with the study of MacWalter et al. [\n46\n] who demonstrate that renal dysfunction had a higher mortality risk after acute stroke. Renal failure is a very rare primary cause of death in acute stroke [\n47\n]. However renal dysfunction represents the influence of generalized vascular disease in the kidney and is a potent predictor of in-hospital mortality in acute ischemic stroke diabetic people.\nConclusion\nIn the present series of ischemic stroke patients with diabetes collected from a prospective hospital-based stroke registry, the clinical picture of these patients was characterized by a more frequent concomitant ischemic heart disease and hyperlipidemia and a more frequent presence of atherothrombotic and lacunar infarcts as compared with ischemic stroke in people without diabetes. The in-hospital mortality is related to the presence of causal factors for stroke, including a more diffuse atherosclerotic disease and atrial fibrillation, and a higher frequency of other factors including a more advanced age, a strategic ischemic stroke in midbrain or large cortical topography, and the occurrence of cardiac or respiratory complications after stroke.\nList of abbreviations\nCI: confidence interval\nCOPD: chronic obstructive pulmonary disease\nHbA1c: hemoglobin A, glycosylated\nOR: odds ratio\nROC: receiver operating characteristics\nRR: relative risk\nTIA: transient ischemic attack\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nA. Arboix, was the principal investigator, chief of the Cerebrovascular Division, designed the study, diagnosed and took care of the patients, contributed to analyze the data, interpreted the results, wrote the paper, and prepared the final draft. He was also responsible for editorial decisions including the selection of the target journal.\nA. Rivas participated in the collection of data, search and review of the literature, analysis of results, review of the manuscript, and approved the final draft.\nL. García-Eroles was the statistician, participated in the study design, analysis and interpretation of data, wrote the part of the paper related to the statistical analysis, and approved the final draft.\nL. de Marcos, J. Massons, and M. Oliveres diagnosed and took care of the patients, contributed in the review of the literature, interpretation of the results, review of the paper for intellectual content, and approved the final draft.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
27
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nReduced coronary flow reserve in Anderson-Fabry disease measured by transthoracic Doppler echocardiography\n\n**Article Abstract:**\n\nCoronary flow reserve was assessed in a patient with Anderson-Fabry disease complicated by symmetric left ventricular hypertrophy. Coronary flow reserve was measurable in all three major coronary arteries providing an opportunity to compare regional coronary flow reserve from different vascular beds. In this patient all the three vascular beds supplied diffusely hypertrophied myocardium. Coronary flow disturbances in small intramyocardial perforating arteries were visible. The coronary flow reserve was reduced to a similar level (around to 2.0) in all three major arteries. In our patient with Anderson-Fabry disease, the coronary vasodilatation was blunted in a diffuse pattern corresponding to the myocardial hypertrophy distribution. In small intramyocardial arteries coronary flow was also disturbed. Accordingly, retrograde systolic flow and accelerated anterograde diastolic flow were documented.\n\n**Article Body:**\n\nBackground\nAnderson-Fabry disease is an X-linked, multisystem, lysosomal storage disease (deficiency of enzyme α-galactosidase A), characterized by the accumulation of glycosphingolipids in various tissues and organs [\n1\n,\n2\n], including skin, vascular endothelium, heart, kidneys, liver, lungs, pancreas and ganglion cells of the peripheral nervous system. The incidence is 1:117000. However, the rate may be underestimated because a common cardiac manifestation is myocardial hypertrophy that mimics hypertrophic cardiomyopathy. Abnormal storage in the cardiovascular system may also involve cardiac conduction system, valvular apparatus and endothelial cells in coronary vessels [\n1\n-\n3\n].\nTo assess coronary flow abnormalities in a patient with Anderson-Fabry disease, we performed transthoracic Doppler echocardiography. Using this method, coronary flow reserve is effectively measurable [\n4\n] and all three major coronary arteries are accessible in some patients [\n5\n,\n6\n]. In a large series of 658 patients [\n6\n], coronary flow reserve was contemporarily recorded in left anterior descending (LAD) coronary artery (98% of patients), right coronary artery (RCA) (66% of patients) and circumflex (Cx) coronary artery (43% of patients). Additionally, flow disturbances in small intramyocardial perforating arteries were assessed as blood flow abnormalities at this level of coronary circulation were previously reported in left ventricular (LV) hypertrophy [\n7\n].\nCase presentation\nThis 49-year-old male patient with Anderson-Fabry disease was referred to our hospital. He did not complain of anginal symptoms or dyspnea. As a part of an overall clinical evaluation, transthoracic echocardiography was performed, revealing a diffusely distributed myocardial hypertrophy, i.e. involving both (LV) free walls and the septum (the myocardial thickness at diastole was measured in the short parasternal-axis: the anterior segment of the septum- 19.6 mm; the posterior segment of the septum – 20.8 mm; the LV posterior wall – 20.7 mm; and the anterolateral wall 16.8 mm). Left ventricular systolic function was preserved (LV ejection fraction 68%). A precise assessment of myocardial hypertrophy by magnetic resonance imaging confirmed increased LV mass to 386 grams.\nMethods\nUsing noninvasive, inexpensive and widely accessible method, B-mode and color Doppler transthoracic echocardiography, the segments of three major coronary arteries: LAD, Cx and right posterior descending (RPD) coronary artery or RCA were visualized (Figure \n1\n,\n2\n). High quality recordings of flow velocity in all these coronary arteries were obtained using spectral Doppler.\nFigure 1\nParasternal short axis view, color Doppler examination at the heart base level. Left main, left anterior descending (LAD) and origin of left circumflex (Cx) coronary arteries are seen. Blood flow within the left main coronary artery and proximal LAD is depicted in red, while in the Cx – in blue.\nFigure 2\nModified apical four-chamber view, color Doppler examination. Flow detected in long segment of the right posterior descending (RPD) coronary artery is depicted in red.\nResults\nThe coronary flow reserve in response to intravenous adenosine (140 μg/kg/min) was homogeneously reduced to a similar value in the major coronary arteries (LAD – 2.07; Cx- 2.18; RPD/RCA- 1.91). Small, intramyocardial branches of epicardial coronary arteries were visualized [intramyocardial perforators originated from LAD (Figure \n3\n) and branches from RPD (Figure \n4\n)]. Increased resistance to flow (probably due to myocardial hypertrophy and increased extravascular compressive forces) was demonstrated by the detection of flow with high velocity in spectral Doppler (figure \n5\n, \n6\n, \n7\n) and color Doppler (Figures \n3\n, \n4\n, \n5\n) in these penetrating vessels. The peak diastolic flow velocity was higher in the LAD perforator (41 cm/s – figure \n6\n) than in the distal portion of LAD (25 cm/s – figure \n7\n). The systolic flow in the LAD perforator was abnormally retrograde (figure \n6\n).\nFigure 3\nModified apical 2-chamber view, apical area, color Doppler examination. The LAD and the penetrating intramyocardial arteries (vertical perforators branching of the LAD) are seen.\nFigure 4\nModified apical 2-chamber view, middle segment of the inferior wall on color Doppler examination. Small (arch-shaped) arteries branching of the right posterior descending (RPD) coronary artery are seen.\nFigure 5\nThe orientation of Doppler gate within the LAD perforator.\nFigure 6\nThe flow velocity spectrum in the LAD perforator visualized in figure 5. In diastole the flow velocity is negative (towards ventricular chamber) and during systole the retrograde flow (towards epicardium) results in positive value of velocity.\nFigure 7\nDiastolic flow velocity spectrum in distal portion of LAD.\nDiscussion\nPrevalence of Anderson-Fabry disease in patients with late-onset hypertrophic cardiomyopathy is about 6.3% in males [\n8\n] and 12% in females [\n9\n]. In contrast, among males with hypertrophic cardiomyopathy diagnosed at <40 years of age, the rate of appropriate verification of the diagnosis to Anderson-Fabry disease was lower i.e. 1.4% [\n8\n]. If properly recognized, Anderson-Fabry disease is treatable by enzyme replacement therapy and both cardiac and non-cardiac abnormalities may be reversed/reduced by substitution of α-galactosidase (especially in the early stage) [\n10\n]. Therefore, it is important to consider Anderson-Fabry disease in the differential diagnosis of hypertrophic cardiomyopathy. Anderson-Fabry disease is hardly indistinguishable from hypertrophic cardiomyopathy by echocardiography [\n9\n,\n11\n,\n12\n], however we made an attempt to identify potential differences (mainly quantitative) in table \n1\n. Recently [\n13\n], the findings of magnetic resonance imaging have appeared useful in differential diagnosis (table \n1\n). Clinical findings may be more helpful in differential diagnosis and we recommend to evaluate the presence or absence of all non-cardiac manifestations (dermatological, nephrological, neurological, ophthamological) of Anderson-Fabry disease in patients diagnosed as having hypertrophic cardiomyopathy.\nTable 1\nComparison of echocardiography and MRI findings between Anderson-Fabry and hypertrophic cardiomyopathy.\nEchocardiography\nAnderson-Fabry\nHCM\nLVH pattern\nConcentric>Asymmetric\nAsymmetric>Concentric\nResting LVOT gradient\nRare\n25–30%\nMassive LVH> 30 mm\nRare\n10–15%\nLV diastolic dysfunction (tissue Doppler, strain rate)\n With LVH\nYes\nYes\n Without LVH (genotype +)\nYes\nYes\nLV systolic dysfunction\nMore frequent especially in older males\nMagnetic resonance\nMost common site of late-enhancement (if present)\nInfero-lateral segment\nVentricular junction, Multi-focal\nLVH- left ventricular hypertrophy; LVOT – left ventricular outflow tract\nConclusion\nIn our patient with Anderson-Fabry disease, the coronary vasodilatation was blunted in a diffuse pattern corresponding to the myocardial hypertrophy distribution. In small intramyocardial arteries coronary flow was disturbed. Accordingly, retrograde systolic flow and accelerated anterograde diastolic flow were documented. Transthoracic Doppler echocardiography is now the only method available to evaluate blood flow characteristics in small intramyocardial arteries.\nList of Abbreviations\nLAD – left anterior descending coronary artery\nRCA – right coronary artery\nRPD – right posterior descending coronary artery\nCx – circumflex coronary artery\nCompeting Interests\nThe author(s) declare that they have no competing interests.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
28
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nParadise – not without its plagues: Overwhelming Blastomycosis pneumonia after visit to lakeside cottages in Northeastern Ontario\n\n**Article Abstract:**\n\nBackground\nVisiting lakes and cottages is a common leisure activity during summer among most Canadians and paradise for some. Various leisure activities are involved during these visits, including cleaning and 'airing' the cottage after long-winters, activities at the lakes and dock building etc, exposing the Canadians to moist soil and decaying woods – a source of white or tan mould – \nBlastomyces dermatitidis \nthat may cause a flu-like illness to severe pneumonia that often remains a diagnostic challenge and results in delay in diagnosis and appropriate treatment thereby increasing associated morbidity and mortality.\nCase Presentations\nFive cases of overwhelming acute blastomycosis pneumonia are presented. Four of the five patients presented within few weeks of their visit to the cottages and surrounding lakes and all were initially treated as \"community acquired pneumonia\" that resulted in delay in diagnosis and poor outcome in the first patient. The first case, however, taught an important lesson that led to high-index of suspicion in the others with early diagnosis and improved outcomes. Interestingly, all patients were obese and had a shorter incubation period and severe clinical course. The possible mechanism for early and severe disease in association with obesity is speculated and literature is reviewed.\nConclusion\nHigh-index of suspicion is important in the early diagnosis and appropriate management acute blastomycosis pneumonia to improve associated morbidity and mortality.\n\n**Article Body:**\n\nBackground\nDuring the few summer months in Canada visit to cottages and lakes is a frequent leisure activity. Access to a second home – camp, cabin, chalet or cottage, whatever we call it – has a strong cultural significance for Canadians. The cottage, for many Canadians, is a paradise where extended family and friends gather together, where there is time for leisure and contact with nature.\nPulmonary blastomycosis can be difficult to diagnose and only 18% of patients were correctly suspected to have blastomycosis in an endemic area and are often initially misdiagnosed and treated as community acquired pneumonia, malignant tumor or tuberculosis resulting in unnecessary surgery and treatment delays[\n1\n]. Experience with five cases of blastomycosis pneumonia from Northeastern Ontario is presented emphasizing the high-index of suspicion for early diagnosis and improving outcome. The patients presented with overwhelming acute blastomycosis pneumonia within few weeks after visiting lakes and cottages. These were initially treated as community acquired pneumonia and a lesson learnt from first case is emphasized and a high-index of suspicion by the author led to early diagnosis in others. Interestingly all patients were obese and had severe disease. A possible association with obesity and severity of disease is observed and mechanism speculated.\nCase presentations\nThe demographics, month of presentation, time to illness and diagnosis after exposure and the outcomes are summarized in table \n1\n. A brief history on all with a detailed history of case 3 is presented.\nTable 1\nA summary of 5 cases\nMonth of presentation to hospital\nAge (years)\nGender\nWeight (Pounds)\n# of days symptoms started after visit to cottage or lake\n# of days to diagnosis after onset of symptoms/after hospitalization\nOutcome\nJuly\n30\nMale\n340\n7–10\n40/22\nDied\nJuly\n34\nFemale\n270\n7\n20/7\nRecovered\nJuly\n36\nFemale\n200\n10\n36/12\nRecovered\nJuly\n36\nMale\n230\n6\n19/1\nRecovered\nFebruary\n57\nFemale\n>350\nNot clear\n30/3\nDied\nCase 1\nIn July 1998, a 30-year old man with morbid obesity [weight 340 pounds] presented to emergency department with 3-weeks history of 'flu-like' symptoms with fever, chills, night sweats and cough with yellowish phlegm that started after building a dock at his cottage. Chest x-ray revealed bibasilar infiltrates. He was admitted with bilateral pneumonia and was started on intravenous penicillin and oral clarithromycin after obtaining blood and sputum cultures. Three days later he developed rash and penicillin was discontinued and antibiotics were changed to intravenous ceftriaxone and erythromycin. He remained febrile for next 7 days. Sputum Gram stain showed many pus cells but cultures remained negative. His condition continued to deteriorate. Local bronchoscopist was unavailable to perform bronchoscopy and arrangements were made to transfer him to another hospital. Before transfer, his condition deteriorated and was intubated. Tracheal secretions were aspirated and sent for cultures – including fungal and tubercular. The night of transfer, he developed cardio-respiratory arrest and couldn't be resuscitated. Next day, the wet preparation on the tracheal secretions revealed thick walled budding yeast consistent with blastomycosis. Autopsy showed severe pulmonary disease with solidification of both lungs and cultures confirmed the diagnosis.\nCase 2\nIn July 2000, a 34-year old obese woman [270 pounds] presented to the emergency department with pleuritic chest pain associated with chills and night sweats about a week after she was camping at the lakeside cottage. She denied symptoms of cough or phlegm. She was diagnosed with musculoskeletal pain and discharged home on analgesics. Five days later she presented with ongoing symptoms of fever, chills with dry cough and right lower chest pain. A chest X-ray revealed an infiltrate in the right lower lobe. She was diagnosed with community acquired right lower lobe pneumonia and sent home on oral clarithromycin. She presented 4-days later with ongoing symptoms to the emergency department and the chest x-ray now showed worsening pneumonia. She was admitted to the hospital and started on intravenous ampicillin and ceftriaxone, and a ventilation-perfusion scan showed a matched perfusion defect in right lower lobe. She continued to feel weak with night sweats and chest X-ray showed worsening of infiltrate. A medical consult was requested. At this time, during consultation it was noted that her symptoms started after a short stay at the cottage that reminded me of the previous case, and the possibility of acute blastomycosis pneumonia was raised. Her white blood cell count remained slightly elevated at 13.0 but erythrocyte sedimentation rate was markedly elevated at 112. As she didn't have productive cough, a bronchoscopy was recommended that couldn't be performed locally [local bronchoscopist was away] and she was referred to a tertiary care center where bronchio-aleveolar lavage showed budding yeast and cultures confirmed growth of blastomycosis. She was treated initially with intravenous amphotericin B and later switched to oral itraconazole for a year and made full recovery.\nCase 3\nIn July of 2002, a 36-year old obese woman [weight 200 pounds, height 5 feet 1 inch] with history of type 2 diabetes for 5 years, presented to the emergency department with 5 days history of fever, chills and cough with yellowish phlegm and sharp pain in her right lower chest that aggravated with deep breathing. Physical examination was unremarkable. She was afebrile and lungs were clear. Homen's sign was negative. Initial laboratory data showed slightly elevated d-dimer of 0.374 ug/mL [normal <0.25 ug/mL]. A chest X-ray (figure \n1\n) showed right lower lobe infiltrate. She was diagnosed with community acquired pneumonia and sent home on oral clarithromycin 500 mg BID, cefurox 500 mg BID for 7 days and acetaminophen as required.\nFigure 1\nChest X-ray (PA view) at initial presentation showing early right lower lobe consolidation.\nShe continued to have symptoms of fever, chills, night sweats with productive cough and dyspnea and presented to the hospital five days later. She denied hemoptysis. Physical examination revealed a temperature of 39 degree Celsius, mild tachycardia with heart rate of 104 beats per minute, normal blood pressure of 125/74 mmHg and respiratory rate of 18. Pulse oxymetry revealed oxygen saturation of 96% on room air. There was decreased air entry with bronchial breath sounds in right lower chest. A white cell count was slightly elevated at 13.5, with normal hemoglobin of 128 g/L and d-dimer between 0.25–0.50 ug/mL. A second chest X-ray (figure \n2\n) showed dense infiltrate in right lower lobe. She was admitted with the diagnosis of community-acquired pneumonia and started on intravenous levofloxacin 500 mg a day.\nFigure 2\nChest X-ray (PA view), 5 days later, showing progression of disease with infiltrates in right and left lower lobes.\nShe had a positive Mantoux test in 1976. There was no history of travel save for visiting her sister's cottage at the local lake a weak before where she slept at the gazebo for two nights. There were no pets at home. She smoked one pack per day and entertained social drinks.\nShe continued to have temperature up to 39 degrees Celsius, productive cough and shortness of breath. Sputum Gram stain showed 4+ neutrophils and 1+ normal flora and blood cultures remained negative. She received intravenous levofloxacin and clindamycin for one week. Bronchoscopy performed on day 6 was unremarkable save for inflammatory changes in lower lungs and samples were collected for bacterial and tuberculosis cultures [in retrospect, the specimen was not sent for fungal cultures]. On 7\nth \nday because of ongoing symptoms, the antibiotics were changed to intravenous imipenem-cilastatin sodium 1 gm every 12 hour and she has had a CT scan of chest (figure \n3\n) that showed bibasilar consolidation with sparing of the apices. The white cell count fluctuated between 13.6 to 20.2 [normal 4.0–11.0 × 10\n9 \n/L]. Hemoglobin decreased to 97 g/L. BUN, serum creatinine, electrolytes, AST, ALT, GGT and ALP were normal. Urinalysis was negative. Blood, urine and sputum cultures remained negative. Sputum gram stain showed 3-4+ neutrophils without organisms. ESR on day 8 was elevated at 112 mm/hr [normal 0–15]. Antinuclear antibody was negative. Arterial blood gas on day 8 showed pH of 7.46, pCO\n2 \nof 35, pO\n2 \nof 59 and oxygen saturation of 91% on room air. She was started on supplemental oxygen by nasal prongs. Bronchoscopic specimen cultures were negative save for pending TB cultures.\nFigure 3\nA section of CT scan of chest performed 8 days after hospitalization showing bilateral consolidation of lungs, mainly of lower lung fields.\nAfter five days of intravenous imipenem-cilastatin sodium therapy, there was no improvement in her clinical condition. Another medical consult was requested, when the author got involved in her care. She had a temperature of 39 C, pulse rate of 104 and blood pressure of 114/70 mmHg. There was no lymphadenopathy and heart sounds were normal. Her chest examination showed decreased breath sounds at both bases with egophony in right lower chest. There were no pleural rubs. There was no clubbing or cyanosis. The rest of the examination was unremarkable save for an obese benign abdomen.\nChest X-ray (figure \n4\n) now showed further deterioration of the bilateral infiltrates with nodular appearance and the radiologist remarked, \"The lesions are suspicious of metastases.\" Sputum cytology showed a large number of acute inflammatory cells without malignant cells. The possibility of vasculitis was entertained because of markedly elevated ESR and antineutrophilic cytoplasmic antibody (ANCA) was negative.\nFigure 4\nChest X-ray (PA view) – after 8 days of intravenous antibiotic therapy, showing further worsening of bilateral lower lung disease with nodular pattern – raising suspicion of metastatic disease.\nThe history of sleeping at the cottage for two nights, a week before her illness started; progressive bilateral pneumonia with ongoing high-grade fever, chills, and night sweats despite sufficient antibiotic coverage and sputum Gram stain showing a large number of neutrophils without organisms (culture negative) raised the author's suspicion for the possibility of fungal process such as acute blastomycosis pneumonia and the Public Health Laboratory (PHL) was specifically asked to perform wet preparation for blastomycosis on the sputum. The PHL laboratory confirmed the presence of 'round thick walled budding yeast like cells (figure \n5\n) suggestive of \nBlastomyces dermatitidis \nand this was confirmed on fungal cultures. She was promptly started on intravenous amphotericin B and responded well and later switched to oral itraconazole 400 mg twice a day for 6 months and then 200 mg a day for another 6 months. She recovered fully.\nFigure 5\nWet preparation of sputum [25% NaOH with 5% Glycerol as the mounting medium, 40× magnification] showing budding yeast [blastocyst]\nCase 4\nSame July of 2002, while case #3 was still-in hospital, a 42-year old man [weight 230 pounds] presented to a peripheral community hospital with symptoms of fever, chills and malaise about 7–10 days after a trip to the local beach. He was diagnosed with community acquired left lower lobe pneumonia and treated with three different kind of antibiotics. He remained febrile with temperature of 39–40 degree Celsius and 10-days after his admission, he was transferred to our hospital and again the past experience and a recent case of similar nature, although from a different region, reminded of the similar process and he underwent bronchoscopy and the wet preparation showed budding yeast and cultures were confirmatory. He was promptly started on intravenous amphotericin B and later switched to oral itraconazole and made full recovery.\nCase 5\nIn February of 2004, a 57-year old woman with morbid obesity [weight over 350 pounds] with history of hypertension and type 2 diabetes presented with one month history of fever, night sweats and cough and was admitted to the hospital with right sided community acquired pneumonia [figure \n6\n] and started on intravenous levaquin. She had history of gall stones and had mild upper abdominal pain. Next morning, while undergoing an ultrasound examination she became unresponsive and suffered cardio-respiratory arrest. She was successfully resuscitated, but remained hypotensive and required inotropic support and admitted to intensive care unit under my care. Because of shock and dense lobar pneumonia, the possibility of severe pneumococcal pneumonia was entertained and intravenous penicillin was added. She had copious amount of thick pus from the endotracheal tube and because of thick pus, possibility of acute blastomycosis pneumonia was entertained although it was -36 degree Celsius outside, and specimen was sent to Public Health Laboratory to perform a wet preparation to confirm or rule out the possibility blastomycosis. Although blastomycosis was suspected but empiric therapy with amphotericin B was not started, as there was no clear cut history of exposure and she presented in the middle of winters when the outside temperature was -30 to -40 degrees Celsius. She was difficult to ventilate and remained unstable during the night. Next morning she arrested and could not be resuscitated after 2-hours of resuscitation. At noon on that day, Public Health Laboratory confirmed the diagnosis of acute blastomycosis pneumonia.\nFigure 6\nChest X-ray (PA view) at initial presentation showing consolidation within the right mid and both lower lobes.\nDiscussion\nBlastomycosis is a relatively rare but important and lethal disease and is caused by a thermal dimorphic fungus – \nBlastomyces dermatitidis \n– that exists in mycelial form in the environment and develops into yeast form in the host [\n2\n-\n4\n]. Clinical spectrum is variable and range from asymptomatic infection to pyogranulomatous inflammation with fulminant hypoxic respiratory failure or acquired respiratory distress syndrome (ARDS) to extrapulmonary manifestations[\n5\n,\n6\n]. Often acute pulmonary disease mimics a bacterial pneumonia or cause respiratory distress syndrome and pose a diagnostic challenge and results in delay in diagnosis, incorrect treatment and poor outcome.[\n1\n,\n5\n,\n7\n]\nThe incidence of blastomycosis remains largely unknown as it is not a reportable disease in Canada and was removed from the list of reportable diseases in Ontario in 1990[\n8\n]. It is an uncommon, though regularly seen, life threatening disease in endemic areas. In North America the disease is concentrated along the Mississippi and Ohio River basins, but also extends into Northern Wisconsin, Minnesota and the Canadian provinces bordering the Great Lakes[\n2\n,\n5\n]. In Ontario, it is endemic especially in Northwestern Ontario, north and west of Lakes Superior and Huron and in neighboring boreal Manitoba[\n9\n]. In the endemic areas the disease is predominantly encountered in rural or wilderness areas where the causative agent likely colonizes the soil or plant litter in riparian sites[\n10\n]. Outbreak studies have implicated, building of a hunting lodge, proximity to a construction site, raccoon hunting, exposure to a beaver lodge, and activities by riverbanks as sources of exposure. [\n9\n,\n11\n-\n13\n] A retrospective review from 1990 to 1998 in Northwestern Ontario revealed an incidence of 117 per 100,000 population with much higher rate of 404 per 100,000 population in aboriginals[\n14\n]. Public Health Laboratory in Timmins covers most of the Northeastern Ontario and identifies an average of 5–6 isolates per year [personal communication, PHL, Timmins]. Three of the patients [#1, 2 and 5] were from Timmins and one [#3] about 200 Km south and the other [#4] about 100 km North of Timmins (figure \n7\n).\nFigure 7\nMap of Northeastern Ontario, showing the location of exposure [adapted from \n, accessed April 2, 2005].© Queens Printer for Ontario, 2002. Adapted and reproduced with permission\nFour of the five patients presented in July compared to the reported occurrence between September and January. The incubation period was much shorter than the reported period of 21 to 106 days with an average of 45 days[\n10\n]. The reason for short incubation period is unclear but it is interesting that all patients were significantly obese and two had diabetes. Diabetes increases the risk for fungal infections and may be present in 22% of patients[\n1\n]. Whether obesity altered the course and severity of disease requires further study but it is known that obesity can alter pulmonary function by its adverse effects on respiratory mechanics, resistance within the respiratory system, respiratory muscle function and lung volumes[\n15\n] and thereby might cause decreased clearance of inhaled spores resulting in severe disease with shorter incubation period. Baik et al noted a two-fold increase in the risk of community acquired pneumonia both in men and women who gained over 40 pounds from their adulthood weight and a direct association with increasing BMI in women[\n16\n]. Obesity is also shown to impair T and B cell function [\n17\n,\n18\n] that may be mediated in part by consequences of obesity, such as hyperglycemia and insulin resistance[\n19\n]. It is possible that non-obese people might have had such exposure and were either able to clear the inhaled spores or developed a milder form of disease indistinct from flu-like illness.\nLaboratory diagnosis\nThe role of sputum culture in the management of community-acquired pneumonia is controversial and only 14.4% of patients yielded good-quality sputum in a recent study[\n20\n] and is not routinely recommended[\n21\n]. However, the yield from respiratory secretions [wet preparation and cultures] is high [80–100%] but is underutilized.[\n22\n] Wet preparation [10% potassium hydroxide] examination of respiratory secretions showing budding yeast is the gold standard initial test and cultures are confirmatory but may take up to 5 weeks. The first case taught an important lesson and re-enforced the old dictum – \"\npresence of a large number of neutrophils on the Gram stain indicates that the sputum is of good quality\"\n. When no organisms are seen or cultured from this quality specimen, it should raise the suspicion for non-bacterial (fungal, mycobacterial, etc.) causes. This lesson was helpful, especially to me, in making a timely diagnosis in other four patients, where the patients were treated initially with different antibiotics for \"pneumonia\" before my involvement. The diagnosis was suspected at my initial encounters and confirmed within 24–72 hours in all.\nLesson: Sputum full of neutrophils indicates 'a good quality specimen' and with negative cultures should alert the physician to look for non-bacterial causes.\nRadiographic features\nThe radiographic features of blastomycosis are highly variable and no one pattern exists[\n23\n], making differential diagnosis from other bacterial, fungal and neoplastic disease difficult. Often initial radiographic presentation tends to be localized airspace disease characterized by patchy and confluent airspace opacities with indistinct borders, in a segmental, subsegmental, or non-segmental distribution[\n3\n]. Due to these radiographic features and clinical presentation of fever, chills and productive cough, the initial diagnosis of blastomycosis is often overlooked in favor of a diagnosis of bacterial pneumonia. In chronic form, when presents as a focal mass it mimics bronchogenic carcinoma prompting additional tests such as needle biopsy and even a lobectomy[\n1\n,\n5\n].\nTreatment\nTreatment of blastomycosis depends on the clinical presentation and presence or absence of extra-pulmonary manifestations. Patients with mild pulmonary disease whose symptoms are resolving at time of diagnosis require observation. All other patients with symptomatic pulmonary disease or extrapulmonary disease require antifungal therapy. amphotericin B is recommended for patients with severe acute pulmonary disease [as in the cases presented], with associated ARDS[\n5\n], immunocompromised hosts and in those with central nervous system involvement. Oral azoles – Itraconazole or fluconazole are recommended for mild to moderate acute, subacute or chronic pulmonary and disseminated forms and after intravenous amphotericin B therapy in severe cases. A 6 to12 months of therapy with antifungal agents is often required.\nPrognosis\nThe prognosis for most patients with mild to moderate pulmonary disease with or without dissemination is good provided that antifungal therapy is initiated promptly after diagnosis[\n23\n]. Mortality is about 10% in patients with severe pulmonary disease without ARDS but reaches close to 90% in patients with associated ARDS.[\n24\n]\nPrevention\nThere are no specific prevention strategies. However, activities that bring individuals closer to rotting wood or moist soil near water are associated with a greater risk and a high-index of suspicion especially in endemic areas with early and appropriate testing is important. Soil testing, even in endemic areas, is neither cost-effective nor reliable and is not recommended.\nConclusion\nVisit to cottages and lakes, is a paradise for most Canadians where they spend most of their summers relaxing and participating in outdoor activities that may expose them to \nBlastomyces dermatitidis\n. The five cases presented here are not to illustrate the drawbacks of these activities but to increase the awareness of blastomycosis to the public, visitors to endemic areas and healthcare providers. It is important for the patients to provide their history of stay at the cottages and lakes and contact with wet soil and decaying woods and for the physicians to be vigilant and consider this diagnosis early and request appropriate testing to reduce associated morbidity and mortality.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
29
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nIdentification of children who may benefit from self-hypnosis at a pediatric pulmonary center\n\n**Article Abstract:**\n\nBackground\nEmotional difficulties can trigger respiratory symptoms. Thus, children presenting with respiratory complaints may benefit from a psychological intervention. The purpose of this study was to define the proportion of patients referred to a Pediatric Pulmonary Center who may benefit from instruction in self-hypnosis, as a psychological intervention.\nMethods\nA retrospective chart review was conducted for all newly referred patients to the SUNY Upstate Medical University Pediatric Pulmonary Center during an 18 month period beginning January 1, 2000. Patients were offered hypnosis if they presented with symptoms or signs suggestive of psychological difficulties. Hypnosis was taught in one or two 15–45 minute sessions by a pediatric pulmonologist.\nResults\nOf 725 new referrals, 424 were 0–5 years old, 193 were 6–11 years old, and 108 were 12–18 years old. Diagnoses of anxiety, habit cough, or vocal cord dysfunction accounted for 1% of the 0–5 year olds, 20% of the 6–11 year olds, and 31% of the 12–18 year olds. Hypnotherapy was offered to 1% of 0–5 year olds, 36% of 6–11 year olds, and 55% of 12–18 year olds. Of 81 patients who received instruction in self-hypnosis for anxiety, cough, chest pain, dyspnea, or inspiratory difficulties, 75% returned for follow-up, and among the returning patients 95% reported improvement or resolution of their symptoms.\nConclusion\nA large number of patients referred to a Pediatric Pulmonary Center appeared to benefit from instruction in self-hypnosis, which can be taught easily as a psychological intervention.\n\n**Article Body:**\n\nBackground\nEmotional difficulties can trigger respiratory symptoms such as dyspnea [\n1\n]. Further, psychological issues can arise as a result of patients' reactions to pulmonary disease, e.g., depression with end-stage cystic fibrosis [\n2\n]. In some patients, a vicious cycle ensues as pulmonary disease leads to psychological difficulties, which in turn trigger further symptoms that can be misinterpreted as arising from the pulmonary disease [\n3\n]. Thus, a patient with severe asthma can develop anxiety as a result of the life-threatening nature of the disease. Such stress can cause dyspnea, which might be treated inappropriately with therapy for asthma rather than anxiety [\n4\n]. In a study by Ortega et al. [\n5\n], 49% of children with asthma from cohorts in New Haven, Atlanta, NewYork, and Puerto Rico were identified through the Diagnostic Interview Schedule for Children as having an anxiety disorder. Further, a history of psychogenic stressors or psychiatric disorder often is identified in pediatric patients with functional respiratory disorders, such as sighing dyspnea, habit cough, and vocal cord dysfunction [\n6\n]. For example, in a literature review, 52% of patients with vocal cord dysfunction were diagnosed as having a conversion disorder [\n7\n]. This evidence suggests that children presenting with respiratory complaints may benefit from a psychological intervention.\nPreviously, we reported the outcome of hypnotherapy offered at our Pediatric Pulmonary Center [\n1\n,\n4\n,\n8\n-\n10\n]. Reported rates of improvement following hypnotherapy ranged from 86% of patients with anxiety [\n8\n], 90% of patients with habit cough [\n10\n], 91% of patients with vocal cord dysfunction [\n8\n], and 100% of patients with chronic dyspnea, who had normal lung function at rest [\n9\n].\nThe purpose of the current study was to define the proportion of all patients referred to our Pediatric Pulmonary Center who might receive benefit from instruction in self-hypnosis as a psychological intervention.\nMethods\nA retrospective chart review was undertaken for all patients newly referred to the SUNY Upstate Medical University Pediatric Pulmonary Center during the 18 months beginning January 1, 2000. Most of these referrals were from primary care providers. Information collected included age, gender, referral diagnosis, whether and for what purpose they were offered hypnotherapy or any other psychological intervention, the results of the intervention, and diagnosis in 2003 at the time of the data collection, or at the time of discharge from the Center if this occurred before 2003. Assessment of intervention effectiveness was based on the patients' subjective reports, except in the cases of patients with habit cough, or stridor associated with vocal cord dysfunction, whose symptoms were observed to have resolved during a visit at our Center.\nPatients were evaluated for their respiratory complaints by a thorough review of their history, physical examination, and laboratory investigations, including pulmonary function testing, radiological investigations, and blood studies. Patients were offered hypnosis if they presented with symptoms or signs suggestive of psychological difficulties, such as those listed in Table \n1\n. Formal testing for psychological disorders or hypnotizability was not utilized. Those who expressed interest in hypnotherapy were instructed in self-hypnosis techniques by a pediatric pulmonologist. Hypnosis was taught in one or two 15–45 minute sessions, as described previously [\n8\n]. Patients who required psychological intervention other than hypnotherapy were to be referred to a child psychiatrist.\nTable 1\nSymptoms and signs suggestive of psychological difficulties*\nRespiratory symptoms\nDifficulty with inspiration\nDisruptive cough\nDyspnea despite normal lung function\nHyperventilation\nInspiratory noise (e.g., stridor, gasping, rasping, or squeak)\nLocalization of breathing problem to the neck or upper chest\nSighing\nOther symptoms\nAnxious appearance\nDizziness\nFeeling something is stuck in the throat\nPalpitations\nParesthesias\nShakiness\nSymptom characteristics\nAbsence during sleep or when patient is distracted\nAssociated with a particular location or activity\nEmotional response to symptoms\nEmotional trigger of symptoms\nExposure to traumatic life event\nIncomplete response to medications\n* Adapted from references 1, 4, 8–10.\nAs this study involved a retrospective chart review without identification of patients, exemption was given from review by the Institutional Review Board.\nResults\nOf the 725 newly referred patients (424 were 0–5 years, 193 were 6–11 years, and 108 were 12–18 years old), 133 (18%) were offered hypnotherapy. No patients required referral to a psychiatrist. Patients offered hypnotherapy tended to be older: Hypnotherapy was offered to 1% of 0–5 year olds, 36% of 6–11 year olds, and 55% of 12–18 year old patients. Table \n2\n lists the main reasons for the hypnotherapy.\nTable 2\nReasons for offering hypnotherapy\nn = 133\nPercent of patients\nRespiratory symptoms\nCough\n19\nChest pain\n8\nDyspnea\n25\nInspiratory difficulties\n8\nOther reasons\nAltering palatability of medications\n8\nAnxiety\n9\nHeadaches\n6\nInsomnia\n4\nRelaxation\n11\nOther\n14\nAnxiety, habit cough, and vocal cord dysfunction were the three diagnoses made at our Center in this study population that are recognized commonly as having major psychological components [\n5\n,\n6\n]. These diagnoses accounted for 1% of the 0–5 year olds, 20% of the 6–11 year olds, and 31% of the 12–18 year olds.\nA referral diagnosis of asthma accounted for 28% of 0–5 year olds, 50% of the 6–11 year olds, and 53% of the 12–18 year olds. Among these patients, anxiety, habit cough, and vocal cord dysfunction were diagnosed in 4% of 0–5 year olds, 21% of the 6–11 year olds, and 26% of the 12–18 year old patients.\nOne hundred sixteen of the 133 patients (87%) offered hypnotherapy agreed to receive instruction in self-hypnosis. Eighty-one of the patients received such instruction for anxiety or the respiratory symptoms listed in Table \n2\n. Among these 81, 75% returned for follow-up, and among the returning patients 95% reported improvement or resolution of their symptoms, as previously described in detail for many of these patients [\n1\n,\n8\n-\n10\n].\nDiscussion\nThis study demonstrates that a large number of patients referred to a Pediatric Pulmonary Center may benefit from instruction in self-hypnosis. As reported elsewhere, many of the patients in this report, e.g., those with anxiety, habit cough or vocal cord dysfunction, failed to improve prior to introduction of hypnosis [\n1\n,\n8\n-\n10\n]. Therefore, it is likely that hypnosis was important for their recovery. It is possible that the time spent with the pulmonologist, or the reassurance received regarding the absence of physiologic disease were the critical parts of the intervention, as opposed to the hypnotherapy. Even if this were the case, the findings in this report underscore that a significant number of patients can respond to a therapeutic interaction that addresses their psychological needs.\nGiven our finding that a large number of referred patients may benefit from psychological intervention, we believe that health care providers should familiarize themselves with symptoms and signs that may indicate psychological difficulties (see Table \n1\n). Further, providers should identify mechanisms by which patients' psychological issues can be addressed appropriately. Provision of instruction in self-hypnosis techniques can allow for a rapid, effective intervention that patients often accept readily [\n8\n-\n11\n]. Hypnosis should not be offered in situations where it might aggravate existing emotional problems, or the problem might be treated more effectively by another method [\n11\n]. Interested clinicians can receive training in self-hypnosis techniques through workshops sponsored by the American Society of Clinical Hypnosis, the Society for Clinical and Experimental Hypnosis, or the Society for Developmental and Behavioral Pediatrics [\n11\n].\nThe proportion of patients with psychological difficulties contributing to respiratory symptoms at our tertiary-care Center may be greater than that in a general pediatric practice because patients who respond well to medical therapy are less likely to be referred. Further, the proportion also may be different when compared to other Pediatric Pulmonary Centers. For example, if the socio-economic mix of referred patients is different between Centers, the proportion of patients with physiologic disease may vary between Centers as a result of different levels of environmental exposures and adherence to prescribed therapy. Also, the type of patient referred to our Center may be biased as a result of our recognized interest in the treatment of symptoms with a possible psychological basis. On the other hand, it is possible that we would have diagnosed more patients with psychological difficulties had we used formal psychological testing [\n5\n,\n11\n]. The relatively high number of patients lost to follow-up in this report is attributable to the study population that was derived from a clinical practice. Thus, controlled studies with close follow-up are needed to help better define the utility of self-hypnosis.\nPsychological intervention in the comprehensive management of pediatric patients also is likely to be of benefit for a large number of patients in other pediatric practice settings including general pediatrics [\n11\n], and sub-specialty centers, including gastroenterology (e.g., for functional abdominal pain) [\n12\n], nephrology (e.g., for enuresis and dysfunctional voiding) [\n11\n], neurology (e.g., for headaches) [\n11\n], and surgery (e.g., for promotion of recovery) [\n11\n].\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nRA is the pediatric pulmonologist described in this report. He conceived the study and wrote the manuscript. SG collected and analyzed the data, and revised the manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
30
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nReckoning with the beast. Animals, pain, and humanity in the Victorian mind\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
31
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nStudy of urban community survey in India: growing trend of high prevalence of hypertension in a developing country\n\n**Article Abstract:**\n\nThe prevalence pattern of hypertension in developing countries is different from that in the developed countries. In India, a very large, populous and typical developing country, community surveys have documented that between three and six decades, prevalence of hypertension has increased by about 30 times among urban dwellers and by about 10 times among the rural inhabitants. Various factors might have contributed to this rising trend and among others, consequences of urbanization such as change in life style pattern, diet and stress, increased population and shrinking employment have been implicated. In this paper, we study the prevalence of hypertension in an urban community of India using the JNC VII criteria, with the aim of identifying the risk factors and suggesting intervention strategies. A total of 1609 respondents out of 1662 individuals participated in our cross-sectional survey of validated and structured questionnaire followed by blood pressure measurement. Results showed pre-hypertensive levels of blood pressures among 35.8% of the participants in systolic group (120-139mm of Hg) and 47.7% in diastolic group (80-89 mm of Hg). Systolic hypertension (140 mm of Hg) was present in 40.9% and diastolic hypertension (90 mm of Hg) in 29.3% of the participants. Age and sex-specific prevalence of hypertension showed progressive rise of systolic and diastolic hypertension in women when compared to men. Men showed progressive rise in systolic hypertension beyond fifth decade of life. Bivariate analysis showed significant relationship of hypertension with age, sedentary occupation, body mass index (BMI), diet, ischemic heart disease, and smoking. Multivariate analysis revealed age and BMI as risk factors, and non-vegetarian diet as protective factor with respect to hypertension. Prevalence of prehypertensives was high among younger subjects - particularly students and laborers who need special attention. Role of non-vegetarian diet as a protective factor might have been related to fish-eating behavior of the sample population, who also use mustard oil as cooking medium - both of which have significant level of essential polyunsaturated fatty acids. The observed prevalence of hypertension in this study and other studies suggest the need for a comprehensive national policy to control hypertension in India, and, in other similar developing countries.\n\n**Article Body:**\n\n1. BACKGROUND\nAn epidemiological shift in the prevalence of hypertension in developing countries as compared to developed countries has been observed \n1\n,\n2\n. Studies from India and Bangladesh have shown upward trend in the prevalence of hypertension \n3\n. India is a vast country with a heterogeneous and young population. Till recent past, control and prevention of communicable diseases was emphasized. Recently, attention has shifted to control and prevention of non-communicable diseases including stroke, hypertension and coronary artery disease at the national level in view of the rising trends. Community surveys from different regions and various ethnic populations are instrumental to formulate national consensus-driven policies to counteract the rising trend of non-communicable diseases. The prevalence of hypertension has increased by 30 times among the urban population over a period of 55 years and about 10 times among the rural population over a period of 36 years \n4\n. Various hypotheses have been put forward to explain this rising trend and among these, consequences of urbanization such as change in life style pattern, diet and stress have been implicated. The current urbanization rate in India is 35% as compared to 15% in the 1950. With growing urbanization, socio-developmental changes have taken place over last 40-50 years. Dramatic changes in life style from traditional to modern have lead to physical inactivity due to technological advances. Rising affluence has modified the dietary pattern characterized by increased consumption of diets rich in fat, sugar and calories. Furthermore, increasing population growth at the current rate of about 2% in each year and technological advances have shrunken the employment opportunities particularly among young generation – leading to stress and hypertension in young persons, including students and laborers. The primary objective of this project was to study the prevalence of hypertension in an urban population in West Bengal- an eastern state of India - using the recently published “The Seventh Report Of Joint National committee on Prevention, Detection, Evaluation and Treatment of High blood Pressure (JNC-VII) criteria” \n5\n. Additionally, the study aimed to identify the various risk factors for hypertension with the purpose to suggest possible interventions based on the risk factor analysis.\n2. METHODOLOGY\nPlace of survey and the population\nMalda, a district town in the state of West Bengal, had been the place of survey. Demographic characteristic of the sample population is given in table \n1\n. The place has a tropical climate and is made of alluvial soil in the Gangetic plain. The population is stable and usually consumes mixed diet consisting of rice, fish as the chief protein component and mustard oil as the main cooking medium.\nPopulation of English bazaar municipality under Malda Town is 1,61,448 (Men- 51.36% : women- 48.63%) according to census report (Census, 2001). It consists of twenty-five wards. About 1% of the population above the age of 18 years was studied in 2001. Initially, families were randomly selected from an administrative database on families residing in the locality. After selection of the families, all available members of the selected family who were at 18 years of age or above at the time of the study were then included for the door-to-door survey.\nDefinition of hypertension (Based on JNC-VII criteria)\nNormal- Systolic and diastolic < 120/80\nPrehypertensives: systolic 120-139 or diastolic 80-89 mm of Hg\nStage-1 hypertensives: systolic 140-159 or diastolic 90-99 mm of Hg\nStage-2 hypertensives: systolic 160 or diastolic 100 mm of Hg\nThe participants with history of hypertension and on antihypertensive drugs were also labeled as hypertensives.\nQuestionnaire\nThe following information was collected from each subject through a validated questionnaire administered by the volunteers: age, sex, occupation, income status, weight, height, pattern of salt intake, dietary pattern, history of diabetes, family history of hypertension, past history of any examination of blood pressure and hypertension, or any its complications, any symptom referable to target organ dysfunction, previous and present treatment profile, and addictions.\nMethods\nThe volunteers had administered the structured questionnaires. After verifying the questionnaire, the doctors measured the blood pressure for each participant.\nBlood pressure Measurement: Two graduate physicians of similar backgrounds with over 20 years of clinical experience (authors SD and KS) measured the blood pressure for each participant, using the auscultatory method with a standardized calibrated mercury column type sphygmomanometer and an appropriate sized cuff encircling at least 80% of the arm in the seated posture, with feet on the floor and arm supported at heart level. Following a standardized protocol, they made two separate measurements and recorded the average of the two measurements after proper rest and due explanation to the examined participant about the objective of the study. In some cases, where high blood pressure was recorded for the first time, the physicians checked the blood pressure more than twice and took the average of the two close readings. Systolic BP is the point at which the first of 2 or more sounds is heard (phase I) and diastolic BP is the point before the disappearance of sounds (phase 5).\nAll participants above 40 years underwent electrocardiograms (ECG), irrespective of level of blood pressure. Participants who were below 40 years of age, only those who had hypertension and complained of typical precordial pain suggestive of ischemic heart disease, had ECGs. Participants with typical central chest pain, suggestive ECG changes and on anti ischemic drugs are considered to be suffering from myocardial ischemia. Salt intake was assessed from the amount of salt used in cooking and extra salt used during meal.\nStatistical Analysis\nWe used EPI-INFO-2002 software for data entry and analysis. We applied chi-square test to find out the results at 5% significance for the select risk factors and outcome variables. We put the significant variables from the bivariate analysis into a series of stepwise, unconditional multivariate logistic regression and calculated the Odds Ratios with 95% confidence intervals (CI) to assess the association between these variables and each of the following outcome measures: normal blood pressure, prehypertensive status, Stage I and Stage II hypertensives status.\n3. RESULTS\nTotal 1662 participants were screened. Of them, 53 (3.2%) persons did not want to participate in the survey. Thus the results of 1609 persons could be analyzed. Detail demographic data was given in Table \n1\n and the proportionate national data had been given simultaneously. Our population showed slightly older than the national data. Total family screened was 526 (average adult persons per family was 3.15).\nFig \n1\n shows the distribution of mean systolic and diastolic pressure in different age groups of the sample population among both men and women.\nOut of 1609 persons, Table \n2\n shows the distribution of different pressure range among various groups according to JNC-VII criteria. Only 14.1% of the participants had normal blood pressure. A large number of participants could be categorized in prehypertensive group. Overall prevalence of hypertension with a cut off mark of 140/90 mm of Hg is 24.9% (men and women). If cut off mark is 165/95 mm of Hg, the overall prevalence stands at 8.5% (men -7.6% and women-9.6%). Of the hypertensives, only 3 percent individuals were on antihypertensive medications at the time of survey, and half of them had blood pressure within normal range.\nFig \n2\n shows the influence of age and sex on distribution of both systolic and diastolic hypertension among the sample population. In participants below 40 years, both systolic and diastolic hypertension showed higher prevalence in men. After 40 years, systolic hypertension showed progressive age-dependent increase up to eighth decade in both sexes and only in women, the prevalence of diastolic hypertension remained higher up to eighth decade. Maximum prevalence of systolic hypertension was 64% among men in eighth decade and women in seventh decade. Maximum prevalence of diastolic hypertension had been recorded up to 50 % among women in seventh decade and 37% among men in eighth decade.\nPrevalence of stage I and stage II hypertension was higher among older individuals, sedentary workers, those with high body mass indices, smokers, individuals with history of ischemic heart disease and vegetarians (Table \n3\n).\nAfter adjusting for the effects of all other variables, older age, higher body mass index and vegetarian diet turned out as independent risk factors for stage I or stage II hypertension (Table \n4\n). Compared to those below 20 years of age, people who were 40 years or older had significantly increased risk of stage I and stage II hypertension. For stage II hypertension, association of age with risk of hypertension increased in a dose response manner. Thus, compared to those who were younger than 20 years, people between 40-49 years were nearly 4 times at risk of stage II hypertension, people between 50-59 years were more than 8 times at risk, and people above 60 years were over 14 times at risk of stage II hypertension.\nAfter adjusting for the effects of all other factors, people with higher body mass indices were at significantly higher risk of stage I and stage II hypertension. Compared to people whose BMI were at the lower quantiles (i.e. people with BMI 18.4 or lower), people whose BMI was in the highest quantile (BMI equal to or more than 25.6) were about 2.5 times at risk of stage I hypertension and nearly 3 times at risk for stage II hypertension. Finally, after adjusting for the effects of all other factors, compared to vegetarians, non-vegetarians in this population (predominantly fish eaters) were about 40 percent lower risk of stage II hypertension (Table \n4\n).\n4. DISCUSSION\nHypertension is a major public health problem in India and in other developing countries \n1\n-\n2\n. This is obvious from several Indian urban and rural studies \n4\n, \n6\n-\n16\n. The various studies estimated a prevalence rate of hypertension among urban population ranging from 1.24% in 1949 to 36.4 % in 2003 and for rural people from 1.99% in 1958 to 21.2% in 1994 \n1\n. However differential rates are due to different cut off marks in determining the level of hypertension and also differing age groups constituting the study population. Countries with an ageing population in developed countries will be expected to have a higher prevalence of hypertension than a developing country with a younger population such as India, but there are studies, which have documented a high prevalence rate of hypertension in developing countries \n1\n,\n2\n.\nUrban studies from India in last decade have shown increasing overall prevalence of hypertension from 6.64% in 1988 to 36.4% in 2003 considering cut off mark 140/90 mm of Hg \n6\n-\n16\n. Our study showed an overall prevalence range of 24.9% among men, which is twenty times higher than a documented prevalence rate of 1.24 % among apparently healthy men in the police personnel carried out in 1949 in the same state \n6\n. Unfortunately cut off mark of hypertension was not defined in the above study and the low rate in the previous study may be due to younger population, due to the study being restricted to an age – range between 18 to 50 years. Progressive urbanization, life style modification and sedentary habits are probably some of the important factors considered to be responsible for the higher prevalence of hypertension \n17\n.\nAn analysis of mean systolic and diastolic pressures among Urban Indian population in the age range between 40-49 years showed an increase of mean systolic pressure 120.4 mm Hg and mean diastolic pressure 73.2mm Hg in 1942 to 128.7 and 84.2 in 1985, 128.8 and 83.2 in 1995 to 141 and 85 in the present study \n4\n. Higher prevalence of hypertension is often indicated by a rise in mean systolic and diastolic pressure. Similar observation has been noted in Yugoslavia and in Japan when it was a developing nation and decrease in prevalence has also been noted in seven countries' study along with decrease in mean systolic and diastolic pressures \n18\n.\nAge related increase of hypertension is a common, but not a universal phenomenon. This is predominantly influenced by environmental factors as certain non migrant or tribal populations, who follow a primitive life style do not develop age related rise of prevalence of hypertension \n19\n-\n21\n.\nHigh prevalence of systolic hypertension at advanced age had been documented in few recently conducted surveys from India such as from Parsi community in Western India (73% in age group equivalent to 70 years) \n13\n, among Kerallite (51.8%) from South India \n12\n, Assamese (63.63% for people above 60 years of age) from North eastern India \n22\n and among elderly participants from WHO sponsored multicenter study in Southeast Asia (65%) \n3\n as compared to an age specific prevalence rate of 64% in seventh to eighth decade in the present study (Fig.\n2\n). Thus all the studies have recorded a high prevalence of hypertension. Systolic hypertension has been considered to be one of the most important cause of morbidity and mortality leading to cerebrovascular stroke, cardiovascular and renal diseases \n23\n-\n24\n.\nInfluence of gender in hypertension prevalence has been observed among men who showed higher prevalence of both systolic and diastolic hypertension in young age, but higher prevalence of diastolic hypertension in women after 40 years may be related to increasing family stress and obesity which is common in middle aged woman \n25\n.\nThe present study had shown a large proportion of sample population in the prehypertensive group. Table \n2\n has shown an inverse relation between prevalence of prehypertension and age and the particularly victims were students and laborers. These participants are of great interest since chance of progression to hypertension is high. Incidentally the previous study has shown increasing prevalence of coronary artery disease among young in India \n26\n. The younger people in India are stressed out because of heavy competition in academic fields and also for securing employment. Studies have already established that the relationship between BP and risk of cardiovascular disease events is continuous, consistent and independent of other risk factors \n5\n and prehypertensives have greater chance to go into hypertension \n27\n. Hence it is also possible that the young stressed individuals with prehypertensives level of blood pressures may be at risk factor to develop ischemic heart disease. However no study from India based on JNC- VII criteria is available for comparison. Future longitudinal study involving regular check up of blood pressure of students from secondary level as well as of laborers should be carried out to study the causal relationship between age-specific prehypertensive level of blood pressure and subsequent development of hypertension and coronary artery disease.\nThough bivariate analysis showed significant correlation between hypertension with higher age, sedentary activity, smoking, body mass index which was an indicator of obesity and history of target organ dysfunction, multivariate analysis using the logistic regression only documented older age, non vegetarian diet and increasing BMI had significant influence on prevalence of hypertension. The relation of hypertension with advancing of age and BMI has already been documented in the past among Indian subjects \n4\n.\nThe point of interest is protective effect of non-vegetarian diet. The study participants by custom are predominantly fish eater and they also consume mustard oil, which is a principal cooking medium. Mustard oil is edible oil and it has a right blend of n-3/n-6 polyunsaturated fatty acids, which help in reducing LDL, and it has very low amount of saturated fatty acids. Extraction of different fatty acids from mustard oil has shown the presence of erucic acid which is a monounsaturated fatty acid (cis-13-Docosenoic acid) and found in the range of 42-55% in Indian Mustard. Fish oil is the main source of omega-3 fatty acids (EPA- eicosapentaenoic acid and DHA -docosahexaenoic acid) and also omega-6 fatty acids- two main classes of essential fatty acids. Omega –3 fatty acid found in fish oil lowers blood triglyceride level and blood pressure possibly through generation of nitric oxide which has vasodilator property. EPA is more effective in reducing triglyceride level and DHA is more effective for reducing blood pressure. Thus in combination, they might have protective effect on the non-vegetarians as compared to the vegetarians \n28\n-\n30\n. Beneficial effect of mustard oil has been observed among Indians in reducing ischemic heart disease in a recent study \n31\n.\nHowever, several potential limitations should be considered while interpreting the results of this study. First, the dietary data were obtained from a structured questionnaire and therefore response bias could not be ruled out. Data on cooking medium was not sought at the initial survey. However, subsequent surveys and common social norms indicate that the preferred cooking medium for about 98% of the population was mustard oil. Second, when considering systolic hypertension, diastolic pressure may vary widely from normal to abnormal range and vice-versa. And that we have not analyzed the correlation of socio-economic status with stage of hypertension to avoid bias, as participants did not want to reveal their actual income status.\nIn conclusion, we have shown that there is increasing trend of mean systolic and diastolic pressures and higher prevalence of hypertension in the urban community. We have also documented a large number of prehypertensive individuals according to the JNC-VII criteria, who are young and need special attention to avoid early progression to hypertension and possibly coronary artery disease that is common in India. Age and sex specific increase of prevalence of systolic and diastolic hypertension in both women and men indicate significant role of environmental factors. This suggests public health remedial measures to address growing hypertension in the community through health education about lifestyle changes, dietary modification, and avoidance of urban stress through, for example, practice of yoga. Our findings also suggest a protective role of non -vegetarian diet such as fish cooked in mustard oil on hypertensives. Individually, both fish and the mustard oil are rich in unsaturated fatty acids, and biologically, their beneficial effects are related not only to reduction of blood pressure, but also to lowering of lipids and to their antithrombotic effects \n28\n. Useful role of fish cooked in mustard oil, as a protective factor needs to be probed further in future longitudinal studies.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
32
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nIs obesity a risk factor for low back pain? An example of using the evidence to answer a clinical question\n\n**Article Abstract:**\n\nBackground\nObesity as a causal factor for low back pain has been controversial with no definitive answer to this date. The objective of this study was to determine whether obesity is associated with low back pain. In addition this paper aims to provide a step-by-step guide for chiropractors and osteopaths on how to ask and answer a clinical question using the literature.\nMethods\nA literature review using the MEDLINE search engine using the keywords \"obesity\", \"low back pain\", \"body mass index\" \"BMI\" and \"osteoarthritis\" from years 1990 to 2004 was utilised. The method employed is similar to that utilised by evidence-based practice advocates.\nResults\nThe available data at this time is controversial with no clear-cut evidence connecting low back pain with obesity.\nConclusion\nThere is a lack of a clear dose-response relationship between body mass index (BMI) and low back pain. Further, studies on the relationship between obesity and related lumbar osteoarthritis, knee pain, and disc herniation are also problematic.There is little doubt that future studies with controlled variables are needed to determine the existence of an unambiguous link, if any.\n\n**Article Body:**\n\nIntroduction\nObesity is a problem of epidemic proportion [\n1\n,\n2\n]. Despite record rates of non-physician supervised dieting and the availability of numerous weight loss programs, the problem is not abating [\n3\n]. Complicating this, is that most primary care physicians do not treat obesity, citing a lack of time, resources, insurance reimbursement, and knowledge of effective interventions as significant barriers [\n4\n]. Musculoskeletal disorders including low back pain (LBP) represent a considerable public health problem and a common diagnosis creating absenteeism and the need for disability pensions [\n5\n]. It is estimated that about 80% of the United States and Canadian population will experience LBP during adulthood [\n6\n]. Most low back pain is self-limiting and will ultimately resolve in two weeks (50% of those affected) to six weeks (90% of those affected), however it remains an intriguing clinical problem [\n6\n].\nIt is widely noted that the economic cost of obesity and its related disorders are staggering, with lifestyle related conditions such as diabetes mellitus and coronary heart disease placing a large economic burden on the health care system [\n1\n-\n4\n]. However, low back pain also has a significant socioeconomic impact. Cost estimates range from US$20 billion to $50 billion annually, with 10% of the patients accounting for 85 to 90% of the costs [\n6\n]. In Australia, Walker et al estimated the cost of low back pain in 2001 alone to be AUD$9.17 billion [\n7\n].\nOne question, which arises from the discussion concerning obesity, is whether obesity is a risk factor for low back pain. \"Buckwalter et al contended that a number of medical conditions including obesity, along with diabetes and hypertension, may influence the pathophysiology of diseases of the tendons and ligaments during the process of aging thus potentially leading to low back pain [\n8\n]. Along with low back pain, the conventional wisdom is that overweight persons are at risk of osteoarthritis in weight-bearing joints such as the knee, the hips, and feet [\n9\n].\nTo date, literature reviews have given conflicting views based on the available data and method of data retrieval. The purpose of this review is to establish, from recent research, if there is a causal link between obesity and the affliction of low back pain. A secondary purpose of this review is to present the concepts of evidence-based practice to aid the chiropractor or osteopath in looking for health-related evidence for their patients who present with obesity.\nMethods\nA MEDLINE search, from the National Library of Medicine, was used to ascertain pertinent articles between the years 1990 and 2004. The use of keywords \"obesity\", \"body mass index\", \"BMI\" and \"low back pain\" was used to obtain relevant studies. The references of papers retrieved were also reviewed, as were key texts and references.\nThis section is devoted to presenting the concepts of evidence-based practice (EBP) to demonstrate to the reader the discovery process for finding a possible link between obesity and low back pain. The EBP method used is shown in Table \n1\n.\nTable 1\nSteps to asking the answerable question using EBP principles\nStep 1: Asking an answerable question\nStep 2: Selecting an evidence resource\nStep 3: Executing the search strategy\nStep 4: Examining the evidence summary\nStep 5: Application of the evidence\nThe first step in this process is \"asking an answerable question.\" In this paper we assume a patient has asked whether being overweight can cause low back pain. Construction of an appropriate answerable question would possibly be \"Does an increased BMI cause low back pain?\" \"Does being overweight create osteoarthritis?\" In this way questions can be constructed to allow the practitioner to effectively answer a clinical concern.\nOnce the answerable question has been constructed the next task is to find an adequate resource. Internet access to the U.S. National Library of Medicine's MEDLINE or PUBMED, these database systems are considered by many experts to be the most up to date data source on medically related topics. The next step is to determine keywords to place in the search engine. From the answerable question(s) it can be appreciated that the initial keywords will be \"low back pain\", \"BMI\" and \"osteoarthritis.\" This search constitutes the third step. In initiating the search, one should look for the search engines \"limits\" area. In this area can one designate an age group (ex: 45 to 60 years), date span of the literature search, (ex: 1998 to 2003), and to select either English language or articles in foreign languages.\nOnce the search has been completed, the articles, which may answer the question, are isolated and can be read. Step four involves collating the evidence to answer the question. In searches one may find answers that were not known to exist, and information that may challenge an already preconceived notion. The evidence summary should list the main author and year the paper was published. This is in order to retrieve the data should anyone wish to examine the source. As an example of an evidence summary see Table \n2\n.\nTable 2\nRecent evidence: Obesity and low back pain (chronological order)\nAuthor, Year (Ref)\nN\nBMI\nLBP\nAssociation\nMelissas, 2003 [14]\n50\n>40\n58%\ndirect\nBener, 2003 [10]\n802\n(26.4 males/ 27.8 females)\n56.1% males\n73.8% females\nmoderate\nTsuritani, 2002 [16]\n709\n--\n40.3%\nnone\nBowerman, 2001 [4]\n252\n--\n29.2%\nnone\nKostova, 2001 [12]\n898\n--\n--\nincreased risk\nBayramoglu, 2001 [15]\n25\n--\n--\ndirect\nMortimer, 2001 [13]\n475\n30 (43.6%)\n31–40 (28.8%)\n40+ (1.3%)\n--\nincreased risk\nHan, 1997 [11] 7018 women\n5887 men NR\n--\nfemales increased risk\nN = number; BMI = body mass index; LBP = low back pain; NR = not reported\nIt is at this time that the clinician is ready for the final step of applying the evidence. In our example clinical data from the experimental literature may or may not indicate that there is a link between overweight and low back pain.\nResults\nThe literature search into obesity and joint pain revealed several studies pertinent to the debate. Table \n2\n reveals an overview of the studies selected. Several studies [\n4\n,\n10\n-\n13\n] had large populations to draw from yet the data from these studies were not in agreement as to a cause or association. In fact, only two studies [\n14\n,\n15\n] found a direct association for obesity as a risk factor while two [\n4\n,\n16\n] studies found no association. Several of the studies reviewed were unable to clarify BMI to the satisfaction of the authors.\nDiscussion\nInterest in the association between obesity and low back pain has piqued researchers interest for many years. Intuitively, a burgeoning waistline and an increased lordotic lumbar spine led researchers to conclude that overweight people would be more prone to low back pain. Historically, Kellgren and Lawrence (1958) found that that the prevalence of disk degeneration with obesity was not significant [\n17\n]. However, it was not until the mid-1970's when several studies observed a possible association. Obesity was found to increase the prevalence of disk degeneration significantly in a study by Magora and Schwartz in 1976 [\n18\n]. Barton et al (1976), in a review of 144 cases, found that 70% of those who complained of low back pain had been classified as being overweight [\n19\n]. This basic research appeared to conclude what was already intuitively thought about low back pain and increased weight.\nBody mass index\nBefore an in-depth discussion of low back pain and obesity can ensue, the concept of Body Mass Index (BMI) needs to be discussed. BMI is a measure of fatness and is calculated by dividing the patient's weight in kilograms by height in metres squared kg/M\n2 \n[\n20\n]. It is widely accepted, easily measured, and predicts morbidity and mortality in many populations [\n15\n]. Obesity is generally defined as a BMI of 30 kg/m2 and higher [\n20\n,\n21\n]. Overweight is defined as a BMI between 25 and 30 kg/m2 [\n19\n,\n20\n]. Overweight tends to be more common in men with obesity being more prevalent among women [\n21\n]. When body weight is increased 20% above average, mortality rises to 20% for men and 10% for women [\n22\n]. (Table \n3\n) Overweight individuals demand more from their cardio-respiratory and musculoskeletal systems [\n22\n]. It is known that more than 50% of adult Americans have a BMI equal to or greater than 25 [\n23\n]. Although there are certain limitations to BMI i.e. large muscular athletes who are in good cardiovascular shape, the rationale behind these numbers is that, across large population groups, there is an increased prevalence of certain diseases in people with a BMI over 25, and a much greater risk of disease and death in those with a BMI over 30 [\n4\n]. Being overweight or obese substantially raises the risk of developing hypertension, coronary heart disease, type 2 diabetes, stroke, gallbladder disease, sleep apnea and other respiratory problems, prostate and colon cancers [\n4\n,\n23\n]. Yet, the evidence to date linking it to low back pain is not as clear cut as it is with the previously stated pathologies.\nTable 3\nClinically relevant differentiation between obesity and overweight\nOverweight\nObesity\nBMI of 25.0 to 29.9 kg/m\n2\nBMI greater than 30 kg/m\n2\nBMI calculation without benefit of BMI charts\nBody Mass Index (BMI) charts and hand held scales are available for individual clinician use. It is, however, unknown to what degree chiropractors or osteopaths use such tools. The following section is designed to aid the clinician with calculating BMI without benefit of chart or hand held scales.\nAs noted earlier, BMI is calculated as weight in kilograms divided by height in square metres [\n20\n,\n24\n]. This method is often too difficult to calculate for most people. A simpler method for those using the imperial system of measures is to take body weight in pounds × 703/height in inches squared.\nFor example, a person weighing 150 pounds at 6 foot tall would correspond to a BMI of 20.3. TABLE \n4\nTable 4\nCalculation of BMI\n150 × 703 = 105450 divided by 72 inches (6 foot) squared.\n105450 divided by 5184 (72 × 72) = 20.3 BMI.\nAdditional research findings\nLeboeuf-Yde concluded from a review of the literature that due to lack of evidence, body weight should be considered a possible weak risk indicator and suggested that there is insufficient data to assess if it is a true cause of LBP [\n25\n]. Kostova found that in men over 40, overweight, obesity and number of pack years of smoking, estimated by duration of smoking and daily cigarette consumption (more than 20 years and more than 20 cigarettes per day), increased the risk of developing back disorders [\n12\n].\nDespite these two studies, Garzillo et al and Leboeuf-Yde et al have given conflicting opinions [\n26\n,\n27\n]. Garzillo's review of the data revealed a possible association between obesity and low back pain only in the upper quintile of obesity, and no evidence of a temporal relationship between weight change and changes in low back pain [\n26\n]. Leboeuf-Yde concluded from a twin study that obesity is modestly positively associated with low back pain, in particular with chronic or recurrent low back pain [\n27\n].\nWhat appears to be a main concern in linking obesity as a causal factor for low back pain is the numerous variables encountered in these subjects. For example, it is hypothesized that overweight adult females may have negative self-concepts and body images compounded by chronic low back pain and obesity, these may be confounding factors [\n28\n]. Other variables such as less activity and/or muscular weakness leading to obesity are also possible considerations.\nObesity and low back pain-related conditions\nNot only is there controversy in obesity and low back pain, but there exists conflicting views of obesity and low back pain-related conditions such as spondylosis, decreased physical activities and discal herniation. The studies demonstrating a positive association are many. O'Neil \net al \nnoted that increasing BMI is associated with more frequent findings of osteophytes (bone spurs) at both the thoracic and lumbar spines [\n29\n]. The correlation of osteophytes and increased BMI is highest at the thoracic level [\n29\n]. Biering-Strenson \net al \nnoted absolute weight and BMI are significantly higher in persons 60 years of age with spondylosis [\n30\n]. Both men and women with BMI of 30 kg/m2 or higher were twice as likely to have difficulties in performing a range of basic daily physical activities [\n30\n]. Compared with women with BMI lower than 25 kg/m2, those with BMI of 30 kg/m2 or higher were 1.5 times more likely to have symptoms of intervertebral disk herniation [\n31\n].\nConversely, Luoma \net al \nconcluded that disc degeneration is not related to body height, overweight, smoking, or the frequency of physical activity [\n32\n]. In addition, studies by Riihimaki, Symmons, and Kang have shown no association between BMI and low back related problems [\n33\n-\n35\n].\nConfounding the data is that the mechanism by which excess body weight causes osteoarthritis is poorly understood [\n9\n]. It is believed that contributions from both local increased force across the joint and systemic factors play a role [\n9\n]. A discriminating factor between fit and unfit patients with back pain may be the fact that fit persons more frequently are still employed, and as such may be involved more in physical activity [\n36\n]. Table \n5\n indicates where the research currently exists for the link between low back pain and obesity along with obesity and osteoarthritis.\nTable 5\nBMI-related risk of osteoarthritis and low back pain\nIf your BMI is\nthen your risk based solely on BMI\n<25\nminimal\n25 – <27\nminimal\n27 – <30\nminimal\n30 – <35\nmoderate\n35 – <40\nmoderate\n>40\nmoderate to high\nWe conclude, based on the available evidence to date, that those individuals with a BMI of under 30 are at a minimal risk of developing low back pain while those persons whose BMI increases to over 30 are a moderate risk of developing low back pain. We also suggest, based on the findings of the Melissas study [\n14\n] of those patients who relieved their low back pain symptoms after obesity surgery, that patients with a BMI of greater than 40 are at a high risk of developing low back pain. Albeit controversial, Table \n5\n may lead to a further refinement of risk of osteoarthritis and low back pain based solely on BMI.\nLimitations of obesity as a risk factor for low back pain\nA significant difficulty in ascertaining cause and effect between obesity and low back pain is undoubtedly the term \"low back pain\" itself. Low back pain is a symptom not a diagnosis. A specific diagnosis, instead of the generalized form of \"low back pain\" may help separate out the association between LBP and obesity.\nThe Agency for Health Care Policy and Research (AHCPR) in their 1995 \nAcute Low Back Problems in Adults \nnoted common diagnoses used to explain back problems [37] (Table \n6\n). Given these possible diagnoses one can readily appreciate the dilemma in attempting to link obesity with its specificity in measurement to a broad symptom such as low back pain.\nTable 6\nCommon diagnoses used to explain back symptoms\nAnnular tear\nAdult spondylolysis\nMyofascitis\nFibromyalgia\nDisc syndrome\nStrain\nSpondylosis\nLumbar disc disease\nFacet syndrome\nDegenerative joint disease\nSprain\nSpinal OA\nDisc derangement/disruption\nDislocation\n*Other potential causes of low back pain symptomology\nFailed Back Surgery Syndrome*\nOsteoporosis*\nUrinary tract infection*\nCompression fracture*\nSomato-visceral mimicry syndrome*\nOrganic pathology (tumor, rheumatoid, endometriosis, arthritic disorders)*\nLeg length inequity*\nSacro-iliac dysfunction*\nHip disorder*\n**Disagreement in research as cause of low back symptomology\nMorbid obesity?**\nOA = osteoarthritis\nAnother problem is the hypothesis that a person who suffers with continuing bouts of low back pain may be predisposed, due to inactivity or inability to exercise, to gain weight thus increasing their BMI. This hypothesis to our knowledge, has yet to be fully discussed and investigated.\nConclusion\nThe data for a link between obesity and low back pain appears to be controversial. Yet, this does not adequately address the appropriate therapeutic approach to the obese patient with low back pain. The studies chosen for this review fail to document a definitive causal link between obesity and low back pain. Further research and epidemiologic data is needed to continue the search for a definitive answer.\nCompeting interests\nThe author(s) declare that they have no competing interests.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
33
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nEchinococcal disease in Alberta, Canada: more than a calcified opacity\n\n**Article Abstract:**\n\nBackground\nMost cases of echinococcal disease (ED) acquired in Canada are thought to be due to the sylvatic form of \nEchinococcus granulosus\n, which may be more benign than ED due to either \nEchinococcus multilocularis \nor the pastoral form of \nE. granulosus\n. There are limited descriptions of the clinical course and outcome of Canadian patients with ED in the modern era.\nMethods\nA retrospective chart review was performed of patients hospitalized with echinococcal disease (ED) from 1991 to 2001 in Edmonton, Alberta.\nResults\nForty-two cases of ED were identified of which 19 were definite, 3 probable, and 20 possible. Further analysis was limited to the 22 definite and probable cases, of which 77% were female and 41% aboriginal, with an age range of 5 to 87 years. Nine patients (40%) had pulmonary involvement and 11 (50%) hepatic involvement. One patient had an intracardiac mass presenting as a cerebrovascular event and one had a splenic cyst. Seven of the 22 patients had combined surgical resection and medical treatment, six had surgical resection of the cyst alone, four had cyst aspiration, one had medical treatment alone and four had no specific treatment. There was no mortality attributable to ED but three patients died of unrelated illnesses.\nConclusion\nEchinococcal disease in northern Alberta has a marked diversity of clinical presentations, and generally has a good prognosis despite a wide variety of therapeutic interventions.\n\n**Article Body:**\n\nBackground\nEchinococcal disease (ED) is a zoonotic infection caused by cestodes of the genus \nEchinococcus\n. Alveolar echinococcosis results from infection with the species \nEchinococcus multilocularis\n. Disease occurs in the Northern Hemisphere including Alaska, Japan, China, Russia and most countries in continental Europe [\n1\n], and results in multilocular cystic lesions. Cystic echinococcosis (CE) results from infection with the species \nEchinococcus granulosus\n. Disease occurs worldwide with the highest incidence in Mediterranean countries, Russia and the adjacent newly independent states, China, north and east Africa, Australia, and South America [\n1\n]. \nEchinococcus granulosus \ninfections have been further classified as pastoral or sylvatic variants or biotypes. In the pastoral variant, sheep serve as the most common intermediate hosts while in the sylvatic variant the usual intermediate hosts are caribou or moose.\nMost cases of ED acquired in Canada are thought to be due to the sylvatic form of \nE. granulosus\n. In the Northwest Territories and the northern portion of the Canadian Prairie Provinces of Alberta, Saskatchewan and Manitoba, the barren ground caribou is the most common intermediate host [\n2\n]. Moose with hydatid cysts have been found in every province of Canada west of the Maritimes and it is estimated that 50% of moose in Ontario and British Columbia are infected with the parasite [\n3\n]. Hydatid cysts have also been found in wapiti, elk, reindeer, coastal deer, white tail deer and bison. The definitive host is a canine (dog, fox, or wolf) that harbors the tapeworm after ingestion of tissue from an infected intermediate host. Twenty-eight to fifty percent of dogs in the Northwest Territories are infected with \nE. granulosus \n[\n2\n]. Intermediate hosts or humans can ingest eggs shed in the feces of the definitive host, with humans being dead-end hosts. Ingestion of \nE. granulosus \neggs by intermediate hosts or humans is followed by the release of an oncosphere; the larva is subsequently transported via the blood stream or lymphatics to primary target organs (the lung or liver, and rarely the central nervous system, bone, or myocardium). Within the affected organ, the oncosphere matures into a vesicle, which grows expansively by concentric enlargement. A fully mature hydatid cyst, normally fluid-filled and unilocular, represents the final stage [\n4\n].\nEdmonton is a referral center for northern Alberta and the Northwest Territories, thereby affording us an opportunity to see the complications of hydatid disease. We reviewed a decade of our experience with ED to gain further understanding of the epidemiological and clinical features of this disease.\nMethods\nA retrospective chart review was performed of all cases identified as ED using International Classification of Disease (ICD) Ninth Edition codes [ICD-9 122.0 to 122.9] from 1991 – 2001 in all Edmonton regional hospitals. Demographic, clinical and diagnostic data were collected. Aboriginal persons were defined as self-identified native Indian or Inuit people, or individuals with addresses that were on reserve land.\nDefinite ED was defined by evidence of ED on pathology (hooklets, brood capsules, or parasitic degenerative elements), probable ED by positive serology for \nEchinococcus \nand possible ED by a clinical presentation compatible with ED but with no corroborative histologic or serologic evidence.\nUltrasounds of all cystic lesions from patients who met the study criteria were reviewed by a radiologist who was blinded as to whether the patients had possible, probable, or definite ED. Cysts were then classified according to the proposed international classification system [\n5\n].\nResults\nIllustrative case\nA 28-year-old aboriginal female who was five days postpartum had productive cough, pleuritic chest pain, dyspnea, fever, chills and sweating, and had received cephalexin, ciprofloxacin and cloxacillin without clinical improvement. She lived in an aboriginal community and had a history of contact with dogs and the ingestion of meat from a variety of wild animals. Laboratory results included a white blood cell count of 13.3 × 10\n9\n/L, with 1.8 × 10\n9\n/L (14%) eosinophils, erythrocyte sedimentation rate of 47 mm/hr, AST 32 U/L, and ALT 112 U/L. The chest radiograph showed a cavity in the left lower lobe and lingula with an air fluid level. Computed tomography of the chest showed a solitary (4.5 × 6.3 × 7.7 cm) lingual cavity with calcification, septation and a small amount of fluid with an opacity in the posterior segment of apico-posterior segment of the left upper lobe in addition to a left pleural effusion.\nThe patient underwent thoracotomy and left segmental pneumonectomy, left lingulectomy and decortication of the lung. Histologic examination of the lung cysts showed occasional hooklets and degenerative parasitic elements. She had a relatively uncomplicated post operative recovery and was discharged on albendazole 400 mg PO bid for 4 weeks. Echinococcal serology revealed an antibody titer to \nEchinococcus \nof 1:1024 using an Enzyme-linked immunosorbent assay (ELISA) technique.\nReview of cases\nDemographics\nForty-two cases of ED were identified, of which 19 were classified as definite, 3 as probable, and 20 as possible. The demographic features are shown in Table \n1\n. Of the 22 definite and probable cases, 77% were female and 41% were aboriginal. The mean age of the definite and probable cases was 32 years (range 5 – 87 years). Possible cases were predominantly male (55%) and older (mean age 54 years). Eight of the total 42 patients had a history of eating caribou, elk or moose meat. Seven patients had a history of contact with dogs, and none had a history of contact with foxes or wolves. Unfortunately this information was not consistently recorded in the patient records.\nTable 1\nDemographic features of 42 patients hospitalized in Edmonton, Alberta with echinococcal disease 1991–2001\nDefinite/Probable (N = 22)\nPossible (N = 20)\nTotal (N = 42)\nMale\n5 (23%)\n11 (55%)\n16 (38%)\nFemale\n17 (77%)\n9 (45%)\n26 (62%)\nBorn in Canada\n14 (64%)\n14 (70%)\n28 (67%)\nForeign born*\n4 (18%)\n2 (10%)\n6 (14%)\nPlace of birth unknown\n4 (18%)\n4 (20%)\n8 (19%)\nEdmonton residence\n6 (27%)\n6 (30%)\n12 (29%)\nNWT residence\n9 (41%)\n8 (40%)\n17 (40%)\nRural Alberta residence\n7 (32%)\n6 (30%)\n13 (31%)\nMean age (years)\n32 ± 16\n54 ± 25\nPulmonary disease\n9 (40%)\n2 (10%)\n11(26%)\nHepatic disease\n12 (55 %)\n16 (80%)\n28 (67%)\nSpleen /kidney\n0\n2 (10%)\n2 (5%)\nCardiac\n1 (5%)\n0\n1 (2%)\n*Patients were born in Lebanon, Ukraine, Iraq, Paraguay, Poland, or Yugoslavia\nOf the 22 definite and probable cases of ED, 9 (40%) had pulmonary involvement, 11 (50%) had hepatic involvement, one (5%) had splenic involvement and one (5%) had cerebral disease. The patient with cerebral disease was a 28-year-old woman with cerebral emboli, who had a pre-operative diagnosis of cardiac myxoma based on echocardiography and magnetic resonance imaging. The cardiac mass was resected and found to be an echinococcal lesion. Ten percent of the possible ED patients had pulmonary lesions, 80% had hepatic lesions, and 10% had non-hepatic intra-abdominal lesions (an immigrant from Poland with a calcified 10 cm diameter cyst in the spleen, and a man with adenocarcinoma of the rectum who had several calcified cysts in the right kidney).\nThe presenting symptoms of the 38 patients with pulmonary or hepatic disease are shown in Table \n2\n. Predominant symptoms were pleuritic chest pain (82%), cough (73%), and dyspnea (56%) in the patients with pulmonary involvement, and abdominal pain (64%) in the patients with hepatic involvement.\nTable 2\nSymptoms in 38 patients with echinococcal disease and pulmonary or hepatic involvement\nPulmonary\nHepatic\nSymptom\nDefinite/probable (N = 9)\nPossible (N = 2)\nDefinite/probable (N = 11)\nPossible (N = 16)\nAsymptomatic\n0\n0\n2\n2\nWeight loss\n2\n2\n1\n2\nPleuritic chest pain\n7\n2\n1\n2\nCough\n6\n2\n1\n4\nHemoptysis\n1\n1\n0\n1\nDyspnea\n5\n1\n2\n4\nAbdominal pain\n0\n0\n9\n9\nFever\n3\n0\n4\n5\nNight sweats\n2\n0\n1\n2\nAnorexia\n4\n0\n1\n4\nMalaise\n2\n1\n1\n2\nJaundice\n2\n0\n1\n2\nChills\n1\n0\n3\n1\nVomiting\n4\n0\n2\n4\nInvestigations\nResults of laboratory investigations in the 38 patients with pulmonary or hepatic disease are shown in Table \n3\n. Mild anemia was common, and 37% of the 19 patients with definite and probable ED who had a differential white blood cell count performed had eosinophilia. Of the12 patients with definite and probable pulmonary or hepatic ED who had ELISA testing performed, six had positive results. Testing was performed using a titer method (four of seven were positive) or an optical density method (two of five were positive).\nTable 3\nMean values and ranges of results of laboratory investigations in 38 patients with pulmonary or hepatic echinococcal disease *\nPulmonary\nHepatic\nLaboratory test\nNormal values\nDefinite/probable\n(N = 9)\nPossible\n(N = 2)\nDefinite/probable\n(N = 11)\nPossible\n(N = 16)\nHemoglobin\n135 – 175 g/L\n120(112–133)\n114.5(113–116)\n123.7 (96–180)\n124 (93–161)\nWhite blood cell count\n4–11 × 10\n9 \n/L\n10(6.4–18)\n9.7(9.6–9.8)\n8.7 (4.3–14.5)\n8.26 (3.8 – 14)\nEosinophilia\n>= 0.1 × 10\n3 \n/L\n2(0.1–7)\n1.95(0.3–3.6)\n1.8 (0 .1–6)\n1.5 (0 .1 – 4.7)\nESR\n0–20 mm/hr\n28.5(10 – 47)\n30.5(28–33)\n32.6 (18–47)\n23 (11–35)\nAST\n<40 U/L\n30.4 (14–49)\n25.5(22–29)\n32 (12–59)\n63 (14 – 432)\nAlkaline Phosphatase\n30–130 u/L\n122.3(48 – 231)\n137(123–152)\n141 (62 – 461)\n168 (41 – 892)\nTotal Bilirubin\n3.4–17.1 umol/l\n11(4–27)\n4.5(2–7)\n15.7 (4–32)\n24.4 (3.3 – 98)\nELISA\n(positives/ number tested)\n3/7\n0/2\n3/5\n0/5\nLegend: ELISA – enzyme-linked immunosorbent assay; ESR – erythrocyte sedimentation rate\n* Results are incomplete in some patients.\nResults of chest radiographs for the 38 patients with pulmonary or hepatic involvement are shown in Table \n4\n. Six of the 11 lesions in the patients with pulmonary involvement were in the left lung with either a cystic mass (present in nine of 11 cases) or nodular appearance associated with a pleural effusion in five of nine pulmonary cases. One patient had a pneumonic presentation with no cyst. Four of the 27 patients with hepatic disease had multiple liver cysts. The right lobe of the liver was involved in about two-thirds of the hepatic cases.\nTable 4\nChest radiographic findings in 42 patients with echinococcal disease\nPulmonary\nHepatic\nOther\nChest radiograph\nDefinite/probable N = 9\nPossible N = 2\nDefinite/ probable N = 11\nPossible N = 16\nCardiac (definite) N = 1\nKidney or spleen (probable/possible) N = 3\nNormal\n0\n0\n5\n7\n0\n1\nAbnormal\n9\n2\n6\n9\n1\n2\n Cyst\n7\n2\n0\n2\n0\n0\n Pleural effusion\n4\n1\n4\n3\n1\n0\n Pneumonia\n5\n1\n0\n4\n0\n0\n Cavity\n2\n1\n1\n0\n0\n0\n Granuloma\n0\n0\n1\n0\n0\n0\n Atelectasis\n1\n0\n1\n3\n0\n1\n Calcified cyst\n6\n2\n0\n1\n0\n0\nUltrasounds were available for review in 15 of the 30 patients with intra-abdominal disease. Results are shown in Table \n5\n with seven showing active cysts (CE1 or CE2) and eight showing inactive cysts (CE 4 or CE5) [\n5\n].\nTable 5\nUltrasound findings in 15 patients with intra-abdominal cystic echinococcosis graded according to the proposed international classification (5)*\nDefinite/probable hepatic (N = 4)\nPossible hepatic (n = 8)\nPossible kidney (N = 1)\nProbable splenic (N = 1)\nPossible splenic (N = 1)\nCL\n-\n-\n-\n-\n-\nCE1\n-\n3\n1\n-\n-\nCE2\n1\n2\n-\n-\n-\nCE3\n-\n-\n-\n-\n-\nCE4\n3\n-\n-\n1\n1\nCE5\n-\n3\n-\n-\n-\n*Ultrasounds were no longer available for review on the other 15 patients with intra-abdominal disease.\nTherapy and outcome\nTreatment of all patients with is shown in Table \n6\n. Of the 22 patients with definite and probable ED, seven had surgical resections of cyst(s) combined with medical treatment (albendazole or mebendazole), six had surgical removal of the cyst alone, four had cyst aspiration, one had medical treatment alone and four were not specifically treated. Of the 20 cases with probable ED, one had surgical resections of cyst combined with medical treatment, one had surgical removal of the cyst alone, one had medical treatment alone and 17 were not specifically treated. Pre-operative complications included suspected rupture of a cyst into a bronchus in two patients, suspected bacterial infection of the cyst in two patients with pulmonary cysts and one patient with a hepatic cyst, and obstructive jaundice in one patient. Major complications after surgical resection occurred only with hepatic disease and included single cases of pleural effusion, wound infection, biliary leak, and intra-abdominal bleeding resulting in a hepatic lobectomy.\nTable 6\nTherapy of patients with hydatid disease\nPulmonary\nHepatic\nOther\nTherapy\nDefinite/probable N = 9\nPossible N = 2\nDefinite/probable N = 11\nPossible N= 16\nCardiac (definite) N = 1\nKidney or spleen (probable/possible) N = 3\nMedical only*\n0\n1\n1\n0\n0\n0\nSurgical resection only\n3\n0\n2\n1\n1**\n0\nMedical therapy and surgical resection\n5\n0\n2\n1\n0\n0\nAspiration of cyst only\n0\n0\n4\n0\n0\n0\nAspiration of cyst and medical treatment\n0\n0\n0\n0\n0\n0\nObservation only\n1\n1\n2\n14\n0\n3\n* mebendazole or albendazole\n**echinococcal cyst was resected from left ventricle\nThree patients with possible hepatic ED died of illnesses that were not directly related to ED. The first patient had cryptogenic cirrhosis and chronic cholelithiasis, as well as a left lobe liver cyst. She had an open cholecystectomy for acute cholecystitis, and died post-operatively from intra-abdominal bleeding and sepsis (pathology was not performed on the hepatic cyst). The second patient with multiple myeloma and paraplegia was incidentally noted to have a hepatic cyst and died of unexplained respiratory failure. The third patient admitted with bilateral deep vein thromboses and incidentally found to have hepatic cysts died of bronchopneumonia and heart failure.\nComparison of Canadian-born to foreign-born patients\nIn comparing the clinical features and outcome of Canadian-born patients (presumed to have the sylvatic variant of \nE. granulosus\n) and foreign-born patients (who could have any type of \nEchinococcus \ninfection), no differences were noted (data not shown).\nDiscussion\nOver a ten-year period there were 19 definite, 3 probable, and 20 possible cases of ED identified at a northern Alberta referral center. In North America, ED was previously considered a disease of immigrants. Of 596 cases of ED reported up to 1950, only 36 occurred in persons born in Canada or the United States [\n3\n]. In our series, only 6 of 36 cases where the country of birth was known were foreign-born. Forty-one percent of the 42 cases occurred in aboriginal Canadians, who represent only 5.3% of the population of Alberta and 3.4% of the population of Canada (2001 Canadian census data). The majority of patients were middle-aged females. Previous studies have shown a predominance of males [\n4\n] and females [\n6\n], and it has been postulated that the sex predominance may be determined by which sex has more contact with the usual definitive host in that country [\n3\n].\nTwo-thirds of the cases of ED in our study were pulmonary, but for the definite and probable cases, half were hepatic. A previous study from northern Canada and the United States described hepatic involvement in 71% of cases and pulmonary involvement in only 7% of cases [\n4\n]. The results of a recent study of 17 patients from Manitoba and northwestern Ontario were comparable to ours with pulmonary involvement in 47% and hepatic involvement in 47% of cases [\n7\n]. However, the true rate of hepatic versus pulmonary ED cannot be determined by these studies as detection is often on the basis of radiographic studies performed for reasons unrelated to the ED. Previous reviews suggested that pulmonary cysts are more common in children and young adults while hepatic cysts are more common in older persons [\n2\n], which is compatible with our findings (data not shown).\nLaboratory tests are of limited value in the diagnosis of ED. One study showed that only 29% of cases with pulmonary cysts and 15% of cases with hepatic cysts had eosinophilia [\n8\n]. In our series, 54 % of the pulmonary cases and 22% of the hepatic cases had eosinophilia. Perhaps this low rate is explained by the chronicity of the disease with eosinophilia being present only early in the course via stimulation of Th2 lymphocytes and production of IL-4 and IL-5 subsequently generating IgG1 and IgE-secreting cells, and eliciting eosinophilia [\n9\n,\n10\n]. Another possibility is that eosinophilia is only likely after cyst rupture and release of antigenic material [\n11\n].\nSerology for ED has variable sensitivity depending on the type of test. The most sensitive is IgG ELISA with an 83% sensitivity [\n10\n] although this test may only become positive after cyst rupture [\n11\n]. In our study, serology was positive in 54% of cases of definite and probable ED.\nThere are no clinical features that can reliably distinguish \nE. granulosus \nfrom \nE. multilocularis\n. However, a specific \nE. multilocularis \nantigen such as the high affinity purified Em2 antigen AE metacestodes has been reported to be able to discriminate between \nE. granulosus \nand \nE. multilocularis \nin 95% of cases [\n12\n]. This test was not available at the time of this review. Molecular methods to distinguish the pastoral from the sylvatic form of \nE. granulosus \nhave recently been described [\n13\n]. Daughter cysts have not been reported in sylvatic disease [\n14\n], and this form of the disease appears to be more benign than the pastoral form with a far lower incidence of complications even when cyst rupture occurs [\n14\n]. Most cases of the sylvatic form of ED are asymptomatic and are diagnosed when cysts are found during procedures performed for other reasons [\n14\n]. It seems likely that most of our Canadian-born patients had sylvatic disease as they reside in areas where exposure to sheep is rare. Most of our patients with pulmonary cysts were minimally symptomatic on presentation with cough or chest pain, and cyst rupture was recognized in only two pulmonary cases. In addition, four patients with definite and probable ED were discharged with no therapy and had no apparent sequelae.\nTraditionally, surgical resection of the cyst was the treatment for ED, but simpler surgical procedures such as hydatid cyst aspiration have been shown to result in low mortality and improved outcome [\n6\n]. However, medical management of relatively asymptomatic presumed sylvatic cases can be considered, as the natural history of the sylvatic variant is to rupture without any complications or anaphylaxis [\n14\n]. It is not clear if albendazole or mebendazole are indicated or if observation is sufficient. Surgical resection or cyst aspiration is recommended in sylvatic cases only for complications such as secondary infection or pressure symptoms.\nAlthough the outcome of our patients was generally good complications did occur. Two patients had symptomatic rupture of a pulmonary cyst and two patients had suspected bacterial infection of pulmonary cysts. Pressure or mass effects of hepatic cysts on the bile ducts, portal and hepatic veins, or on the inferior vena cava can result in cholestasis, portal hypertension, venous obstruction, or Budd-Chiari syndrome, sometimes resulting in the need for liver transplantation [\n15\n]. Obstructive jaundice was described in 18% of 132 patients in one case series [\n16\n] and occurred in one of our 12 definite and probable hepatic cases. Rupture of cysts into the biliary tree can produce biliary colic, obstructive jaundice, cholangitis or pancreatitis [\n17\n]. Cerebral disease is more common in children than in adults, and occurs in 1.5%–2.0% of patients, with the most common presentations being seizures or signs of raised intracranial pressure secondary to the cysts in the brain [\n7\n]. In our single case, cerebral disease was due to emboli from a cardiac echinococcal lesion.\nConclusion\nPrevention of ED has been attempted by distributing praziquantil bait in areas where there is a high prevalence of infected foxes [\n18\n]. Unfortunately, such strategies are not practical in a vast country such as Canada. Until our understanding of the modes of transmission of ED improves, education of the public about this relatively rare disease is unlikely to be effective. Therefore, from a public health perspective, the emphasis must be on further progress in management of this disease, which will require increasing awareness on the part of physicians regarding the multitude of presentations, improved diagnostics, and further study of long-term outcomes with different treatment modalities.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nAll authors contributed to study design and to revising the manuscipt. AS collected and analyzed the data and wrote the manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
34
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nInnate immunity and inflammation in ageing: a key for understanding age-related diseases\n\n**Article Abstract:**\n\nThe process of maintaining life for the individual is a constant struggle to preserve his/her integrity. This can come at a price when immunity is involved, namely systemic inflammation. Inflammation is not per se a negative phenomenon: it is the response of the immune system to the invasion of viruses or bacteria and other pathogens. During evolution the human organism was set to live 40 or 50 years; today, however, the immune system must remain active for much a longer time. This very long activity leads to a chronic inflammation that slowly but inexorably damages one or several organs: this is a typical phenomenon linked to ageing and it is considered the major risk factor for age-related chronic diseases. Alzheimer's disease, atherosclerosis, diabetes and even sarcopenia and cancer, just to mention a few – have an important inflammatory component, though disease progression seems also dependent on the genetic background of individuals. Emerging evidence suggests that pro-inflammatory genotypes are related to unsuccessful ageing, and, reciprocally, controlling inflammatory status may allow a better chance of successful ageing. In other words, age-related diseases are \"the price we pay\" for a life-long active immune system: this system has also the potential to harm us later, as its fine tuning becomes compromised. Our immune system has evolved to control pathogens, so pro-inflammatory responses are likely to be evolutionarily programmed to resist fatal infections with pathogens aggressively. Thus, inflammatory genotypes are an important and necessary part of the normal host responses to pathogens in early life, but the overproduction of inflammatory molecules might also cause immune-related inflammatory diseases and eventually death later. Therefore, low responder genotypes involved in regulation of innate defence mechanisms, might better control inflammatory responses and age-related disease development, resulting in an increased chance of long life survival in a \"permissive\" environment with reduced pathogen load, medical care and increased quality of life.\n\n**Article Body:**\n\nInnate immune system\nThe first line of immune defence mainly operates by detection of a broad range of molecular patterns foreign to mammalian tissues, called pathogen-associated molecular patterns that induce the activation of the innate immunity and inflammatory response [\n1\n]. The constitutive expression of a limited set of pattern recognition receptors by many cell types of the innate immunity does not require clonal expansion of specific cell populations. These germ cell-encoded proteins recognize microbial pathogens or ligands from damaged tissues based on shared molecular structures and induce host responses that localize the spread of infection and enhance systemic resistance to infection. Therefore, the expression of a limited number of highly active genes during the activation of innate immunity is able to induce rapid (minutes to hours) efficient defensive immune responses [\n2\n].\nSeveral cell types contribute to innate immunity and the mononuclear phagocyte lineage plays a pivotal role in innate immunity. Monocytes, macrophages and their tissue-differentiated derivatives, such as microglia in the nervous system, express pattern recognition receptors, namely various scavenger and Toll-like receptors [\n3\n]. These receptors induce transmembrane signals that activate NF-kB and mitogen dependent protein kinase pathways [\n4\n]. Toll-like receptor activation also induces the expression of a wide number of genes encoding proteins, such as cytokines, with regulatory functions upon leukocyte activation and tissue inflammation [\n5\n]. Therefore, the capacity of each individual organism to regulate the activation of innate immunity and local inflammatory responses is crucial for initiating defensive action against pathogens, limiting tissue damage and enhancing fast recovery and tissue healing.\nThe inflammatory response\nIn response to cell injury elicited by trauma or infection the inflammatory response sets in, constituting a complex network of molecular and cellular interactions directed to facilitate a return to physiological homeostasis and tissue repair. The response is composed of both local events and a systemic activation mediated by cytokines. If tissue health is not restored or in response to stable low grade irritation, inflammation becomes a chronic condition that continuously damages the surrounding tissues. In fact, during chronic inflammatory immune responses, tissue injury and healing proceed simultaneously. The collateral damage caused by this type of inflammation usually accumulates slowly, sometimes asymptomatically for years but can eventually lead to severe tissue deterioration [\n6\n].\nCytokines are largely secreted molecules that act on the surrounding microenvironment by providing cell to cell signalling. Cytokines are components of a large, complex signalling network. The effects of cytokines on target cells may be inhibited or enhanced by other cytokines, hormones, and cytokine-receptor antagonists and circulating receptors. Tumor necrosis factor α (TNF-α), Interleukin-1 (IL-1) and IL-6 are the classical pro-inflammatory cytokines. Their ability to activate both local and systemic effects is well established. Locally, they contribute to the activation of the inflammatory cells and together with chemokines, which induce the expression of adhesion molecules, cause their local recruitment. When the causes of the inflammatory reaction are of a high intensity, the production of cytokines is increased and they are released in the circulation provoking the \"acute phase response\". On the other hand, \"inhibitory\" cytokines such as IL-10 damp down the activation of some effector functions of T lymphocytes and mononuclear phagocytes, by inhibiting the release of pro-inflammatory cytokines and therefore turning off the inflammatory processes [\n7\n,\n8\n].\nThe acute phase response e.g. leukocytosis, fever, somnelence, anorexia and acute phase proteins synthesis, such as C reactive protein (CRP) in the liver, is a highly conserved inflammatory response which is rapidly activated by infections or trauma via pattern recognition molecules. Acute phase protein concentration rapidly increases after infection, and their production is controlled primarily by IL-6- and IL-1-type cytokines. The acute phase proteins provide enhanced protection against microorganisms and modify inflammatory responses by affecting cell trafficking and mediator release. The more traditional view of acute phase proteins has extended beyond that of opsonization of microorganisms. Some acute phase proteins have anti-inflammatory effects while others have important effects on leukocyte activation and trafficking [\n9\n].\nCRP, named for its capacity to precipitate the somatic C-polysaccharide of Streptococcus pneumoniae, was the first acute-phase protein to be described, and is an exquisitely sensitive systemic marker of inflammation and tissue damage. It is a member of the pentraxin family of plasma proteins, which are part of the lectin fold superfamily of calcium-dependent ligand-binding and lectin (carbohydrate-binding) proteins. In healthy blood donors, the median concentration of CRP is 0.8 mg/l, but following an acute-phase stimulus, values may increase 10 000-fold. In an apparently healthy population the median baseline value is slightly higher and tends to increase with age with females showing slightly higher circulating concentrations. In most, but not all diseases, the circulating value of CRP reflects on-going inflammation much more accurately than do other biochemical parameters of inflammation, such as plasma viscosity or the erythrocyte sedimentation rate [\n10\n].\nInnate immune system during ageing\nAge related changes in clonotypic immune system are well documented. For instance, involution of the thymus gland is an early feature of the immune reconfiguration and several age- related alterations of T or B cell compartments have been described [\n11\n-\n13\n]. Studies on age-associated changes of the innate immunity are not as advanced as those of the clonotypic immune system. However, investigations from aged mice showed a functional decline of monocytes and macrophages, a low expression level of Toll-like receptors from activated splenic and peritoneal macrophages and an altered secretion of several chemokines and cytokines [\n14\n,\n15\n]. Aged macrophages also contribute to an impaired the proliferative response of activated peripheral T lymphocytes [\n16\n].\nAged phagocytes, such as macrophages and neutrophils, showed an impaired respiratory burst and reactive nitrogen intermediate production with a decreased ability to destroy pathogens. Moreover, aged dendritic cells were less efficient in activating both T and B cell populations and aged NK cells showed a decreased ability in killing tumour cells [\n17\n,\n18\n].\nHowever, not all immune activities are decreased during ageing. In fact, the 'in vitro' production of pro-inflammatory cytokines, such as IL-1, IL-6 and TNF-α, by mitogen activated peripheral blood monuclear cells from elderly persons was higher than that from young donors [\n19\n]. Cytokine production may also be up-regulated 'in vivo' in old subjects resulting in an abnormal elevation of pro-inflammatory cytokines during inflammatory responses [\n20\n]. An age- related increase of IL-6 levels has also been reported in plasma, serum and supernatants from healthy elderly and centenarians [\n19\n,\n21\n,\n22\n]. It is interesting to note that 'in vitro' addition of IL-1 and TNF-α to fibroblasts induced an accelerated senescent phenotype which was rescued by anti-oxidant addition [\n23\n].\nInflammatory responses during ageing\nA dramatic increase in mean life span and life expectancy, coupled with a significant reduction in early mortality, has lead to a large increase in the number of elderly people in modern societies. This demographic phenomenon has been paralleled by an epidemic of chronic disease usually associated with advancing age [\n24\n]. Most age-related diseases have complex aetiology and pathogenic mechanisms. The clinical diagnosis and therapy of these diseases requires a multidisciplinary medical approach with progressively increased costs. A body of experimental and clinical evidence suggests that the immune system is implicated, with a variable degree of importance, in almost all age-related or associated diseases. Both innate and the clonotypic immune system are usually involved in the pathogenesis of these chronic diseases [\n11\n,\n25\n]. However, inflammatory responses appear to be the prevalent triggering mechanism driving tissue damage associated with different age-related diseases and the term \"Inflammaging\" has been coined to explain the underlining inflammatory changes common to most age-associated diseases [\n26\n]. This new term indicates that ageing is accompanied by an age-dependent up-regulation of the inflammatory response, due to the chronic antigenic stress which bombards the innate immune system thorough out life and potentially triggers the onset of inflammatory disease.\nChronic inflammation is considered to be involved in the pathogenesis of all age-related diseases: Alzheimer's disease, atherosclerosis, diabetes, sarcopenia and cancer all have important inflammatory components. Inflammaging, i.e. the up-regulation of a variety of anti-stress responses at the cellular and molecular level, is the consequence of the body's ability to counteract and modulate the effects of a variety of stressors, which cause the accumulation of molecular and cellular scars [\n26\n,\n27\n]. However, as recently discussed [\n28\n], a wide range of different aetiological factors is likely to contribute to increased low-grade inflammatory activity in elderly populations including a decreased production of sex steroids, smoking, subclinical disorders such as arteriosclerosis, asymptomatic bacteruria and a higher relative/absolute amount of fat tissue, which has been suggested to produce pro-inflammatory cytokines [\n29\n] (see below). Furthermore, increased levels of circulating inflammatory mediators may result from a constant, low-grade activation of cytokine-producing cells or a dysregulated cytokine response following stimulation [\n28\n], which does not readily become damped down. On the other hand, a recent hypothesis suggests that the reduction in lifetime exposure to infectious diseases and other sources of inflammation – the cohort mechanism – may also contribute to the historical decline in old-age mortality [\n30\n].\nRecent studies have linked an individual's exposure to past infection to levels of chronic inflammation and to increased risk of heart attack, stroke, and cancer. For example, the risk of heart attack is correlated with serum levels of inflammatory proteins such as CRP [\n31\n]. Within individuals, CRP levels are also correlated with the number of seropositivities to common pathogens, suggestive of infection history [\n32\n].\nLow-grade increases in levels of circulating TNF-α, IL-6, soluble IL-2 receptor (sIL-2R), and CRP and low levels of albumin and cholesterol, which also act as inflammatory markers, are strong predictors of all-cause mortality risk in several longitudinal studies of elderly cohorts. The effects of inflammatory mediators upon survival are independent of pre-existing morbidity and other traditional risk factors for death (smoking, blood pressure, physical exercise, total cholesterol, co-morbidity, body mass index, and intake of anti-inflammatory drugs) suggesting that cytokines may induce exaggerated pathological processes. Furthermore these molecules appear to be sensitive markers of pre-clinical disorders in elderly populations [\n28\n,\n33\n-\n39\n].\nIn the following sections we will focus on the role of innate immunity and inflammation in the most common diseases of elderly in order to direct the reader's interest to these emerging topics in modern gerontology and geriatrics investigations.\nFrailty and sarcopenia\nFrailty has been defined as an age-related decline in lean body mass, decreased muscle strength, endurance, balance and walking performance, low activity and weight loss accompanied by a high risk of disability, falls, hospitalisation and mortality [\n28\n,\n40\n]. It has been suggested that this syndrome reflects a metabolic imbalance caused by overproduction of catabolic cytokines and by the diminished availability or action of anabolic hormones, resulting from ageing itself and the presence of associated chronic conditions [\n28\n,\n41\n]. Sarcopenia is obviously a central part of the frailty syndrome [\n28\n]. Sarcopenia is the loss of muscle mass and strength that occurs with normal ageing. In elderly, there is a decline in a variety of neural, hormonal, and environmental trophic signals to muscle. However, the most important endogenous cause may be the irreversible age-related loss of α-motor units in the central nervous system [\n42\n-\n44\n]. The most important environmental cause of sarcopenia is lack of physical activity which is an age-related phenomenon which shows universal decline with age in industrialized societies; obesity and type 2 diabetes being concomitant epidemics (see below). An emerging issue in the past few years for sarcopenia research has been whether there is also an increased catabolic signal, driven by systemic inflammation [\n44\n]. Systemic low-grade inflammation has been associated with decreased muscle mass as well as the development of functional disability in elderly populations [\n33\n,\n44\n-\n47\n]. TNF-α has special effects that may contribute directly to sarcopenia [\n44\n], including increased basal energy expenditure, anorexia, loss of muscle and bone mass 'in vivo' and association with wasting/cachexia in chronic inflammatory disorders. Consistent with these findings, muscle protein synthesis was inversely related to local levels of TNF-α protein in skeletal muscles in frail very old humans [\n48\n]. In a recent study of nursing home residents aged 85–96 years, systemic low-grade activation of the TNF-α system at baseline was inversely correlated to muscle strength after resistance training for 12 weeks, demonstrating that TNF-α could also be a limiting factor for training-induced improvement in muscle strength in very old people [\n49\n]. The role of IL-6 in sarcopenia is not clear. Epidemiological studies have reported that IL-6 is strongly associated with functional disability and loss of muscle mass but experimental studies have not been able to link IL-6 to sarcopenia [\n28\n,\n44\n]. Human investigations have shown that inflammation impairs muscle strength in elderly people [\n50\n] while Insulin Growth Factor 1 and IL-6 plasma levels were synergistically related to disability and mortality in older women [\n51\n].\nA complicating factor in untangling the cause-effect relationships underlying sarcopenia is the ability of IL-6, TNF-α, physical inactivity, abdominal obesity, and other factors to cause insulin resistance in the elderly [\n52\n-\n54\n]. Loss of control of the anabolic action of insulin on muscle would be another factor favouring sarcopenia, resulting in the elevation of one or more catabolic signals. Thus, the weight gain that occurs in most adults during middle age may actually predispose to sarcopenia as they age [\n44\n].\nObesity, the metabolic syndrome, type II diabetes\nWestern societies face a health care crisis of epidemic proportion, since the number of people with the metabolic syndrome is rising exponentially. This condition constitutes a major challenge for public health professionals in the field of preventive medicine and estimates suggest that more than 40 million US adults will be affected by the syndrome [\n55\n].\nThere is not known survival advantage of morbid obesity; on the other hand increased body fat is linked to high mortality [\n56\n]. In the past, humans have been plagued by famine when survival advantage would have been conferred by genes favouring an available energy source: the so called 'thrifty gene' hypothesis. These genes led to genetic selection toward insulin resistance in the peripheral tissue in order to preserve glucose supply of the brain during starvation [\n57\n]. Human obesity shows a clear genetic component, which is usually polygenic and polymorphic variances in a number of 'thrifty' genes could contribute to different susceptibilities to obesity and diabetes [\n58\n,\n59\n].\nMetabolic syndrome may be detected by 5 clinical diagnostic criteria 1) abdominal adiposity, 2) hypertriglyceridemia, 3) low high density lipoprotein, 4) hypertension, 5) fasting hyperglycaemia [\n55\n].\nAn involvement of inflammation with pathogenic mechanisms influencing the development of the metabolic syndrome has been suggested [\n55\n,\n60\n,\n61\n] and elevated CRP, IL-6 and TNF-α, associated with visceral adiposity, have been reported in this syndrome [\n61\n]. Adipocytes constitutively express the pro-inflammatory TNF-α [\n54\n] which decreases after weight loss [\n62\n]. Further work in this area has confirmed increased plasma concentrations of CRP, IL-6, and plasminogen activator inhibitor-1 (PAI-1) [\n63\n-\n65\n]. Therefore, a complex interplay may exist between inflammatory responses and general metabolism in atherosclerosis, cardiovascular disease, metabolic syndrome.\nIt is becoming clear that the increased adipose tissue is not a simple reservoir for excess nutrients, but rather an active and dynamic organ capable of expressing several cytokines and other fat-derived peptides (FDP). Some FDP may have a role in the development of the metabolic syndrome but there is no evidence that these FDP are directly causing inflammation. It has been suggested that high levels of inflammatory factors are markers for obesity/abdominal obesity seen with aging, but some of these may not necessarily have a causative role in the development of inflammation [\n29\n]. Alternatively, a positive correlation was found between the body mass index and the percentage of resident macrophages, suggesting that fat tissue growth is associated with a recruitment of blood monocytes, responsible for cytokine production [\n66\n].\nInsulin resistance is due to the reduced ability of peripheral tissues to properly respond to the activation induced by insulin. It is a key feature in the pathogenesis of type II diabetes and this condition may precede by 10–20 years the onset of hyperglycaemia and the clinical manifestation of the disease. Recent data suggests that a defect in insulin activation of glucose transportation in muscle cells could be induced by serine kinase cascade activation, which is down stream mediators of tissue inflammation factors [\n67\n].\nData from the Insulin Resistance Atherosclerosis Study showed that insulin resistance, as assessed by frequently sampled glucose tolerance tests, correlated with high blood levels of CRP, fibrinogen and PAI-1 and levels of these inflammatory factors were predictors of type II diabetes development [\n68\n]. Increased blood concentrations of TNF-α and IL-6 were associated with obesity and type II diabetes [\n69\n]. Finally, results of the population study from the European Prospective Investigation into Cancer and Nutrition Potsdam indicated a significant interaction between plasma IL-1β, IL-6 and type II diabetes development. In fact subjects with detectable IL-1β levels and increased levels of IL-6 showed an independently elevated risk of developing the disease [\n70\n].\nInflammation may predispose to a pre-diabetic state by increasing insulin resistance, since pre-diabetic subjects showed increased plasma levels of inflammatory proteins without primary defects of beta cell functions [\n71\n]. Sub-clinical inflammation was found significantly related to insulin resistance in a high risk group for diabetes, i.e. in subjects with positive family history of diabetes, obesity and hyper or dyslipoproteinemia [\n72\n]. Recent results from the INCHIANTI population study showed that subjects in the upper tertile of insulin resistance had increased serum levels of TNF-α, IL-1R antagonist and IL-6 and low levels of sIL-6R [\n73\n].\nTNF-α causes an inhibition of auto-phosphorylation of tyrosine residues of the insulin receptor (IR) and an induction of serine phosphorylation of insulin receptor substrate-1, which in turn causes serine phosphorylation of the IR in adipocytes and inhibits tyrosine phosphorylation [\n74\n]. More recently, IL-6 has been shown to inhibit insulin signal transduction in hepatocytes [\n53\n]. Therefore, cytokines show relevant metabolic effects.\nNovel data have now appeared showing that the concomitant presence of the promoter polymorphisms of TNF-α and IL-6, linked to high production of these cytokines increases the risk of conversion to type 2 diabetes in obese subjects with impaired glucose tolerance response [\n75\n].\nAs discussed by Dandona et al. [\n69\n], two mechanisms might be involved in the pathogenesis of inflammation. Glucose and macronutrient intake causes oxidative stress and inflammatory changes. Chronic overnutrition (obesity) might thus be a pro-inflammatory state with oxidative stress. The increased concentrations of TNF-α and IL-6, associated with obesity and type 2 diabetes, might interfere with insulin action by suppressing insulin signal transduction, which in turn might promote inflammation. In fact, insulin reduces ROS generation by mononuclear cells, suppresses NADPH oxidase expression and intranuclear NF-kB binding, induces IkB expression and suppresses some inflammatory molecules [\n69\n,\n76\n].\nThe well-known beneficial effects of caloric restriction on longevity in animal models by inducing reduced visceral fat mass might also induce a reduced secretion of multiple metabolically active factors, which are potentially responsible for the development of insulin resistance. This decrease in fat mass and its beneficial effects observed in ageing animal models might apply also to human ageing and its related pathology [\n77\n].\nCancer diseases\nThe majority of cancer occurs in subjects over the age of 65 years. Cancer rates increase sharply with age in both sexes: the incidence of cancer is 12–36 times higher in individuals aged 65 years or older compared with individuals aged 25–44 years, and 2–3 times more common than in persons aged 45–64 years. It is worth noting that 70% of deaths attributable to all cancer occur in men and in women aged 65 years or older whereas 35% cancer deaths in men and 46% of cancer deaths in women occur in those aged 75 years or older. The relationship between ageing and cancer is similar for most cancers, and it is well described by the multistage model. So, ageing might be considered not as a determinant of cancer per se, but as a surrogate marker of the duration of exposure to relevant carcinogenic factors [\n78\n-\n80\n].\nChronic inflammation induced by either biological, chemical, mechanical or physical injuries has been associated with increased incidence of cancer in different human tissues [\n81\n]. For instance, inflammatory bowel disease, ulcerative colitis and Crohn's disease are clinical conditions predisposing to cancer development of the large bowel or terminal ileum [\n81\n,\n82\n].\nHelicobacter pylori microorganisms are associated with atrophic gastritis, mucosal dysplasia, gastric adenocarcinoma and an unusual form of gastric lymphoma [\n81\n,\n82\n]. Schistosome and trematode infections have been associated with cancers of the bladder and the biliary tracts [\n81\n].\nThe recognition of a role for inflammation in the natural history of a tumor has been known stretching from the mid-19th century [\n83\n]. The inflammatory microenvironment of tumors is characterised by the presence of host leucocytes both in the supporting stroma and in the tumor area [\n84\n]. The question whether the inflammatory infiltrate helps or hinders tumors is still open. In fact, inflammatory cells and cytokines found in tumors can contribute to tumor growth, progression, and immunosuppression as well mounting an effective host anti-tumor response. However, in most cases inflammation plays a role in the development of solid cancer. That is clearly demonstrated by a prospective, nested case-control study of a cohort of 22,887 adults followed for 11 years. A total of 172 colorectal cancer cases were identified. Up to 2 controls (n = 342) were selected for each case and matched by age, sex, race, and date of blood draw. Plasma CRP concentrations were higher among all colorectal cases combined compared with controls and the risk of colon cancer was higher in persons in the highest vs. lowest quartile of CRP [\n85\n].\nFurthermore, in another recent study, a total of 174 patients considered to have undergone curative resection for cancer were studied. The results show that raised circulating concentrations of CRP, whether measured before or after operation, predict overall and cancer-specific survival in patients undergoing potentially curative surgery for colorectal cancer suggesting that the presence of a systemic inflammatory response predicts a poor outcome [\n86\n]. This data supports the hypothesis that inflammation is a risk factor for the development of some kind of solid tumors such as colon cancer.\nCancer susceptibility and severity may also be associated with functional polymorphisms of cytokine genes involved in regulation of inflammation. In particular, as discussed in a recent review [\n79\n], a considerable body of data indicates that particular cytokine polymorphisms, especially those involving IL-6 and IL-10 genes, may influence susceptibility to, and in some cases prognosis in neoplastic diseases. It is intriguing that these two cytokines are involved in longevity [\n87\n-\n89\n]. Discrepant results might depend on confounding factors that affect case-control studies [\n90\n] or as discussed by Caruso et al. [\n79\n] might also depend on pleiotropic action of cytokines. It is paradigmatic in this respect that the favourable effect of high producer IL-10 genotype on hepatocarcinoma induced by HBV [\n91\n], may be due to the relative lack of control of HBV infection by immunosuppressive effects of high IL-10 levels.\nOn the other hand, several and diverse mechanisms may link inflammation to cancer.\n1) Free radical production, derived by oxygen or NO metabolic pathways; the respiratory burst of leukocytes, and the arachidonic acid cascade activation are strongly implicated in DNA modification and protein damage which in turn promotes carcinogenesis [\n92\n].\n2) High constitutive hyper-expression of NF-kB, an ubiquitous transcription factor with regulatory effect upon different inflammatory, apoptotic and oncogenic genes [\n82\n].\n3) Alterations of the p53 gene induced by NO derived radicals promoting clonal expansion of aberrant or mutated cells [\n92\n].\n4) Induction of angiogenesis by inflammatory factors favouring cancer progression [\n92\n].\n5) Increased release of key pro-inflammatory factors and some cytokines, such as IL-1β, TNF-α and interferon (IFN)-γ, implicated in both the regulation of inflammation and the development of cancer [\n92\n,\n93\n].\nAtherosclerosis and cardiovascular diseases\nAtherosclerosis and its complications are a major problem\ncontributing to large sections of morbidity and mortality in old people. Cardiovascular disease is the leading worldwide cause of morbidity and death in Western societies [\n94\n]. However, our understanding of pathogenic mechanisms underling atherosclerosis and its complications is still incomplete, since more than half of patients with atherosclerosis do not show classical risk factors, such as hypercholesterolemia, hypertension, history of smoking, diabetes, obesity and sedentary life style [\n94\n,\n95\n].\nOn the other hand, atherosclerosis, formerly considered an inocuous lipid storage disease, actually involves an ongoing inflammatory response (Figure \n1\n). Recent advances in basic science have established a fundamental role for innate immunity in mediating all stages of this disease from initiation through progression and, ultimately, the thrombotic complications of atherosclerosis [\n96\n-\n98\n]. Clinical studies have shown that the emerging biology of inflammation in atherosclerosis applies directly to human patients. Elevation in markers of inflammation predicts outcomes of patients with acute coronary syndromes, independently of myocardial damage. In addition, low-grade chronic inflammation, as indicated by levels of the inflammatory marker CRP and cytokines, prospectively defines risk of atherosclerotic complications, thus adding to prognostic information provided by traditional risk factors. In fact, levels of CRP or IL-6 have been suggested as significant predictive risk factors for future development of cardiovascular events [\n31\n,\n95\n,\n99\n-\n103\n]. Increased levels of serum IL-1β have also been associated with high risk of congestive heart failure and angina pectoris [\n104\n]. Altered level of IL-1β is also suggested to be implicated in chronic inflammation underlining high blood pressure [\n105\n].\nFigure 1\nSchematic representation of inflammatory mechanisms involved in pathogenesis of atherosclerosis and plaque formation. Monocytes and macrophages are the protagonists of atherosclerotic processes.\nAn initiating event is the accumulation of lipids in the vessel wall, which subsequently will become modified and triggers an inflammatory process. Low-density lipoproteins (LDL) are taken up by macrophages through scavenger receptors, leading to foam cells; the lipid deposits become oxidized forming pro-inflammatory lipid peroxides. Monocytes are attracted from the blood and differentiate into macrophages that take up the modified LDL and form lipid-laden foam cells, which is the first hallmark of atherosclerotic plaque development. Later on, inflammatory mediators increase, other immune cells are attracted, and smooth muscle cells are activated and become involved. More advanced stages of plaque development are characterized by increased deposition of extra cellular lipid cores, fibrous material, and often necrosis. Subsequently, these macrophages are further activated, leading to the production of a wide range of cytokines and growth factors. Myocardial infarction may occur as a result of erosion or uneven thinning and rupture of the fibrous cap, often at the shoulders of the lesion where macrophages enter, accumulate and are activated and where apoptosis may occur [\n7\n,\n96\n-\n98\n].\nBecause genetic traits contribute significantly to the risk of coronary heart disease [\n106\n], a number of studies have now addressed the hypothesis that allelic variations in genes of innate immunity may increase the risk of this disease [\n107\n,\n108\n]. Differences in the genetic regulation of inflammatory processes might partially explain why some people, but not others, develop the disease and why some develop a greater inflammatory response than others. Accordingly, common gene polymorphisms controlling high production of inflammatory molecules have been associated with atherosclerosis and a good control of inflammation might play a protective role against atherosclerosis [\n107\n-\n110\n]. Recently, a combination of alleles in different inflammatory genes has been associated with increased risk of developing acute myocardial infarction in elderly men [\n111\n].\nIn addition to innate immunity, clonotypic immunity plays also a role in atherosclerosis. Recent findings support the hypothesis that a crucial component of atherosclerosis is represented by T cell-mediated immune responses that are inappropriate in terms of time of onset, intensity, and target [\n112\n]. On the other hand, the most direct evidence for the critical role for T cells, IFN-γ, and IFN-γ-driven molecules in atherosclerosis is provided by mice with combined deficiencies of apolipoprotein E (apoE) and the IFN-γ receptor, in which the development of atheroma is significantly reduced in comparison to mice with only apoE deficiency, whereas exogenous IFN-γ enhances atherosclerosis [\n113\n,\n114\n]. In contrast, the role of B cells has remained unclear. B-cells are not always present and may be protective. In fact, recent studies suggest that this cell type may inhibitthe development of vascular pathology in models of atherosclerosisand restenosis [\n115\n]. Finally, Wick et al. [\n116\n] have developed an \nautoimmune-inflammatory \nconcept of atherogenesis based on experimental and clinical models. They argue that atherosclerosis may be the price humans pay for pre-existing immunity to microbial or autologous heat shock protein (HSP) 60. In summary, their autoimmune hypothesis of atherogenesis postulates that HSP60 expression is induced in arterial endothelial cells as a response to the action of stress factors, notably the classical atherosclerotic risk factors. Autologous HSP60 epitopes exposed on the surface of stressed endothelial cells are recognized by either pre-existing humoral and cellular anti-microbial HSP60 immune reactions or by invoking \nbona fide \nautoimmunity based on exposure of altered autologous HSP60 epitopes. The authors accept the importance of well-established atherosclerotic risk factors during atherogenesis, but assign a new role for them in the earliest stages of the disease, viz. acting as stressors [\n116\n].\nBrain degenerative diseases: Alzheimer's disease\nAlzheimer's disease (AD), a heterogeneous and progressive neurodegenerative disease which in Western societies mainly accounts for clinical dementia, is expected in the USA to rise from 4.6 today to 16 millions cases in 2050 [\n117\n]. Neuro-pathological hallmarks of AD are neuronal and synapsis loss, extracellular amyloid deposits (neuritic plaques) and intracellular deposition of degenerate filaments (neurofibrillary tangles) [\n118\n]. Major clinical manifestations of the disease are memory loss and cognitive impairment [\n119\n].\nInflammation clearly occurs in pathologically vulnerable regions of the AD brain, and it does so with the full complexity of local peripheral inflammatory responses. In the periphery, degenerating tissue and the deposition of highly insoluble abnormal materials are classical stimulants of inflammation. Likewise, in the AD brain damaged neurons and neuritis, highly insoluble Aβ42 peptide deposits and neurofibrillary tangles provide obvious stimuli for inflammation. Senile plaques in AD brains are associated with reactive astrocytes and activated microglial cells; cytokines and acute phase proteins are also overexpressed in microglia and astrocytes surrounding neuropathological lesions in AD brains. Inflammatory factors, such as cytokines, chemokines, complement components and acute phase proteins co-localize as secondary components in neuritic or senile plaques, or are over-produced in AD brains. Finally, activated microglia surrounds senile plaques and areas of neurodegeneration [\n120\n,\n121\n]. There is accumulating evidence that Aβ peptide may promote or exacerbate inflammation by inducing glial cells to release immune mediators. Moreover, microglial and astroglial cells surrounding mature plaques in AD brains have been found to express activation markers. Enriched populations of human microglial cells isolated from mixed cell cultures prepared from embryonic human telencephalon tissues are able to express constitutively mRNA transcripts for cytokines and chemokines and treatment with pro-inflammatory stimuli as lipopolysaccharide or Aβ peptide leads to increased expression of mRNA levels of these inflammatory molecules [\n122\n].\nThe role of inflammation is further emphasized by a number of epidemiological studies demonstrating that the long-term use of nonsteroidal anti-inflammatory drugs may protect against AD. There are now a several published observational studies demonstrating that people who are known to be taking anti-inflammatory drugs considerably reduce their odds of developing AD and population studies have confirmed this negative association [\n123\n]. However, alternative hypothesises have been proposed. In particular, this effect has been hypothesised as relating to the ability of these drugs to inhibit angiogenesis. In fact, the brain endothelium secretes the precursor substrate for the β-amyloid plaque and a neurotoxic peptide that selectively kills cortical neurons. So, antiangiogenic drugs targeting the abnormal brain endothelial cell might be able to prevent and treat this disease [\n124\n]\nThe long-term prospective association between dementia and the well known inflammation marker CRP was evaluated in a cohort of Japanese American men. These subjects were seen in the second examination of the Honolulu Heart Program (1968–1970) and subsequently were re-examined 25 years later for dementia in the Honolulu-Asia Aging Study (1991–1996). In a random subsample of 1,050 Honolulu-Asia Aging Study cases and noncases, high-sensitivity CRP concentrations were measured from serum taken at the second examination; dementia was assessed in a clinical examination that included neuroimaging and neuropsychological testing and was evaluated using international criteria. Compared with men in the lowest quartile (<0.34 mg/L) of high-sensitivity CRP, men in the upper three quartiles had a 3-fold significantly increased risk for all dementias, mainly Alzheimer's disease and vascular dementia. These data support the view that inflammatory markers may reflect not only peripheral disease, but also cerebral disease mechanisms related to dementia, and that these processes are measurable long before clinical symptoms appear [\n125\n].\nOn the other hand, several other investigations have shown increased blood levels of some cytokines, such as IL-1β and IL-6, and acute phase proteins α-1-antichymotrypsin, (ACT) in patients with clinical AD [\n126\n-\n129\n]. Therefore, altered immune responses in the brain and the peripheral blood appeared to be associated with the disease. Finally, plasma levels of ACT also correlated with the degree of cognitive impairment in AD patients from a case-control study [\n126\n] suggesting that peripheral markers of inflammation or impaired immune responses could be used for monitoring the progression of the disease.\nElevated levels of IL-6 in both brain homogenates and peripheral blood from AD patients have also been reported [\n130\n]. These findings suggest that an important, but still largely unknown, interplay between brain and peripheral immune responses may exist in the disease.\nIn conclusion, the brain lesions associated with AD, which are referred to as neurofibrillary tangles and senile plaques, are characterized by the presence of a broad spectrum of inflammatory mediators, produced by resident brain cells, including neurons. Although secondary to the fundamental pathology caused by the presence of tangles and plaques, there is strong evidence that inflammation exacerbates the neuronal loss. Accordingly, several reports have appeared indicating that the risk of AD is substantially influenced by several polymorphisms in the promoter region, and other untranslated regions, of genes encoding inflammatory mediators. Alleles that favour increased expression of the inflammatory mediators or alleles that favour decreased expression of anti-inflammatory mediators are more frequent in patients with AD than in controls. The polymorphisms are fairly common in the general population, so there is a strong likelihood that any given individual will inherit one or more of the high-risk alleles [\n121\n,\n127\n,\n129\n-\n135\n] (Figure \n2\n).\nFigure 2\nAlzheimer's disease: amyloid deposition is one the main pathogenetic mechanism. Accumulation of Aβ peptide may be caused by 1) gene mutations (PS1, PS2 and APP human mutations in familial Alzheimer's disease) 2) genotype (and/or phenotype) favoring unbalanced inflammatory responses (pro-inflammatory genotype/anti-inflammatory genotype).\nConclusion\nIn this presentation we have presented evidence linking innate immunity with the pathogenesis of age-related chronic degenerative diseases. Inflammation may be a pivotal and common background shared by the majority of these pathological conditions. Although evidence already presented has focused on innate immunity, clonotypic immunity has support as an emerging mechanism related to the pathogenesis of these diseases [\n116\n].\nThe evidence that a decline in mortality exists when comparing Swedish cohorts born in the middle of the 18\nth \ncentury to those in the 20\nth \nsuggests important links between mortality in old age and in early life. Cohort mortality during childhood has been linked to cohort mortality in old age, implying that early exposure to infection is important in determining and imprinting the cohort morbidity phenotype [\n30\n]. Thus, chronic inflammatory mechanisms carry the imprint of early-life infections into later life morbidity and mortality. Evidence presented suggests that serological indicators of infection and inflammation in present day populations are related to vascular disease and other morbidities of ageing. Such inflammatory responses can be induced by invading pathogens, as well as by trauma or internal tissue injury. Thus, adaptive responses to short term infections or injury can become maladaptive as life progresses -a double-edged sword that evolutionary biologists refer to as antagonistic pleiotropy [\n136\n].\nThe process of life for the individual is the struggle to preserve its biological and immunological integrity. However, the preservation of the integrity of the organism comes with the price of responsiveness to systemic inflammation [\n137\n] which must be finely tuned otherwise dysregulation becomes a damaging accompanynt. With ageing, the reason why the innate immune system becomes over-activated is not clear, but increased exposure to infectious agents or cumulative damage to tissues could spark the change. Inflammation is not 'per se' a negative phenomenon: it is the response of the immune system to pathogenic viruses or bacteria. Thorough out evolution, man has been set to live about 40 or 50 years but in today's world the immune system is active for several decades compared with the past centuries. A long period of activitation may lead to chronic inflammation which inexorably damages several/all organs and is the phenotype linked to both ageing and chronic disease. In cardiovascular disease, conventional risk factors remain important, but differential baselines in inflammatory status may explain why cholesterol levels seem not always directly associated with cardiovascular disease [\n22\n,\n109\n].\nLow-grade inflammation is also associated with parameters such as obesity, smoking, and physical inactivity, so inflammatory mediators constitute a link between life style factors, infections and physiological changes in the process of ageing on the one hand, and risk factors for age-related diseases on the other [\n28\n]. This immune response also depends on the genetic background of individuals. In fact, emerging evidence suggests that polymorphic alleles of inflammatory cytokines, involved in high cytokine production, are related to 'unsuccessful' ageing as noted previously with respect to atherosclerosis and AD. On the other hand, controlling inflammatory status may enhance individual chance of achieving 'successful' ageing. So, major findings reporting a relationship between cytokine polymorphisms and longevity suggest that those individuals who are genetically predisposed to produce low levels of inflammatory cytokines or high levels of anti-inflammatory cytokines may have an increased capacity to reach the extreme limit of human life-span [\n87\n-\n89\n,\n109\n,\n138\n,\n139\n].\nIn other words, age-related diseases are \"the price we pay\" for an active immune system that defends us in youth but may harm us later on [\n139\n,\n140\n]. Such data support the notion that antagonistic pleiotropy [\n136\n] plays a relevant role in diseases and longevity. Pro-inflammatory genotypes may therefore be both friends and foes. They are an important and necessary part of the normal host responses to pathogens, but the overproduction of inflammatory molecules may aggravate immune-inflammatory-related disease and contribute to earlier death. An immune system evolved to control pathogens is likely to favour a highly charged pro-inflammatory response programmed to resist fatal infections with avoidance of early mortality. However, persons with low responder genotypes may risk earlier mortality in response to serious infection but if they survive may respond less aggressively to age-related disease development. Such conditions might result in an increased chance of longevity in an environment with reduced pathogenic antigen load and/or adequate medical treatment [\n139\n,\n141\n,\n142\n].\nFurther studies on this field will open the way for new diagnostic approaches for early diagnosis of relevant pre-clinical states of age-related diseases. It may be possible, before clinical manifestations appear, that anti-inflammatory or other treatments might play a decisive role in preventing or significantly retarding the manifestation of the disease. Other studies focused on clarifying the specific contribution of each immune factor to a given disease will also contribute to the discovery of new drugs and/or innovative intervention protocols specific for these diseases related to ageing.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
35
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nEpidemiological study air disaster in Amsterdam (ESADA): study design\n\n**Article Abstract:**\n\nBackground\nIn 1992, a cargo aircraft crashed into apartment buildings in Amsterdam, killing 43 victims and destroying 266 apartments. In the aftermath there were speculations about the cause of the crash, potential exposures to hazardous materials due to the disaster and the health consequences. Starting in 2000, the Epidemiological Study Air Disaster in Amsterdam (ESADA) aimed to assess the long-term health effects of occupational exposure to this disaster on professional assistance workers.\nMethods/Design\nEpidemiological study among all the exposed professional fire-fighters and police officers who performed disaster-related task(s), and hangar workers who sorted the wreckage of the aircraft, as well as reference groups of their non-exposed colleagues who did not perform any disaster-related tasks. The study took place, on average, 8.5 years after the disaster. Questionnaires were used to assess details on occupational exposure to the disaster. Health measures comprised laboratory assessments in urine, blood and saliva, as well as self-reported current health measures, including health-related quality of life, and various physical and psychological symptoms.\nDiscussion\nIn this paper we describe and discuss the design of the ESADA. The ESADA will provide additional scientific knowledge on the long-term health effects of technological disasters on professional workers.\n\n**Article Body:**\n\nBackground\nIn the early evening of October 4\nth\n, 1992, an El Al Boeing 747-F cargo aircraft lost two of its engines just after take off from Schiphol Airport and crashed into two apartment buildings in the Bijlmermeer, a densely populated suburb of Amsterdam (the Netherlands) [\n1\n]. The air disaster killed 43 people, and destroyed 266 apartments [\n1\n,\n2\n]. Fire-fighters and police officers were called to the scene to extinguish fires, to search and rescue people, to assist in the identification of human remains and personal belongings, to secure the surroundings and to clean-up the devastated area. Many of them were faced with bewildered residents and extensive destruction, and some witnessed dead or injured victims. Within a few days the wreckage of the aircraft was transported to a hangar at Schiphol Airport, where employees (i.e. 'hangar workers') sorted and inspected the wreckage.\nIn the extensive aftermath of the disaster, rumors and questions arose about the cause of the accident, the contents of the cargo, potential exposure to hazardous materials, and health consequences [\n2\n,\n3\n]. Every now and then the media highlighted stories of individual victims, as well as uncertainties about potential exposures during the disaster [\n4\n]. One of the major topics concerned exposure to depleted uranium from the aircraft's balance weights, particularly because some of the depleted uranium has never been recovered from the rubble [\n1\n]. However, the authors of a retrospective risk analysis \"considered it improbable that the missing uranium had indeed led to the reported health complaints\" [\n5\n]. Nonetheless, it appeared that a growing number of exposed workers and affected residents reported health complaints, which some of them attributed to the disaster [\n6\n]. Public and political unrest thus waxed and waned in the aftermath of the disaster [\n2\n,\n3\n]. Eventually, a parliamentary inquiry, that was held in 1998, recommended an epidemiological study on the health effects of the disaster [\n1\n].\nAbout the same time, in 1998, the employers of professional fire-fighters and police officers in Amsterdam decided to start an independent assessment of the health status of professional workers involved in the disaster. The mayor of Amsterdam assigned their occupational health service, the KLM Health Services, to organize this assessment. The employer of the hangar workers at Schiphol Airport joined this initiative, as did government representatives of the affected inhabitants and volunteer workers. It was decided to offer a medical examination to all people involved in the air disaster, residents as well as assistance workers, and that an epidemiological study would be performed simultaneously by the Institute for Research in Extramural Medicine (EMGO Institute). In this paper we report on the design of the epidemiological study among professional assistance workers: the Epidemiological Study Air Disaster in Amsterdam (ESADA). Unfortunately, the epidemiological study among residents had to be cancelled, due to low response rates.\nThe ESADA is the first epidemiological study that has ever been conducted after a major technological disaster in the Netherlands. The aim of this study is to assess the long-term psychological and physical health effects of occupational exposure to the air disaster in Amsterdam on professional assistance workers, i.e. fire-fighters, police officers and hangar workers. Based on the scientific literature on the health effects of disasters, the main hypotheses of the ESADA concern unexplained physical symptoms [\n7\n-\n12\n], and post-traumatic stress symptoms and associated psychological symptoms [\n13\n-\n15\n]. Due to the fact that the ESADA originated partly from societal concerns, we considered it necessary to also include some additional outcomes that will answer questions for some of the affected people, which, in turn, might help to reassure them. These societal questions relate to depleted uranium, Mycoplasma species and carnitine levels in plasma. The first of these questions stems from the concerns about the depleted uranium from the aircraft's balance weights, described above. The other two questions are primarily based on an alleged resemblance between the symptoms of some of the people affected by the air disaster in Amsterdam and the symptoms of patients with chronic fatigue syndrome (CFS) and Gulf War (I) Syndrome (GWS). Although some authors may have suggested a link between these syndromes and Mycoplasma species [\n16\n-\n21\n] or carnitine deficiency [\n22\n-\n26\n], others have rejected the existence of such links [\n27\n-\n29\n].\nIn this paper we describe and discuss the design of the ESADA. More details on the (organization of the) ESADA can be found on its website [\n30\n].\nMethods / Design\nDesign\nThe ESADA is designed as a historical cohort study, in which the health status of the professional fire-fighters, police officers and hangar workers who were occupationally exposed to the air disaster in Amsterdam is compared with the health status of reference groups of workers with the same jobs and employers at the time of the disaster, but who were not occupationally exposed to this disaster.\nStudy population\nThe ESADA study population consisted of professional fire-fighters, police officers and hangar workers. Eligible subjects had to (1) sign informed consent; (2) have sufficient mastery of the Dutch language to fill in the questionnaires; and (3) belong to one of the following three occupational groups:\n1) All professional fire-fighters who were, according to company records, employed in the Amsterdam fire department at the time of the disaster. Additional professional fire-fighters who started working in this fire department after the disaster were also invited to participate in the study, as almost the entire fire department had been exposed to the disaster.\n2) All police officers (\ni.e. \nconstables, warrant officers, sergeants and their supervisors) who were, according to company records, employed in the Amsterdam-Amstelland regional police force on the date of the disaster (October 4\nth\n, 1992), and were still employed there on the 1\nst \nof January 2000.\n3) All the hangar workers registered as working for one of the departments involved in the transport, security and sorting of the wreckage on the date of the disaster (October 4\nth\n, 1992), and who reported to have been involved in these activities; as well as a random sample, matched with their colleagues for age, sex, department and job title, who were also registered as working for these departments on 30\nth \nNovember 1992, but who did not report to have been involved in any disaster-related activities.\nProcedures and data-collection\nThe study design was approved by the two independent Medical Ethics Committees of the medical facilities involved in this project: the VU University Medical Center (VUmc) and the 'Onze Lieve Vrouwe Gasthuis' (OLVG) in Amsterdam. Potential participants were initially informed about the study via announcements in staff magazines, after which they were approached via personal letters, and eventually by telephone. All participants signed informed consent and participated voluntarily. Data were collected at the Prinsengracht out-patient clinic of the OLVG from January 2000 to March 2002, i.e. on average 8.5 years after the disaster. In addition, data on about half of the hangar workers were collected at Schiphol Airport for logistic reasons. Trained medical research assistants checked that the questionnaires had been completed, measured body height and weight, drew blood samples, and assisted with the collection of urine and saliva samples. A team of administrative employees carried out the data-entry of the questionnaires. Data of each participant were entered twice by two of these employees independently, after which inconsistencies were reviewed and any mistakes rectified. All remaining problems in the interpretation of data, such as dubious handwriting, were consistently resolved by one of the authors (AH, PS or AW).\nBlood, saliva and urine samples were dealt with according to standard procedures for collection, transportation, storage and laboratory analysis. Laboratory technicians could have been aware that the samples were from the ESADA, but they were blinded for exposure and health status. The laboratories were all certified according to accredited Dutch standards.\nOccupational exposure to the disaster\nAll participants were asked to fill in a questionnaire on occupational exposure to the air disaster. This questionnaire addressed several specific disaster-related tasks, and also the total time spent on these tasks and the location in which they were performed (e.g. on or near the disaster site, in the hangar where the wreckage was temporarily placed, or elsewhere). They were also asked to describe any other disaster-related task(s) that they had performed. Answers to the latter question were categorized (by PS and AW). The questionnaire also covered disaster-related psychosocial events in a number of items on personal experiences during the disaster (e.g. \"were you in life-threatening danger?\", \"did you see the disaster scene during the first hours after the crash?\", and \"were any of your family members injured?\").\nThese personal records of occupational exposure to the disaster were used to define 'exposed' workers, i.e. those who reported at least one disaster-related task, and 'non-exposed' workers, i.e. those who did not report any disaster-related tasks.\nIn addition to comparing exposed and non-exposed workers, we examined exposure-response relationships among exposed workers, in which level of exposure is characterized by the type of tasks and psychosocial events and the duration of exposure. As an additional dimension of level of exposure, we took into account the differences in potential psychotraumatic impact of exposure items, based on criterion A1 of the diagnostic criteria for Post Traumatic Stress Disorder (PTSD; American Psychiatric Association [APA]; Diagnostic and Statistical Manual of Mental Disorders-IV-Text Revision [DSM-IV-TR, 2000]) [\n31\n]. This criterion states that \"the person has experienced, witnessed, or been confronted with an event or events that involve actual or threatened death or serious injury, or a threat to the physical integrity of oneself or others\". Five experts on PTSD from different universities and psychiatric hospitals independently rated the likelihood of potentially psychotraumatic disaster-related tasks and events to meet this criterion on a 4-point Likert Scale ranging from 1 = 'very unlikely' to 4 = 'very likely'. Subsequently, we assumed that items with a mean item score of three or higher met the A1 criterion for PTSD (i.e. A1 tasks and events), as opposed to items with a lower mean score (i.e. non-A1 tasks and events). Table \n1\n lists the disaster-related tasks and the psychosocial events according to their potential psychotraumatic impact.\nTable 1\nDisaster-related tasks and psychosocial events according to their potential psychotraumatic impact\nA1* (traumatic)\nNon-A1* (non-traumatic)\nTasks\n1. Identification or recovery of victims from the rubble/transport or search for human remains\n2. Rescue people\n1. Fire-extinguishing\n2. Clean up of destructed area\n3. Transport of injured victims\n4. Provide first aid/support injured victims or workers\n5. Security tasks (surveillance, prevent burglary, keep disaster area free of bystanders)\n6. Other tasks (e.g. traffic management)\n7. Sort wreckage in hangar (at Schiphol Airport)\n8. Other tasks in hangar in the presence of the wreckage\n9. Transport of wreckage\n10. Burning of contaminated soil remnants (from disaster site)\nPsychosocial events\n1. Having been in life-threatening danger during disaster\n2. Personal injuries due to disaster\n3. Witnessed dead or injured victims\n4. Having been in or near one of the destroyed buildings at the time of the disaster\n5. Immediate family members (partner, children) died / in life-threatening danger / injured due to the disaster\n6. Other family members died due to the disaster\n1. Saw the aircraft crash / saw or heard the aircraft when it crashed\n2. Felt or heard the impact of the crash\n3. Saw the fire\n4. Saw the disaster site during the first hours after the crash/when the wreckage was still there\n5. Other family members in life-threatening danger or injured due to the disaster\n6. Friends or acquaintances died, injured or in life-threatening danger due to the disaster\n7. Apartment of other family members, friends, or acquaintances damaged due to the disaster\n8. Lived in the affected suburb of Amsterdam (Bijlmermeer) at the time of the disaster\n9. Visited the hangar where the wreckage was kept\n*A1 and non-A1 = items with a mean score of ≥ 3 or <3, respectively, on a 4 point Likert Scale indicating the likelihood for an item to meet criterion A1 for post-traumatic stress disorder (from 'very unlikely' [=1] to 'very likely' [=4]) (see Methods).\nMain health outcomes\nSelf-reported health measures\n• \nPost-traumatic stress symptoms\n: (a) The Dutch 22-item Self-Rating Inventory for PTSD (SRIP) [\n32\n-\n34\n] and, among exposed subjects only, (b) The 15-item Dutch version of the Impact of Event Scale (IES), which addressed post-traumatic stress symptoms with explicit reference to the air disaster in Amsterdam [\n35\n-\n37\n].\n• \nGeneral mental health\n: (a) The 90-item Symptom Checklist (SCL-90) [\n38\n,\n39\n]; (b) The 20-item General Health Questionnaire (GHQ-12) [\n40\n].\n• \nFatigue and associated symptoms\n: The 20-item Checklist Individual Strength (CIS) [\n41\n,\n42\n].\n• \nHealth-related quality of Life\n: The MOS 36-item Short-Form Health Survey (SF-36) [\n43\n,\n44\n].\n• \nChronic conditions\n: One questionnaire assessed the current presence and history of the following chronic conditions, which are considered to have a significant impact on well-being: diabetes; stroke, brain hemorrhage or infarction; heart attack; other heart problems (such as heart failure, or angina pectoris); cancer; chronic osteoarthritis (wear) of the hip or knee joints; hypertension; asthma, chronic bronchitis or lung emphysema (Chronic Obstructive Pulmonary Disease [COPD]); serious or persistent intestinal disorders (longer than 3 months); chronic stomach disorders, stomach or duodenal ulcers; serious or persistent back complaints (including hernias); chronic inflammation of the joints (chronic rheumatism, rheumatoid arthritis). Workers with these chronic conditions were subsequently asked in what year the onset was, to determine whether this was before the disaster took place.\n• \nPhysical symptoms\n: Multiple questionnaires were used to assess the current presence of various physical symptoms, such as a number of respiratory, musculoskeletal, and skin symptoms.\n• \nAttribution of current problems to the air disaster in Amsterdam and its aftermath\n. Another questionnaire assessed the extent to which exposed workers related any of their current physical, psychological or practical/financial problems to the air disaster and its aftermath. Those who attributed physical symptoms to the disaster and its aftermath were asked to specify these symptoms.\nLaboratory outcomes\nGeneral laboratory tests [\n1\n]:\n• \nHematological and blood chemical outcomes\n: hemoglobin, leukocyte count, differential count, platelet count and mean corpuscular volume (Sysmex SE 9000, TOA medical electronics Co. ltd); potassium (Roche Modular ISE900, Roche Diagnostics); creatinine, alkaline phosphatase, gamma-glutamyl transferase, alanine aminotransferase, creatine kinase and C-reactive protein (Roche Modular P800, Roche Diagnostics); ferritin and thyroid stimulating hormone (Centauer, Bayer Diagnostics); β2-microglobuline (IMx Abbott).\n• \nAutoantibodies\n: nuclear antigen antibodies, anti-double stranded DNA antibodies [\n46\n], Immunoglobulin (IgM) rheumatoid factor [\n47\n], antineutrophil cytoplasmic antibodies [\n48\n,\n49\n], and cardiolipin antibodies [\n50\n,\n51\n].\n• \nUrine outcomes\n: creatinine (Hitachi 747, Roche Diagnostics GmbH, Mannheim, Germany); micro-albumin (Beckman Array 360 system); and β2-microglobuline (IMx Abbott); screening for protein, glucose, pH, blood and leukocytes (teststrip Boehringer Mannheim B.V.), followed by microscopic evaluation of the urinary sediment if indicated.\n• \nSaliva outcome\n: cortisol concentration (Wizard 1470, Perkin Elmer).\nAdditional laboratory tests with respect to the societal questions:\n• \nUranium 238\n: concentration in urine (Inductively Coupled Plasma-Mass Spectrometry [ICP-MS] analyser, Finnigan Mat Element) and, at concentrations above 50 ng/l or above 50 ng/g creatinine, also the ratio of uranium 235/238 isotopes [\n52\n].\n• \nTotal and free carnitine\n: concentration in blood plasma (Mira Plus, Roche Diagnostics) [\n53\n,\n54\n].\n• \nDNA of any Mycoplasma species\n: presence in peripheral blood mononuclear cells (DNA-isolation, Magna Pure, Roche Diagnostics; real time PCR, Taqman, Applied Biosystems); positive samples were subsequently evaluated for the presence of DNA of Mycoplasma fermentans [\n55\n,\n56\n].\nSelf-reported socio-demographic characteristics\n• \nAge\n: at time of assessment in years.\n• \nSex: \nmale or female.\n• \nEthnicity: \ncategorized into those who considered themselves as European (i.e. Dutch, British, Dutch/Irish, Dutch/Chinese, Dutch/Indonesian, Portuguese, Spanish, Dutch/ Spanish and European), and others (\ne.g. \nMoroccan, Turkish, Surinam).\n• \nLevel of education\n: highest level of education completed, categorized as: high (higher vocational education, university); medium (intermediate vocational education, higher general secondary education, or pre-university education); and low (no education, elementary school, lower vocational education, or lower general secondary education).\n• \nCurrent executive function\n: yes (i.e. supervising one or more people) or no.\n• \nLevel of physical activity\n: the total number of hours spent each week on physical activities such as physical exercise, gardening and housekeeping, classified into high, medium and low according to the 33\nrd \nand 66\nth \npercentiles.\n• \nAlcohol consumption\n: Usual and exceptional consumption of alcoholic beverages, classified into: none; light-moderate; and (extremely) excessive, i.e. consumption of (a) six or more glasses on 9–20 days a month and on 3–4 days in the last week, (b) four or more glasses on at least 21 days a month and on at least 5 days in the last week, and/or (c) more than six glasses a day, on a weekly basis.\n• \nCigarette-smoking: \ncategorized as: never, former smoker, and current smoker.\n• \nNegative life events: \nthe number of reported negative life events, based on a questionnaire which specified 13 such events and also included two open-ended questions in which other events could be described. Subjects were asked to indicate whether any of these events happened to them before or after the disaster.\nRole of funding sources\nThe study was funded by the Dutch Ministry of Health, Welfare and Sports; the City of Amsterdam; the Amsterdam-Amstelland regional police force; and KLM Royal Dutch Airlines. The funding sources had no role in the collection, analysis, or interpretation of the data, or in the decision to submit a manuscript for publication.\nDiscussion\nIn recent years there has been increasing scientific and societal interest in the health consequences of man-made, technological disasters, i.e. a collective stressful experience with a sudden onset due to technological failure. Technological disasters have had psychiatric consequences [\n13\n-\n15\n,\n57\n], such as PTSD, as well as medical consequences, in particular those of toxic exposures [\n58\n-\n61\n]. In addition to direct toxic health effects, the mere suspicion and fear of exposure to hazardous materials can also take its toll on the quality of physical, psychological and social well-being in the community [\n62\n-\n64\n].\nTechnological disasters strike unexpectedly and suddenly, which puts time-pressure on researchers to develop study protocols, gather exposure data, call in multidisciplinary experts, and obtain financial resources for immediate epidemiological research. Disaster researchers may also have to deal with complicated socio-political and legal aspects. In addition, they have to face a number of methodological problems. These difficulties include: (a) defining the entire potentially 'affected' population and appropriate reference groups; (b) contacting potential participants, particularly in the case of evacuation and hospitalization; low response rates; usually without data on non-respondents [\n65\n]; (c) collecting exposure data immediately after the event, which is actually also needed for long-term epidemiological studies.\nProbably due to these difficulties, evidence from large-scale epidemiological studies that have been carried out after technological disasters is rather scarce [\n66\n,\n67\n]. Furthermore, before-after comparisons are rare and only possible by chance in ongoing research projects, due to the unexpected nature of technological disasters [\n68\n-\n70\n]. Most of the studies that have been conducted so far have relied on 'convenience samples', which were mainly composed of those who were directly affected, such as victims and residents; were based on non-epidemiological study designs; and used group-level or retrospective, self-reported exposure data, which can be affected by recall and reporting bias [\n71\n-\n74\n].\nESADA approach\nThe purpose of the ESADA is to assess long-term health effects of occupational exposure to the air disaster in Amsterdam on professional assistance workers. In view of the above-mentioned difficulties in epidemiological research on disasters, the ESADA has some strong methodological points. With respect to the study population, we have been able to identify the complete cohort of exposed and non-exposed workers accurately, based on company records of employment at the time of the disaster.\nAnother strong point of the ESADA is that we included reference groups of colleagues, who had the same jobs and employers, but who were not occupationally exposed to the disaster. Hence, we are able to draw group-level conclusions on associations between health status and occupational exposure to the disaster.\nWith respect to exposure assessment, we were able to collect individual data on occupational exposure to the air disaster. Moreover, this consisted of multiple aspects of self-reported occupational exposure, including the duration and location of various disaster-related tasks and the experience of potentially stressful events during these tasks. Finally, we also included various assessments of long-term health, such as laboratory tests and self-reported symptoms and health-related quality of life, to obtain an integral evaluation of health status.\nNotwithstanding these strong methodological qualities, some limitations of the ESADA design should also be mentioned. Firstly, although company records of employment were available, we still had to resolve a few difficulties regarding the definition of the study population. For the fire-fighters, this was due to the fact that almost the entire fire department of Amsterdam had been exposed to the disaster. Therefore, in order to achieve an adequate reference group, we decided to also include fire-fighters who joined this fire department after the disaster took place. With respect to the police officers, we were unable to trace those who had left the Amsterdam-Amstelland regional police force in the years after the disaster, due to administrative difficulties. Hence, it was necessary to restrict this group to those who were still working for this police force in 2000.\nA second methodological issue concerns the self-report nature of occupational exposure status, and the average time-lag of 8.5 years between the disaster and the assessment. Due to administrative deficiencies in the historic registration of the exposure status, we used our detailed questionnaire data to define exposure status for all workers. Strictly speaking, the ESADA is therefore not a historic cohort study, but a cross-sectional one. The time-lag between the disaster and the exposure assessment may have led to recall bias, especially concerning certain details of exposure to the disaster, such as the duration of activities. However, it seems reasonable to assume that the workers did recollect whether or not they performed any as opposed to no disaster-related tasks, which was used to define occupational exposure status. It is therefore very unlikely that recall bias has resulted in (non-)differential misclassification of exposed and non-exposed workers. Nevertheless, recall bias should be kept in mind with respect to exposure-response relationships. We included multiple aspects of level of exposure, such as the duration and the potential psycho-traumatic character of disaster-related tasks, as it is unknown which aspect of occupational exposure to disasters is relevant for long-term health. However, we may still have missed other potentially relevant aspects, such as exposure to disaster-related media reports in the aftermath of the disaster [\n4\n,\n75\n].\nThirdly, we acknowledge the fact that, with the exception of the laboratory variables, we rely on self-reported health outcomes. However, most of the health questionnaires that we used have been validated and widely accepted, except for those used to assess the physical symptoms. Differential misclassification in self-report health measures could occur if exposed workers are more likely than non-exposed workers to interpret and report bodily sensations as symptoms. On the other hand, hypervigilance and hypochondria themselves could well be adverse health effects of (toxicological) disasters [\n76\n,\n77\n].\nIn conclusion, to increase our knowledge of potential health consequences of (technological) disasters, it is important to be prepared for epidemiological disaster research. Incorporating basic multidisciplinary, epidemiological research protocols into disaster management plans will stimulate scientifically sound research on the health effects of disasters. The ESADA will provide additional scientific knowledge on the long-term health effects of technological disasters on professional workers.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nAll authors participated in the multidisciplinary ESADA project team of the EMGO Institute, provided comments on the draft versions and approved the final manuscript. PS drafted the manuscript and performed statistical analyses. AH coordinated the acquisition of data and supervised the first part of the ESADA study. JT contributed to the design and supervised the statistical analyses. AW coordinated the rating of the potential psychotraumatic impact of exposure items and performed statistical analyses. HP and IB participated in the conception and design of the ESADA with respect to psychological outcomes, and IB rated the potential psychotraumatic impact of exposure items. NS supervised the second part of the ESADA. As Medical Director JB coordinated the data-collection. LB contributed to the design of the ESADA. WM contributed to the design and is Vice-President of the ESADA project team. TS conceived the study, and participated in its design and coordination as President of the ESADA project team.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
36
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nLow back pain in military recruits in relation to social background and previous low back pain. A cross-sectional and prospective observational survey\n\n**Article Abstract:**\n\nBackground\nTraditionally, studies on the etiology of low back pain have been carried out in adult populations. However, since low back pain often appears early in life, more research on young populations is needed. This study focuses on the importance of social background factors and previous low back pain in the development of low back pain in military recruits.\nMethods\nDuring a three-month period, Danish military recruits with different social backgrounds live and work under the same conditions. Thus, there is an opportunity to investigate the influence of social background on the development of low back pain, when persons are removed from their usual environment and submitted to a number of new stressors. In addition, the importance of the recruits' previous low back pain history in relation to low back pain during military service was studied. This was done by means of questionnaires to 1,711 recruits before and after this three-month period.\nResults\nSedentary occupation was negatively associated with long-lasting low back pain (>30 days during the past year) at baseline with an odds ratios of 0.55 (95% CI: 0.33–0.90). This effect vanished during service. Having parents with higher education increased the risk of low back pain during service (OR: 1.9;1.2–3.0, for the highest educated group), but not of the consequences (leg pain and exemption from duty), whereas high IQ decreased the risk of these consequences (odds ratios as low as 0.2;0.1–0.8 for exemption from duty in the group with highest IQ). Long-lasting low back pain prior to service increased the risk of long-lasting low back pain (OR: 4.8;2.1–10.8), leg pain (OR: 3.3;1.3–8.3) and exemption from duty during service (OR: 5.9;2.4–14.8).\nConclusion\nSedentary occupation is negatively associated with low back pain at baseline. This protective effect disappears, when the person becomes physically active. For predicting trouble related to the low back during service, the duration of low back pain prior to service and IQ-level are the most important factors.\n\n**Article Body:**\n\nBackground\nLow back pain (LBP) is a very common ailment in the Western World and musculoskeletal disorders are leading causes of long-term sick leave [\n1\n]. Thus, it has a major social and economic impact on society. Although elimination of LBP is only wishful thinking, prevention of chronicity may be within the scope of reality – with obvious gains for society. To obtain this goal, a thorough understanding of the etiology is necessary. Presently, etiological research has a broad approach to LBP, based on the bio-psycho-social model and several studies have been performed in which risks associated with physical characteristics [\n2\n], psychological characteristics [\n3\n], lifestyle factors [\n4\n], employment [\n5\n-\n8\n], social factors [\n9\n,\n10\n] and genetic components [\n11\n,\n12\n] were investigated. However, these studies are difficult to interpret due to the close relationship between social factors, intellectual capacity, coping strategies, education, profession etc., causing a mesh of interactions and confounding.\nTraditionally such studies have been carried out on working-age populations, but there is growing evidence that LBP has an earlier onset than hitherto thought. In a study of Danish twins, aged 12 to 41, the one-year prevalence of LBP was found to rise from 7% in those aged 12 to above 50% in those aged 22 and to increase only slightly thereafter to reach 56% in those at the age of 41 [\n13\n]. Furthermore, earlier studies have shown that the risk of LBP at age 30 is significantly increased for individuals with LBP at age 18 [\n14\n]. Obviously, to obtain a thorough understanding of the etiology of LBP, young populations should be investigated.\nThe Danish Army has a system of mandatory conscription for six months of service. Usually, there is an intake in August and one in January, with most high school graduates commencing in August after finishing high school, whereas the January-intake mainly consists of those with no academic education beyond primary school. However, due to special circumstances, there was no intake in January 2000 and therefore the August-intake of that year represented the social variety of the Danish society, as reflected by education. During the first three months of service all the recruits receive the same training, housing etc. Therefore, we had a unique opportunity to investigate the development of LBP in young persons (primarily males) of different educational backgrounds, who were fit for military service, at a time when they were submitted to the same living and working conditions. This made it possible to investigate the impact of various social background factors on the occurrence of LBP, without results being confounded by differences in lifestyle and type of work. By surveying these conscripts on their first day of enrollment, we can estimate how their background influences their prevalence of LBP, reflecting the influence of their usual environment. After three months of being subjected to unusual stressors in a different environment, like performing physically demanding tasks whilst being deprived of their normal personal freedom, we can estimate how the occurrence of LBP is influenced by their social background as well as their baseline LBP-status. Thus, the present study has two objectives:\n1) To investigate possible associations between social background factors and the prevalence of LBP in young persons, both in their usual environment and in a new setting.\n2) To identify possible predictors, both social and LBP-related, for reporting LBP during military service.\nMethods\nSubjects\nDuring the year of 2000, 2,343 persons, aged 18–24, were enrolled as military conscripts at 15 locations across Denmark. Upon reporting for duty, the recruits had a medical examination and during the course of this, a research questionnaire was administered. The medical officer filled in the first part, which contained the army's own information: personal identification number, years of schooling, the score from the military's intelligence test, and type of work. The second part was filled in by the conscripts themselves and contained questions relating to their LBP-history and the education of their parents. After three months of basic training the conscripts were given different tasks, thus conditions were no longer the same for all and our follow-up period ended. At this time they were given a second questionnaire relating to LBP during their first three months of service. An information letter accompanied the questionnaires, explaining the purpose of the project and assuring the confidentiality of the informant. It was stressed, that the information would not be available to the army, as only staff at the Medical Research Unit in the county of Ringkøbing would have access to the information.\nVariables\nSocial background variables\nThe following background information was collected routinely by the military on all potential recruits:\n• Years of school: Years of schooling from 1\nst \ngrade till joining the military. Treated as a continuous variable.\n• IQ-score: Result of an intelligence test performed when examined for liability for military service. Divided into three categories with cutpoints close to the 25- and the 75-percentile (low, medium, high) and treated as a categorical variable.\n• Occupation: Each profession has its own code in the military. These codes were translated and dichotomized into sedentary or manual work.\nThe questionnaires contained the following information:\nParents' education: The level of the highest educated parent. Choices were: grade school only, high school level, or >12 years (university/other type of higher education).\nLB-related variables\n• LBP: Questionnaire 1: Pain or discomfort in the lower back during the past year (yes/no). Questionnaire 2: Pain or discomfort in the lower back during military service (yes/no). This was accompanied by a drawing, showing the lower back as the area between the gluteal folds and the 12\nth \nribs.\n• Duration: Questionnaire 1: Number of days with LBP during the past year. Questionnaire 2: Number of days with LBP during military service. This was treated as a categorical variable (0 days, 1–7 days, 8–30 days, >30 days) and as a dichotomous variable (long-lasting LBP (LLBP) = LBP>30 days, yes/no).\n• Leg pain: Questionnaire 1: Leg pain radiating from the low back during the past year (yes/no). Questionnaire 2: Leg pain radiating from the low back during military service (yes/no).\n• Exemption: Questionnaire 2: Number of days exempted from duty due to LBP during the follow-up period. Due to the small number of exemptions, this was formed into a dichotomous variable (Exemption yes/no).\nThe questions of one-year prevalence of LBP, duration of LBP, and leg pain were modeled on the Nordic low back pain questionnaire [\n15\n] of which the LBP-questions have been validated in previous studies [\n16\n,\n17\n].\nAnalysis\nThe analysis is divided into two parts: 1) a cross-sectional study investigating associations between LBP and the described social variables (IQ, years of schooling, occupation and parents' education) and 2) a three-months follow-up study investigating how LBP during military service is related to the social background factors and baseline low back related (LB-related) factors: LBP, long-lasting LBP and radiating pain to the leg. All outcome variables were analyzed seperately for the total sample, i.e. leg pain against no leg pain, regardless of LBP-status. Since the social background variables are closely related, they were all tested for interactions by means of the Mantel-Haenzel homogeneity test.\nAll analyses were performed with Stata 7.0. Statistical significance was defined at the 5%-level. However, since multiple associations were tested, one might choose to be restrictive in the interpretations of significance. Therefore, statistical significance has been indicated in the relevant tables at the 1%-level as well.\nCross-sectional study\nThe baseline outcome variables were analyzed with respect to the social background variables by means of multivariate logistic regression. Following multivariate analyses, forward exclusion was applied to decide which variables to keep in the models for the different outcome variables. The variables were kept in the models if they were statistically significant or if they had a bearing on the estimates of the variables that were statistically significant in the multivariate analyses. They were included if they changed the estimates of the statistically significant variables by 25% or more, if they changed the corresponding p-values with 25% or more, or if they changed the significance status of the relevant estimates. Results are presented as odds ratios with 95% confidence intervals (CI).\nFollow-up study\nThe same type of regression-analyses were used to analyze the follow-up outcome measures with respect to the social background variables. The most relevant baseline LB-related variable(s) was/were determined through univariate logistic regression, and a final model for predicting LB-related trouble during military service was constructed by combining social and LB-related variables.\nPost-hoc analyses\nDue to the low response rate at baseline, it was decided to compare the prevalence rates of the baseline LBP-variables to those of the background population. This was done by means of data from the Danish Twin Register, which previously has been shown to be representative of the general Danish population and is described in detail elsewhere [\n18\n]. The twins had answered a questionnaire containing the same LBP-questions in 1994. Therefore, a nested cohort of 18–22 year old males was selected for comparison to the soldiers in the present study.\nFinally, the consequence in relation to exemption from duty were demonstrated by calculating the reduction in intake of recruits and the corresponding reduction in exemptions, if the identified significant factors were to be used as part of the inclusion criteria for military service. In this analysis, only subjects who have answered all the relevant questions are included.\nResults\nResponse rate\nOf the originally planned enrollment of 2,343 individuals, 1,711 (73%) returned the baseline questionnaire with valid answers to the LBP-questions. The follow-up response rate is 58% (985/1711). The numbers of valid responses to the individual variables are shown in Table \n1\n.\nTable 1\nNumber of responses to the questionnaires.\nYears of school\n.\nn: 1,657\nIQ\nLow score\nMedium score\nHighest score\nn\n351\n682\n406\n1,439\nOccupation\nSedentary occupation\nManual occupation\nn\n840\n807\n1,647\nParental education\nGrade school only\nHigh school\n>12 years of education\nn\n474\n521\n461\n1,456\nLBP\nYes\nNo\nn\nQuestionnaire 1\n712\n999\n1,711\nQuestionnaire 2\n345\n639\n985\nDuration:\n0 days\n1–7 days\n8–30 days\n>30 days\nn\nQuestionnaire 1\n948\n243\n259\n158\n1,608\nQuestionnaire 2\n637\n140\n119\n49\n945\nLeg pain\nYes\nNo\nn\nQuestionnaire 1\n82\n1589\n1,671\nQuestionnaire 2\n66\n912\n982\nExemption\nYes\nNo\nn\n65\n806\n871\nGender and age\nThe study sample is predominantly male with only 4% females. The mean age is 20.57 years with a standard deviation of 2.16 years, ranging from 18 to 30 years of age.\nQuality of data\nDouble entry of a 10%-subsample revealed an error-rate of less than 0.6%, which we consider satisfactory.\nExternal validity (post-hoc analysis)\nThe one-year prevalence rates of LBP, leg pain and long-lasting LBP (LLBP) are shown in Table \n2\n for 18–22 year old male twins from the Danish Twin Register and for the soldiers at baseline of the present survey.\nTable 2\nOne-year prevalence rates with 95% confidence intervals of the soldiers at baseline in the present study and in an age-matched cohort, representative of the background population (18–22 year old male twins, surveyed in 1994).\nCohort\nLBP\nLLBP\nleg pain\n2,213 twins\n43% (41–45%)\n7% (6–9%)\n5% (4–6%)\n1,711 soldiers\n42% (39–44%)\n7% (6–9%)\n5% (4–6%)\nThe present sample of soldiers is perfectly comparable to an age- and almost sex-matched sub-sample from the Danish Twin Registry with regard to the outcome variables: one year prevalence of LBP, long-lasting LBP and leg pain.\nAnalysis of non-responders at follow-up\nThere was no difference in responders and non-responders at follow-up with regard to any of the social background factors or the one-year prevalence of LBP at baseline. However, non-responders had more days with LBP during the past year than the responders (mean 16.11 (SD 59.45) and mean 10.74 (SD 37.24), respectively, p = 0.000), and there was also a statistically significant difference in leg pain (p = 0.027) with 6% (5–8%) of non-responders and 4% (3–5%) of responders complaining of leg pain, indicating that the LBP in non-responders might be more severe in nature.\nInteractions between social background variables\nAll the background variables were positively interrelated (p ≤ 0.08), but tests for homogeneity showed no interactions (p ≥ 0.72).\nCross-sectional analysis\nModel for associations between LB-related variables at baseline and social background variables\nThe statistically significant factors found in the multivariate analysis were parents' education for LBP, occupation and parents' education for long-lasting LBP, but none for leg pain. The forward exclusion method left parents' education, sedentary job and IQ in the model for LBP and all four variables in the model for long-lasting LBP (removing years of schooling or IQ both lead to a decrease in the p-value of the effect-estimate of occupation of more than 25%).\nHaving a sedentary job showed a reduced association with LBP. Although this was not statistically significant for simply having LBP, it was highly significant for long-lasting LBP.\nHaving the highest educated parent at high school level lead to a statistically significant higher prevalence of LBP and long-lasting LBP whereas the findings for those with a parent with >12 years of education were not statistically significant and no gradient across groups was detected. The results are presented in Table \n3\n.\nTable 3\nFinal model for associations between LBP-variables at baseline and social background variables (odds ratios with 95% confidence intervals). Significant findings are indicated with bold typing.\nN = 1708\nLBP n = 710\nLLBP n = 157\nIQ-score low\n1.00\n1.00\nIQ-score medium\n1.09 (0.81–1.48)\n1.09 (0.69–1.73)\nIQ-score high\n1.19 (0.84–1.68)\n0.95 (0.54–1.68)\nSedentary occupation\n0.84 (0.65–1.08)\n0.55 (0.33–0.90)*\nParents grade school\n1.00\n1.00\nParents high school\n1.39 (1.05–1.84)*\n1.67 (1.05–2.64)*\nParents >12 years education\n1.23 (0.93–1.64)\n1.33 (0.82–2.17)\nYears of school\n-\n0.98 (0.89–1.08)\n*: p < 0.05, **: p < 0.01\nFollow-up analysis\nModel for associations between social background variables and LBP during military service\nThe multivariate analysis showed no statistically significant findings for long-lasting LBP. Parents' education was found to be statistically significant for LBP during service with an increasing gradient, i.e. higher education associated with higher prevalence of LBP. IQ was inversely related to both leg pain and exemption during service with decreasing gradients, i.e. the higher the score, the lower the risk. Years of schooling could be excluded from the model for LBP and leg pain without any bearing on the estimates, and type of occupation could be excluded from the model for exemption from duty. The exact estimates are shown in Table \n4\n.\nTable 4\nFinal model for associations between social background variables and LBP during military service (odds ratios with 95% confidence intervals). Statistically significant findings are indicated with bold typing.\nN = 982\nLBP n = 345\nLeg pain n = 66\nExemption n = 65\nIQ-score low\n1.00\n1.00\n1.00\nIQ-score medium\n1.02 (0.68–1.52)\n0.72 (0.37–1.42)\n0.56 (0.27–1.17)\nIQ-score high\n0.99 (0.64–1.53)\n0.33 (0.13–0.88)*\n0.26 (0.09–0.79)*\nParents grade school\n1.00\n1.00\n1.00\nParents high school\n1.58 (1.06–2.34)*\n1.25 (0.62–2.54)\n1.17 (0.54–2.55)\nParents >12 years education\n1.81 (1.20–2.72)**\n1.19 (0.56–2.49)\n1.22 (0.54–2.76)\nSedentary occupation\n0.84 (0.59–1.20)\n0.69 (0.36–1.33)\n-\nYears of school\n-\n-\n0.89 (0.71–1.10)\n*: p < 0.05, **: p < 0.01\nModel for associations between LB-related trouble at baseline and LB-related trouble during military service\nAll the LB-related variables were significantly associated with all the outcome variables. We decided to use number of days with LBP during the past year rather than LBP at all during past year to obtain more detailed analyses. There is a high correlation between baseline leg pain and the outcome variables (73 of the 82 (89%) persons with leg pain also had LBP), and adding leg pain to the models does not alter the estimates significantly. With regard to leg pain at follow-up, baseline leg pain is the most important factor. The results of the bivariate logistic regression analyses are shown in Table \n5\n.\nTable 5\nAssociations between baseline LB-related variables and LBP during military service (odds ratios with 95% confidence intervals) as assessed by univariate logistic regression analyses. Statistically significant findings are indicated with bold typing.\nN = 982\nLBP n = 345\nLeg pain n = 78\nLLBP n = 56\nExemption\n1 \nn = 74\nBaseline LBP\n3.52** (2.68–4.63)\n1.71** (1.15–2.54)\n1.58* (0.01–1.28)\n2.89* (1.70–4.89)\nBaseline leg pain\n2.22* (1.15–4.30)\n8.78** (4.23–8.21)\n4.92** (2.03–11.89)\n3.61** (1.50–8.69)\n0 days with LBP previous year\n1.00\n1.00\n1.00\n1.00\n1–7 days with LBP previous year\n2.04** (1.39–2.99)\n0.90 (0.36–2.24)\n1.11 (0.44–2.84)\n1.96 (0.95–4.06)\n8–30 days with LBP previous year\n5.42** (3.63–8.08)\n2.57** (1.28–5.14)\n2.47* (1.14–5.32)\n1.44 (0.63–3.30)\n>30 days with LBP previous year\n6.45** (3.86–10.79)\n5.51** (2.73–11.12)\n4.80** (2.13–10.84)\n6.13** (3.05–12.50)\n*: p < 0.05, **:p < 0.01\nFinal models for predicting trouble related to LBP during military service combining social background variables and LB-related baseline-variables\nWhen the models for associations between social background and LB-related trouble during military service were combined with LB-related baseline variables, the following models could be derived:\nLBP during military service\nThe model for the association between social background variables for LBP during service included IQ and parents' education. When this was combined with the number of days with LBP the year prior to service, parents' education remained statistically significant with an increase in education resulting in an increase in odds ratio. Number of days with LBP showed the strongest correlation with odds ratios above 6. IQ-level could not be excluded from the model without altering the significance level of parents' education\nLong-lasting LBP during military service\nNone of the social background variables had significant influence on the development of long-lasting LBP, thus only the LB-related baseline variable, duration of LBP, was included. The effect of LBP-duration was statistically significant, demonstrating a positive association (OR = 4.8 for LBP>30 days at baseline).\nLeg pain related to LBP during military service\nIQ, parents' education and type of occupation were included in the model for leg pain during service. Adding leg pain during the year prior to service and number of days with LBP during the same period, leave the same variables as significant, but excluding parents' education from the model would change the significance of both IQ and duration of LBP. A high IQ-level showed a negative association with leg pain during service, whereas long duration of LBP and previous leg pain both showed positive associations (OR = 3.3 and 3.1, respectively).\nExemption from duty due to LBP during military service\nIncluding the relevant factors in the model (IQ, parents' education, years of schooling and number of days with LBP), left IQ and number of days with LBP to be significant. However, once more, excluding parents' education or years of schooling, changed the significance level for IQ and it was therefore kept in the model. A high IQ lowered the risk of exemption (OR = 0.2) whereas long-lasting LBP the previous year increased the risk (OR = 5.9).\nThe results of the final models for all outcome measures are shown in Table \n6\n.\nTable 6\nThe final models for outcome measures during service, combining social and physical factors (odds ratios with 95% confidence intervals). Statistically significant findings are indicated with bold typing.\nN = 982\nLBP n = 345\nLLBP n = 56\nLeg pain n = 66\nExemption\n1 \nn = 65\nIQ-score low\n1.00\n-\n1.00\n1.00\nIQ-score medium\n1.14 (0.73–1.79)\n-\n0.75 (0.35–1.61)\n0.56 (0.25–1.25)\nIQ-score high\n1.00 (0.61–1.63)\n-\n0.24 (0.08–0.74)**\n0.24 (0.08–0.76)*\nParents grade school\n1.00\n-\n1.00\n1.00\nParents high school\n1.56 (1.01–2.42)*\n-\n1.05 (0.48–2.27)\n1.14 (0.48–2.71)\nParents >12 years education\n1.90 (1.21–2.99)**\n-\n1.06 (0.47–2.38)\n1.40 (0.59–3.35)\nSedentary occupation\n-\n-\n0.87 (0.42–1.79)\n-\nYears of school\n-\n-\n-\n0.91 (0.72–1.14)\nBaseline Leg pain\n-\n-\n3.14 (1.13–9.85)*\n-\n0 days with LBP previous year\n1.00\n1.00\n1.00\n1.00\n1–7 days with LBP previous year\n2.31 (1.49–3.59)**\n1.11 (0.44–2.84)\n0.79 (0.28–2.22)\n2.33 (0.94–5.79)\n8–30 days with LBP previous year\n6.09 (3.78–9.84)**\n2.47 (1.14–5.32)*\n2.52 (1.28–6.20)**\n1.78 (0.64–4.94)\n>30 days with LBP previous year\n6.18 (3.42–11.17)**\n4.80 (2.13–10.84)**\n3.28 (1.31–8.25)**\n5.93 (2.37–14.83)**\n*: p < 0.05, **:p < 0.01\nConsequences\nFor practical purposes, in the process of selecting military recruits for army, the outcome of interest is exemption from duty. For this outcome, the most interesting factors, of the ones investigated in this study, are the number of days with LBP during the year prior to service and the IQ-level. Table \n7\n presents an estimation of the reduction in the number of soldiers exempted from duty and the corresponding reduction in intake if various combinations of those two factors were used as inclusion criteria. The practical significance must then be judged in the actual situation, for example the number of available potential recruits.\nTable 7\nConsequence in reduction of exemptions and intake-size when excluding subgroups of potential recruits from service, on basis of the two factors found to influence the rate of exemption from duty significantly (IQ-score and duration of prior LBP).\nIncluded\n# exempted from duty\nTotal intake\nFull sample\n45 (100%)\n664 (100%)\nIQ-score=high\n8 (18%)\n187 (28%)\nIQ-score=high or medium\n29 (64%)\n512 (77%)\nLBP-days<30\n34 (76%)\n607 (91%)\nIQ-score=high & LBP-days<30\n6 (13%)\n169 (25%)\nIQ-score=high or medium & LBP-days<30\n21 (47%)\n467 (70%)\nDiscussion\nThe major advantage of our cohort is that people of similar age from backgrounds reflecting the variety of society are all exposed to the same living and working conditions for the same period of time when doing their military service. Obviously, only subjects fit for military service are included, thus excluding the most intellectually and physically disadvantaged. It has, however, previously been established, that the prevalence of LBP in Danish conscripts is similar to the rest of the Danish population of that age [\n19\n]. This we confirmed, as the present cohort does have similar prevalence rates of the LBP-variables as a comparable background population. The major problem of our study is the low response rate (58%). There might have been whole platoons/units (rather than individuals) that did not return the questionnaires. However, we were unable to confirm this, as all the questionnaires were collected in one box upon arrival at the research centre and the place of duty was not stated in the questionnaire. Furthermore, the personal identification number of each soldier was used to combine the first and second questionnaires. A large number of soldiers returned the second questionnaire without stating this number, therefore leaving us with a large number of un-identifiable, although otherwise completed, questionnaires. Thus, most of this is likely to reflect an administrative error (whole platoons not returning the questionnaires) and poor design of the questionnaires (the first and second questionnaire could not be linked) and therefore one would not expect any disease-specific bias as a result of non-response. This is also confirmed by the similarity of prevalence rates between our study sample and the sample from the Danish Twin Register. Anyway, the problem of non-responders having more severe LBP at baseline still remains. This could be related to termination of service prior to follow-up due to LBP of some individuals with a high level of baseline-LBP. Unfortunately, we did not have access to such information. In the protocol, the army staff was asked to administer the second questionnaire to the recruit in case of rejection during service, but this did not happen in any instance. This bias does not directly influence the results relating to the social background variables, but it might weaken the results relating to baseline LBP-status with associations actually being stronger than our findings indicates, if the rejected recruits were the ones with the more severe LBP-symptoms at baseline.\nAs for the influence of social background factors on the presence of LBP at baseline in our population, we found a statistically significant increase in odds ratios if parents belonged to educational group 2 (high school-level). This is an illogical finding that might be an effect of multiple testing and since there is no gradient from the lowest to the highest group, the practical significance of this result is limited. However, when analyzing the occurrence of LBP and related trouble during military service, parents' education does show an increasing gradient for LBP lending support to the credibility of the baseline-findings. A previous study found no association between parents' education and back pain in Danish adolescents [\n20\n].\nThe most important factor for LBP at baseline was found to be type of occupation. This is in line with a previous study, showing sedentary occupations to have a \"protective effect\" on LBP [\n21\n]. Interestingly, there was no effect of pre-service occupation on LBP and related troubles during military service – those with sedentary occupations were as likely as the rest to develop LBP, when they were exposed to the same stress. This implies that the association with a sedentary occupation is direct, rather than a proxy of intelligence level, social class or other similar confounders/interactions.\nIntelligence level, as measured by the army's IQ-test, did not influence any of the LBP-variables at baseline, and did not influence the occurrence of LBP during service. A high test-result did, however, limit the occurrence of leg pain and exemption from duty. Both sedentary occupation and parents' education are strongly associated with intelligence level (p = 0.000 and p = 0.008, respectively). Thus, by taking our results a step further, it could be speculated that the group with above-average intelligence, well-educated parents and a sedentary occupation has a low occurrence of LBP at baseline, an increased risk of LBP during the physical demands of service, but seem to suffer less from the consequences (leg pain and exemption from duty). This might be a sign of better coping strategies in this group. Coping strategies as they relate to dealing with chronic pain has been a focus of research in recent years [\n22\n-\n24\n], but coping abilities as part of the etiology of back pain has only received limited attention yet. In a recent study of a general population, high levels of passive coping were found to be associated with disabling neck and back pain [\n25\n].\nWhen the LBP-variables at baseline are added to the model for LBP-related trouble during service, the duration of LBP the previous year is the important variable. LBP in itself does not predict LBP during service but a longer duration of LBP at baseline increased the risk of long-lasting LBP, leg pain and exemption from duty during the study period. This might indicate that short-lasting LBP is more co-incidental and a normal life experience. This is consistent with the literature, where the duration of LBP is considered to be an important prognostic factor [\n26\n-\n29\n]. Furthermore, we showed that leg pain at baseline is a strong predictor for continued leg pain.\nAs a screening tool to predict which recruits will develop LBP during military service, models containing the investigated variables are not sufficiently accurate. If used to exclude vulnerable subjects from military service, many would be excluded unnecessarily.\nKey points\n• Having a sedentary occupation is negatively associated with long-lasting LBP and leg pain in this population, irrespective of intelligence level and education.\n• Having parents with a high education may increase the risk of developing LBP during military service, but not of its consequences.\n• A high IQ seems to protect against leg pain and exemption from duty during military service.\n• Long-lasting LBP at baseline increases the risk of long-lasting LBP, leg pain and exemption during the course of duty.\n• The predictive value of the investigated factors is too low to be used as a screening tool for the military.\nConclusion\nWith regard to the social variables (IQ, occupation, and parents' education), type of occupation is the most important factor at baseline with a sedentary occupation having a negative association with LBP. This protective effect disappears, when the person actually enrolls and becomes more physically active. Then, a higher level of parents' education seems to predispose for simple LBP, whereas a high intelligence level is a protective factor for the development of leg pain and exemption from duty.\nWith regard to the LBP-related variables (LBP at all, long-lasting LBP, and leg pain), longer duration of LBP during the previous year increases the risk of all LBP-related problems during military service. Finally, the presence of leg pain at baseline predicts leg pain during service.\nOur findings provide important information in relation to etiology, but a suitable screening instrument will require further refinement.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nLH participated in the design and coordination of the study, double-entered a sub-sample of data, performed the statistical analyses and drafted the manuscript. KL participated in the design and coordination of the study and confirmed the statistical analyses. FW provided contact to the army practitioners and participated in the coordination of the study. CL-Y participated in the design of the study and in drafting the final manuscript. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
37
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nChiropractic as spine care: a model for the profession\n\n**Article Abstract:**\n\nBackground\nMore than 100 years after its inception the chiropractic profession has failed to define itself in a way that is understandable, credible and scientifically coherent. This failure has prevented the profession from establishing its cultural authority over any specific domain of health care.\nObjective\nTo present a model for the chiropractic profession to establish cultural authority and increase market share of the public seeking chiropractic care.\nDiscussion\nThe continued failure by the chiropractic profession to remedy this state of affairs will pose a distinct threat to the future viability of the profession. Three specific characteristics of the profession are identified as impediments to the creation of a credible definition of chiropractic: Departures from accepted standards of professional ethics; reliance upon obsolete principles of chiropractic philosophy; and the promotion of chiropractors as primary care providers. A chiropractic professional identity should be based on spinal care as the defining clinical purpose of chiropractic, chiropractic as an integrated part of the healthcare mainstream, the rigorous implementation of accepted standards of professional ethics, chiropractors as portal-of-entry providers, the acceptance and promotion of evidence-based health care, and a conservative clinical approach.\nConclusion\nThis paper presents the spine care model as a means of developing chiropractic cultural authority and relevancy. The model is based on principles that would help integrate chiropractic care into the mainstream delivery system while still retaining self-identity for the profession.\n\n**Article Body:**\n\nBackground\nIt is always fashionable to speak of an issue or controversy as reaching a \"crisis point,\" or of an organization or profession reaching a \"crossroads\" in its development. However such exhortations are often merely hyperbole. At the risk of committing this offense, we believe that the chiropractic profession today faces an exceptionally difficult set of challenges and, yes, a crisis. The nature of this crisis is the profession's continued inability to define itself. The chiropractic profession, more than 100 years after its founding, does not project a definition of itself that is consistent, coherent or defensible. The healthcare system is increasingly intolerant of such ambiguity and uncertainty; an intolerance which will only intensify in the future.\nThe primary purpose of this paper is to offer a coherent and defensible professional identity. We argue that chiropractic's identity is as a provider of spine care. We argue further that such a model is consistent with the best available scientific evidence, is consistent with the current public perception, provides benefit to both the profession and the public, and is capable of gaining for the profession the cultural authority it now lacks. In developing this model we established a set of criteria that the model must meet:\n1. It must be consistent with accepted modes of scientific reasoning and knowledge.\n2. It must accommodate future changes in scientific understanding.\n3. It must represent a set of clinical competencies within the reach of practicing chiropractors.\n4. It must be consistent, credible and communicable to external constituencies on whom the profession relies.\n5. It must represent the evidence of practice experience.\n6. It must find a substantial presence within the healthcare marketplace.\n7. It must be compatible with the training, licensure, history and heritage of chiropractic.\nPart I: The Context of the Identity Crisis\nThe Search for Cultural Authority\nAll healthcare disciplines have members who quibble over priorities and preferred belief systems. To prevent these squabbles from limiting advancement and productivity, there must be an understanding of common ground on which to build. With that in mind, it helps to ask \"What are the core values/concerns held by the members of the chiropractic profession on which nearly all parties can agree?\" We propose that there are a number of common factors even among the most diverse viewpoints within chiropractic.\n• Patients benefit from chiropractic care.\n• Over the past several decades, a substantial body of evidence has accumulated to inform decision-making on the value of chiropractic manipulation for low back, neck and headache complaints.\n• A large population exists that is underserved by chiropractic.\n• Extra-disciplinary competition is increasing, with greater encroachment on traditionally chiropractic domains.\n• Significant barriers persist which obstruct the profession and its members from reaching their group and individual potentials.\nWith this common understanding we can ask, \"Why is the modern evidence largely being ignored by policy makers and the access to chiropractic care being impeded by arbitrary obstacles?\" To answer this question, we should step back and take a dispassionate assessment of how society invests its trust in professionals. The trivial answer identifies institutional bias as the cause; that is, policy makers rely solely on practitioners of medicine as their advisors. Although there is evidence that these attitudes are easing, stereotyping and bias toward the chiropractic profession remains pervasive. However, this is a superficial and inadequate explanation, as the sovereignty of medicine over healthcare has eroded significantly and its biases are increasingly evident to decision makers.\nThe more complete answer is based on the competition for cultural authority that each profession faces during its evolution. Cultural authority is granted by society based on recognition of a professional group's competency and legitimacy with respect to the domain over which it professes dominance. With cultural authority comes a certain degree of autonomy and privilege. Chiropractic has not anchored its cultural authority. Evidence of competency exists by virtue of years of practical experience and the presence of substantial evidence of effectiveness for methods of care for which the profession has held as its primary domain for the majority of the 20\nth \nCentury. It is on the front of legitimacy that we have failed. This failure is fueled by a mismatch between the profession's assessment of the value the practice of chiropractic offers and society's assessments of the same. Some chiropractors lament that the profession has done a poor job of educating the public about chiropractic. They posit that if we would just do enough advertising and more effective public relations, the resistance to using chiropractic services would decrease. As enticing as the argument sounds, that experiment actually has been done and has proven not only to be false but counterproductive. Canadian chiropractors found, in two separate samples, that marketing to the public about subluxation and the adjustment resulted in a backlash against the term \"subluxation\" and an increase in the public's desire to consult a medical doctor if they perceived they might have a subluxation [\n1\n]. The educational materials about chiropractic ideology were created by advertising professionals and broadcast under supervision of the chiropractors. The public is clearly not interested in, or receptive to this sort of message from the chiropractic profession.\nLegitimacy, as defined above, is the active battleground today. Points of contention are the credibility of clinical claims for effectiveness of chiropractic manipulation for a variety of non-spinal conditions, cost of chiropractic care versus \"standard care,\" and the presence of real or perceived unethical practices. Certainly, there is room to argue about most of these points. The profession is further encumbered by questionable institutionalized practices. For example, some practice consultants promote the policy of withholding administration of treatment on the first visit, preferring to reschedule the patient for a report of findings on a subsequent visit. Where is the clinical rationale for such practice? Are these doctors insufficiently skilled in interpreting the history and examination findings for a routine first visit without time to confer and study? Others promote the use of x-rays on nearly every patient in order to determine biomechanical deviations from a theoretical \"model\" of a normal spine implying that this information is so essential to successful treatment that the benefit outweighs the very real risk of radiation exposure [\n2\n]. These and other business practices promoted across the profession are tolerated without challenge by the rank and file. These practices degrade the credibility of the profession and its members as competent clinicians and diminish the public's trust and level of cultural authority. Considering these various threats to professional legitimacy, a new model is needed. Such a model will provide the chiropractic profession with common core values that permit the development and expansion of chiropractic as future evidence arises. A significant component of this new model must take into account accepted concepts of professional ethics.\nProfessional Ethics and Chiropractic Identity\nThis discussion occurs within the context of chiropractic as a licensed healthcare profession. The status of \"licensed healthcare profession\" confers upon the chiropractic profession certain privileges, but it also imposes upon it a specific set of expectations and ethical obligations. Professional ethics differ from the ethics of mercantilism. For the customer, the relationship with a merchant has always been governed by the dictum \ncaveat emptor \nor, let the buyer beware. Mercantilism demands that, for the merchant, pecuniary interests supersede others. Despite the fact that a chiropractic practice is typically a commercial, for-profit enterprise, the chiropractor is not governed by the dictates of mercantilism but rather by professionalism. Professions are so-called because they \"profess\" to have knowledge and skills beyond the comprehension of the laity. The theory of professionalism is predicated on this asymmetry of knowledge. Classically, the only professions were medicine, law, and the clergy, to which modern disciplines can be added, such as engineers, financial planners, etc. Hughes coined the expression \ncredat emptor\n, let the buyer have faith, to describe the special relationship professionals have with their patient, client or parishioner [\n3\n]. Thus, chiropractors, as health professionals, are expected to make recommendations that are in the best interest of the patient, superseding the doctor's pecuniary interests.\nAs a result of patients' ignorance concerning the specialized knowledge of the professional, the faith a patient places in his or her doctor must extend to the information they are given by their doctor. The imbalance in knowledge means that the doctor not only must not lie to a patient (the ethical duty of veracity) but also must take pains to ensure that what they tell the patient is the truth (the ethical duty of fidelity), as best as it can be known by the doctor and understood by the patient.\nAt first glance, avoiding a lie and telling the truth may appear to be synonymous but they are not. If one honestly believes a piece of information told to another, then one is not lying. However, if that information is in fact not valid, one has not lied but has told an untruth. Thus, the person has erroneously transmitted incorrect information. Transmission of false information, if correct information is reasonably available to the profession, is a violation of one's duty of fidelity. The duty of fidelity is, in part, to comply with the reasonable expectations of the patient including the expectation that information given is in fact valid.\nThe ethics of professionalism require not only veracity, but also fidelity. Neither a chiropractor nor any other healthcare provider practicing under the protection of a licensed profession has the ethical right to promote unscientifically unreasonable beliefs. The principle of fidelity and the state of scientific knowledge regarding certain historical chiropractic beliefs should not allow the expression of these beliefs to the patient as clinical truths.\nAfter D.D. Palmer founded chiropractic in 1895 his original body of work contained a number of postulates. Below, we will present an analysis of Palmer's Postulates. This analysis is not new and has been available to the whole profession. We do not regard this analysis as anything that should be regarded as controversial or contentious. It is merely an observation that conventional scientific methods should be applied to the principles of chiropractic. Despite the critical threats to the validity of this paradigm, a sizable proportion of the profession still holds these postulates to be valid [\n4\n]. The segment of the profession that continues to hold firmly to Palmer's Postulates do so only through a suspension of disbelief. Given that one of the philosophical pillars of science is skepticism, a suspension of disbelief or a lack of skepticism, is evidence of antiscientific thinking [\n5\n,\n6\n]. These stratagems to avoid the truth that Palmer's Postulates are unproven might be beneficial to the chiropractor, but are ethically suspect when they allow the practitioner to maintain a \"faith, confidence and belief\" in that paradigm to the patient's ultimate detriment.\nMisplaced Optimism\nOver the past two decades it has been possible to view the chiropractic profession and its prospects for advancement in an extremely optimistic light. Compared to the profession's first 85 years of existence, the period of time from, say, 1980 to 2000 saw what seemed to be an unbroken string of successes. This period saw the ongoing development of the first chiropractic scientific journal, the first evidence (through clinical trials) of effectiveness of spinal manipulation, a legal anti-trust victory over the institution of medicine in the USA (\nWilk v. AMA); \nan explosion in the number of students enrolled in chiropractic colleges, and the publication of a United States government report supporting the use of spinal manipulation for low back pain. In addition to these concrete developments the chiropractic profession benefited from the widely documented increase in interest and utilization of what has become known as complementary and alternative medicine (CAM) [\n7\n-\n9\n]. By the end of the century, as the result of these events and trends, the profession enjoyed a level of public acceptance (including that of other healthcare professions) that was unprecedented in its history. Some analysts of the healthcare system projected that by the year 2010 there would be over 100,000 chiropractors practicing in the United States alone [\n10\n,\n11\n]. It appears that reality will fall well short of that prediction.\nAs propitious as these developments appeared at the time, they have not secured the future of the chiropractic profession. A recent assessment by Richard Cooper MD, identified a variety of factors that threaten the future of chiropractic [\n12\n]. Dr. Cooper's analysis has captured the attention of many in the chiropractic profession and represents a realistic set of concerns, and calls for corrective action by the leadership of this profession.\nDuring this same period, the healthcare system as a whole has undergone profound scientific, regulatory, political and economic changes that impose new expectations and responsibilities on all healthcare providers. An unprecedented level of professional accountability, predictability, and consistency are expected from all healthcare professionals. The chiropractic profession of the 21\nst \nCentury is obligated to provide a mature, ethical, and moral response as it seeks to anchor its professional jurisdiction and cultural authority.\nInternal Confusion\nThe chiropractic profession is not currently prepared to effectively meet these challenges. More than 100 years after its origins, the chiropractic profession remains focused on the internal debate \"What is chiropractic?\" – a quandary shared by many other stakeholders in the healthcare system. Perhaps as testimony to some underlying strength of chiropractic, the profession has managed to survive in spite of its confused self-vision. The more important issue is the profound organizational weakness suggested by the century-old debate on fundamental identity. It is difficult to fault decision-makers within the healthcare industry for any reluctance to embrace chiropractic when they do not know what it is they are asked to embrace.\nThere is a lack of uniformity and consensus within the profession about the proper role of chiropractic. Depending upon whose point of view is solicited; chiropractors are subluxation-correctors, primary care physicians (PCP), neuromusculoskeletal (NMS) specialists, wellness practitioners, or holistic health specialists. Within each of these models there are many competing factions. While the many professional subgroups of medicine (pediatrics versus cosmetic surgery, for example) converge, at least in theory, on broad but common ideology and professional attributes, the same is not true among the more divergent chiropractic factions. The differing chiropractic schools of thought form competing professional models that are not mutually compatible. Moreover, the disparities are indefensible in the context of the scientific, regulatory, political and economic criteria under which healthcare delivery is expected to operate. A number of models are impractical, implausible or even indefensible from a purely scientific point of view (e.g., subluxation-based healthcare), from a professional practice perspective (e.g., the primary care model), or simply from common sense (e.g. Innate Intelligence as an operational system for influencing health).\nPart II: The Failed Identities of Chiropractic\nThe \"ACC Paradigm\" document developed by the Association of Chiropractic Colleges in 1996 currently represents the closest thing to an official consensus of chiropractic identity [\n13\n]. This paradigm was formed by consensus among the 16 presidents of the member ACC institutions – a group generally believed to hold divergent beliefs and interests. We respectfully submit that this widely disseminated document does not fulfill the criteria outlined above. While perhaps a political triumph (getting all the presidents to sign on to the same document), it contributes little to the understanding of the profession's role in modern healthcare delivery by the relevant stakeholders. It is interesting that two major sources of contentious debate, the terms \"subluxation\" and \"diagnosis,\" are both used in the same document. Even in that context, the reader may be left with a feeling of internal tension between them. It is otherwise a recitation of the trivial (the purpose of chiropractic is to optimize health), the obvious (doctors of chiropractic establish a doctor/patient relationship and utilize adjustive and other clinical procedures unique to the chiropractic discipline.), and of the tautological ([chiropractors]...employ the education, knowledge, diagnostic skill, and clinical judgment necessary to determine appropriate chiropractic care and management.) Experience with healthcare decision-makers at both the local and federal levels makes it appear highly unlikely that the ACC Paradigm will prove useful when these decision-makers assess the practical role of the profession.\nThe chiropractic profession has succeeded in a number of important ways. Foremost, it has provided an effective and much needed healthcare service; that is, the conservative management of common musculoskeletal disorders in a population of patients who would otherwise be less well treated. It has devoted its resources in creating a sizable infrastructure of schools, publications, research centers, and scientific conferences. It has succeeded in providing economically viable careers for tens of thousands of individual chiropractors. Inroads have been made in policy-making arenas and in efforts to train its members in practice protocols to facilitate a stronger interface with payers and policy makers. Interdisciplinary training has begun to establish a cadre of qualified clinical and fundamental scientists with a chiropractic background. Chiropractic has succeeded in transforming itself from a marginal discipline into one that has an opportunity (if it acts wisely) to become an integral part of the healthcare system.\nThe basic premise of this paper is that existing institutions within chiropractic have not expressed a model of chiropractic that empowers the granting of cultural authority, sustained economic viability, and scientific integrity. There are two particular perspectives we believe are at odds with the seven criteria outlined above: 1. The philosophical model and 2. The primary care model. In order to effectively make a case for the Spine Care model that we propose, we must first directly address these two differing points of view.\nThe Philosophical Model of Chiropractic\nThe word \"philosophy\" is a much used but much misunderstood term within chiropractic. Most of the time those who invoke a \"philosophical\" argument are using the term in its colloquial sense: \"I believe in a traditional set of chiropractic beliefs (chiropractic philosophy).\" This set of beliefs is probably more correctly described as the ideology of chiropractic or the hypothesis of chiropractic, rather than as a philosophy.\nThis model of chiropractic has continued to advance a hypothetical model of health and disease divergent from other (particularly mainstream) modes of thought among the health professions. Indeed, some aspects of the hypothesis are now known to be at odds with scientific fact. To what extent can this chiropractic hypothesis be credited with the past successes of the profession? We argue that it is incorrect to interpret the success of the chiropractic profession as evidence of the validity of this chiropractic hypothesis. The profession has recorded limited successes in spite of what is largely the failure of this hypothesis.\nWhat is the Chiropractic Hypothesis?\nBefore going further it is necessary to specify exactly what is meant by the \nchiropractic hypothesis\n. While there are an abundance and variety of competing versions of this hypothesis, all of which are ferociously defended by their adherents, it is still possible to identify several principles that are both common to the majority of these, and distinct from other healing systems. These principles are:\n1. There is a fundamental and important relationship (mediated through the nervous system) between the spine and health.\n2. Mechanical and functional disorders of the spine (subluxation) can degrade health.\n3. Correction of the spinal disorders (adjustments) may bring about a restoration of health.\nFor the purpose of this discussion, these three principles will be referred to as Palmer's Postulates. There are a variety of different ways in which these postulates are expressed. The structure/function metaphor is often invoked – alterations of the body's structural components will result in functional aberrations and disease. Others emphasize the neurological aspect, the spine being both the source of noxious neurological stimuli and the locus of therapy where treatment can be administered to correct such stimuli.\nBut in the end, all of these modes of expression converge on essentially the same end point. That is the concept that the spine is not just another conglomeration of bone and muscle like the shoulder or the knee. Rather, it occupies a unique and privileged position in the makeup of the human body, representing both a vulnerability to our health and also a means of achieving optimal health. Expressions of Palmer's Postulates are ubiquitous within the profession and are not confined to extreme or narrow elements of the profession. These principles are to be found in some form in the mission statements of every North American chiropractic college and in the curricula of those colleges. They are further embodied in the ACC Paradigm paper. With the understanding that there is a great deal of room for qualification, clarification, and interpretation, we believe that Palmer's postulates do capture the essential hypothetical premise of chiropractic, and it is an error to underestimate the degree to which this theoretical model continues to define chiropractic. Even in the context of chiropractic research, where you might not expect a great deal of sympathy for these ideologies, Palmer's Postulates continue to guide the research priorities and agenda in the chiropractic profession.\nWe must also consider the concept of vitalism (in chiropractic, Innate Intelligence) as a component of Palmer's Postulates. Although there is a long historical legacy of vitalism, and although it continues to be a feature within many contemporary belief systems, there really can be no compromise on its inclusion as a defining principle of chiropractic. It was precisely the rejection of vitalism in the 18\nth \nCentury and the emerging understanding (through the invention of the microscope and other technological advances) of biological mechanisms that marks one of the watershed moments in the evolution of science. Chiropractic can choose to retain its vitalistic component only if it chooses to operate completely outside the scientific healthcare community. Vitalism does not require any further or more extensive analysis before rejecting it. To reject vitalism is to simply to announce that one accepts the conventional view of biology similar to the way one accepts the convention view of cosmology by rejecting a geocentric universe. In making this categorical rejection of vitalism one important distinction is necessary. While vitalism is incompatible with a valid professional model of chiropractic, it is not incompatible with an individual chiropractor's professional beliefs. An individual physician of any type may have religious convictions that inform their professional lives, and yet these convictions remain totally outside the domain of the professions' common identity. Similarly, an individual chiropractors belief (or non-belief) in vitalism can be considered to be entirely a personal matter so long as these beliefs do not distort the discharge of professional duties and obligations.\nA distinction can be drawn between the \"classical vitalism\" described above and a \"modern vitalism\" that can be accommodated by conventional biomedical science. This modern vitalism is best described by the phrase \nvis medicatrix naturae \n– the healing power of nature. The truth of this proposition is indisputable. Nature, or more specifically, the body's natural healing mechanisms, is the principle mechanism by which any healing process occurs. Without these natural mechanisms (our immune system, our wound healing capacity, and countless other regulatory and corrective systems) life itself is barely possible.\nThis modern vitalism can also serve as a useful and valid guiding clinical principle. It implies, correctly, that these natural healing systems should be given every opportunity to operate with minimal interference by outside agencies, including by chiropractors. This sort of therapeutic minimalism is, in fact, an important part of model that we will propose.\nWe have asserted that Palmer's Postulates have failed. To understand our assertion, please first consider the nature of a scientific theory. A theory is an explanation. It is an effort to explain and make understandable a set of observations or facts that are otherwise confusing, paradoxical, or self-contradictory in some way, and for which our existing theoretical understanding offers an inadequate explanation. Implicitly, every theory is an answer to the question, \"Why is it that...?\" or, \"How could it be that...?\" A theory should be a solution to a puzzle. If a theory is sound it will solve the puzzle and also accurately predict as yet unobserved phenomena, thus increasing our ability to understand and manipulate our world. For example:\n• William Jenner's theory of acquired immunity provides an explanation for the observation that milkmaids with cowpox scars do not contract smallpox.\n• John Snow's theory of cholera transmission answers the question, \"Why did almost everyone who drank from the Broad Street well contract cholera, and those who drank from other water sources did not?\"\n• Barry Marshall's theory of the infectious nature of ulcers answers, \"Why does the occurrence of peptic ulcers, thought to be a psychogenic disease, very closely resemble that of infectious diseases?\"\nWhen looking at these and other successful theories, there are some important common elements:\n• In each case, there was a riddle to be solved, a set of unexplained facts. The theories did not arise out of a vacuum. They arose out of the necessity to explain some new observations.\n• The observations were accurate. The phenomena that Jenner, Snow, and Marshall were trying to explain were real. They had correctly perceived and recorded events in their world. For great scientists, observation implies a deliberate, systematic, and disciplined process, and not simply the casual perceptions of our surroundings and experiences.\n• The observations could not be explained by existing theory. Each of the sets of observations described above were either at odds with our existing understanding of the world or simply not taken into account by other theories.\n• All have survived repeated experimental test.\nWhen one examines Palmer's Postulates in this light, their limitations become obvious. First, we need to ask what phenomena, exactly, are these postulates trying to explain? Particularly with respect to the first postulate that establishes the relationship between the spine and health, what observations gave rise to this hypothesis? Is there some set of facts or observations that cannot be understood without the insight provided by the postulates? D.D. Palmer might state that he was trying to explain why a deaf man with a vertebral misalignment recovered his hearing following re-alignment of that vertebra. However, there is no evidence that Palmer undertook any sort of systematic exploration of the spine/health relationship following his epiphany. What we know about D.D. Palmer suggests that patient and disciplined observation was not his forte. His method of discovery was by inspiration and revelation.\nSubsequent generations of chiropractors might say that Palmer's Postulates are required to explain why there are so many healthy, happy, satisfied, apparently healed chiropractic patients. But there is nothing puzzling or mysterious about doctors having content patients – all healing systems from Ayurveda to chiropractic to medicine to therapeutic touch can make such claims. The power of natural history, regression to the mean, and non-specific treatment effects guarantee such results and unless one sets out to deliberately harm patients, it's difficult to avoid having satisfied and improved patients. Recovered patients are the inevitable consequence of having patients and no insight is gained into the validity of any of these healing systems by observing this fact.\nThe problem, simply, is that there is no need for Palmer's Postulates. There never has been a set of facts or phenomena concerning the relationship between the spine and health that require Palmer's postulates to understand them. The spine/health theory does not rest on any foundation of careful, comprehensive, and reliable observational data.\nTo illustrate this absence, the sort of observations that would require the explanations of Palmer's Postulates might look something like this:\n• The observations that most persons with idiopathic scoliosis suffer from a wide range of diseases that non-scoliotics do not.\n• The observation that persons with a specific spinal characteristic suffer inordinately from a particular health problem.\n• The observation that back pain predictably results from certain postural defects.\nThe problem is that none of these observations, or any similar, are known to be true. Where evidence exists on these questions it points mostly in a direction the opposite of Palmer's Postulates. The real paradoxes and riddles are questions like, \"Why is it that a scoliotic, osteophytic, degenerated spine with asymmetrical facets and collapsed discs can so often result in no clinical problems?\" Or, conversely, why is it that someone with no identifiable anatomic spinal disorder can suffer from low-back disability. A disinterested party, dispassionately examining the evidence available today regarding the relationship between the spine and health, or the structure/function relationship, would arrive at the following conclusion:\nThe human organism is highly resilient and broadly adaptable to a wide range of structural imperfections, and it is only after a rather high threshold of deformity is surpassed, that function is degraded\n.\nThe Primary Care Model of Chiropractic\nThe other great divide within chiropractic concerns the question of whether or not chiropractic is a primary care profession. Unfortunately, just as the word \"philosophy\" is routinely misused, so is the concept of \"primary care.\" Paradoxically, even the extremes of the profession on the philosophy question (e.g., Sherman College and National University) both endorse the notion of chiropractic as a primary care profession. This agreement does not suggest that chiropractic, as primary care is a valid and compelling concept. Rather, it suggests that the concept has been unexamined and hastily adopted. This section will examine the meaning of primary care as it applies to chiropractic.\nWhat is Primary Care?\nThere are several definitions of primary care physicians (PCP), but possibly the most accepted is the definition provided by the Institute of Medicine in a 1996 report. It defines primary care as, \"the provision of integrated, accessible, health care services by clinicians who are accountable for addressing a large majority of personal health care needs, developing a sustained partnership with patients, and practicing in the context of the family and the community [\n14\n].\" The essence of the IOM definition, as well as others, is of a primary care physician as a generalist and not a specialist. This is most easily illustrated by the prototypical examples of PCPs as identified in the IOM report: family practitioners, pediatricians and internists. The report also identifies nurse practitioners and physician assistants who are specifically trained in providing primary care.\nIn each of these examples, the PCP provider sees a wide range of complaints (respiratory, cardiovascular, gastrointestinal, and musculoskeletal) within the specified patient population, treats most of these complaints directly, and refers the rest as appropriate. Even in the more limited primary care professions (nurse practitioner, physician assistant) the generalist theme is also fundamental to defining their practice. These practitioners provide more limited care than medical PCPs and act more in a triage capacity than in a therapeutic capacity depending on complexity of the case. But there is general agreement that these providers fit the primary care model when they opt for the generalist practice.\nTo what extent do chiropractors satisfy the generalist model? Not at all, as it turns out. The most obvious index of this is the chiropractic patient population. In the last decade there have been many studies, surveys, and analyses that have described and characterized the chiropractic patient population [\n15\n-\n21\n]. These studies all reach the same conclusion: the chiropractic patient population consists, almost in its entirety, of persons with musculoskeletal pain complaints, the overwhelming majority of which are spine related. A small subset, approximately 5%, of patients have headache as a primary complaint. Any reasonable estimate would place the percentage of chiropractic patients with somatic pain at >95%. Most of the balance of patients receive some sort of \"maintenance\" or \"wellness\" care. A very small number (<1%) have complaints that fall outside these categories.\nIt might be argued that the make-up of chiropractic patient population simply represents a cultural and historical artifact; that the public has not been educated as to the suitability of chiropractors as PCPs and it's simply a question of providing proper education to the public on this matter. The fundamental limitations imposed by the profession upon itself make this argument implausible.\nThe first limitation is therapeutic. By intent, chiropractic has limited its therapeutic armamentarium to manual and physical techniques. This limited set of therapies is well suited to the set of complaints normally seen by and successfully treated by chiropractors. This limited set of therapies also offers the advantage of a very low risk of harm. However, this limited set of effective services is poorly suited for providing primary care. Beyond musculoskeletal conditions, there are very few conditions for which manual therapies provide optimal effectiveness. The vast majority of human health problems that require an intervention do not fall within the chiropractic therapeutic spectrum. Chiropractic cannot simultaneously retain its limited set of therapies and pursue primary care status.\nIt might be argued that even with its therapeutic limitations chiropractic could provide the services of a diagnostic generalist and make therapeutic referrals as needed. However, the defining characteristic of any diagnostic generalist is a rigorous training and experience with the spectrum of disorders likely to be encountered. Any intellectually honest analysis of this question will not support the supposition that chiropractic training provides such rigor in this domain. The length, breadth, and depth of chiropractic clinical training do not support the claim of broad diagnostic competency required of a PCP. Studies of chiropractic intern clinical experience provides no evidence that chiropractors are trained to a level of a diagnostic generalist for non-musculoskeletal conditions [\n22\n,\n23\n]. For chiropractors to describe themselves as PCP diagnosticians is to invite comparisons to other PC diagnosticians, i.e., family practitioners, pediatricians and internists. Such comparisons will not reflect favorably on chiropractic.\nFinally, it might be argued that although the chiropractic profession is not currently trained to provide PCP care, it \ncould \nbe and we should set ourselves to the goal of making this happen. If a chiropractor as PCP is not at this moment a reality, we can imagine a different reality in the future in which the Chiropractor/PCP model made sense. What would have to change for this reality to come true? At a minimum, the following:\n1. Chiropractic would have to dramatically increase the length, breadth and depth of its clinical education at all its accredited institutions.\n2. Chiropractic would have to develop an acceptable solution to its therapeutic limitations, either through changes in state licensure or by some as yet unidentified process.\n3. Chiropractic would have to demonstrate its ability to deliver safe and effective care beyond its current model.\n4. Having achieved goals 1-3, the chiropractic profession would have to change the view of the public and other health professions of chiropractors as back doctors.\n5. And finally, the profession would have to convince the healthcare marketplace (in which there is no current or anticipated shortage of PCPs) that there is some point to expanding the number of PCPs.\nThese events do not appear to be likely to occur in the near future.\nPart III: The Spine Care Model\nIn the course of discussions among the authors of this paper as well as others who were involved in the process, it became clear that there were many points of consensus. These consensus points are listed below in the approximate order of their importance to the model.\n• Chiropractic as an NMS specialty, with particular emphasis on the spine.\n• Chiropractic as a portal of entry (POE) physician/provider.\n• Chiropractic as a willing and contributing part of the evidence based healthcare (EBHC) movement.\n• Chiropractic as conservative/minimalist healthcare provider.\n• Chiropractic as a fully integrated part of the healthcare system, rather than as an alternative and competing healthcare system.\nIncorporating all of the above elements, chiropractic should actively market itself to the public and to the rest of the healthcare system in a sober and moderate fashion, and with a message that is completely compatible with current social, economic, political, and scientific realities. The balance of this paper will be devoted to examining these issues.\nThe Dental Model\nAs a start to defining the model it is helpful to find another profession with analogous clinical jurisdiction e.g. focused practice emphasis on a region or set of problems, limited therapeutic regimen, and broad public identification with a selected role in healthcare. We believe the dental profession is a practical and successful parallel. Consider the advantages of the dental model:\n• Dentists and dental surgeons have established themselves as the absolute, undisputed authorities in tooth care, a critical and essential component of human health, and a contributor to care for orofacial disorders generally. No one suggests they should not be portal of entry providers. No other profession considers usurping the role as tooth-care expert.\n• In the public's perception, dentists are among the most highly esteemed of the healthcare professions.\n• Dentists are recognised with the title \"doctor\" and reap the social, professional and financial benefits of their reputation and training.\n• Dentists, though primarily focused on the dental anatomy and disease, are also expected to understand differential diagnosis of conditions related to their area of focus.\n• The services that dentists provide, focused though they are to tooth, gums, and mouth, are of immense benefit to the health and well being of the public.\nAs this model unfolds, this is the image we might want to keep in mind – chiropractors as dentists of the back.\nThe Vocational Role of Chiropractic: Treatment of Back Pain\nThe purpose of this essay is to define chiropractic as a \nprofession\n. The term is emphasized because it is necessary to remind ourselves what this means and what are the consequences of being a profession. A profession is not defined by a set of ideas and values. Professions may have ideas and values, but these are not what distinguish or differentiate them as professions. Those organizations that are defined by ideas and values are entities like political parties, ideologies, religions, or organizations devoted to narrow issues like pro-life or pro-choice organizations. For such organizations, it is correct to state that the idea comes first, and everything else – strategy, tactics, etc. – flows from the question: what will best promote our idea?\nA profession is about a specific vocational role that the profession fills. A profession is defined by the work it does and the role it fills, not by its ideas and values [\n24\n]. The ideas and values of a profession must be secondary – they exist to answer the question: \"How can we best discharge our designated role in society?\" Professions do not or should not exist to be champions of ideas. This is most specifically true of the licensed professions. Society grants a license, a franchise, to a profession, not so that profession can champion its ideals, but because society wants some specific work done and it feels that granting a franchise is the best way to do it. This social contract is quite explicit. In most cases the vocational role of professions is quite obvious and can be stated in a few syllables:\n• Tooth and gum care.\n• Design and engineering of buildings.\n• Measurement of financial performance.\n• Legal services.\nThis simple and coherent vocational role is what the chiropractic profession seems to have so much difficulty in defining, and what the ACC paradigm fails to provide. Among the reasons for this failure is that chiropractic has always been confused about the concept of a profession and has tended to view itself a champion of ideas rather than as a provider of service. This confusion is perhaps understandable in an historical context. Chiropractic didn't begin as a profession; it began as an idea or set of ideas (vitalism, subluxation). Palmer and company were champions of these ideas, competing with charlatans and learned (not scientific) professional rivals for status. Over the decades, the institutions and each individual chiropractor saw themselves as a champion of the chiropractic idea.\nBut, at some point over the last 100 years, and unbeknownst to the individuals and institutions of chiropractic, it became a profession with a specific vocational role. As these thousands of chiropractors over the decades were advancing the ideals of the profession through manipulation of the spine, the public, which is largely disinterested in the ideas, decided that chiropractic had a professional role to fill. Thus, creating the profession as it exists today.\nThe irony is that the specific professional/vocational role that chiropractic fills is obvious to the majority of patients and other non-chiropractors – it is chiropractors themselves who seem to be confused by the issue and who then provide confounding answers and contradictory testimony to policy makers. For all other mainstream healthcare professions it is easy to provide a straightforward answer to this question of role. Whether it is an optometrist, a pediatrician, a dentist, a family medical practitioner, or a psychologist, each has clinical domain that is essentially self-evident. For all other PCPs, and POE (point of entry) providers there is a relatively clearly defined patient population for whom the practitioner is an appropriate provider. This patient population may be defined by age, gender, and most importantly, by nature of healthcare problem or complaint. There may be some disagreement among various professions at the margins of this question, but only at the margins.\nA somewhat different state of affairs obtains for those health professionals whose clinical purpose is not defined by a patient population, but by a specific technique or skill. For example, consider a general surgeon, pathologist or radiologist. The potential patient population of these providers is virtually everyone, as a function of their specific need for the service. To some this might seem an attractive model for chiropractic – our patient population is everyone who needs spinal correction, which is to say, everyone. In fact chiropractic has attempted this by defining itself in metaphysical terms (Innate Intelligence), as a technique (chiropractic adjustment), and as an ideology (Palmer's Postulates), rather than as a provider of specific clinical services. The failure of this approach is in fact the genesis of this paper. To define the clinical purpose of chiropractic, it is necessary only to observe what chiropractors actually do and for what purposes patients seek care from doctors of chiropractic: the provision of portal-of-entry care for the diagnosis and management of back pain, neck pain, and related disorders. In the shorthand that the public might use, chiropractors are back doctors. Restating some of the earlier points, this conclusion is based on these facts:\n• The population – Over 90% of chiropractic patients seek care for back-related problems.\n• The evidence – Clinical science provides a body of evidence for the effectiveness of chiropractic care for back pain, neck pain, and headache.\n• The education and training – Chiropractic clinical education and training are focused almost exclusively on the conservative treatment of spine complaints.\n• The public identity – The public perception of chiropractic is that of a back pain specialist and nearly a total rejection of an alternate role.\n• The competition – The legitimate professional claim for chiropractic in the remainder of healthcare and public policy lies strictly within the domain of back- related pain outside the bounds of medical emergency.\n• The claim of professional jurisdiction – Credibility for the claim, either diagnostically or therapeutically, for a broader role beyond the realm of this definition is lacking.\nShould the chiropractic profession concern itself with what others think? It should, must and had certainly better do so as it is reliant upon its consumers for its existence. A profession \nis \na public trust. The privileges accorded to a member of a profession are in direct exchange for professional members' service to the public. It is nonsensical to organize a profession in terms that are at odds with the public's perceptions of its interests unless a compelling and persuasive argument can be made that the public's perception is not in their best interest and is amenable to change. We maintain that there is no such argument. In fact, efforts to launch such a campaign have failed. For example, two recent public relations efforts have been attempted by chiropractic organizations. These efforts were preceded and followed by measure of the public attitudes toward the profession. In both cases, efforts to convince healthcare consumers about the role of subluxation in their lives backfired miserably. Not only were few persons encouraged to consult a chiropractor, but, the number of skeptics was increased and more respondents stated that they would seek a medical consultation first following the PR effort than before the campaign. The argument that the public can be persuaded to understand and accept the subluxation model of chiropractic has been tested and it has failed.\nFinding a substantial presence within the healthcare marketplace is well satisfied by the spinal care model. A recent analysis of healthcare and productivity costs associated with specific complaints reveals the following:[\n25\n]\n• Three of the top 10 conditions suffered by the US population (in terms of costs) are back pain related.\n• Collectively, the annual rate of back pain-related healthcare episodes is 157 episodes per 1000 covered lives, making it the single most common complaint.\n• Collectively, the annual direct healthcare cost for back pain is US $122 per person, second only to the cost of managing angina pectoris.\n• Collectively the annual average cost of payment for lost work and short-term disability is US $87 per person, making back pain the most costly of all diagnostic categories in disability-related costs.\nIt should be noted that while some of these back pain episodes are undoubtedly not chiropractic cases (that is, they are legitimate in-patient or surgical cases) almost all are. Conservatively, at least 75% of this spine care patients potentially stand to benefit from chiropractic care, compared to the 12-17% who currently avail themselves of the services. This study, and many others, provides ample evidence that the clinical domain of back pain provides an enormous potential patient base and subsequent economic base for chiropractic.\nThus, the logic of the chiropractor as spinal care doctor proceeds as follows. First, chiropractors are \nde facto \nback pain/spine doctors seeing a limited proportion of the population, today. That is, as chiropractic is currently practiced (even given the confused message that chiropractic projects) it is entirely dependent on back pain/spine care for its economic survival. Second, the back pain market is enormous and can provide, by itself, a sufficient patient base to support the entire profession. Third, expansion of the chiropractic market share for spine-related symptoms is hindered primarily by a lack of credibility of its claims and the resistance that this lack generates among consumers and policy makers. Fourth, chiropractic has the most clinical training, expertise, and demonstrated clinical effectiveness as conservative back pain/spine doctors. Fifth, chiropractic as a spinal care specialty is the only basis on which the profession is understood and accepted by those outside the profession. Sixth, there is nothing to be lost, either in the short or long term by adopting this strategy. The state of mind regarding the profession that we would like to make is: \nGo to a DC for your spinal health and prevention as you would go to your dentist for your dental health and prevention\n. We reemphasize that there is nothing to be lost, either in the short or long term, by adopting this strategy. This model of chiropractic as the spinal care profession is in no way intended to preclude the patient population of extra-spinal musculoskeletal complaints. However there are several reasons why we feel it is reasonable to de-emphasize, relative to spinal care, this patient population.\n1. It represents a very small percentage (<5%) of the current chiropractic patient population.\n2. There is very little evidence of effectiveness of chiropractic care for this population and it is unlikely that a sufficient number of these patients present for care in order to conduct appropriate studies in a reasonable and timely manner.\n3. It is unclear what advantage(s) chiropractic care might offer relative to other providers (physical therapists, rheumatologists, etc.) for care of these problems.\n4. It is likely, with today's knowledge, that the proportion of extra-spinal MS patients for whom conservative manual therapy is the optimal approach is significantly less than is the case for spinal conditions.\n5. There is far less public awareness or willingness (as reflected the utilization of services) of chiropractic as a provider of care for these conditions.\nPortal of Entry Status\nWe suspect that among some chiropractors there is confusion about the two terms \"primary care,\" and \"portal of entry,\" and that this confusion is at least partially responsible for the enthusiasm for the primary care model. The American Chiropractic Association, in fact, uses both terms to describe the profession [\n26\n,\n27\n]. However, primary care, as discussed above, describes a generalist provider, while a portal of entry (POE) describes a health care provider who may practice autonomously and to whom the public has direct access. The confusion lies in the belief that in order to achieve portal of entry status one must first be a primary care provider. A primary care physician is certainly a portal of entry provider, but one need not be the former to be the latter. The examples of dentistry, optometry, and clinical psychology illustrate this point.\nOn this question there is virtual unanimity in the chiropractic profession and the logic of chiropractors as portal of entry providers is obvious to all but the most vociferous opponents of the profession. The POE status of chiropractic is guaranteed in all the 50 American states as well as in most countries outside the US where chiropractic is licensed. There is no credible case that can be made that in some manner the public will be better served by requiring them to go through a gatekeeper (presumably an MD) to seek care from a chiropractor. The primary impediment to full implementation of portal of entry status is not a regulatory or a statutory problem, but a problem of inter-professional trust. Within specific health care delivery and financing systems there are gatekeeper provisions that require patients to be referred for chiropractic care. These gatekeeper arrangements arise either through concern of improper diagnostic workup and clinical decision-making, or through concerns of utilization abuse. While the fairness and appropriateness of these gatekeeper requirements is certainly in doubt, the surest way for the profession to protect and expand its POE status is to establish the cultural authority, and thus, the trust, that will make these gatekeeper provisions unthinkable.\nThe Acceptance of Evidence-Based Healthcare\nFifteen years ago, the editor of the \nNew England Journal of Medicine\n, Arnold Relman, MD, wrote an editorial in which he announced that healthcare had entered a new age, The Age of Accountability [\n28\n]. What he was describing is what we now call Evidence-Based Healthcare (EBHC). During the same period of time in which the CAM revolution was taking place, a second less visible revolution was also taking place – the establishment and application of the principles of EBHC.\nEvidence-based healthcare is often ill defined, misunderstood, and a basis for concern or even fear by health-care providers. One of the best definitions we have seen appeared in an editorial in the \nBritish Medical Journal \nin 1996 written by some of the most prominent educators in EBHC, David Sackett and his colleagues [\n29\n]. They defined EBHC as the conscientious, explicit and judicious use of current best external scientific evidence in making decisions about the care of patients. EBHC does not mean that individual clinical experience is of limited or no value; on the contrary, EBHC offers advice on how to maximize the clinical expertise and combine that with the best available external scientific evidence that usually comes from systematic reviews and evidence-based clinical guidelines. Another important aspect of EBHC is the identification and incorporation of informed patient preferences.\nThe concern and fear that many health-care providers have is that EBHC will be misused by healthcare policymakers and health insurance companies to curtail the cost and limit reimbursements. Such policies would be inconsistent with the fundamental principles of EBHC. Clinicians who practice EBHC will develop the skills to identify and apply one or a combination of the most efficacious treatments, which if based on the individual patient profile will tend to maximize the benefit and minimize the risk. This may sometimes raise rather than lower the cost of their care. EBHC is not about proof or certainty. It is a method of dealing with uncertainty. It is about weighing the evidence and weighing alternatives.\nThere is one additional element of EBHC that requires amplification. It is important to understand EBHC does not mean care should be withheld if there is no proof of efficacy from systematic reviews or meta-analyses of randomized clinical trials. Absence of evidence of treatment efficacy does not equate with evidence of its absence. Such a standard would produce therapeutic paralysis. For example, there are virtually no clinical studies, chiropractic or otherwise, that have evaluated the effectiveness of treatment for thoracic spine pain. Obviously it is not reasonable to send a thoracic spine patient home with the apology, \"Sorry, can't treat you – no evidence of efficacy.\" It is however essential that clinicians understand that evidence ranges from the weakest (clinical experience or expert opinion) to the strongest (high quality systematic reviews of all available relevant scientific studies). Many different systems for grading the evidence and making recommendations currently exist, and major efforts are underway internationally to standardize this process.\nThe Role of Clinical Experience in EBHC\nThe central premise of EBHC is that even the most well thought out, tightly reasoned, and scientifically plausible treatment regimen may not produce benefit to the patient. The scientific literature is overflowing with examples of commonly used treatment procedures or regimens which were based on sound pathophysiologic principles, but were ultimately found to be of no benefit or even harmful to the patient [\n30\n-\n33\n]. For the chiropractic profession the lesson is obvious. Whether its Palmer's Postulates or any of its innumerable variations (in the form of proprietary techniques) the chiropractic profession cannot predicate its clinical validity upon untested theories.\nEBHC principles state that healthcare providers need to combine their clinical expertise with the best available external evidence and that neither alone is sufficient. The most difficult and counter-intuitive notion for clinicians to accept is that their everyday experience of satisfied and seemingly recovered patients is not evidence of clinical effectiveness. There are several competing explanations for this apparent success. Many of the conditions treated by chiropractors, such as back pain, neck pain and headache, have a self-limiting natural history although they may be recurrent. The nonspecific placebo effect of the doctor-patient relationship explains many of the results attributed to specific interventions. Clinicians notoriously have selective memories and tend to recall success stories and generalize from those. The lack of systematic and standardized recording of diagnoses and clinical outcomes that could be gathered in databases and summarized objectively prevents clinicians from having an unbiased knowledge of the effect of their therapeutic efforts. EBHC recognizes the limitations and inherent unreliability of uncontrolled clinical observations and impressions and the inevitability of mistaken conclusions based on those uncontrolled observations. EBHC stresses the importance of outcomes-based clinical research, of regularly consulting the scientific literature, of optimizing the clinical skills of healthcare providers, and taking patients preferences into account.\nAs a practical matter, many chiropractors, and medical physicians as well, fear that EBHC will result in a change and possible limitation of their individual clinical prerogatives. They are correct in this conclusion. It is in fact the precise purpose of EBHC to help define what constitutes best practices-different from what would be the case if individual providers were given free reign to continue with their habitual practice behavior based exclusively on clinical experience.\nIt is also important to recognize that EBHC is in its infancy. The processes of EBHC will continue to accelerate in the future. When there is enough evidence to justify it, relative to a particular condition, we see the development of \"disease management\" programs. Disease management represents nothing more than a highly evolved implementation of EBHC. When there is sufficient evidence available, it becomes possible to implement very specifically defined (and also, very effective) treatment protocols that take into account important differences in prognostic factors among patients. These programs already exist for congestive heart failure, asthma, urinary tract infections, diabetes and other common illnesses. It is currently not feasible but only a matter of time before disease management of back pain, for example, becomes possible and necessary. If the chiropractic profession hopes to make progress within the healthcare mainstream, it must go out of its way to be clear that it understands EBHC, that it embraces its principles, and that it is acting to advance its implementation.\nConservative/Minimalist Healthcare\nOne of the general truths revealed through the application of EBHC is that less is often more in healthcare. There are countless examples where clinical studies have shown that providing less healthcare, doing fewer procedures, taking a more conservative approach, even doing nothing, is superior to a more aggressive approach. This idea has always been understood at some level (it is the premise behind the \"First, do no harm,\" doctrine), but it has been difficult for our healthcare system to act on the idea. Most incentives, economic and otherwise, propel care in the direction of more, rather than of less.\nChiropractic has a considerable advantage when it comes to implementing the doctrine of \"First, do no harm.\" The scientific literature strongly supports the finding that chiropractic, and specifically, spinal manipulation, is generally safe. The evidence regarding spinal manipulation indicates that the incidence of serious injury is, if not trivial, extremely low. Of the more common adverse effects resulting from spinal manipulation, nearly all are transient and minor. Overall, the safety profile of spinal manipulation is excellent and more so when compared to other treatment options.\nThrough historical precedent, by intent and by design chiropractic has evolved using a conservative therapeutic regimen consisting of manual and physical therapies as well as exercise. The clinical effectiveness of this approach has been established, the safety profile is excellent and there are distinct cost advantages to this approach when used appropriately. We see no reason to change the therapeutic scope of chiropractic. It should be understood that this is a contingent position. It is contingent upon the continued clinical effectiveness and superior safety profile of these conservative modalities relative to other more aggressive interventions, particularly medication and surgery. None of these therapies, conservative or otherwise, will remain static and as they are improved upon in the future their relative merits may change as well. Chiropractic's allegiance to a conservative therapeutic regimen is valid only as long as it remains a clinically and economically sensible thing to do.\nIn order to fully exploit the advantages of its current conservative approach the chiropractic profession must take active measures to curb abuses that run counter to this approach. There is a long tradition in the profession of promoting the idea that the unadjusted spine is an invitation to disease. There are practice management procedures that attempt to maximize the number of patient visits that can be extracted from each new patient. There is nothing conservative about a treatment regimen of 3-times-a-week, forever. There is a commonly expressed notion among the public and among other health professionals that chiropractic treatment is open-ended and often never-ending. By these and other similar offenses, chiropractic has surrendered the high ground when it comes to delivering conservative healthcare. Using its current set of conservative therapies and incorporating the best published data, chiropractic can make a credible case that it offers the best combination of safety, effectiveness and cost for the management of back pain.\nIntegration\nThe spine care model will facilitate integration of the chiropractic profession into the mainstream of healthcare. Integration offers substantial advantages toward addressing professional values and resolving the concerns outlined in the beginning of this essay. It is the primary vehicle by which cultural authority can be anchored for its competencies currently supported in the scientific literature. Integration brings with it a greater responsibility, but also brings the resources and patient access necessary to answer the core issues common to all chiropractic ideological debates.\nChiropractic has operated a parallel tract of professionalization since its inception. As Abbott observed, parallel development is associated with significantly greater obstacles and opposition than a profession that evolves as a branch from common roots [\n24\n]. While there is much accomplishment to appreciate, the profession continues to be hindered by limited resources for its stability and advancement. While at least partial acceptance and licensure has been achieved in many countries, many challenges remain before the profession can establish its reputation of competence and legitimacy necessary for full cultural authority. In modern society, training and licensure is no longer sufficient to demonstrate competence. That requires continued validation, which, in turn, requires credible data and a coherent identity. Legitimacy is eroded if practice patterns are tied to reimbursement, profit margin, or professional rivalry.\nPerhaps the most fundamental question that the chiropractic profession must answer to finalize its cultural authority is: \"Does the chiropractic profession continue to position itself in opposition to orthodox medicine, or does it stand as an advocate of the patient's best interests, as a part of mainstream healthcare, along with medicine?\" To date, the chiropractic profession has enjoyed the ability to evade that decision, occupying an ambiguous position between opposition of medicine and full participation in the mainstream. The profession and its members have often used marketing methods offering an alternative to medicine. At the same time, political activism in the USA has yielded many of the benefits of the mainstream through participation in the private third-party payment system, in Medicare and a variety of other state-sponsored programs, as well as inclusion in student loan programs and in the Veterans Administration and Defense Department programs.\nThe emergence of the phenomenon of CAM has also played a role over the past few decades. Analyzed in both scientific publications and the popular media, the CAM phenomenon is now a well-established and positively recognized element within our healthcare system. The difficulty is that the CAM phenomenon has reinforced the cultural authority chasm in which the profession finds itself. There is such significant evidence supporting chiropractic benefits for spine care that it is considered by policy makers to be more mainstream than CAM. Yet, professional claims over the non-musculoskeletal domain and questionable practice behaviors obstruct full consideration within the mainstream by purchasers of healthcare research and delivery. While for some, the notion of being an alternative healthcare provider has a certain cache; this notion is neither clinically nor scientifically justified. It is a cultural and political status crafted by society for the prime purpose of evaluating whether the claims made by such practitioners are of any value. In the long run, the evaluation will elevate some and will degrade others. As noted by Marcia Angel, in the special \nNew England Journal of Medicine \nissue on alternative healthcare: \n\"There is only medicine that has been adequately tested and medicine that has not, medicine that works and medicine that may or may not work.\"\n[\n34\n].\nFurther, the barrier to entry into CAM is too low for the profession of chiropractic. There are too many CAM-related procedures, practices and providers that lack scientific rigor. Chiropractic is by far the most mature profession among those associated with CAM. Its pre-professional requirements are the highest; the professional education the most developed; its research capacity, the most advanced; and its presence in the healthcare marketplace, the most comprehensive. Simply, the chiropractic profession undermines its legitimacy and authority by striving to remain within the CAM phenomenon.\nWe do not believe that this intermediate status of half-alternative/half-integrated is sustainable for much longer. The profession needs to decide in which of these two camps to plant both feet. Without the intent of its members, like the question of chiropractic's clinical purpose, this question of integration has largely been decided by default – chiropractic is an integrated part of the healthcare system, and the profession must continue to promote further integration. The benefits of integration to the profession are too great to ignore. To be a part of the system is to have access to all the resources of the system- funds for research, state supported education institutions, training opportunities in hospitals and other integrative clinical settings, access to other educational institutions and nearly universal inclusion in all reimbursement systems. We must take particular note of the recent approval and funding of a chiropractic college at Florida State University. This was a tremendously important development in this history of chiropractic and one that had the potential to profoundly deepen and accelerate the integration of chiropractic into the mainstream. What is unsettling is the fact that the college failed before it could even enroll a single student almost exclusively because of the failure of the profession to advance a coherent credible message regarding its role within the healthcare system.\nFor the profession, integration will insist on clinical accountability and responsibility, a demand that our members feel even now with the increased pressures of healthcare reform. The rewards of integration, however, are extensive. The experience of individuals who have broken down many of the barriers and succeeded in establishing chiropractic programs within mainstream healthcare centers is expanding. The development of chiropractic facilities for the United States Congress, within the military, and within private musculoskeletal centers has been universally positive for patients and for the participating chiropractors. Beside personal professional success, these experimental programs have bought additional trust and credibility within the system. The participants have experienced a hitherto unheard of expansion in clinical exposure. Increased patient volumes, case variation and complexity and provider satisfaction are evident. Doctors can experience a new freedom from the tyranny of personality cults and practice-builder manipulations. New opportunities for career track development are opening as healthcare policy makers, clinical and basic scientists and educators for interested individuals who are interested in cross training.\nFor the profession's infrastructure, integration confers enormous advantages. By functioning within the mainstream of healthcare, chiropractic will be able to gain access to a far broader population of patients and practice within a more varied set of patient care settings. The academic institutions will be able to free themselves from the stranglehold of economic dependence on tuition and the political reliance on ideological gurus who manipulate alumni and support to garner institutional control. The results will expand the jurisdiction and influence of the profession's cultural authority as warranted. The profession will be a member at the table of discussions and debate over the future of healthcare delivery. As a participant, chiropractic autonomy over its domain will be more certainly assured than in our current reactive conflict postures.\nOther Issues\nThere are a variety of other questions that bear upon the issue of the chiropractic model.\n1. The role of spinal manipulation in chiropractic. There is no foreseeable future in which spinal manipulation is not the primary therapeutic tool of chiropractic. But if or when that changes, it will be a function of the progress and evolution of clinical science, and not as a principle of chiropractic. That is, SMT should be viewed not as a defining element of chiropractic, but simply as what we happen to do. Invoking the dental analogy again, dentists do not define themselves as \"implanters of dental amalgam,\" although that is probably what they do the most. As the discussion above on chiropractic philosophy illustrates, to do otherwise, to focus exclusively on SMT, as \nthe \nchiropractic therapy will hinder our ability to pursue a more optimal treatment for back pain. We must make sure that we are prepared and equipped to identify and deliver whatever conservative therapies for back pain prove to be most effective.\n2. The use of drugs. Should chiropractors seek limited prescribing rights as has been attempted in the past? Or should chiropractic promote itself as a \"drugless\" profession? We believe the answer to both these questions is \"no.\" In the first instance (should chiropractors prescribe), clinical science has created a very strong case for conservative healthcare. Much of the advantage that chiropractic currently enjoys in the realm of back pain treatment (in terms of cost, safety, and satisfaction) is directly attributable to its conservative (non-drug) interventions. The US osteopathic experience is informative in this regard. Given the option of prescribing and using other more invasive interventions, it is much easier to prescribe than it is to use a manual therapy, and the role of manipulative therapy has diminished and nearly vanished from the profession.\nRegarding the second question (should chiropractic promote its \"drugless\" nature), we should not promote the juvenile notion that drugs are bad and SMT is good. Our non-use of drugs should simply be regarded as a conscious decision to focus on a particular therapeutic approach, rather than a comprehensive rejection of drug therapy (or any other specific intervention that we do not happen to provide). Our position on drug use should be precisely the same as medicine: all drug use should be appropriate and guided by the scientific literature. And we should acknowledge that sometimes the correct treatment would involve drugs.\nThe decision to reject the use of drugs should always be contingent upon the scientific literature. The literature currently provides that conservative and manual therapies are legitimate treatment options for a large percentage of the patient population with spinal complaints. Until such point as it becomes clear that it is not possible to practice EBHC without drugs (and that point may never arrive) chiropractic should remain committed to conservative manual therapies.\n3. Chiropractic education and licensing. The model we have proposed does not require any specific change in chiropractic education or licensure to be implemented. In fact, one criterion behind our model is that it reflects how chiropractors are educated, and how they practice. So, we already have concluded that the \nde facto \nmodel being taught at chiropractic colleges is that of a back pain specialist (their proclamations of primary care, notwithstanding). We do believe that a more explicit embrace of the Spine Care model would lead to a higher quality of education. We do, of course, hope that chiropractic education improves, particularly with respect to the patient care component of the education. Similarly, the Spine Care model is completely consistent with current state licensing. There will always be disputes and turf wars at the margins of the licensing process, and there are some onerous elements to some state laws, but we do not propose any wholesale revision or alteration of the statutory scope of chiropractic practice.\n4. Wellness/prevention as a principle of chiropractic. Nearly all factions of the profession make the claim that chiropractic represents a \"wellness\" approach to health. Some factions use this term to mean, \"We will prevent disease by eliminating subluxations.\" Others use the term to mean, \"We will prevent back pain and related disorders by providing comprehensive spine care.\" And still others use the term to mean, \"We will prevent a variety of degenerative diseases (cardiovascular, neoplastic, etc.) by advising patients on how to live a more healthy life.\" The first example is unproven and unlikely to be true. The second two examples are also unproven, although they are not scientifically implausible as is the first example. The question is whether the chiropractic can actually deliver on the promise to promote health and prevent disease (as opposed to treating symptomatic patients). To date chiropractic has not demonstrated that it can deliver on the promise of prevention. It is difficult to make the case that chiropractic, uniquely or distinctively among health profession, is concerned with, and capable of providing effective preventive health care. Chiropractors should certainly concern themselves with patients' behavior that may affect patients' health, and provide whatever advice, council, and encouragement they can to improve health related behavior. But, until we can demonstrate that we are effective where others are not, the proposition of chiropractic as the \"wellness profession\" is not defensible.\nSummary\nTo date, the chiropractic profession has failed to develop the legitimacy necessary to defend its autonomy and cultural authority. It has not shown the will or ability to define for itself a coherent and consistent identity that takes into account the realities of the healthcare world in which we operate. If the profession fails to do so its future will be imperiled. We offer a professional model for the chiropractic profession. The essential characteristics of this model are:\n• Spinal care as the defining clinical purpose of chiropractic.\n• Chiropractic as a portal-of-entry provider.\n• The acceptance and promotion of EBHC.\n• A conservative clinical approach.\n• Chiropractic as an integrated part of the healthcare mainstream\n• The rigorous implementation of accepted standards of professional ethics.\nAuthors' contributions\nThe cover letter describes the general context and process by which this manuscript was created. After the first set of meetings Dr. Nelson wrote an initial draft document, which reflected the collective thoughts and analyses of the participants. All of the authors participated and contributed in the initial and subsequent meetings during which the overall themes were identified and described. All of the authors made original contributions to the content of the draft and final manuscript. And all of the authors participated in the editing and revisions of the multiple drafts that existed between the initial and final draft.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
38
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nWhich diagnostic tests are most useful in a chest pain unit protocol?\n\n**Article Abstract:**\n\nBackground\nThe chest pain unit (CPU) provides rapid diagnostic assessment for patients with acute, undifferentiated chest pain, using a combination of electrocardiographic (ECG) recording, biochemical markers and provocative cardiac testing. We aimed to identify which elements of a CPU protocol were most diagnostically and prognostically useful.\nMethods\nThe Northern General Hospital CPU uses 2–6 hours of serial ECG / ST segment monitoring, CK-MB(mass) on arrival and at least two hours later, troponin T at least six hours after worst pain and exercise treadmill testing. Data were prospectively collected over an eighteen-month period from patients managed on the CPU. Patients discharged after CPU assessment were invited to attend a follow-up appointment 72 hours later for ECG and troponin T measurement. Hospital records of all patients were reviewed to identify adverse cardiac events over the subsequent six months. Diagnostic accuracy of each test was estimated by calculating sensitivity and specificity for: 1) acute coronary syndrome (ACS) with clinical myocardial infarction and 2) ACS with myocyte necrosis. Prognostic value was estimated by calculating the relative risk of an adverse cardiac event following a positive result.\nResults\nOf the 706 patients, 30 (4.2%) were diagnosed as ACS with myocardial infarction, 30 (4.2%) as ACS with myocyte necrosis, and 32 (4.5%) suffered an adverse cardiac event. Sensitivities for ACS with myocardial infarction and myocyte necrosis respectively were: serial ECG / ST segment monitoring 33% and 23%; CK-MB(mass) 96% and 63%; troponin T (using 0.03 ng/ml threshold) 96% and 90%. The only test that added useful prognostic information was exercise treadmill testing (relative risk 6 for cardiac death, non-fatal myocardial infarction or arrhythmia over six months).\nConclusion\nSerial ECG / ST monitoring, as used in our protocol, adds little diagnostic or prognostic value in patients with a normal or non-diagnostic initial ECG. CK-MB(mass) can rule out ACS with clinical myocardial infarction but not myocyte necrosis(defined as a troponin elevation without myocardial infarction). Using a low threshold for positivity for troponin T improves sensitivity of this test for myocardial infarction and myocardial necrosis. Exercise treadmill testing predicts subsequent adverse cardiac events.\n\n**Article Body:**\n\nBackground\nThe chest pain unit (CPU) has been developed to provide standardised care for patients presenting with acute chest pain, undiagnosed by initial clinical assessment, electrocardiogram (ECG) and chest radiograph. The CPU aims to rapidly diagnose acute coronary syndrome (ACS), providing early access to appropriate care for those with positive test results and discharge home for those who test negative. Although a variety of different tests have been used in CPU protocols, most units use a combination of ECG monitoring, biochemical diagnostic testing and provocative cardiac testing to diagnose ACS [\n1\n]. This has led to some debate regarding the most appropriate testing regime. In particular, the role of the exercise treadmill test has been questioned [\n2\n] and does not feature in some protocols [\n3\n].\nSince 1999 a CPU has been operating at the Northern General Hospital in Sheffield. Patients are investigated with a combination of serial ECG recording, ST segment monitoring, biochemical cardiac markers (CK-MB(mass) and troponin T) and an exercise treadmill test [\n4\n]. We aimed to determine the value of each of the constituent elements of this protocol by measuring: a) the diagnostic accuracy (sensitivity, specificity and likelihood ratios) of each test for ACS at presentation, and b) prognostic value of each test for major adverse cardiac events over six months.\nMethods\nThe Northern General Hospital is a 1100-bedded urban teaching hospital with the only adult emergency department for the 530,000 population of Sheffield, United Kingdom. The emergency department see approximately 90,000 new patients per year, of whom approximately 6% have chest pain. The hospital is a tertiary referral centre for cardiology, with cardiac catheterisation and cardiac surgery facilities. The CPU is a two-bedded, nurse-run unit based in the emergency department. Patients are assessed on the unit if they present with acute chest pain and have a normal or non-diagnostic ECG, no co-morbidity requiring admission, no serious alternative cause for chest pain (such as pulmonary embolus) and pain that is potentially compatible with cardiac ischaemia (i.e. not chest wall pain). Patients with known coronary heart disease can be assessed on the CPU provided they do not have prolonged (> one hour) or recurrent (more than one episode) pain that is characteristic of their angina.\nThe diagnostic testing regime consists of ST segment monitoring and serial ECG recording every hour for two to six hours; CK-MB(mass) assay on arrival, repeated either two hours later or six hours after symptom onset, whichever is later; troponin T assay at least six hours after symptom onset; and, if appropriate, exercise treadmill testing. Exercise testing is not performed if any preceding test is positive, if the patient has had recent diagnostic testing for coronary heart disease (e.g. coronary angiography), or if they are unable to exercise.\nFrom 1/3/99 to 30/9/00 presenting details, CPU processes and diagnostic test results were prospectively recorded for all patients assessed on the CPU. Patients admitted after assessment received further testing and management at the discretion of the admitting physician and were followed up by case note review. Patients discharged after assessment were invited to attend a review appointment on the CPU 72 hours later for clinical assessment, ECG and troponin T measurement.\nSix months after assessment the emergency department computer database was searched for details of any further hospital attendances or admissions. Case notes were reviewed for all cases identified. The general practitioners of all patients presenting between 1/3/99 and 29/2/00 were contacted by post to determine if they had suffered any adverse cardiac event or received diagnostic cardiac testing or procedures during the previous six months. This survey revealed no previously unidentified episodes so for patients attending from 1/3/00 to 30/9/00 the general practitioner was only contacted if the patient resided outside the Sheffield area. We did not attempt to contact patients at six months to confirm whether they were still alive.\nST segment monitoring and serial ECG recording was performed using Spacelabs monitors. These functions will be evaluated together, because: 1) serial ECG recording is facilitated and influenced by the availability of this monitoring equipment, and 2) ECG changes detected on ST segment monitoring may also be detected on serial recording and vice-versa. Each patient received between two and six hours of ST segment monitoring and at least two ECGs, one hour apart. Results were dichotomised into positive (>1 mm ST segment elevation or depression; T wave inversion > 2 mm or normalisation; ventricular arrhythmia; or second or third degree heart block) or negative (none of these changes). ECGs were interpreted by the specialist chest pain nurses who managed the unit. Positive changes were defined a priori and used for CPU decision-making.\nThe absolute value of CK-MB(mass) at baseline and on repeat sampling was defined as positive if it exceeded 5 ng/ml. The rise in CK-MB(mass) (delta CK-MB(mass)) was defined as positive if it exceeded 1.6 ng/ml. The diagnostic performance of baseline, repeat assay and change in CK-MB(mass) were analysed separately and then combined to give an overall result. This was defined as positive if either assay or the change were positive, and negative if all three results were negative. Two thresholds for positivity were analysed for troponin T: 1) the traditional threshold of 0.1 ng/ml or above, and 2) a more sensitive threshold of 0.03 ng/l. The CK-MB(mass) thresholds and the 0.1 ng/ml threshold for troponin were defined a priori and used for decision making on the CPU. The 0.03 ng/ml troponin threshold was only used for post hoc analysis.\nThe exercise treadmill test was performed according to the Bruce protocol. A positive test was defined as more than 1 mm horizontal or down-sloping ST segment depression; more than 1 mm ST elevation; or ventricular arrhythmia. For the purposes of this analysis, any test that did not produce these changes was considered to be negative, regardless of the duration of exercise or heart rate achieved.\nThe diagnostic performance of all tests except the exercise treadmill test was evaluated by comparison to the reference standard diagnosis of ACS at presentation, categorised as recently recommended [\n5\n] into: 1) ACS with clinical myocardial infarction (defined as a typical clinical syndrome associated with a troponin T elevation greater than 1.0 ng/ml), or 2) ACS with myocyte necrosis (defined as a typical clinical syndrome with any detectable troponin T less than 1.0 ng/ml). Sensitivity, specificity, positive and negative predictive values, and likelihood ratios were calculated for each test, along with 95% confidence intervals.\nThe prognostic value of each test was evaluated by measuring the relative risk of a major adverse cardiac event during the six months following a positive result, compared to a negative result. The following were defined as major adverse cardiac events: cardiac death, non-fatal myocardial infarction, arrhythmia, or revascularisation procedure. Because revascularisation procedures may be precipitated by the diagnostic tests under investigation, we repeated the analysis with these excluded from the definition.\nData were analysed using SPSS for windows version 11.5 (SPSS Inc., Chicago) and 95% confidence intervals for all proportions, likelihood ratios and risk ratios were calculated using CIA, Confidence Interval Analysis software. The North Sheffield Research Ethics Committee approved the evaluation of the chest pain unit.\nResults\nDuring the study period 706 patients were assessed on the CPU. Details of the study population characteristics are outlined in table \n1\n. All patients received baseline blood sampling. This was performed at a mean time from symptom onset of 6.2 hours (median 3.0 hours). Repeat blood sampling was performed on 604 patients (86%) at a mean time from symptom onset of 8.6 hours (median 6.5 hours). After CPU assessment 596 (84%) were discharged home and 110 (16%) were admitted. Of those discharged, 515 (86%) returned for review at 72 hours. At review one patient had a previously undetected rise in troponin T (0.8 ng/ml) and was classified as having ACS with myocyte necrosis. All other cases of ACS were detected by the CPU protocol.\nTable 1\nCharacteristics of the study population\nMean age\n53.6 years (range 22 to 99)\nMale\n431 (61%)\nKnown coronary heart disease\n150 (21%)\nDiabetes\n48 (7%)\nHypertension\n181 (26%)\nHyperlipidaemia\n114 (16%)\nSmoker\n215 (35%)\nACS with clinical myocardial infarction was ultimately in diagnosed in 30 patients (4.2%), while another 30 (4.2%) had ACS with myocyte necrosis. Over the following six months 32 patients (4.5%) had a major adverse cardiac event. These included eight cardiac deaths, five non-fatal myocardial infarctions, two arrhythmias, and 17 revascularisation procedures.\nSerial ECG/ST segment monitoring was performed for 690 patients, baseline CK-MB(mass) was measured in 687, repeat CK-MB(mass) was measured in 601, troponin T was measured in 686 patients, and 422 patients received an exercise treadmill test. Table \n2\n shows the sensitivity, specificity, positive and negative predictive values and table \n3\n shows the likelihood ratios of the tests for ACS with clinical myocardial infarction at presentation. The same parameters are outlined for ACS with clinical myocardial infarction or myocyte necrosis in tables \n4\n and \n5\n. Serial ECG / ST segment monitoring added relatively little to the assessment. None of the positive cases involved ST elevation myocardial infarction requiring reperfusion therapy. All the biochemical markers were useful for ruling in ACS with clinical myocardial infarction and ACS with myocyte necrosis. The second CK-MB(mass) sample and the delta CK-MB(mass) were useful for ruling out myocardial infarction, but did not reliably rule out myocyte necrosis. Using a lower threshold for troponin T positivity markedly improved sensitivity with only a modest loss of specificity. Only troponin T, using a lower threshold, was useful for ruling out ACS with myocyte necrosis. However, it should be recognised that this diagnosis is based upon detection of troponin T.\nTable 2\nSensitivity, specificity, positive and negative predictive values for the diagnosis of ACS with clinical myocardial infarction at presentation\nSensitivity (95% CI)\nSpecificity (95% CI)\nPositive predictive value (95% CI)\nNegative predictive value (95% CI)\nSerial ECG & ST monitoring N = 690\n33.3% (19.2 to 51.2)\n95.3% (93.4 to 96.7)\n24.4% (13.8 to 39.3)\n96.9% (95.3 to 98.0)\nInitial CK-MB(mass) N = 687\n63.3% (45.5 to 78.1)\n97.0% (95.3 to 98.0)\n48.7% (33.9 to 63.8)\n98.3% (97.0 to 99.0)\nDelayed CK-MB(mass) N = 601\n95.7% (79.0 to 99.2)\n96.2% (94.3 to 97.5)\n50.0% (35.8 to 64.2)\n99.8% (99.0 to 100)\nDelta CK-MB(mass) N = 601\n95.7% (79.0 to 99.2)\n98.4% (97.0 to 99.1)\n70.0% (53.4 to 83.9)\n99.8% (99.0 to 100)\nAny positive CK-MB(mass) N = 601\n100% (88.6 to 100)\n95.6% (93.7 to 96.9)\n50.8% (38.3 to 63.2)\n100% (99.4 to 100)\nTroponin T > = 0.1 ng/ml N = 686\n83.3% (66.4 to 92.7)\n98.8% (97.7 to 99.4)\n75.8% (59.0 to 87.2)\n99.3% (98.3 to 99.7)\nTroponin T > = 0.03 ng/ml N = 686\n96.4% (82.3 to 99.4)\n95.9% (94.1 to 97.2)\n50.0% (37.1 to 62.9)\n99.8% (99.1 to 100)\nTable 3\nLikelihood ratios for the diagnosis of ACS with clinical myocardial infarction at presentation\nPositive likelihood ratio (95% CI)\nNegative likelihood ratio (95% CI)\nSerial ECG & ST monitoring N = 690\n7.1 (3.8 to 13.1)\n0.700 (0.543 to 0.901)\nInitial CK-MB(mass) N = 687\n20.8 (12.5 to 34.7)\n0.378 (0.236 to 0.605)\nDelayed CK-MB(mass) N = 601\n25.1 (16.5 to 38.2)\n0.045 (0.007 to 0.307)\nDelta CK-MB(mass) N = 601\n61.4 (39.1 to 118.1)\n0.044 (0.006 to 0.300)\nAny positive CK-MB(mass) N = 601\n~25*\n~0*\nTroponin T > = 0.1 ng/ml N = 686\n70.4 (34.1 to 140.8)\n0.169 (0.079 to 0.387)\nTroponin T > = 0.03 ng/ml N = 686\n23.5 (16.1 to 34.2)\n0.037 (0.005 to 0.255)\n*Unable to calculate precisely as no false negative were recorded\nTable 4\nSensitivity, specificity, positive and negative predictive values for the diagnosis of ACS with myocyte necrosis or clinical myocardial infarction at presentation\nSensitivity (95% CI)\nSpecificity (95% CI)\nPositive predictive value (95% CI)\nNegative predictive value (95% CI)\nSerial ECG & ST monitoring N = 690\n23.3% (14.4 to 35.4)\n95.7% (93.8 to 97.0)\n34.1% (21.6 to 49.5)\n92.9% (90.7 to 94.6)\nInitial CK-MB(mass) N = 687\n43.3% (31.6 to 55.9)\n97.9% (96.5 to 98.8)\n66.7% (51.0 to 79.4)\n94.8% (92.8 to 96.2)\nDelayed CK-MB(mass) N = 601\n63.5% (49.9 to 75.2)\n98.0% (96.4 to 98.9)\n75.0% (60.6 to 85.4)\n96.6% (94.7 to 97.8)\nDelta CK-MB(mass) N = 601\n55.8% (42.3 to 68.4)\n99.6% (98.7 to 99.9)\n93.5% (79.3 to 98.2)\n96.0% (94.0 to 97.3)\nAny positive CK-MB(mass) N = 601\n71.7% (59.2 to 81.5)\n97.4% (95.9 to 98.4)\n72.9% (60.4 to 82.6)\n97.3% (95.7 to 98.3)\nTroponin T > = 0.1 ng/ml N = 686\n55.0% (42.5 to 66.9)\n100% (99.4 to 100)\n100% (89.6 to 100)\n96.0% (94.2 to 97.2)\nTroponin T > = 0.03 ng/ml N = 686\n89.7% (79.2 to 95.2)\n99.7% (98.8 to 99.9)\n96.3% (87.5 to 99.0)\n99.6% (97.9 to 99.9)\nTable 5\nLikelihood ratios for the diagnosis of ACS with myocyte necrosis or clinical myocardial infarction at presentation\nPositive likelihood ratio (95% CI)\nNegative likelihood ratio (95% CI)\nSerial ECG & ST monitoring N = 690\n5.4 (3.0 to 9.8)\n0.801 (0.696 to 0.922)\nInitial CK-MB(mass) N = 687\n20.9 (11.3 to 38.5)\n0.579 (0.464 to 0.722)\nDelayed CK-MB(mass) N = 601\n31.7 (17.0 to 58.9)\n0.373 (0.261 to 0.534)\nDelta CK-MB(mass) N = 601\n153.1 (37.6 to 623.5)\n0.444 (0.327 to 0.602)\nAny positive CK-MB(mass) N = 601\n28.1 (16.9 to 46.7)\n0.291 (0.194 to 0.435)\nTroponin T > = 0.1 ng/ml N = 686\n~25*\n~0*\nTroponin T > = 0.03 ng/ml N = 686\n281.5 (70.4 to 1126)\n0.104 (0.049 to 0.221)\n*Unable to calculate precisely as no false positives were recorded\nTable \n6\n shows the relative risk of all cardiac events over the subsequent six months for each diagnostic test and table \n7\n shows the relative risk of cardiac death, non-fatal AMI or arrhythmia. Positive results for serial ECG / ST segment monitoring or biochemical cardiac markers showed a weak association with cardiac events over the following six months. This association disappeared when revascularisation procedures were excluded from the definition of cardiac events. Positive exercise stress test result showed a much stronger association with cardiac events, which was maintained even when revascularisation procedures were excluded.\nTable 6\nRelative risk of a cardiac event over the following six months\nTest\nEvent rate:\npositive test\nEvent rate:\nnegative test\nRelative risk (95% CI)\nSerial ECG & ST monitoring N = 690\n5/41\n27/649\n2.72 (1.10 to 6.74)\nInitial CK-MB(mass) N = 687\n5/39\n27/648\n2.84 (1.15 to 7.02)\nDelayed CK-MB(mass) N = 601\n5/44\n23/557\n2.57 (1.02 to 6.47)\nDelta CK-MB(mass) N = 601\n3/31\n25/570\n2.10 (0.67 to 6.61)\nAny positive CK-MB(mass) N = 601\n8/59\n24/628\n3.24 (1.52 to 6.93)\nTroponin T > = 0.1 ng/ml N = 686\n8/33\n24/673\n6.80 (3.31 to 13.96)\nTroponin T > = 0.03 ng/ml N = 686\n9/54\n23/632\n4.58 (2.23 to 9.40)\nExercise treadmill test N = 422\n9/37\n4/385\n19.03 (6.10 to 59.34)\nTable 7\nRelative risk of cardiac death, non-fatal myocardial infarction or arrhythmia over the following six months\nTest\nEvent rate: \npositive test\nEvent rate: \nnegative test\nRelative risk\nSerial ECG & ST monitoring N = 690\n1/41\n15/649\n1.06 (0.14 to 7.79)\nInitial CK-MB(mass) N = 687\n0/39\n16/648\n-\nDelayed CK-MB(mass) N = 601\n1/44\n13/557\n0.97 (0.13 to 7.28)\nDelta CK-MB(mass) N = 601\n0/31\n14/570\n-\nAny positive CK-MB(mass) N = 601\n1/59\n15/628\n0.71 (0.09 to 5.28)\nTroponin T > = 0.1 ng/ml N = 686\n1/33\n15/673\n1.36 (0.18 to 9.98)\nTroponin T > = 0.03 ng/ml N = 686\n2/54\n14/632\n1.67 (0.39 to 7.17)\nExercise treadmill test N = 422\n2/37\n3/385\n6.63 (1.14 to 38.50)\nDiscussion\nThese findings suggest that serial ECG recording and ST segment monitoring, as applied in our protocol, add little diagnostic value in patients with a normal or non-diagnostic initial ECG. Only a minority of cases of ACS were detected by ECG monitoring and most of the positive results from this test were false positives. Serial ECG recording and ST segment monitoring offers the potential advantage of allowing early detection of ST segment elevation myocardial infarction that may be eligible for thrombolysis [\n6\n], but no such cases occurred in our cohort. Our findings are consistent with those of Decker et al [\n7\n] who found that serial ECG was of limited value in their CPU protocol. It should be appreciated, however, that our protocol used a variable duration of ST segment monitoring and a variable number of serial ECGs, with some patients receiving only two hours of monitoring and two serial ECGs. Hence these findings may not apply to more prolonged regimes, or to populations with a higher prevalence of ACS.\nBaseline CK-MB(mass) testing allows early detection of ACS and calculation of a CK-MB(mass) rise. However, the initial CK-MB(mass) alone has insufficient sensitivity to rule out ACS. The addition of a repeat sample at least two hours later and at least six hours after the onset of pain provides adequate sensitivity to rule out ACS with myocardial infarction, but not myocyte necrosis. Our estimate of sensitivity for myocardial infarction is consistent with previously published estimates [\n3\n,\n8\n,\n9\n]. If we simply wish to rule out myocardial infarction then this would appear to be a relatively cheap and effective way of achieving that aim.\nUsing a traditional threshold for positivity of 0.1 ng/ml for troponin T [\n10\n,\n11\n] in this protocol does not reliably rule out myocardial infarction or myocyte necrosis. However, if a lower threshold of 0.03 ng/ml is used then 96% of cases of myocardial infarction and almost 90% of cases of myocyte necrosis will be detected. This finding is consistent with previously published data showing that use of a lower threshold for positivity for troponin T is associated with improved early sensitivity [\n12\n]. However, since we tested this threshold as a post hoc analysis, further prospective validation of the performance of a lower threshold is required. Furthermore, lowering the threshold would be expected to reduce specificity and lead to more false positives being generated. Potential incorporation bias (see limitations section) means that it is difficult to determine the impact of altering the threshold upon specificity.\nThe question of whether to use CK-MB(mass) or troponin T or both is a subjective judgement in which the benefits of detecting and treating cases of ACS must be weighed against the costs of additional testing and management of false positives. ACS with myocardial infarction is associated with a markedly increased risk of adverse events[\n5\n,\n10\n] and thus an increased expectation of benefit from treatment [\n13\n]. The risks of ACS with myocyte necrosis are smaller, but still indicate potential benefit from detection and treatment [\n5\n]. In estimating the potential costs and benefits of detecting cases of ACS we also need to consider prevalence. CPU patients have a low prevalence of ACS, so a large number of additional patients will need to be tested to detect a small number of additional cases.\nThe value of exercise treadmill testing in a CPU protocol has been questioned [\n2\n]. It may be costly to implement and risks generating large number of false positives due to poor specificity. This study has shown that exercise treadmill testing offers useful prognostic information that is not provided by ECG or biochemical testing. Meanwhile, concerns about false positives are undermined by evidence from a recent randomised controlled trial [\n14\n] in which two-thirds of patients randomised to CPU care received an exercise treadmill test compared to only one-third of the routine care group. Despite this difference the rate of referral for angiography was identical. Whether the additional prognostic information provided by treadmill testing justifies the addition cost remains debatable.\nThis study has a number of limitations that should be appreciated. The reference standard for diagnosis was not independent of the tests being evaluated. Troponin elevation was the diagnostic criterion for ACS so estimates of sensitivity and particularly specificity will be subject to incorporation bias. Any patient who has an elevated troponin will, by definition, have a diagnosis of ACS, unless repeat sampling shortly afterwards is negative. Therefore specificity of troponin, using this definition of ACS, is expected to be high. The value of our analysis of troponin therefore lies in assessment of early sensitivity, particularly in comparing the early sensitivity of using different thresholds for positivity.\nCaregivers were aware of the results of all the tests under evaluation and thus would be more likely to rigorously follow-up those with positive tests, raising the possibility of work-up bias. Patients with positive tests were admitted while those with negative tests were discharged. Although 86% of discharged patients attended review at 72 hours, it is possible that some patients with false negative initial tests may have failed to attend follow-up, and were thus misclassified as true negative. A similar bias may influence the association between test results and adverse events when revascularisation procedures are included in the definition, but not the association between treadmill testing and adverse events limited to cardiac death, non-fatal myocardial infarction or arrhythmia.\nStatistical analysis inevitably requires some simplification of the data used. For ST segment monitoring / serial ECG and for exercise treadmill testing this involved categorising all results into positive or negative. For exercise treadmill testing inconclusive results were classified as negative. This approach may lead to under-estimation of the diagnostic value of the tests. Furthermore, since patients with new abnormalities on their ECG were excluded from CPU evaluation, it is perhaps not surprising that further ECG-based tests had limited value. This again reinforces the importance of not extrapolating these findings to different populations, such as those with a high prevalence of ACS.\nConclusion\nST segment monitoring and serial ECG recording, as applied in our protocol, appears to add little diagnostic value in patients with a normal or non-diagnostic initial ECG. CK-MB(mass) measurement allows reliable detection of ACS with myocardial infarction but not myocyte necrosis (defined as a troponin elevation without myocardial infarction). Using a low threshold for positivity for troponin T improves sensitivity of this test for myocardial infarction. Exercise treadmill testing offers additional prognostic information regarding the risk of subsequent adverse cardiac events.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nSG conceived the idea, planned the study, analysed the data, and wrote the paper. TL, JA and KA collected the data and helped to write the paper. FM helped conceive the idea and write the paper. All authors contributed to the final draft.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** definitely relevant"
}
] |
definitely relevant
|
39
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nHealth-related quality of life in patients with pulmonary arterial hypertension\n\n**Article Abstract:**\n\nBackground\nImproved outcomes with expanding treatment options for patients with pulmonary arterial hypertension present the opportunity to consider additional end-points in approaching therapy, including factors that influence health-related quality of life. However, comparatively little is known about health-related quality of life and its determinants in patients with pulmonary arterial hypertension.\nMethods\nHealth-related quality of life was evaluated in a cross sectional study of 155 outpatients with pulmonary arterial hypertension using generic and respiratory-disease specific measurement tools. Most patients had either World Health Organization functional Class II or III symptoms. Demographic, hemodynamic and treatment variables were assessed for association with health-related quality of life scores.\nResults\nPatients with pulmonary arterial hypertension suffered severe impairments in both physical and emotional domains of health-related quality of life. Patients with idiopathic (\"primary\") pulmonary arterial hypertension had the best, and those with systemic sclerosis the worst health-related quality of life. Greater six-minute walk distance correlated with better health-related quality of life scores, as did functional Class II versus Class III symptoms. Hemodynamic measurements, however, did not correlate with health-related quality of life scores. No differences in health-related quality of life were found between patients who were being treated with calcium channel antagonists, bosentan or continuously infused epoprostenol at the time of quality of life assessment.\nConclusion\nHealth-related quality of life is severely impaired in patients with pulmonary arterial hypertension and is associated with measures of functional status. Specific associations with impaired health-related quality of life suggest potential areas for targeted intervention.\n\n**Article Body:**\n\nIntroduction\nPulmonary arterial hypertension (PAH) is a devastating disease, characterized by progressive dyspnea and exercise limitation. If not effectively controlled, PAH often progresses to right heart failure and premature death [\n1\n-\n3\n]. Fortunately, recent dramatic advances in pharmacological treatment have brought about significant improvements in physical functioning and survival, and new therapeutic options are emerging at a rapid pace [\n4\n]. Improved outcomes with expanding treatment options present the opportunity to consider additional end-points in choosing approaches to therapy, including factors influencing health-related quality of life.\nPresently, little is known about the determinants of health-related quality of life (HRQOL) in patients with PAH. An improved understanding of these determinants will be essential as HRQOL becomes an important outcome in research on therapeutics for PAH [\n5\n,\n6\n].We studied health-related quality of life in a large population of PAH patients and performed an initial assessment of the clinical factors associated with better (or worse) HRQOL.\nMethods\nStudy Design and Patients\nWe conducted a cross sectional survey of HRQOL in patients cared for in the Pulmonary Vascular Disease Program at the University of Pennsylvania Health System. Previously established as well as newly referred patients with PAH were asked to complete HRQOL questionnaires over one year (October, 2002 – September, 2003). PAH was defined according to standard criteria, including a mean pulmonary artery pressure >25 mmHg at rest or 30 mmHg with exertion, and the absence of significant left heart dysfunction [\n7\n,\n8\n]. Patients completed questionnaires without assistance at regularly scheduled appointments prior to the physician evaluation. Physicians and nurses were not aware of HRQOL survey responses.\nPatient demographics, symptoms, medications, and physical exam findings on the day of HRQOL evaluations were obtained by chart review, as were demographic values. Test results within three months of HRQOL assessment were recorded (e.g. hemodynamic values from cardiac catheterization in 103 patients and six-minute walk distance in 33 patients).\nHealth-Related Quality of Life Measurements\nWe administered a generic and a respiratory disease-specific quality of life questionnaire. The Medical Outcome Study 36 Item Short Form health survey (SF-36, standard form, version 2; Quality Metric, Lincoln, RI) yields scaled scores in 8 physical and mental health areas affected by health and disease conditions, in addition to physical component and mental component summary scores [\n9\n]. The St. George's Respiratory Questionnaire (SGRQ) is a well validated respiratory disease specific HRQOL measure, yielding scores related to symptoms (concerning the frequency and severity of respiratory symptoms), activity (the degree to which activities are limited by breathlessness), and impact (aspects of social and psychological function affected by respiratory disease). In addition, a total score summarizes disease impact on overall health status [\n10\n].\nStatistical Analysis\nScores for the 8 domains and 2 summary measures of the SF-36, and the 4 scores of the SGRQ were calculated electronically according to published guidelines, including imputation for missing responses [\n9\n]. Higher SF-36 scores indicate better quality of life, whereas higher SGRQ scores indicate poorer HRQOL. SF-36 scores are normalized to a mean of 50 and standard deviation of 10, based on the normal US population. Mean raw scores on the SGRQ were compared with established normal population scores [\n11\n].\nData were entered into a Microsoft Access 5.1 database (Microsoft Corporation) and statistical analysis performed with SAS 8.2 software (SAS Institute, Cary, NC). Data were analyzed for differences using an independent t-test for binary predictors, ANOVA for categorical predictors, and correlation coefficients for continuous measures. Comparisons between patient groups were limited to the physical and mental component summary scores of the SF-36, and significant associations defined as those having a p ≤ 0.05.\nNormalized physical and mental component summary scores were calculated from published studies of populations with various chronic diseases using reported individual SF-36 domain scores and an on-line scoring program \n.\nThis study was approved by the Institutional Review Board of the University of Pennsylvania.\nResults\nPatient Characteristics\nHealth-related quality of life was examined in 155 adult outpatients. The population was 81% female with an average age of 53 years, ranging from 18 to 84. Other physical and social characteristics of the study population are shown in Table \n1\n. Thirty-three patients (21% of the sample) completed HRQOL questionnaires at the time of initial evaluation in a pulmonary vascular disease specialty program. Patients who had been followed for treatment of PAH for up to 1, 2 or 3 years accounted for 19, 25 and 14 percent of evaluations, respectively; the remaining 21% of patients had been followed longer than 3 years. Approximately one third of patients had idiopathic (\"primary\") pulmonary arterial hypertension and most had either World Health Organization Class II or III symptoms. The majority were married and only 14 percent lived alone. Thirty-five percent of the patients were employed.\nTable 1\nBaseline Characteristics\nPhysical Characteristics\nSocial Characteristics\nPatients, n\n155\nMarital Status\nAge, years (mean ± SD)\n53 ± 13\n Single\n25 (16)\nFemale, n (%)\n126 (81)\n Married\n100 (65)\nCaucasian\n106 (68)\n Separated\n4 (3)\nAfrican-American\n34 (22)\n Divorced\n11 (7)\nHispanic\n7 (5)\n Widowed\n15 (10)\nOther\n8 (5)\nLives Alone\n21 (14)\nPAH Diagnosis\nCurrently employed\n55 (35)\n Idiopathic (\"Primary\")\n63 (41)\nOccupation\n Familial\n2 (1)\n Prof/Exec\n22 (14)\n Systemic Sclerosis\n32 (21)\n Manager\n17 (11)\n Other CVD\n13 (8)\n Clerical\n45 (29)\n Portal Hypertension\n11 (7)\n Skilled Labor\n4 (3)\n Anorectic Agent Use\n7 (5)\n Unskilled Labor\n16 (10)\n Other (i.e., HIV, PVOD)\n27 (17)\n Homemaker\n12 (8)\n Other\n9 (6)\n WHO I, %\n3 (2)\n Not Available\n30 (19)\n WHO II, %\n80 (52)\nSubstance Abuse\n WHO III, %\n65 (42)\n Prior Alcohol\n11 (7)\n WHO IV, %\n7 (5)\n Current Alcohol\n0 (0)\n Prior Smoking\n66 (43)\nMean RA pressure (mmHg)\n8.7 ± 2.6\n Current Smoking\n12 (8)\nMean PA pressure (mmHg)\n47 ± 17\nCardiac output (liters/min)\n4.9 ± 1.8\nPVR (dynes·sec·cm\n-5\n)\n630 ± 425\nTreatments\nSymptoms\nEpoprostenol\n50 (32)\nDyspnea\n105 (68)\nBosentan\n89 (57)\nFatigue, Weakness\n55 (35)\nCalcium Channel Blocker\n52 (34)\nLightheadedness/Pre-syncope\n31 (20)\nSildenafil\n3 (2)\nChest Pain\n31 (20)\nSpironolactone\n40 (26)\nCough\n27 (17)\nOther Diuretic(s)\n76 (49)\nLeg Pain\n26 (15)\nWarfarin\n74 (48)\nJaw Pain\n15 (10)\nDigoxin\n47 (30)\nDepression\n15 (10)\nOxygen, continuous\n29 (19)\nAnxiety\n14 (9)\nOxygen, nocturnal\n17 (11)\nPalpitations\n15 (10)\nOxygen, as needed\n15 (10)\nDiarrhea\n22 (14)\nAbdominal Complaints\n7 (6)\nLeg Weakness\n7 (6)\nDifficulty Sleeping\n3 (2)\nHealth-Related Quality of Life Scores\nPatients with PAH had significantly depressed physical and mental health-related quality of life (Figure \n1\n). On the SF-36, a \"generic\" measure of HRQOL applicable to a wide range of populations and disease states, HRQOL was impaired in every domain, representing a broad range of quality of life concepts (p < 0.001 for each). Mean scores were particularly depressed for the general health, physical functioning, role physical and emotional domains. In addition, the physical component summary (PCS) and mental component summary (MCS) scores, which broadly measure overall effects on HRQOL, were significantly decreased (p < 0.001 for each).\nFigure 1\nHealth-Related Quality of Life Scores for Patients with Pulmonary Arterial Hypertension. Shown are mean (±SE) scores on each domain and summary component score of the SF36. Numerically higher scores indicate better health-related quality of life. All domain and summary scores are significantly lower than the US population normal score of 50 (p < 0.001 for each).\nQuality of life was also assessed using a respiratory-disease specific instrument for comparison. Scores of patients with PAH were similarly abnormal on each component of the Saint George's Respiratory Questionnaire (Figure \n2\n). Abnormally elevated scores (indicating a worse HRQOL) were seen in assessments of patient symptoms, activity, and the impact of disease on social and psychological function (p < 0.0001 for the comparison of each with normal). Further, PAH patients' mean total score, summarizing the effect of respiratory disease on overall health status, was markedly abnormal (p < 0.001).\nFigure 2\nRespiratory-Disease Specific Health-Related Quality of Life Scores in Patients with Pulmonary Arterial Hypertension. Mean (±SE) scores on the Saint George's Respiratory Questionnaire for patients with pulmonary arterial hypertension are compared with the normal population. Numerically lower scores indicate better health-related quality of life. P < 0.0001 for the comparison between normal scores and PAH patients for each.\nFactors Associated with Impaired Quality of Life\nIdiopathic pulmonary arterial hypertension (IPAH) was associated with better health-related QOL than other causes of PAH (Figure \n3\n). Physical component summary scores of the SF-36 were highest for patients with IPAH. Patients with disease associated with systemic sclerosis, on the other hand, had the poorest physical QOL scores. Mental component summary QOL scores differed only for patients with anorectic agent associated PAH, whose scores were lowest (p = 0.02; not shown). World Health Association (WHO) Class II patients had better physical component summary scores than those with Class III symptoms (p < 0.001); small numbers of patients with Class I and IV symptoms precluded further comparisons. Active employment was the only additional demographic variable associated with better physical component summary scores (p < 0.0001 for the comparison with patients who were not employed). HRQOL scores were not associated with gender, race or age. Correlation coefficients for age with physical and mental component scores were -0.148 (p = 0.08) and 0.05 (p = 0.58), respectively.\nFigure 3\nBox and whisker plots of scores on the physical and mental component summary measures of the SF36 according to PAH diagnosis and World Health Organization (WHO) Functional Class. ** indicates p < 0.0001 for the difference between patients with idiopathic pulmonary arterial hypertension (IPAH) and systemic sclerosis (SSc) related PAH, and for the difference between WHO Class II and III patients.\nCertain symptoms were associated with worsened HRQOL. Chest pain and pre-syncope were each associated with poorer physical component scores (p ≤ 0.02 for each), generalized fatigue with lower physical and mental component scores (p ≤ 0.03, each). Common side effects of epoprostenol therapy (diarrhea, jaw pain) were not related to further impairment in HRQOL. Patients who reported abdominal discomfort had significantly worse physical and mental component summary scores, and the presence of abdominal tenderness on physical exam was associated with worsened MCS scores (p ≤ for each). The only additional finding on physical examination associated with poorer HRQOL was the presence of peripheral edema, with which lower physical component summary scores (p ≤ 0.0001) and mental component scores (p = 0.02) were seen.\nTherapies were also assessed. No differences in summary physical or mental component HRQOL scores were found between patients who were being treated with calcium channel antagonists, intravenous epoprostenol or bosentan at the time of HRQOL assessment (Figure \n4\n). The use of diuretics or continuous oxygen was each associated with worsened physical summary scores. No differences were observed for the use/non-use of either warfarin or digoxin (not shown).\nFigure 4\nBox and whisker plots of scores on the physical and mental component summary measures of the SF36 according to treatments received at the time HRQOL assessment was performed. * indicates p ≤ 0.001 for the comparison between patients receiving or not receiving diuretics; ** p = 0.03 for the comparison between patients receiving or not receiving continuous oxygen therapy.\nThe distance walked in six minutes was significantly correlated with the physical component summary HRQOL score and approached significance in correlation with the mental component summary scores (Figure \n5\n). The degree of perceived exertion reported by patients during exercise testing (Borg dyspnea index; higher reported exertion indicating more severe dyspnea) was inversely correlated with the physical component score (correlation coefficient -0.46; p = 0.02). Oxyhemoglobin saturation at rest also correlated with physical component summary scores (correlation 0.24, p = 0.005), but not mental component scores. No correlation was observed between hemodynamic measurements and HRQOL scores (Figure \n6\n). Neither physical nor mental component summary scores correlated with the mean right atrial or pulmonary artery pressures, cardiac output or pulmonary vascular resistance.\nFigure 5\nCorrelation of six-minute walk distance and health-related quality of life scores. Y-axes indicate scores on the physical and mental component summary scores of the SF-36.\nFigure 6\nLack of correlation of hemodynamic values and health-related quality of life scores. RA, right atrial pressure (mmHg); PA, mean pulmonary artery pressure (mmHg); PVR, pulmonary vascular resistance (dyne·sec·m\n5\n), Cardiac output = liters/minute. Y-axes indicate the physical and mental component summary scores of the SF-36.\nDiscussion\nChanges in health-related quality of life have been reported in trials of medications for pulmonary arterial hypertension. Improvements over pre-treatment scores have been seen in association with increased exercise capacity resulting from various therapies [\n12\n-\n16\n]. Focused assessments of health-related quality of life itself, however, are lacking and a systematic evaluation of the factors influencing it has not been previously reported in this patient population. A recent cross-sectional study of 53 patients with PAH reported moderate to severe impairments in multiple domains of HRQOL, both physical and emotional [\n17\n].\nIn the present study we have assessed a large population of patients with PAH and have identified demographic, symptom and treatment factors associated with better or poorer health-related QOL. Significantly impaired HRQOL was found in each of the eight domains of the SF-36, representing those physical, social and emotional characteristics generally accepted as most directly affected by health and disease [\n18\n,\n19\n]. Similarly, impaired HRQOL was observed on all scales of a respiratory-specific assessment tool (the Saint George's Respiratory Questionnaire). We found HRQOL to be best for patients with idiopathic PAH and worst for those with systemic sclerosis, unrelated to the type of vasodilator therapy used, and to be correlated with functional but not hemodynamic assessments.\nWhile we are not surprised to find reduced health-related quality of life in patients with PAH, the severity of impairment is remarkable. Impaired HRQOL – both physical and emotional – is associated with many chronic and physically debilitating conditions. The impairments observed in our population of PAH patients are as severe (and in many respects more so) than those reported in studies of patients with other severely debilitating and life-threatening conditions such as spinal cord injury, interstitial lung disease or cancer unresponsive to therapy (Figure \n7\n) [\n20\n-\n26\n]. Indeed, Shafazand et al. found their patients with PAH unhappy enough with their condition as to be willing to accept a significant risk of death in exchange for a potential cure [\n17\n].\nFigure 7\nComparison of health-related quality of life scores between disease states. Shown are mean population scores for the physical and mental component summary scores of the SF-36. Scores shown are derived from previous reports of cardiac rehabilitation [20], metastatic prostate cancer unresponsive to therapy [21], bone marrow transplantation for breast cancer [22], survivors of acute respiratory distress syndrome [23], interstitial lung disease [24], chronic obstructive lung disease [25] and spinal cord injury [26]. Previously published scores were normalized for comparison, as described in methods. Data shown for patients with pulmonary arterial hypertension are from the present study (as in Figure 1), shown here for comparison. Y-axis indicates the physical and mental component summary scores of the SF-36.\nSeveral important clinical parameters were associated with the degree of impairment in quality of life we observed, including diagnosis and exercise capacity. In addition to their poorer overall prognosis [\n27\n,\n28\n], we found that patients with PAH associated with systemic sclerosis experience worse health-related QOL than patients with other forms of the disease. Despite clear improvements in hemodynamics and exercise capacity as compared to untreated patients, those with systemic sclerosis do not benefit to the same degree as patients with IPAH in response to PAH-specific therapies [\n29\n,\n30\n]. Further investigations are required to determine whether these patients derive less benefit in HRQOL in response to these therapies, or whether other specific interventions can result in improvements.\nThe results of a six-minute walk test have been shown to correlate with each the WHO functional Class and patient survival [\n31\n]. In our sample, the distance walked in six minutes correlated with health-related quality of life. Scores worsened as exercise capacity declined. Our data similarly indicated worse scores in patients with WHO Class III symptoms as compared with Class II. The low number of patients with WHO Class I or IV symptoms in our population, however, limits further comparisons. By contrast, it is interesting that our data did not indicate a correlation with hemodynamic values. This suggests that a patient's overall functional status is of greater importance than actual hemodynamic values in determining HRQOL. Such findings, if confirmed, emphasize the importance of such functional endpoints in clinical trials, and may help direct choices of therapy so as to bring about the greatest improvement in a patient's sense of well-being. These findings, however, require confirmation with larger data sets that allow for HRQOL assessments both before and after cardiac catheterization, the results of which frequently change in response to therapy.\nThat abdominal complaints were associated with impaired HRQOL may be an important finding among patients with PAH. While abdominal discomfort might be caused by impaired splanchnic perfusion due to poor cardiac performance, it can also (perhaps more commonly) result from any of a number of processes common in non-PAH patients (e.g. gastroesophageal reflux and peptic ulcer disease). Even if not the result of PAH's effect on circulatory function itself, the significant association of abdominal discomfort with HRQOL noted here warrants further investigation. Similarly, while swelling and edema are a common symptom and finding among patients with advanced PAH and cor pulmonale, the additional impairment in HRQOL associated with diuretic use emphasizes the need to be mindful of appropriate titration to the degree required to prevent significant fluid collection.\nNo difference was found in HRQOL between patients who were receiving calcium channel antagonists, bosentan or epoprostenol therapies at the time HRQOL assessments were made. We cannot determine from the present study whether this reflects differences in the factors that determined the choice of therapy, or if these treatments do indeed result in equivalent HRQOL. While it might be expected that the need for continuous intravenous therapy would be associated with worse HRQOL, the inconveniences of such treatment might be off-set by the resultant substantial and sustained improvements in exercise capacity. Further, HRQOL reflects an individual's satisfaction with his or her life as it is affected by health. As such, HRQOL will be affected differently on the basis of individual desires, perceptions and expectations [\n17\n]. Epoprostenol therapy requires a motivated patient willing and able to provide a high degree of self-care. Such therapy may thereby select for individuals whose HRQOL is influenced to a greater degree by a sense of control over one's disease and its treatments. Additional prospective studies will be required to further evaluate these possibilities, and to determine whether choice of therapy can be expected to influence a patient's HRQOL.\nThere are several limitations of this study. Retrospective collection of patient symptoms and diagnoses may have resulted in misclassification bias and thereby influenced the observed effects of various factors on HRQOL. Missing items on HRQOL questionnaires may not be equally distributed among patients, and could therefore serve as an additional source of bias. Multi-centered studies will be required to be sure that the associations with reported symptoms and treatments found here do not overly reflect the practice styles of the physicians at this single specialized center. Larger prospective studies are required to better assess potential differences in HRQOL resulting from different treatments.\nThere is no currently available instrument designed specifically for the assessment of health-related quality of life in patients with pulmonary arterial hypertension [\n5\n]. We have used the SF-36, a non-disease specific instrument and the most widely used worldwide in studies of many individual disease populations [\n9\n]. While we have used the SGRQ (an instrument aimed a patients with respiratory disease) as a means to compare and provide some validation of the results seen with the SF-36, this too is limited in its ability to evaluate many items contributing to HRQOL in patients with pulmonary arterial hypertension. The SGRQ was developed to assess patients with COPD. As such, many of its questions address symptoms not typical of pulmonary arterial hypertension (e.g. wheezing and productive cough). Further, other symptoms attributable to cor pulmonale and commonly faced by patients with pulmonary arterial hypertension are not addressed in the SGRQ. While several HRQOL instruments have been developed for patients with left heart failure, these too have significant limitations in application to other populations and have not been validated for use in patients with cor pulmonale. Indeed, pulmonary arterial hypertension represents a hybrid of respiratory and cardiac symptoms, signs and treatments. Pepke-Zaba and colleagues have recently reported on the development of a PAH-specific HRQOL questionnaire [\n32\n]. The availability of such an instrument specifically developed for evaluation of patients with pulmonary arterial hypertension will be an important contribution to future studies aimed at better understanding and improving HRQOL [\n5\n].\nConclusion\nOur study provides an initial systematic evaluation of health-related quality of life in a large population of patients with pulmonary arterial hypertension. We found profound impairment in all domains of HRQOL measured by both generic and respiratory-disease specific measures, and associations with assessments of functional status as well as specific demographic, symptom and treatment factors. As therapeutic options expand, the factors associated with impaired HRQOL identified here may suggest areas for further study and targeted intervention in efforts to improve outcomes for patients with pulmonary arterial hypertension.\nList of Abbreviations Used\nPAH: Pulmonary Arterial Hypertension\nHRQOL: Health-Related Quality Of Life\nSF-36: Medical Outcomes Study 36 Short Form\nSGRQ: St. George's Respiratory Questionnaire\nPCS: Physical Component Summary\nMCS: Mental Component Summary\nIPAH: Idiopathic Pulmonary Arterial Hypertension\nWHO: World Health Organization.\nCompeting interests\nDrs. Palevsky and Taichman have each served as consultants or on speaker's bureaus for Actelion Pharmaceuticals.\nAuthors' contributions\nDBT, JS, LH and HP designed and SK coordinated this study. JS, LH and CAC performed chart reviews. DBT, RG, JHF, JSS and JC interpreted the data and DBT wrote the manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
40
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nManagement of chest pain: exploring the views and experiences of chiropractors and medical practitioners in a focus group interview\n\n**Article Abstract:**\n\nBackground\nWe report on a multidisciplinary focus group project related to the appropriate care of chiropractic patients who present with chest pain. The prevalence and clinical management, both diagnosis and treatment, of musculoskeletal chest pain in ambulatory medical settings, was explored as the second dimension of the focus group project reported here.\nMethods\nThis project collected observational data from a multidisciplinary focus group composed of both chiropractic and medical professionals. The goals of the focus group were to explore the attitudes and experiences of medical and chiropractic clinicians regarding their patients with chest pain who receive care from both medical and chiropractic providers, to identify important clinical or research questions that may inform the development of 'best practices' for coordinating or managing care of chest pain patients between medical and chiropractic providers, to identify important clinical or research questions regarding the diagnosis and treatment of chest pain of musculoskeletal origin, to explore various methods that might be used to answer those questions, and to discuss the feasibility of conducting or coordinating a multidisciplinary research effort along this line of inquiry. The convenience-sample of five focus group participants included two chiropractors, two medical cardiologists, and one dual-degreed chiropractor/medical physician. The focus group was audiotaped and transcripts were prepared of the focus group interaction. Content analysis of the focus group transcripts were performed to identify key themes and concepts, using categories of narratives.\nResults\nSix key themes emerged from the analysis of the focus group interaction, including issues surrounding (1) Diagnosis; (2) Treatment and prognosis; (3) Chest pain as a chronic, multifactorial, or comorbid condition; (4) Inter-professional coordination of care; (5) Best practices and standardization of care; and (6) Training and education.\nConclusion\nThis study carries implications for chiropractic clinical training relative to enhancing diagnostic competencies in chest pain, as well as the need to ascertain and improve those skills, competencies, and standards for referrals and sharing of clinical information that may improve cross-disciplinary coordination of care for chest pain patients.\n\n**Article Body:**\n\nBackground\nWhile the main focus of chiropractic care centers on treatment of musculoskeletal disorders, chiropractors serve as first point of contact with the health care system for patients presenting with a broad range of conditions [\n1\n]. As a portal-of-entry healthcare provider in a primary ambulatory setting, the professional responsibilities of the practicing chiropractor include proper assessment, documentation, and treatment of chest pain/discomfort cases, and appropriate and timely referral of chest pain patients as needed.\nAn extensive body of primary empirical literature addresses patient management protocols (differential diagnosis and diagnostic/treatment algorithms) for patients presenting with chest pain, primarily focusing on cardiopulmonary, gastroesophageal/gastrointestinal, and psychological conditions causing chest symptoms [\n2\n-\n17\n]. These etiologic sources are ruled out as the cause for many chest pain sufferers, and such patients essentially 'fall out of the algorithm' with ongoing chest pain that remains undiagnosed, untreated, and unresolved.\nA small but growing body of literature estimates the presumed prevalence of musculoskeletal chest pain in medical settings at 20–50% [\n14\n-\n18\n], and reflects a growing awareness that musculoskeletal causes remain largely unexplored as potential sources of chest pain, particularly for chronic or recurrent chest pain that remains undiagnosed and unresolved.\nThe Cochrane Database of Systematic Reviews (CDSR), containing completed reviews carried out by the Cochrane Collaboration \n, contains only one citation for chest pain, not musculoskeletal [\n19\n]. The Database of Abstracts of Reviews of Effects (DARE), maintained by the NHS Centres for Reviews and Dissemination and linked to the Cochrane Library \n, includes a number of reviews that focus on comparing various clinical diagnostic test strategies for cardio-related chest pain [\n20\n-\n29\n], as well as numerous organizational-level studies examining the clinical safety and cost-effectiveness of shifting cardio-related chest pain evaluation units from hospital inpatient to hospital outpatient settings [\n30\n-\n44\n]. Other review articles returned in the DARE search confirms our impression that current medical approaches to diagnosing, treating, or managing non-specific or non-cardiac chest pain focus principally on psychological and gastroesophageal/gastrointestinal causes and essentially ignore the potential for musculoskeletal etiologies [\n45\n-\n51\n].\nWe report on a multidisciplinary focus group project, one aspect of which specifically addressed issues related to the appropriate care of chiropractic patients who present with chest pain, whether as a main presenting complaint or as a co-morbid condition. The prevalence and clinical management, both diagnosis and treatment, of musculoskeletal chest pain in ambulatory medical settings, was explored as the second dimension of the focus group project reported here. The objective was to gain insight into the care and management of patients with musculoskeletal chest pain as experienced by both those with chiropractic training, medical training or combined training.\nMethods\nData collection\nFocus Group\nThis project collected observational data from a multidisciplinary focus group composed of both chiropractic and medical professionals. The goals of the focus group were to explore the attitudes and experiences of medical and chiropractic clinicians regarding their patients with chest pain who receive care from both medical and chiropractic providers, to identify important clinical or research questions that may inform the development of 'best practices' for coordinating or managing care of chest pain patients between medical and chiropractic providers, to identify important clinical or research questions regarding the diagnosis and treatment of chest pain of musculoskeletal origin, to explore various methods that might be used to answer those questions, and to discuss the feasibility of conducting or coordinating a multidisciplinary research effort along this line of inquiry.\nPopulation, setting, timeframe\nThe convenience-sample of five focus group participants included two chiropractors, two medical cardiologists, and one dual-degreed chiropractic/medical physician. The focus group was conducted in early 2004 at the offices of the medical cardiologists.\nSupport documents/instruments\nThe questions posed to focus group participants are provided in \nAdditional file 1\n. Aside from presenting the semi-structured questions, running the audio recorders, and ensuring that all questions were addressed within the time allotted for the focus group meeting, the facilitator's role during the focus groups session was intentionally minimalized in order to enhance the authenticity of the observations offered by focus group participants.\nHuman subjects\nThe Institutional Review Board of Palmer College approved this study of human subjects, including the Informed Consent document signed by all Focus Group participants. To protect subject confidentiality, subject records (i.e., signed Informed Consents and verbatim unblinded master transcript) were maintained in a locked file cabinet. The final 'blinded' transcript (all subject identifiers removed) was used during the content analysis, which was performed by all three investigators, although two of the study investigators were also present during the focus group.\nData management and analysis\nFocus Group Qualitative Analyses\nThe focus group was audiotaped and transcripts were prepared of the focus group interaction. Content analysis of the focus group transcripts were performed to identify key themes and concepts, using categories of narratives. All three authors analyzed complete transcripts and developed independent lists of overall themes and concepts subsumed within the general themes. Once completed, the investigators came together to collapse their lists of themes into one set of themes as reached via consensus. This process involved examining themes for commonality, classifying them for uniformity, and then reaching agreement on the final list of six key themes. Once the themes were set and subordinate concepts identified, each investigator looked for quotes and comments which exemplified those themes and concepts (which are presented in the Results, below)\nAs a methodological 'cross-check', the investigative group's consensus process confirmed observations drawn from each investigator's independent analysis of the transcripts, which strengthened the validity and reliability of the study findings reported from this qualitative research [\n52\n,\n53\n]. It is important to note that this research is an exploration into the specifics of the convenience sample drawn for the project; therefore, generalizability is not a significant consideration in this study.\nResults\nSix key themes emerged from the analysis of the focus group interaction, including issues surrounding (1) Diagnosis; (2) Treatment and prognosis; (3) Chest pain as a chronic, multifactorial, or comorbid condition; (4) Inter-professional coordination of care; (5) Best practices and standardization of care; and (6) Training and education. These thematic issues are summarized below, and key excerpts from the focus group transcript exemplifying these thematic issues are included in \nAdditional file 2\n.\n(1) Diagnosis\nParticipants reported that a good history and physical exam are essential and important to good diagnosis, that a history should include all prior care received for that condition, that records of prior care should be obtained directly from the source provider, and that history, exam, and differential diagnosis are central to the provision of portal-of-entry primary care as well as secondary specialty care. They noted that diagnostic uncertainty, complexity, and discriminant variability are characteristic of chest pain assessment and diagnostic tests, that the inherently high risk of chest pain determines the order of differential workup and the path of diagnostic referral care (e.g., rule out cardiac and other major medical conditions first), and that musculoskeletal chest pain is principally a diagnosis by exclusion. Anecdotal experience of both chiropractic and medical cardiology focus group participants confirms reports in the literature of a high prevalence of suspected musculoskeletal chest pain in ambulatory practice settings.\n(2) Treatment and prognosis\nChiropractic participants reported anecdotal evidence (their personal practice experience) of the effectiveness of manual/manipulative approaches to resolve chest pain of suspected musculoskeletal origin. Chiropractic and medical participants both noted lack of formal clinical studies examining effectiveness of manual/manipulative approaches to manage (diagnose and treat) musculoskeletal chest pain, and lack of evidence supporting effectiveness for medical drug interventions for musculoskeletal chest pain (e.g., oral nonsteroidal anti-inflammatory drugs or steroid injections into chest wall), and that it is unknown to what extent drug interventions are prescribed for such conditions in actual current medical practice (generalist or specialist). The agreed that both effectiveness and safety concerns should direct the appropriateness and order of trying various clinical approaches to resolve musculoskeletal chest pain in a given patient, and that a better understanding of the etiology of musculoskeletal chest pain condition(s) would also help discriminate between different conditions and guide the search for identifying effective interventions for a given condition. Natural history or prognosis of treated versus untreated acute or chronic musculoskeletal chest pain is also unknown.\n(3) Chest pain as a chronic, multifactorial, or comorbid condition\nIt is unknown to what extent chronic, unresolved chest pain may represent undiagnosed musculoskeletal chest pain, or to what extent patients with undiagnosed and unresolved musculoskeletal chest pain are perhaps being misclassified as psychological or psychiatric cases. The participants commented that chronic recalcitrant chest pain is associated with high resource use and unsatisfied, distressed patients, that it is unknown to what extent early manual/manipulative intervention in acute musculoskeletal chest pain may prevent development of chronic musculoskeletal chest pain, that chronic musculoskeletal chest pain may raise patient care issues similar to other chronic conditions (i.e., providers and patients may manage some chronic conditions, rather than resolve them), and that the diagnostic and treatment considerations are further complicated when musculoskeletal chest pain and non-musculoskeletal chest pain may exist together as related or unrelated comorbidities. Finally, they noted that with a higher likelihood of degenerative musculoskeletal disorders in older patients and also higher likelihood of visceral (cardiopulmonary or gastrointestinal) disorders in older patients, chest pain in older patients therefore may be more likely of multi-factorial etiology and more likely associated with comorbidities.\n(4) Inter-professional coordination of care\nParticipants reported that referrals should be based on evidence of efficacy/effectiveness for a given condition such as musculoskeletal chest pain, that the path of referral for chest pain will depend on the nature of the condition and the urgency of the situation, that the point of referral may depend on the familiarity or relationship between the providers, and that the nature of the referral (e.g., amount and type of information accompanying the referral) may depend on the nature of the condition, whether the referral is for reasons of diagnosis and/or treatment, the preference of the provider, and the relationship between the providers. Medical specialists (e.g., cardiology) who receive referrals from primary medical practitioners will most typically return the patient to the primary medical practitioner rather than referring them elsewhere, although this also may depend on the nature of the condition and the relationship between the specialty and primary medical practitioner.\nParticipants felt that patients with co-morbidities (e.g., having both musculoskeletal and non-musculoskeletal chest pain) may be more likely to receive concurrent care from more than one provider, that providers can pro-actively improve interprofessional relationships by being diligent about sharing pertinent information and reports during referrals. Participants felt that educating other providers about available evidence, recognizing and addressing issues of professional boundary protection (often referred to as 'turf'), and that patients' direct experience (with successful or unsuccessful treatment outcome) and their preferences will also impact provider perceptions and interprofessional relationships.\n(5) Best practices and standardization of care\nParticipants reported that standardizing care within professions may facilitate opportunities for interprofessional referrals, that guidelines and care standards are an issue for all professions, that interactions between providers and professions (e.g. referrals) may also be standardized, and that 'best practices' for coordinating musculoskeletal chest pain care would center on the role of primary medical practitioners rather than specialist medical practitioners.\n(6) Training/Education\nCompetencies in exam, diagnostic, and clinical decision-making skills for chest pain were raised as issues for, and by, both chiropractors and medical practitioners. Medical practitioners' perception, familiarity and comfort with chiropractors' diagnostic skills largely comes via direct exposure in postgraduate practice (exchanging clinical reports, etc.) rather than during their medical training. Participants commented that there is a perception that medical education/training is more standardized than chiropractic, and a perception that medical practice is more consistent with medical training (i.e., chiropractors' clinical practice may be more likely to deviate from what they were taught). A comment was made that medical training includes developing skills/competencies in referral practices (e.g., standardized referral forms are used in medical academic practice and teaching clinics).\nDiscussion\nThe focus group dialogue suggested several implications for current and future chiropractic practice, undergraduate and post-professional chiropractic education and clinical training, research, and professional organization or policy. These implications for practice, education, research, and policy are summarized below along with our recommendations.\nClinical practice\nWith all portal-of-entry providers such as chiropractors, the responsibility to diagnose chest pain is vital. The focus group touched on this point several times. In order to arrive at a diagnosis for chest pain, or any other condition, they stressed the importance of first taking a good history and then performing a thorough examination. The diagnosis of chest pain, however, is complicated and requires excellent diagnostic skills. The focus group (both the chiropractors and the medical practitioners) expressed a concern over the ability of chiropractors to accurately diagnose chest pain. In order for chiropractors to have a role in managing chest pain from the point of entry, they must acquire and demonstrate competence in diagnosing the complaint.\nChest pain can have a multitude of etiologies, involves an inherently high level of diagnostic uncertainty, and diagnostic algorithms are complex. The clinician's most immediate concern is ruling out emergent versus non-emergent conditions [\n54\n-\n58\n]. The focus group participants were unified in voicing the need for rapid diagnosis and management for cardiopulmonary conditions such as myocardial infarction and pulmonary embolism, among others. They also pointed out that the clinical picture of chest pain can be complicated by simultaneous etiologies. For example, one of the medical doctors noted that in his own practice he saw patients with cardiac disease and chest wall tenderness. This sentiment was echoed by one of the chiropractors who noted that simply palpating a patient's chest wall and finding tenderness does not rule out cardiac or other life threatening causes of chest pain. Therefore, a full chest pain work up must include evaluations for cardiac, pulmonary, gastrointestinal, musculoskeletal and psychological causes of chest pain.\nOnce life threatening causes of chest pain have either been ruled out or managed, other possible etiologies may be investigated. The focus group expressed concern that musculoskeletal chest pain may be either missed or misdiagnosed as psychological in nature. The misdiagnosis of musculoskeletal chest pain as psychological could cause much distress, cost, and unnecessary suffering for patients. It is important, therefore, to investigate efficient and accurate diagnostic strategies for this complaint.\nParticipants in the focus group commented that musculoskeletal chest pain is common in their practices, both chiropractic and medical. This is consistent with reports in the literature that 20%–50% of chest pain presentations in ambulatory settings may be musculoskeletal [\n14\n-\n18\n]. Management of chest pain of cardiac or gastrointestinal origin is much more standardized than musculoskeletal chest pain. Appropriate protocols and treatment algorithms do not exist for musculoskeletal chest pain. Manipulation, physiological therapeutics, injections, analgesics, and other treatments may be employed, but none have been extensively investigated.\nThe opportunity for cross-disciplinary coordination of care for chest pain certainly exists. Unfortunately, effective referral pathways do not exist. Chest pain in medical practice is often diagnosed by cardiologists who then send patients back to their referring clinicians, most likely a primary care medical physician. Therefore, it is important to ascertain and possibly improve those skills, competencies, and standards for referrals and sharing of clinical information that may improve current and future cross-disciplinary coordination of care for chest pain patients.\nClinical and health services research\nIt is apparent that there is insufficient scientific evidence to guide clinical practice and decision making for musculoskeletal chest pain. The focus group chiropractic participants largely reported only personal anecdotal evidence for the effectiveness of manipulative interventions for chest pain of suspected musculoskeletal origin, and both the chiropractors and medical practitioners commented upon this lack of evidence, both in terms of therapy as well as for diagnosis. Similarly, there is a concomitant lack of evidence supporting the chemotherapeutic interventions used by medical doctors for suspected musculoskeletal chest pain.\nThus, there is much that is not known. Research questions worth investigating include:\n• What is the incidence and prevalence of musculoskeletal chest pain in chiropractic clinical practice?\n• What is the incidence and prevalence of musculoskeletal chest pain in specialist cardiologist practice? In general medical practice?\n• What percentage of chiropractors treat musculoskeletal chest pain compared to those who refer out for care?\n• How effective is manipulation for treating musculoskeletal chest pain?\n• What other modalities do chiropractors use during such treatments?\n• What diagnostic methods are used for determining the presence of musculoskeletal chest pain? What is the reliability, validity, sensitivity and specificity of each test?\n• What are the costs involved in treating such cases?\n• What interdisciplinary models exist with regard to developing coordinated-care protocols for diagnosis and treatment of acute musculoskeletal chest pain? For long-term management of chronic or recurrent musculoskeletal chest pain?\n• Do incidence and prevalence rates vary geographically or by setting?\nOne challenge relative to chiropractic research is that funding sources are limited and few opportunities exist. So, this presents a conundrum, in that more research is needed but the greatest amount of resources (both funding, and limited research workforce) are directed toward conditions which are already well established with regard to chiropractic research: low back pain, neck pain, and headache.\nA Search using the key terms \"Chiropractic\" and \"Musculoskeletal Chest Pain\" on PubMed yielded only three papers, two of which had no real pertinence to the issue at hand. The third paper was a case report that looked at using a specific chiropractic adjusting procedure for managing chronic chest pain [\n59\n]. There were no randomized trials found in the literature. Shifting the search to the terms \"Medicine\" and \"Musculoskeletal Chest Pain\" improved the yield to just nine papers, one of which was a repeat from the chiropractic search, and several of which were tangential to this issue. Obviously, this is an area needing far more research.\nAs a first pass at documenting and better understanding this problem area, it would be useful to survey the chiropractic profession to quantify rates of musculoskeletal and non-musculoskeletal chest pain presentations in clinical practice, whether as a chief complaint, or as a related or unrelated comorbid condition. The incidence rate of chest pain presentations to chiropractic teaching clinics has been estimated to range from 1% to 7% [\n60\n,\n61\n], but rates in a typical chiropractic practice are essentially unknown. In surveying chiropractors regionally or nationally, it would also be worthwhile to compare incidence and prevalence rates in rural versus non-rural chiropractic practice, given that chiropractors located in rural or underserved areas may be more likely to serve as the patient's first contact with the health care system, or to function as their patient's main or usual source of care in a broader generalist capacity compared to chiropractors in other areas [\n62\n,\n63\n]. Chiropractors serving as a first contact or portal-of-entry in a primary care setting may be more likely to see chest pain cases presenting earlier during an episode of care-seeking, or more likely as a generalist to serve as a main source of care overall for an entire chest pain episode. Along that same line, a comparison of rates in chiropractic versus medical practice may also provide insight as to potential implications for management and co-management of these conditions and patients in the primary care setting.\nIt is important to note that such research should of necessity be collaborative and interdisciplinary. As noted, funding opportunities within chiropractic are limited, yet chiropractors are working in collaboration with medical physicians in a variety of settings. Following case reports and case series which suggest a role for manipulative intervention in musculoskeletal chest pain, the next step would be to devise collaborative research within medical settings, acknowledging that this is likely the best location to obtain participants for research. A multi-disciplinary practice-based research effort could provide a foundation for conducting the requisite feasibility studies and generating the necessary preliminary clinical data and methods (e.g., developing protocols and establishing reliability of procedures), that can then guide and justify more extensive, more rigorous, controlled preclinical and clinical trial work along this line of inquiry.\nEducation and educational research\nWhat becomes obvious is that a lack of research has impact and implications for the education of both chiropractors and medical physicians with regard to managing chest pain of musculoskeletal origin. This is also the case with inter-professional collaboration and referral. One comment made by a participant (the dual qualified chiropractor/medical practitioner) was that most medical physicians do not know enough about the training of chiropractors, and do not know about chiropractic diagnostic acumen.\nIn responding to the question asked by one participant as to how relations between chiropractors and medical practitioners might change, one of the chiropractic physicians answered \"better education\" and noted that the Council on Chiropractic Education has laid out what he referred to as \"the minimum requirements\" for education in this field. This suggests that not enough is being done to enhance the education of chiropractic students with regard to musculoskeletal chest pain, and perhaps it is necessary to undertake a study across the chiropractic colleges.\nChiropractic colleges in North America tend to use chiropractic physicians as the main faculty in the diagnosis classes. Therefore, it is commonly the case that cardiology classes are taught by chiropractic physicians with expertise in family practice, such as those who have earned diplomate certification (advanced postgraduate training programs) in family practice and internal medicine. However, these programs should not be seen as equivalent to medical residencies in family practice. They usually require approximately 360 additional hours of didactic training, with only part of that training in a clinical setting. There are efforts underway to develop the 'advanced practice' chiropractic physician, with one chiropractic educational institution offering a training program coordinated by a medical physician. However, this is in its infancy and much needs to be worked out. This does indicate a growing level of interest in this kind of training, and will produce chiropractic physicians even better able to correctly differentiate a diagnosis of musculoskeletal chest pain. The participants in the focus group made no mention of postgraduate training or opportunity, yet this represents the one area beyond the standard curriculum where further training can be gained and is therefore the only way in which current chiropractors may finally gain new understanding of processes such as discussed here.\nIt would be worthwhile to survey the academic institutions to gain a better understanding of what is currently being taught across the chiropractic curriculum, as well as through postgraduate offerings. Focus groups comprised of diagnosis and cardiology instructors, postgraduate instructors, and representative field practitioners, can be performed. Such efforts would help derive a better picture of the current reality across the chiropractic profession with regard to education in musculoskeletal chest pain.\nInterestingly, concern was also raised by participants that the current training in medical schools was inadequate, and that in part this was due to instructors who were not completely conversant with some of the more traditional means of diagnosis. An excerpt from the medical focus group comment underscores this observation: \"... most cardiology now is very simple... Which test will give me the diagnosis? Most cardiologists...don't know auscultation... how to listen to the heart... professors for 15–20.... were never taught.\" This comment suggests that the 'low-tech' art of auscultation is being lost in medical practice, or increasingly replaced by 'higher-tech' laboratory testing in driving the process of diagnosis for cardiac problems, an opinion echoed in the literature [\n64\n,\n65\n]. A study of curricular and postgraduate medical education may similarly provide insights relative to current teaching and skills development for medical practitioners in managing musculoskeletal chest pain.\nProfession and health policy\nAs a professional issue, attention needs to be afforded the inherent uncertainty and complexity of chest pain diagnosis and the sometimes dynamic interplay between 'diagnosis' and 'treatment' whether in managing a given patient in actual practice or in attempting to define an appropriate evidence-based professional 'standard of care'. This is perhaps particularly true for a condition such as musculoskeletal chest pain, given the obvious dearth of established evidence from which the clinician may draw or on which to form definitive professional recommendations to guide current clinical practice. As a corollary example of an empirical 'treatment-based' diagnostic strategy, a presumptive diagnosis of gastroesophageal reflux disease (GERD) may be pragmatically validated in practice following a patient's favorable symptomatic response to a short course of prescriptive therapy such as proton-pump inhibitors, perhaps preempting or potentially avoiding more invasive or costly diagnostic tests such as endoscopy [\n66\n-\n72\n]. Non-cardiac chest pain, defined most simply as recurrent episodes of unexplained retrosternal pain in patients lacking a cardiac abnormality after a reasonable evaluation, is associated with repeated emergency room utilization [\n73\n] and may be treated empirically with antidepressants [\n74\n].\nWe might ask whether there is a role for musculoskeletal assessments within clinical chest pain diagnostic algorithms that is not being fully exploited in current practice, particularly given the relative costs and safety of the more invasive and resource-intensive alternatives, not to mention patient preferences. In cases where an early 'low-tech' assessment offers a presumptive suggestion that chest pain may be musculoskeletal in nature, might a short course of manual therapy help to validate a presumptive diagnosis and guide treatment decisions [\n75\n-\n80\n]? How much, and what level, of current available evidence is needed to support clinical decisions or professional recommendations that favor low-technology, low-cost noninvasive procedures early in the diagnostic workup, or that justify manual therapy following an empirical validation of a presumptive musculoskeletal diagnosis? These are tough questions with no easy answers, especially given the inherent high-risk, uncertainty, and complexity of chest pain diagnosis, and the possibility that chest pain may present with any mix of multiple musculoskeletal or non-musculoskeletal etiologies or comorbidities.\nMusculoskeletal chest pain as an area of inquiry fits well within the health services research agendas outlined in health policy initiatives to improve primary care, patient safety, and the delivery of evidence-based cost-effective care. As identified earlier, the appropriate management of chest pain raises a host of considerations relative to improving cross-disciplinary coordination of care within the health care system, whether for diagnostic consult, referral for treatment, or continuity of care in the overall management of the patient's total care plan. The potential implications for improving patient safety are also worth noting, specifically relative to enhancing prompt accurate diagnosis, and where possible decreasing unnecessary exposure of patients to higher risk or more invasive procedures. As a specific target within the primary care, patient safety, and cost-of-care initiatives, 'ambulatory-care sensitive conditions' are identified as those conditions that, when managed appropriately in the outpatient setting, can prevent unnecessary and costly inpatient care. Chest pain is high on the list of high prevalence ambulatory conditions associated with 'avoidable hospitalizations', and with repeated high-cost hospital emergency room utilization [\n73\n]. While discipline-specific approaches to diagnosing or treating non-cardiac chest pain of gastrointestinal, psychiatric, or musculoskeletal origin have served useful, the quality and safety of patient care may be even better served by a coordinated cross-disciplinary research effort and practice approach.\nA final health policy consideration relative to health workforce planning and development, is in acknowledging that chiropractors serve a role as a first point of contact with the health care system or as the main source of care for many patients, particularly in rural or medically underserved areas [\n62\n,\n63\n]. Policies to improve access to care by promoting the primacy of the relationship between usual-source practitioners and their patients, must also pay due attention to developing the role and requisite skills of non-medical practitioners such as chiropractors to appropriately manage or co-manage a broad range of conditions such as chest pain in primary care settings.\nConclusion\nOur research leads us to offer a number of recommendations for practice, research, education, and policy. Certainly, the investigators and members of the focus group feel that more education should be required in the diagnosis and management of chest pain. Research is also needed about the educational opportunities and challenges revolving around interdisciplinary care and practice.\nGreater outreach to the medical research community, and indeed to the wider medical community, will help to enhance skill sets and collaborative opportunities. This outreach may help to drive research in those areas where it is most needed: diagnosis, incidence/prevalence, treatment, and clinical protocols within and across disciplines. By developing a research base, it will be possible to establish appropriate standards for care, and these can be enhanced by creating multidisciplinary panels to explicitly improve cross-disciplinary coordination of care.\nCompeting interests\nThe author(s) declare they have no competing interests.\nAuthors' contributions\nMonica Smith conceived the study, and coordinated the focus group meetings as well as performed thematic analysis of transcripts and helped write the manuscript. Dana Lawrence performed thematic analysis and coding of transcripts and prepared components of the manuscript. Robert Rowell also performed thematic analysis and coding of transcripts and prepared components of the manuscript. All three authors read and approved the final manuscript.\nSupplementary Material\nAdditional File 1\nFocus Group Questions for MD & DC Chest Pain Study.\nClick here for file\nAdditional File 2\nSeminal excerpts of dialogue from focus group transcripts, bytopic.\nClick here for file\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** definitely relevant"
}
] |
definitely relevant
|
41
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe association between noise exposure and blood pressure and ischemic heart disease: a meta-analysis.\n\n**Article Abstract:**\n\nIt has been suggested that noise exposure is associated with blood pressure changes and ischemic heart disease risk, but epidemiologic evidence is still limited. Furthermore, most reviews investigating these relations were not carried out in a systematic way, which makes them more prone to bias. We conducted a meta-analysis of 43 epidemiologic studies published between 1970 and 1999 that investigate the relation between noise exposure (both occupational and community) and blood pressure and/or ischemic heart disease (International Classification of Diseases, Ninth Revision, codes 410-414). We studied a wide range of effects, from blood pressure changes to a myocardial infarction. With respect to the association between noise exposure and blood pressure, small blood pressure differences were evident. Our meta-analysis showed a significant association for both occupational noise exposure and air traffic noise exposure and hypertension: We estimated relative risks per 5 dB(A) noise increase of 1.14 (1.01-1.29) and 1.26 (1.14-1.39), respectively. Air traffic noise exposure was positively associated with the consultation of a general practitioner or specialist, the use of cardiovascular medicines, and angina pectoris. In cross-sectional studies, road traffic noise exposure increases the risk of myocardial infarction and total ischemic heart disease. Although we can conclude that noise exposure can contribute to the prevalence of cardiovascular disease, the evidence for a relation between noise exposure and ischemic heart disease is still inconclusive because of the limitations in exposure characterization, adjustment for important confounders, and the occurrence of publication bias.\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
42
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe environmental pain of pleasure boating.\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
43
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nCocaine-induced renal infarction: report of a case and review of the literature\n\n**Article Abstract:**\n\nBackground\nCocaine abuse has been known to have detrimental effects on the cardiovascular system. Its toxicity has been associated with myocardial ischemia, cerebrovascular accidents and mesenteric ischemia. The pathophysiology of cocaine-related renal injury is multifactorial and involves renal hemodynamic changes, alterations in glomerular matrix synthesis, degradation and oxidative stress, and possibly induction of renal atherogenesis. Renal infarction as a result of cocaine exposure, however, is rarely reported in the literature.\nCase presentation\nA 48 year-old male presented with a four-day history of severe right flank pain following cocaine use. On presentation, he was tachycardic, febrile and had severe right costovertebral angle tenderness. He had significant proteinuria, leukocytosis and elevated serum creatinine and lactate dehydrogenase. Radiographic imaging studies as well as other screening tests for thromboembolic events, hypercoagulability states, collagen vascular diseases and lipid disorders were suggestive of Cocaine-Induced Renal Infarction (CIRI) by exclusion.\nConclusion\nIn a patient with a history of cocaine abuse presenting with fevers and flank pain suggestive of urinary tract infection or nephrolithiasis, cocaine-induced renal infarction must be considered in the differential diagnosis. In this article, we discuss the prior reported cases of CIRI and thoroughly review the literature available on this disorder. This is important for several reasons. First, it will allow us to discuss and elaborate on the mechanism of renal injury caused by cocaine. In addition, this review will demonstrate the importance of considering the diagnosis of CIRI in a patient with documented cocaine use and an atypical presentation of acute renal injury. Finally, we will emphasize the need for a consensus on optimal treatment of this disease, for which therapy is not yet standardized.\n\n**Article Body:**\n\nBackground\nCocaine abuse has been known to have detrimental effects on the cardiovascular system. Its toxicity has been associated with myocardial ischemia, cerebrovascular accidents and mesenteric ischemia. The pathophysiology of cocaine-related renal injury is multifactorial and involves renal hemodynamic changes, alterations in glomerular matrix synthesis, degradation and oxidative stress, and possibly induction of renal atherogenesis. Renal infarction as a result of cocaine exposure, however, is rarely reported in the literature.\nCase presentation\nA 48 year-old African American male presented to our hospital with a four-day history of severe right flank pain starting several hours after smoking cocaine. His pain was associated with subjective fevers, nausea and vomiting. There was no gross hematuria or dysuria. His blood pressure was 140/78 mmHg, heart rate 130 beats per minute, temperature 39.5 °C, respiratory rate 18 breaths per minute and his oxygen saturation was 98% on room air. Pertinent exam findings included severe right costovertebral angle tenderness, diffuse right-sided abdominal pain and a positive psoas sign on the right. Laboratory data showed a white blood cell count of 14 × 10\n9\n/L (76% neutrophils), serum creatinine 1.4 mg/dL (124 μmol/L), lactate dehydrogenase (LDH) 704 U/L and serum creatinine kinase (CPK) 259 U/L. A urinalysis showed 3+ proteinuria, 1 to 3 red blood cells per high power field and no white blood cells or casts. Urine toxicology confirmed the presence of cocaine. A Computerized Tomography (CT) scan with contrast revealed a sharply-demarcated heterogenous area of focal decreased enhancement in the anterior right kidney consistent with renal infarct, but pyelonephritis could not be completely ruled out (figure \n1\n). Volume-rendered Single Photon Emission-Computed Tomography (SPECT) image of a gallium scan showed no evidence of tracer localization in the right kidney to suggest an infection. It did reveal absence of tracer localization in the upper pole of the right kidney suggesting absence of perfusion to that area (figure \n2\n). Blood and urine cultures were negative. A trans-thoracic and a subsequent trans-esophageal echocardiogram showed no evidence of intra-cardiac thrombus or valvular vegetations. Further screening tests for hypercoagulability (factor V Leiden, prothrombin gene, protein C and protein S, anti-thrombin III, anti-phospholipid antibody and homocysteine); collagen vascular disease (rheumatoid factor and antinuclear antibody); and lipid disorders were within normal limits. Our patient was then diagnosed with CIRI by exclusion.\nDiscussion\nCocaine abuse and addiction continues to be a problem that plagues the entire world. Cocaine (benzoyl methylecgonine) is available in two forms: cocaine hydrochloride and the alkaloid cocaine (freebase/crack), which is made by alkanizing the salt, followed by extraction with non-polar solvents. Both forms are well absorbed through most mucous membranes [\n1\n]. The plasma half-life is approximately 45 to 90 minutes. The elimination of cocaine is predominantly controlled by its biotransformation since its renal clearance is only 27 mL/min [\n2\n]. The pathways for the biotransformation involve plasma and liver cholinesterases that produce benzoyl and ethyl methylecgonine which are water-soluble metabolites excreted in urine [\n3\n].\nThe pathophysiologic effects of cocaine-induced renal injury involve several mechanisms. First, cocaine affects vascular reactivity and renal hemodynamics. This is thought to be due to its ability to inhibit uptake of catecholamines in the synapse, inhibit re-uptake of norepinephrine in sympathetically innervated tissues and release norepinephrine and epinephrine from the adrenal medulla [\n4\n,\n5\n]. There's also evidence that cocaine can directly increase calcium influx in vascular smooth muscle [\n6\n,\n7\n]. This effect has been documented in post-sympathectomy arteries as well as in umbilical arteries, which lack sympathetic innervation [\n6\n,\n7\n]. Second, cocaine has been shown to affect matrix synthesis degradation and oxidative stress in kidney [\n8\n]. Third, cocaine has been shown to accelerate renal atherogenesis [\n9\n,\n10\n].\nAlthough major toxic effects of cocaine such as myocardial ischemia, cerebrovascular accidents, mesenteric ischemia and placental infarcts have been well- documented in the literature, renal infarction as a complication of cocaine toxicity is rare. In this article, we will attempt to raise awareness of this under-reported entity by discussing its pathophysiology, clinical presentation and the current treatment modalities.\nCommon risk factors for renal infarction include valvular heart disease and atheroembolic events. Hypercoagulopathy, systemic vasculitis, blunt trauma, collagen vascular disorders, vascular intervention procedures and endocarditis are other less common risk factors associated with renal infarct.\nCocaine-induced renal damage is well-documented in the literature; however, renal infarction due to cocaine is not a well-known entity. Throughout our literature search, we identified seven other such reports (table \n1\n) [\n11\n-\n17\n]. In one patient, a renal infarct was thought to be due to unilateral right renal artery thrombosis and embolization associated with intravenous cocaine injection [\n11\n]. Kramer et al. described a patient with a right renal thrombosis and infarction associated with protein C deficiency [\n12\n]. In another report, Antonovych et al. noted unusual renal involvement in two cocaine addicts [\n13\n]. One patient was a 26 year-old male who presented with malignant hypertension, who was found to have renal infarction. From this report, it is uncertain whether cocaine-induced malignant hypertension led to renal infarction or if cocaine-induced renal infarction presented as a case of malignant hypertension. The other patient was a 39 year-old male with recent cocaine use who had an emergent surgical nephrectomy for unclear reasons, and was found to have arterial and venous thrombosis with massive infarction. Two other cases describe right renal infarctions in patients with recent cocaine use in whom no other abnormalities were found [\n14\n,\n15\n]. Edmondson et al. described a 40-year-old male with renal artery dissection and thrombosis presumed to be due to cocaine which led to renal infarction [\n16\n]. Mochizuki et al. reported a 52-year-old female with recent intranasal use of cocaine who presented with acute aortic thrombosis associated with renal infarct [\n17\n].\nIt is not known whether there is a gender predilection for this disorder. Interestingly, all but one of the reported cases of CIRI has occurred in males. This occurrence may be due to an increased prevalence of cocaine use in males. It is also possible that males may be more genetically prone to this disorder. However, given the small number of reported cases, one cannot make any certain conclusions about genetic susceptibility.\nIn our review, we also noted that all but one of the reported cases of CIRI have involved the right kidney. It is generally accepted that the right renal artery is longer than the left due to its anatomical position in relation to the great vessels. Merklin et al. investigated the varied blood supply of the kidneys by dissecting 185 kidneys obtained from adult cadavers. The length of the right renal artery from the aortic origin to its division point was as long as 8.0 cm and that of the left varied from 0.5 to 6.0 cm [\n18\n]. The calibers of these arteries were similar in diameter, and their average diameter was 5.5 mm with variations from 4 to 7 mm [\n18\n]. One must keep in mind that neither p-values nor confidence intervals were described in this study.\nSteady flow models for blood flow analysis in human circulation are very complex. The simplest model for blood flow through any vessel assumes a flow of a fluid with a constant viscosity through a non-tortuous and straight cylindrical tube of circular cross-section [\n19\n]. Such fluid flows are well-described by Poiseuille Equations in the honor of J. L. M. Poiseuille who performed many experiments relating pressure gradient, flow, tube geometry and length [\n19\n].\nPoiseuille formulated the factors that affect flow of fluid in a tube as:\nQ = (P\n1\n-P\n2\n) π r\n4\n/8ήL\n(Q = flow rate; P\n1\n- P\n2 \n= pressure difference across a circuit; r = radius; ή = viscosity of fluid; L = length of vessel).\nGiven the inverse relationship of flow to resistance:\nResistance = flow \n-1\nWe can then conclude that resistance in a vessel is directly proportional to its length, and indirectly proportional to the radius to the power of four:\nResistance α Length/radius\n4\nSince the radius of the right and left renal arteries are similar in size, we postulate that the right kidney is more prone to ischemia due to the increased resistance that it encounters by the longer length of its artery. Whether this is true or not, one must take into account the limited number of reported cases along with the lack of advanced studies to investigate the exact anatomy of the renal arteries in these particular patients.\nThe pathophysiology of cocaine-related renal injury is multifactorial and involves renal hemodynamic changes, alterations in glomerular matrix synthesis, degradation and oxidative stress, and possible induction of renal atherogenesis [\n8\n-\n10\n,\n20\n]. The exact mechanism of how cocaine causes renal infarction, however, is unclear, and several possibilities have been proposed. Cocaine is known to enhance platelet aggregation and increase thromboxane synthesis [\n21\n]. It is also known to inhibit synaptosomal uptake of catecholamines, block the re-uptake of norepinephrine in sympathetically innervated tissues and release norepinephrine and epinephrine from the adrenal medulla [\n4\n,\n5\n,\n21\n]. Other vasoconstrictive factors such as endothelin have also been postulated to play a role in the vascular catastrophes caused by cocaine intoxication [\n22\n].\nThere is evidence that cocaine may enhance the renal cortical messenger RNA expression of tissue inhibitors of metalloproteinase-2 [\n8\n]. This would have the net effect of increasing matrix accumulation. Use of cocaine also increases the oxidative stress in the kidney. In experimental cultured kidney cells exposed to cocaine, there has been a lower level of intracellular glutathione, which is the most abundant cell thiol with antioxidant functions [\n23\n]. There is also supporting evidence that systemic atherosclerosis may be an inflammatory disorder. Both experimental and autopsy findings confirm that cocaine is an accelerator of atherogenesis [\n9\n,\n10\n].\nRenal infarction due to cocaine abuse usually presents with severe persistent flank and/or abdominal pain associated with nausea or vomiting with or without elevated temperature. The onset of pain is usually 2–3 hours after cocaine use, but it can be delayed for up to 4 days. All routes of cocaine administration including intravenous, insufflations, and intranasal and free-basing crack cocaine have been associated with renal infarction. Leukocytosis, microscopic hematuria and elevated levels of serum LDH are common findings. However, these findings are neither sensitive nor specific for CIRI.\nVarious imaging techniques including CT scan, Magnetic Resonant Imaging (MRI), angiography, Ultrasound and Nuclear Scintigraphy Scans have been used to make the diagnosis. However, MRI, angiography and nuclear scintigraphy are expensive, system-specific and time-consuming, and they may not be readily available at all institutions. Ultrasound lacks sensitivity and specificity for renal infarction. Therefore, CT scan has been recommended for the diagnosis of this challenging disease. CT scan, however, becomes less reliable when the infarct is global and there is loss of viable cortical rim, or when the infarct simulates a tumefactive process.\nThere is no consensus on the treatment of renal infarction due to cocaine use. Prior treatment modalities in the literature range from no treatment to anticoagulation, thrombolytic use, aspirin therapy and surgical nephrectomy. Given that no evidence of underlying coagulopathy or thromboembolic events were identified in our patient, we opted to conservatively manage him with supportive therapy and pain management. He was successfully discharged on hospital day six with a serum creatinine of 1.2 mg/dL (106.1 umol/L).\nConclusion\nCocaine intoxication is associated with multiple cases of vascular injury. Renal infarction as a result of cocaine use, however, is uncommon. In a patient with a history of cocaine abuse presenting with fevers and flank pain suggestive of urinary tract infection or nephrolithiasis, cocaine-induced renal infarction must be considered in the differential diagnosis. The vasoconstrictive and thrombotic effects of cocaine are most likely the dominant factors in cocaine-induced renal infarction. The possible atherogenic effect of cocaine and the relationship of this effect to renal infarct is likely to be a long term, rather than an acute factor. The diagnosis of CIRI is based on exclusion of other entities that cause renal infarct (e.g. hypercoagulable states due to factor deficiency, autoimmune diseases and thromboembolic events), in conjunction with documented cocaine use and appropriate radiographic studies. We highly recommend non-invasive evaluation of the renal arterial supply in patients with CIRI in order to broaden our knowledge of this disorder, and conceivably better understand its selectivity for one kidney. Thus far, there is no agreement on the management of patients with this disease. In fact, it is difficult to suggest a uniform therapeutic approach to this disorder because one cannot predict whether the infarct will be due to vasospasm, thrombosis or both. In addition, the extent of the renal infarct will likely influence clinical management and outcome. Although anticoagulation, antithrombotic, conservative managements as well as surgical approaches have been attempted with variable success, perhaps the most plausible treatment would be to prevent this misfortune by patient education.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nSB performed the main background search and drafted the manuscript. MM participated in the study design and helped to draft the manuscript. SMN participated in the study design and coordination and helped to draft the manuscript. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
44
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nRheumatoid arthritis is an independent risk factor for multi-vessel coronary artery disease: a case control study\n\n**Article Abstract:**\n\nThe risk for cardiovascular (CV) disease is increased in rheumatoid arthritis (RA) but data on the burden of coronary atherosclerosis in patients with RA are lacking. We conducted a retrospective case-control study of Olmsted County (MN, USA) residents with RA and new-onset coronary artery disease (CAD) (\nn \n= 75) in comparison with age-and sex-matched controls with newly diagnosed CAD (\nn \n= 128). Angiographic scores of the first coronary angiogram and data on CV risk factors and CV events on follow-up were obtained by chart abstraction. Patients with RA were more likely to have multi-vessel coronary involvement at first coronary angiogram compared with controls (\nP \n= 0.002). Risk factors for CAD including diabetes, hypertension, hyperlipidemia, and smoking history were not significantly different in the two cohorts. RA remained a significant risk factor for multi-vessel disease after adjustment for age, sex and history of hyperlipidemia. The overall rate of CV events was similar in RA patients and controls; however, there was a trend for increased CV death in patients with RA. In a nested cohort of patients with RA and CAD (\nn \n= 27), we measured levels of pro-inflammatory CD4\n+\nCD28\nnull \nT cells by flow cytometry. These T cells have been previously implicated in the pathogenesis of CAD and RA. Indeed, CD4\n+\nCD28\nnull \nT cells were significantly higher in patients with CAD and co-existent RA than in controls with stable angina (\nP \n= 0.001) and reached levels found in patients with acute coronary syndromes. Patients with RA are at increased risk for multi-vessel CAD, although the risk of CV events was not increased in our study population. Expansion of CD4\n+\nCD28\nnull \nT cells in these patients may contribute to the progression of atherosclerosis.\n\n**Article Body:**\n\nIntroduction\nInflammation plays a central role in the pathogenesis of atherosclerosis [\n1\n,\n2\n]. Markers of inflammation, such as C-reactive protein, are predictive of future cardiovascular (CV) events in healthy individuals and may be useful in identifying patients with coronary artery disease (CAD) who are at risk for recurrent CV events [\n3\n,\n4\n]. Atherosclerotic plaque is a complex inflammatory lesion characterized by an infiltrate of macrophages and T cells [\n1\n]. Intraplaque immune cells are activated and involved in mediating tissue injury [\n5\n]. T-cell cytokines can drive macrophage activation in atherosclerotic lesions and can also regulate the acute-phase response [\n1\n]. Indeed, T cells in patients with acute coronary syndromes (ACS) are skewed toward the production of interferon (IFN)-γ, a potent monocyte activator largely derived from a distinct subset of CD4\n+ \nT cells [\n6\n,\n7\n] that, in contrast to classic CD4\n+ \nhelper T cells, lacks the costimulatory molecule CD28 [\n8\n]. CD4\n+\nCD28\nnull \nT cells are clonally expanded in ACS and invade the unstable atherosclerotic plaque [\n9\n]. Moreover, CD4\n+\nCD28\nnull \nT cells have cytotoxic capability, can effectively kill endothelial cells \nin vitro\n, and may contribute to endothelial cell injury in coronary plaque [\n10\n].\nExpansion of CD4\n+\nCD28\nnull \nT cells was initially described in patients with rheumatoid arthritis (RA), a chronic autoimmune disease of unknown etiology [\n11\n]. RA is characterized by chronic inflammation and hyperplasia of synovial tissue. More importantly, it is a quintessential systemic disease that can manifest in most major organ systems [\n12\n]. T cells play a central role in the immunopathogenesis of RA and are the key regulators of the chronic destructive joint lesions [\n13\n]. In addition, patients with RA have abnormalities in T-cell homeostasis that affect the entire pool of T cells [\n14\n,\n15\n]. One of the consequences of dysregulated T-cell homeostasis is the emergence of large clonal CD4\n+\nCD28\nnull \nT-cell populations that are autoreactive and cytotoxic, and infiltrate synovial tissue [\n15\n]. The highest frequency of CD4\n+\nCD28\nnull \nT cells is found in severe RA, particularly in patients with rheumatoid vasculitis [\n11\n,\n16\n]. When the inflammatory process in RA spreads to extra-articular sites, such as mid-size arteries and capillaries, morbidity and mortality are clearly increased [\n17\n].\nBecause the chronic inflammatory process and immune dysregulation in RA have features in common with those involved in atherosclerosis, they could predispose patients with RA to accelerated CAD. Several studies have documented an increased risk of atherosclerosis and myocardial infarction in patients with RA [\n18\n-\n20\n]. In addition, RA is associated with a reduced life expectancy, primarily because of excessive deaths from CV disease [\n21\n-\n25\n]. RA is a heterogeneous disease, and the disease phenotype itself is predictive of mortality; patients with more severe clinical disease have higher mortality rates [\n26\n]. Overall mortality is also increased in patients who are positive for the autoantibodies, rheumatoid factors [\n27\n,\n28\n]. In addition, the extent of inflammation in RA has been linked to an increased risk of CV mortality [\n29\n]. The number of swollen joints, independent of traditional CV risk factors, is predictive of CV-related deaths among Pima Indians with RA [\n30\n]. The strongest association with increased CV mortality is seen in patients with extra-articular manifestations of RA [\n17\n].\nOur study demonstrates that patients with RA have significantly more multi-vessel coronary disease by angiography compared with patients with CAD but no RA. This finding may, at least in part, result from the expansion of proinflammatory CD4\n+\nCD28\nnull \nT cells that have previously been shown to play a role in the pathogenesis of CAD.\nMethods\nData source\nThe Rochester Epidemiology Project maintains the medical records of patients from Mayo Clinic Rochester, MN, USA, which is the major referral center for secondary and tertiary care, including coronary angiography, in Olmsted and surrounding counties. The complete medical records of each study subject were retrieved and reviewed. The study was approved by the Mayo Foundation Institutional Review Board and patient consent was obtained.\nPatient population\nWe studied the medical records of patients from Olmsted and surrounding counties. Patients with RA who developed CAD between January 1985 and December 1998 and who had a coronary angiogram at Mayo Clinic Rochester were recruited for the study. Inclusion criteria were: diagnosis of RA according to the 1987 American College of Rheumatology criteria [\n31\n]; diagnosis of ischemic heart disease (ischemic heart disease criteria were anginal pain or anginal equivalent symptoms occurring with exercise, relief by rest or nitroglycerin. If occurring at rest, then symptoms relieved with nitroglycerin); and coronary angiography performed at Mayo Clinic for evaluation of CAD within the first 12 months of disease. Mayo Clinic is the only provider of invasive cardiac care in Olmsted County.\nExclusion criteria were: congestive heart failure without ischemic heart disease; CAD present for more than 12 months prior to the first angiogram at Mayo Clinic (to ensure that all angiograms reflected the status of the patient at onset of CAD symptoms); and prior coronary artery bypass graft (CABG), myocardial infarction (MI) or percutaneous transluminal coronary revascularization (PTCR). Death during the study period 1985 to 1998 was not an exclusion criterion.\nResidents of Olmsted and surrounding counties who were seen at Mayo Clinic between January 1985 and December 1998 and diagnosed with CAD during the study period were used as control subjects. The original study design was to match three controls for each of the 75 RA cases for age, sex and visit date. Controls were matched for age at diagnosis of CAD and year of onset in order to control for shifts in practice and diagnostic patterns. Using these criteria, we were able to identify 130 controls, therefore some cases had one control and others had two controls. After matching, two patients were excluded for prior CABG, MI, PTCR or no angiogram at Mayo Clinic, resulting in 128 controls. Inclusion/exclusion criteria were identical except that a diagnosis of RA was an additional exclusion criterion. The controls were from the local, stable population of Olmsted and surrounding counties. The only rheumatology practice in this geographic area is at Mayo Clinic. The investigators reviewed the entire Mayo medical record (including the master sheet listing all diagnoses for the patient throughout his/her lifetime) for each control. We are confident that symptoms or clinical manifestations of RA would have been recorded in the patients' charts. The diagnosis for RA was based on a rheumatologist's evaluation.\nCoronary angiogram data\nAngiographic data was retrieved from the Mayo Clinic coronary care unit database. Mayo Clinic cardiologists who performed the study and read each angiogram were not directly involved in each patient's medical care and, therefore, not typically informed of the patient's concurrent medical problems. Vessel involvement was defined as >50% stenosis for the left main coronary artery and >70% stenosis for the left anterior descending, right coronary and circumflex arteries. For each involved vessel, the patient received a score of 1.\nIschemic risk factors\nIschemic heart disease risk factors were ascertained by medical record review and were defined as follows: cholesterol ever ≥ 200 mg/dl and/or treated by a physician for hypercholesterolemia, hypertension under treatment, smoking history (yes or no), and type I or type II diabetes. We have selected variables in our analysis where the data sets were largely complete and where there was not a difference between the two patient cohorts in terms of missing data. Variables for which we did not have a complete dataset (such as quantitative details of smoking history) were excluded.\nImmune markers\nIn a nested study, all RA+CAD subjects who were alive at the time of the study were contacted by mail and invited to participate in the immune marker analysis. Of these, 27 individuals consented to blood donation, and peripheral blood was obtained for T-cell phenotyping (\nn \n= 27). This patient subgroup had similar demographic characteristics as the whole RA+CAD cohort. Mean age for the subgroup was 69.2 ± 8.2 years, 58% were male and 87% were rheumatoid factor-positive. RA disease duration was also similar (15.9 ± 9.9 years). Blood samples were also obtained from controls who were classified as having had stable angina (\nn \n= 24). Results were compared with 22 patients with unstable angina type Braunwald IIIb, from a previous study [\n6\n].\nPeripheral blood mononuclear cells were isolated by density gradient centrifugation with Ficoll-Paque (Amersham Biosciences, Arlington Heights, IL, USA). Cell surface staining was performed using anti-CD4\nFITC \nand anti-CD28\nPE \nantibodies (BD Biosciences, San Jose, CA, USA). Data was collected on a FACScan flow cytometer (Becton Dickinson, San Jose, CA, USA), and the frequencies of CD4\n+ \nT-cell subsets were calculated using WinMDI software (Joseph Trotter, Scripps Research Institute, La Jolla, CA, USA).\nStatistical methods\nAll time references are based on the index angiogram. For each patient, the following variables were considered: RA diagnosis; number of diseased vessels (0, 1, 2 or 3); age and sex; history of diabetes, hypertension, hyperlipidemia or smoking; time to death, follow-up angiogram, follow-up CABG or follow-up MI; and time to first event [death, CV death, angiogram, CABG or MI]. In all models, the number of diseased vessels was treated as a four-level categorical variable.\nThe first component of the analyses was the exploration of baseline factors associated with RA diagnosis and number of diseased vessels. These data were cross-tabulated with each other and with each of the other baseline variables. Chi-square tests or Wilcoxon rank-sum tests were performed as appropriate. A multiple logistic regression model, with RA diagnosis as the dependent variable, was constructed using forward selection, with smallest \nP \n< 0.05 as the entry criterion. Additionally, a multiple ordinal logistic regression model, with number of diseased vessels as the dependent variable, was constructed using forward selection, with smallest \nP \n< 0.05 as the entry criterion.\nThe second component of the analyses was the exploration of follow-up events. RA diagnosis was cross-tabulated with the various follow-up events: time to death, CV death, time to follow-up angiogram, follow-up CABG, follow-up MI and first event (death, angiogram, CABG or MI). The cases and controls were defined during a specified time interval and each subject was followed for subsequent events. Therefore, the study group is a sample from a cohort of patients with CAD, some with RA and some without RA, allowing us to use Cox proportional hazards models for each of the five follow-up endpoints and for RA diagnosis. Adjusted Cox proportional hazards models were fit by adding the number of diseased vessels and hyperlipidemia as covariates. For time to death, a Cox model was fit for each of the other baseline variables.\nKaplan-Meier survival plots were constructed for time to death as a function of each baseline variable. Statistical analyses were performed using SAS Release 8.2 (TS2M0) for UNIX (SAS Institute Inc, Cary, NC, USA) and S-PLUS 2000 Professional Release 2 for Windows (Insightful Corp, Seattle, WA, USA). CD4\n+\nCD28\nnull \nT-cell percentages were compared using the Mann-Whitney rank sum test.\nResults\nDemographic characteristics and CAD risk factors\nThe study population consisted of 79 patients with RA who had coronary angiography performed at Mayo Clinic for CAD symptoms. Four were excluded because of history of CAD diagnosis and intervention prior to evaluation at Mayo. The control population consisted of 130 individuals with CAD but no history of RA, two of whom were excluded because of a history of prior CV events. The analyzed dataset consisted of 75 cases and 128 controls.\nThere was no significant difference in the percentage of individuals with traditional risk factors for CAD, including diabetes, hypertension, hyperlipidemia or smoking history in the study group when compared with controls (Table \n1\n). Because age and sex were incorporated in the matching, there was no difference between the two groups.\nCharacteristics of cases with RA and CAD\nTable \n1\n includes characteristics of the patients with RA. Average age at onset of RA was 55 years and the average disease duration was 17.6 years. Approximately 90% of the cases were rheumatoid factor-positive and 53% had nodular disease. One-fifth of the group had extra-articular disease manifestations including vasculitis, rheumatoid lung disease, pericarditis, Felty's syndrome, neuropathy and scleritis. Use of corticosteroids and disease modifying therapy was fairly typical of patients with long-standing RA.\nCoronary artery involvement\nThere was a statistically significant difference in the distribution of the number of involved vessels in the two groups. More patients with RA had significant coronary artery involvement compared with controls (\nP \n= 0.002, chi-square = 14.6866, df = 3; Table \n2\n). Only 4% of the patients with RA had no significant vessel involvement compared with 23% for the control patients.\nRA is an independent risk factor for increased CAD severity\nTable \n3\n shows the ordinal logistic regression model results for number of diseased vessels. One model includes only RA diagnosis and the other also includes the covariates added via the forward selection procedure. These variables were added because they were related to the number of diseased vessels. RA remains a significant risk factor for multi-vessel disease after adjustment for age, sex, and history of hyperlipidemia. The odds ratio of RA diagnosis for an increase of one diseased vessel is 1.73 (95% CI: 1.03, 2.91) unadjusted and 1.97 (95% CI: 1.15, 3.36) adjusted.\nCV events\nBecause RA was associated with more severe coronary disease, we investigated whether this resulted in an increased incidence of CV events and/or premature mortality. Follow-up data for CV events including CV death, death from any cause, CABG, MI and PTCR was recorded by review of the medical record. Mean duration of follow-up was 62.4 months for the RA and CAD cases and 57.8 months for the CAD-only controls. The mean time from CAD onset to occurrence of a CV event (MI, CABG or PTCR) was 18 months and the mean time to death from any cause was 63 months. The risk of non-fatal CV events did not differ significantly between cases and controls. However, RA and CAD cases tended to have increased all-cause mortality (32%) compared with CAD only controls (18%); unadjusted risk ratio = 1.6 (95% CI: 0.9–2.9). In particular, the risk of CV death was increased in RA and CAD cases (17%) compared with CAD-only controls (7%); unadjusted hazard ratio (HR)=2.2 (95% CI: 0.95–5.2). However, neither comparison reached significance.\nTable \n4\n shows raw counts and Cox model results for various follow-up endpoints. Of the 203 patients in the study, 47 died, 52 had follow-up CABG events, 71 had follow-up MI, 74 had follow-up PTCR and 141 had 'any event'. RA is weakly associated with an increased risk of all-cause mortality, adjusted risk ratio = 1.3 (95% CI: 0.7–2.3). There is a stronger association between RA and an increased risk of CV death, adjusted HR = 1.9 (95% CI: 0.8–4.7); however, this is not significant. There is no apparent association between case/control status and the percentage of individuals who had non-fatal CV events during the follow-up period.\nAs expected, other factors were associated with increased mortality. Based on bivariate Cox proportional hazards models including all subjects, the presence of involved vessels is associated with an increase in risk of death (risk ratio = 2.9, 3.0 and 4.6 for 1, 2 and 3 vessels, respectively; \nP \n= 0.06). Also, history of diabetes (risk ratio = 1.9; \nP \n= 0.05) and age is associated with an increase in risk of death (risk ratio per 1 year age increase = 1.07; \nP \n< 0.001).\nSurvival plots\nFigure \n1a\n shows Kaplan-Meier plots of survival by case/control status. Survival probability for patients with RA and CAD was lower than that for patients with CAD only (\nP \n= 0.10). Figure \n1b\n shows Kaplan-Meier plots of survival by number of diseased vessels. Survival probability was lowest for patients with three diseased vessels and was progressively higher as the number of diseased vessels decreased (\nP \n= 0.06).\nCD4\n+\nCD28\nnull \nT cells\nAs previously reported, frequencies of CD4\n+\nCD28\nnull \nT cells were low in individuals with stable angina (median: 0.7%) [\n6\n]. In contrast, individuals with unstable coronary syndromes (without RA) had an almost sevenfold expansion of CD4\n+\nCD28\nnull \nT cells (median: 4.8%, \nP \n= 0.009 for stable vs unstable angina comparison). A similar expansion of CD4\n+\nCD28\nnull \nT cells was found in patients with RA and CAD (median: 3.5%; 25th percentile: 0.9%; 75th percentile: 12.4%). Frequencies of proinflammatory CD4\n+\nCD28\nnull \nT cells were not significantly different between patients with unstable angina (without RA) and those with RA and CAD. Although the patients with RA did not have symptoms of acute plaque instability at the time of the immunological test, the majority of them (81.5%) had a history of unstable angina. The difference between the patients with RA and CAD and stable angina controls was highly significant (\nP \n= 0.001) (Figure \n2\n).\nDiscussion\nOur results show that patients with RA have more advanced coronary atherosclerosis at the time of CAD diagnosis compared with patients without RA (Table \n2\n). This occurs independently of the traditional CV disease risk factors. More importantly, this results in a trend towards increased frequency of CV death for patients with RA.\nIn the general population, the presence of advanced atherosclerosis on angiography is predictive of a worse prognosis [\n32\n]. The extent of atherosclerosis determined by angiography has not been studied in RA. Indirect evidence of accelerated atherosclerosis in RA comes from studies using carotid artery intima medial thickness as a marker of atherosclerotic burden and vascular risk [\n19\n,\n33\n,\n34\n]. Increased intima-media thickness was independent of traditional CV risk factors but was related to RA disease activity [\n20\n], duration and severity [\n19\n]. Data presented here suggest that the acceleration of atherosclerotic disease in RA holds for multiple vascular beds, lending support to a systemic disease mechanism.\nExcess CV morbidity in RA\nPatients with RA have a significantly higher prevalence of angina pectoris [\n34\n]. Also, women with RA have a significantly increased risk of myocardial infarction compared with those without RA [\n18\n]. This excess of CV disease in RA cannot be explained by the traditional Framingham risk factors [\n35\n] and probably arises from the underlying disease and/or its treatment. There is no evidence that disease-modifying antirheumatic drug (DMARD) therapy increases mortality in RA [\n36\n]. Corticosteroids can cause dyslipidemia, hyperglycemia and hypertension but may also control inflammation in RA. Studies have attempted to define the impact of steroids on mortality in RA but the results are inconsistent [\n23\n,\n25\n]. DMARD treatment can actually improve the outcome in RA. Choi and colleagues [\n36\n] have demonstrated that methotrexate-treated patients had a 70% reduction in CV deaths compared with those who did not receive disease-modifying therapy. Other DMARDs such as sulfasalazine, penicillamine, hydroxychloroquine, and gold did not confer this protection. Thus, the RA disease process itself likely contributes to accelerated CAD.\nThe inflammatory mechanisms in RA may enhance atherogenesis in several ways. C-reactive protein, a useful marker of disease activity, is elevated in RA and has prognostic value [\n37\n]. It may also participate directly in endothelial injury by sensitizing endothelial cells to T-cell mediated cytotoxicity [\n10\n]. Circulating cytokines in RA, such as TNF-α, result in endothelial activation and up-regulation of adhesion molecules [\n38\n]. Indeed, endothelial dysfunction is frequently present in RA patients, even in the absence of identifiable CV risk factors [\n39\n] and improves with anti-TNF-α therapy [\n40\n]. Cytokines will also non-specifically activate monocytes and other cells of the innate immune system. RA is characterized by the expansion of autoreactive T-cell clones that typically lack CD28 [\n11\n]. The frequency of such CD4\n+\nCD28\nnull \nT cells correlates with disease severity with respect to erosive progression [\n41\n] and extra-articular manifestations. The frequency in the RA with CAD cohort (median 3.5%) was higher than in historical controls of patients with RA and absence of extra-articular manifestations [\n11\n], suggesting that CV comorbidity in RA is correlated with disease severity and that CD4\n+\nCD28\nnull \nT cells may be involved in the CV complications of RA. CD4\n+\nCD28\nnull \nT cells have been directly implicated in the pathogenesis of coronary artery disease [\n6\n]. Persistent activation of such autoreactive cells in RA may result in a vicious cycle of cytokine release, mononuclear cell activation and tissue injury. However, we cannot exclude the possibility that the high CD4\n+\nCD28\nnull \nT cells levels in RA with CAD patients is reflective of an increased RA disease severity in these patients. Addressing this issue further will require comparing RA patients that are matched for disease severity but are disparate for CAD.\nStudy limitations\nWe adjusted for traditional Framingham risk factors that are commonly considered in epidemiological studies of CV disease. However, factors such as cigarette smoking could possibly have a synergistic effect with chronic inflammation due to RA, resulting in increased atherogenesis. In our study, detailed quantitative data on amounts of tobacco used were not available. Also, data regarding other risk factors, such as family history and body mass index, were not available. Elevated levels of homocysteine could represent another risk factor for atherosclerosis in RA. Methotrexate, a commonly used disease-modifying agent, inhibits dihydrofolate reductase and reduces levels of folate, which in turn increases levels of homocysteine [\n42\n,\n43\n]. The impact of folic acid supplementation on homocysteine levels and CV disease in patients with RA is unknown. Data on homocysteine levels were not available in our study. Finally, it is possible that our findings are a reflection of patients with RA being less symptomatic from CAD than the general population, therefore resulting in later presentation when the disease is more advanced.\nDespite more severe CAD at the time of clinical presentation, the prevalence of non-fatal CV events was not increased in patients with RA. It is possible that significant differences between cases and controls were not detected because of the size of the cohorts studied and also that CV events may have been underestimated due to the retrospective nature of the study.\nConclusion\nIn summary, our results demonstrate that patients with RA have a greater burden of coronary atherosclerosis at their first angiogram that is independent of traditional CV risk factors. This may be due, at least in part, to the expansion of nonclassic CD4\n+ \nT cells that have previously been implicated in the pathogenesis of CAD [\n6\n,\n9\n].\nAbbreviations\nACS = acute coronary syndrome; CABG = coronary artery bypass graft; CAD = coronary artery disease; CV = cardiovascular; HR, hazard ratio; DMARD = disease-modifying antirheumatic drugs; MI = myocardial infarction; OR = odds ratio; PTCR = percutaneous transluminal coronary revascularization; RA = rheumatoid arthritis.\nCompeting interests\nThe authors declare that they have no competing interests.\nAuthors' contributions\nKJW carried out chart reviews, performed the immunological assays, participated in study design and drafted the manuscript. PDK carried out chart reviews and data collection. RLF participated in study design and manuscript preparation. JFL performed the statistical analyses. SLK carried out data interpretation and participated in study design. JJG participated in study design, interpretation of data and manuscript preparation. CMW conceived the study, participated in its design and coordination and helped to draft the manuscript. All authors read and approved the final manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
45
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nMyocardial dysfunction in rheumatoid arthritis: epidemiology and pathogenesis\n\n**Article Abstract:**\n\nData from population- and clinic-based epidemiologic studies of rheumatoid arthritis patients suggest that individuals with rheumatoid arthritis are at risk for developing clinically evident congestive heart failure. Many established risk factors for congestive heart failure are over-represented in rheumatoid arthritis and likely account for some of the increased risk observed. In particular, data from animal models of cytokine-induced congestive heart failure have implicated the same inflammatory cytokines produced in abundance by rheumatoid synovium as the driving force behind maladaptive processes in the myocardium leading to congestive heart failure. At present, however, the direct effects of inflammatory cytokines (and rheumatoid arthritis therapies) on the myocardia of rheumatoid arthritis patients are incompletely understood.\n\n**Article Body:**\n\nIntroduction\nUnique cardiac complications of rheumatoid arthritis (RA), such as cardiac rheumatoid nodules, have been recognized for over a century. It has only been appreciated in the last decades, however, that certain chronic autoimmune inflammatory diseases, such as RA and systemic lupus erythematosis, increase the risk of developing cardiovascular disease (CVD), particularly atherosclerosis and congestive heart failure (CHF) [\n1\n-\n5\n]. In fact, striking commonalities in the cellular and cytokine profiles of the rheumatoid synovial lesion and atherosclerotic plaque [\n6\n-\n8\n] have prompted speculation that the inflammatory pathways of RA may initiate and/or accelerate plaque formation and that this effect may be ameliorated by anti-inflammatory therapies [\n9\n].\nThe link between RA and CHF is less well studied. The CHF phenotype can evolve from a variety of pathogenic conditions, many of which may be promoted by the RA disease process. Yet to date, only a handful of investigations have attempted to dissect this complex issue. A particular source of confusion has been the apparent contradiction between pre-clinical studies linking inflammation to CHF and the lack of efficacy of anti-cytokine therapy in clinical trials in advanced CHF (discussed below). Because anti-cytokine therapy has become a cornerstone in the treatment of RA, it is particularly critical to understand the contribution of cytokine-induced inflammation to myocardial structure and function in RA. Here, we review the current literature on the epidemiology of CHF in RA with an emphasis on the pathogenesis of cytokine induced myocardial dysfunction.\nEpidemiology of congestive heart failure: general considerations\nThe epidemiology of CHF in RA, and the limitations of the available data, are better appreciated in the context of estimates of CHF in the general population. The prevalence of CHF in western countries appears to have been increasing over the past few decades, due primarily to increased longevity rather than to a change in incidence rates [\n10\n]. In the United States, more than 400,000 new cases of CHF are identified each year and added to the estimated 2.5 to 5 million Americans with prevalent CHF [\n11\n,\n12\n], yielding an overall prevalence of 1.1% to 2% of the population. Nearly 300,000 deaths in the US are attributed to CHF annually [\n10\n]. For persons over the age of 65 years, CHF is the most frequent cause of hospitalization [\n11\n,\n13\n].\nIncidence rates of CHF vary among published reports, presumably reflecting differences in the populations studied, diagnostic criteria used, and temporal trends in coding practices for reimbursement [\n14\n]. Recent data from several community-based cohorts [\n15\n-\n18\n] have yielded an estimated age-adjusted incidence of CHF of 3.4 to 17.6 per 1,000 person-years for men and 2.4 to 12.5 per 1,000 person-years for women. The wide range in rates reflects, at least in part, differences in diagnostic criteria used from study to study. For example, age-adjusted incidence rates based on the Framingham diagnostic criteria for heart failure [\n15\n,\n16\n,\n18\n,\n19\n] (Table \n1\n) were between 2 and 4 per 1,000 person-years, whereas rates based on less stringent criteria were three- to four-fold higher [\n17\n].\nThe incidence of CHF increases with age [\n20\n,\n21\n]; 88% of affected individuals are over the age of 65 years, and 49% are over 80 years at diagnosis [\n20\n]. The remaining lifetime risk of developing CHF at all index ages from 40 through 80 years of age is between 20% and 33%, and is roughly equal for men and women [\n17\n,\n22\n]. Levy \net al\n. [\n15\n] have shown that over the past 50 years the incidence of CHF has declined among women but not among men. This lack of decline in CHF incidence among men is largely attributable to advances in the management of acute myocardial infarction, diabetes, and hypertension that have led to an overall decrease in mortality rates from these disorders while adding to the incidence of CHF [\n23\n]. Survival after the onset of CHF has improved in both sexes [\n15\n]. Factors contributing to the decrease in CHF mortality include improved access to care, the introduction of effective therapies, and improved care of comorbid conditions [\n15\n]. Despite these encouraging trends, mortality rates of patients with CHF remain alarmingly high. Recent reports from community-based cohorts [\n15\n-\n18\n] estimate age-adjusted one- and five-year CHF mortality at 23% to 27% and 45% to 65%, respectively. For women in these series, survival was slightly better than [\n15\n,\n16\n] or equal to [\n17\n,\n18\n] men.\nEpidemiology of congestive heart failure in rheumatoid arthritis\nFewer statistics on incidence and prevalence rates for CHF in patients with RA are available and are derived from a handful of population-based [\n24\n-\n26\n] and clinic-based RA cohorts [\n5\n,\n27\n,\n28\n]. Gabriel \net al\n. [\n24\n] estimated the incidence of CHF among all RA patients in Olmsted County, Minnesota, from data abstracted from medical records. Between 1955 and 1985, 78 cases of incident CHF were identified among 450 prevalent cases of RA compared to 54 cases among the same number of non-RA community controls matched for age, sex, and baseline comorbidity, yielding a relative risk of 1.60 (95% CI 1.12–2.27). In contrast, the risk of incident CHF in patients with osteoarthritis (OA), a non-inflammatory arthritis, was not increased compared to non-OA community controls [\n24\n]. In a follow-up retrospective review of the same cohort extended to 1995, now using the Framingham diagnostic criteria for CHF (Table \n1\n), Nicola \net al\n. [\n26\n] confirmed an increased risk of incident CHF in both rheumatoid factor (RF) negative and positive RA patients (hazards ratio 1.34 and 2.29, respectively) compared to non-RA controls adjusted for age, sex, and CV risk factors. Incident CHF risk remained elevated after further adjustment for comorbid ischemic heart disease (hazards ratio 1.28 and 2.59 for RF negative and positive RA patients, respectively), although the risk relationship was no longer statistically significant for RF negative patients in this model [\n26\n].\nIn a combined cohort of RA patients from community-based practices and drug safety monitoring studies (\nn \n= 9093), Wolfe \net al\n. [\n5\n] estimated an adjusted lifetime relative risk of CHF in patients with RA of 1.43 (95% CI 1.24–1.33) compared with OA controls. The adjusted lifetime prevalence of CHF in the RA population was 2.34% compared to 1.64% in OA controls. Data were collected via patient survey of self-reported, physician-diagnosed CHF, and confirmed by review of a random sample of medical records in 50% of patients reporting CVD events. In a subsequent analysis [\n27\n], in which the drug safety cohort represented a third (\nn \n= 4,307) of the total sample (\nn \n= 13,171), Wolfe \net al\n. reported an adjusted frequency of CHF of 3.9% (95% CI 3.4–4.3%) in RA patients compared to 2.3% (95% CI 1.6–3.3%) in controls with knee or hip OA. Factors associated with prevalent and incident CHF were those typically associated with CHF in the non-RA population (e.g., age, male gender, hypertension, coronary artery disease, diabetes, and smoking) while RA-related measures (patient-reported disability, pain, and RA global severity) were also associated with prevalent and incident CHF. As data were collected by mailed questionnaire, objective measures of RA disease activity (e.g., swollen and tender joint counts and serum inflammatory markers) were not available to assess as predictor variables.\nIndeed, the impact of CHF in RA may be under-appreciated due to excess CHF related mortality. Mutru \net al\n. [\n28\n] first reported a higher rate of CHF-attributed mortality in RA patients compared to age- and gender-matched controls with CHF for both males (\nP \n= 0.004) and females (\nP \n= 0.042). In a recent report, Nicola \net al\n. [\n29\n] found that CHF preceded nearly two-thirds of the excess CVD associated deaths in RA patients compared to age- and gender-matched controls. These unexpected results alone emphasize a need for greater understanding of the dynamics of myocardial dysfunction in RA and suggest that survivor-bias may serve to underestimate the true extent of CHF in the RA population.\nAn important limitation of each of these studies is in the method chosen to ascertain the diagnosis of CHF. The application of clinical criteria alone for the diagnosis of CHF is too imprecise, as demonstrated by one study [\n30\n] in which a false positive diagnosis of CHF was made by primary care providers in over one-third of patients. Current guidelines [\n10\n] advocate the need for Doppler echocardiographic confirmation of any diagnosis of CHF when suspected clinically. Reliance on clinical diagnostic criteria alone may result in over-diagnosis of CHF in some case. In others, CHF may be under-diagnosed when dependent ankle edema is mistaken for joint swelling, chronic pulmonary congestion is misinterpreted as rheumatoid lung involvement, and exertional dyspnea is masked by a sedentary lifestyle due to painful joint deformities. Nevertheless, on balance, the available data support higher prevalence and incidence rates of CHF in RA patients compared to matched controls without RA. Many factors unique to or over-represented in RA patients may explain, at least in part, why the myocardium is at risk in RA. In addition, an analysis of the relative contributions of each of these risk factors and associated biomarkers to the development of CHF in RA patients invites speculation into the underlying pathophysiologic mechanisms leading to myocardial dysfunction.\nRisk factors, echocardiographic predictors, and biochemical markers associated with the development of CHF: relationship to RA\nRisk factors for congestive heart failure\nThe risk factors and biochemical markers associated with the development of CHF in the general population are listed in Table \n2\n. Although no systematic investigation has been performed to dissect the relative contribution of each of these factors to the development of CHF in RA, several well-defined contributing factors have been shown to be over-represented in RA. Whether the increased risk of CHF in RA is primarily due to the effects of known risk factors, or to unidentified risk factors unique to RA, is currently unknown, though the predictors analyses by Wolfe \net al\n. [\n27\n] and Nicola \net al\n. [\n26\n] (discussed above) suggest that both traditional and RA-specific risk factors for CHF are operative. The available evidence on the prevalence of some of these important risk factors for CHF in RA is reviewed below, though it is important to recognize that RA is a heterogeneous disorder, and some factors may represent different risks for different subpopulations of RA patients.\nHypertension\nSystemic hypertension is one of the most potent risk factors for CHF, conferring a two- to three-fold increase in CHF risk for affected individuals [\n31\n]. Chronic hypertension promotes the development of CHF by a variety of mechanisms, including the induction of maladaptive myocardial remodeling and atherosclerosis. Reports of the prevalence of hypertension in RA have yielded varied results, with authors reporting lower [\n32\n], equivalent [\n26\n,\n33\n,\n34\n], or elevated [\n3\n,\n24\n,\n35\n] mean systolic and/or diastolic blood pressures in RA patients compared to matched controls. Importantly, although any history of hypertension was strongly associated with prevalent CHF in the study by Wolfe \net al\n. [\n27\n] (odds ratio 2.6 (95% CI 2.1–3.2)), Nicola \net al\n. [\n26\n] found no association between hypertension and risk of incident CHF in RA patients followed for a median of 11.8 years.\nAdditionally, other factors over-represented in RA patients, such as the chronic use of non-steroidal anti-inflammatory drugs and corticosteroids, are both known to promote fluid retention and elevate systemic blood pressure [\n36\n]. The independent effect of these agents on the development of CHF in RA is complex, however, and has yet to be directly investigated.\nCoronary atherosclerosis/myocardial infarction\nMyocardial infarction (MI) is the most potent risk factor for CHF, with a population-attributed risk for the development of CHF in the Framingham cohort of 34% for men and 13% for women [\n31\n]. In most cases, other risk factors for CHF (e.g., hypertension, diabetes, and smoking) also contribute to the pathogenesis of coronary atherosclerosis. Importantly, unrecognized and silent MI represents up to 25% of all myocardial ischemic events [\n37\n] and subclinical atherosclerosis (with no history of MI) is also associated with an increased risk for the development of CHF [\n38\n].\nSeveral studies have confirmed an approximately two- to four-fold increase in risk for MI among RA patients compared to non-RA controls [\n3\n,\n5\n,\n34\n]. Wolfe \net al\n. [\n27\n] showed that recent MI (within six months) and any history of MI were both significant univariate correlates of prevalent CHF in RA patients (odds ratio 16.1 (95% CI 11.0–23.7) and 6.6 (95% CI 5.4–8.0), respectively). In the study by Nicola \net al\n. [\n26\n], ischemic heart disease (including overt MI, silent MI, and angina) and risk factors for CVD accounted for the risk of incident CHF in RF negative, but not RF positive, RA patients.\nSubclinical atherosclerosis, as measured by carotid ultrasound, is more prevalent in RA patients compared to matched controls [\n39\n]. However, the relationship of subclinical atherosclerosis to the risk of CHF (in the absence of clinically recognized ischemic heart disease) in RA patients is currently unknown.\nDiabetes\nAlthough diabetes is a well-recognized risk factor for the development of CHF [\n40\n,\n41\n], the prevalence of diabetes does not appear to be increased in RA patients compared to non-RA controls [\n24\n,\n42\n]. Glucose intolerance/peripheral insulin resistance has, however, been associated with an increase in CHF risk in both cross-sectional [\n43\n] and prospective, population-based [\n40\n] studies, and may be increased in RA [\n44\n,\n45\n]\nValvular heart disease\nHemodynamically significant cardiac valvular disease may lead to overt CHF through maladaptive compensatory mechanisms resulting in myocardial remodeling (the molecular basis of which is discussed below). Both necropsy [\n46\n] and cross-sectional echocardiographic studies [\n47\n] of RA hearts have identified an increased prevalence of granulomatous and non-granulomatous valvular abnormalities, particularly of the mitral valve, and an increased prevalence of mitral regurgitation in RA patients compared to matched non-RA controls. No longitudinal echocardiographic studies have been performed, however, to determine the impact of this finding on the subsequent risk for developing CHF in affected RA patients. Destructive valvular lesions leading to complete valvular incompetence have been reported [\n48\n,\n49\n] but are considered rare occurrences.\nIntrinsic pulmonary disease\nA wide spectrum of intrinsic pulmonary disorders, including disorders of the pulmonary air-spaces (chronic obstructive pulmonary disease), parenchyma (interstitial lung disease, pulmonary fibrosis), and vasculature (primary pulmonary hypertension) are associated with increasing pulmonary vascular resistance, progressive hypertrophy of the right ventricle, and eventual right heart failure with clinical CHF [\n50\n]. In RA, pulmonary disease may be a manifestation of the RA disease process itself or a result of RA-directed therapies (methotrexate, D-penicillamine, gold and others) [\n51\n]. While symptomatic chronic pulmonary diseases are more prevalent in RA patients compared with non-RA controls [\n24\n,\n52\n], subclinical pulmonary disease, including airways disease [\n53\n] (bronchiectasis, bronchiolitis) and parenchymal disease (interstitial pneumonitis), have been noted in nearly 50% of unselected RA patients in one series [\n54\n]. In addition, several echocardiographic studies have suggested higher right ventricular systolic pressures in RA patients compared to non-RA controls [\n55\n-\n57\n]. In the study by Dawson \net al\n. [\n56\n], pulmonary parenchymal disease could only account for 6% of RA cases with increased pulmonary arterial pressures, suggesting that asymptomatic primary pulmonary vascular disease may be under-appreciated in RA. These findings, and their putative effect on the subsequent development of CHF, warrant further study.\nSleep apnea/sleep-disordered breathing\nAlthough sleep apnea has been shown to be highly prevalent in people with CHF in cross-sectional studies [\n58\n], no prospective population-based studies, to date, have investigated the putative effect of sleep apnea on the risk of CHF. Sleep apnea is known, however, to increase systemic blood pressure via hypoxia-induced activation of the sympathetic nervous system [\n59\n], increase right ventricular pressure via hypoxia-induced pulmonary vasoconstriction [\n60\n], potentiate hypoxia-induced coronary ischemia [\n61\n], and induce the production of inflammatory cytokines such as IL-6 and tumor necrosis factor (TNF)-α [\n62\n], all recognized contributors to CHF risk. Few studies of sleep apnea in RA exist, though the disorder has been reported in RA in the context of cervical spine and temporomandibular joint involvement [\n63\n]. Recent reports of substantial improvements in sleep apnea-associated daytime somnolence in patients treated with TNF inhibitors [\n64\n,\n65\n] suggests that the problem may be under-appreciated in RA. At present, however, any link between sleep apnea and CHF risk in RA is speculative.\nOther factors\nSmoking and obesity are established risk factors for both RA [\n66\n] and CHF [\n41\n,\n67\n]. Both are thought to promote CHF primarily through exacerbation of atherogenesis, though both may also potentiate the release of agents with direct toxicity to the myocardium itself [\n68\n,\n69\n]. Interestingly, although RA patients may have similar or lower body mass indices than non-RA counterparts, loss of skeletal muscle mass accompanied by a compensatory increase in total fat mass in RA patients may account for the stability of body mass indices [\n70\n]. Though no focused investigations have been undertaken to date, this condition, termed sarcopenic obesity, could predispose RA patients to higher than expected CHF risk.\nRheumatoid arthritis associated factors\nIn general, myocardial nodules, restrictive pericarditis, and coronary vasculitis are exceedingly rare causes of CHF [\n71\n]; however, older necropsy studies of RA hearts [\n32\n,\n46\n,\n72\n] have indicated a higher prevalence of each of these complications compared to the hearts of autopsied non-RA patients. More recent series using transthoracic echocardiography [\n55\n,\n56\n] have identified a much lower prevalence of pericarditis than that reported in the autopsy studies (2% versus 29% to 40%). In a series using transesophageal echocardiography [\n47\n], however, thirteen percent of RA patients were found to have clinically silent pericarditis versus zero percent of non-RA controls. Case reports of rheumatoid nodules [\n73\n,\n74\n], restrictive pericarditis [\n75\n,\n76\n], and coronary vasculitis [\n77\n] in RA patients resulting in CHF are not uncommon in the literature, although it is likely that these entities account for only a small portion of the excess cases of CHF in RA.\nEchocardiographic predictors of congestive heart failure\nSeveral large prospective studies have identified asymptomatic left ventricular (LV) enlargement, hypertrophy and dysfunction as significant risk factors for the development of CHF [\n78\n-\n80\n]. The strength of these associations, combined with the documented efficacy of angiotensin converting enzyme inhibitor therapy in delaying disease progression, have prompted consensus recommendation of medical treatment for these conditions classified as subclinical stages of CHF [\n81\n]. Importantly, once global alterations of LV architecture and function are established, progression to CHF with functional deterioration and eventually death is inexorable [\n82\n]. This unfavorable evolution highlights the need to define earlier stages of myocardial dysfunction, particularly in individuals with known risk factors for CHF.\nCHF with preserved systolic function\nBetween 30% and 50% of patients with CHF have preserved systolic function (defined as LV ejection fraction (LVEF) ≥ 45–50%) [\n83\n,\n84\n]. Despite the fact that this condition is associated with lower mortality when compared to heart failure with reduced LVEF, patients with CHF and normal LVEF have a four-fold increase in mortality relative to the normal population [\n83\n]. In asymptomatic individuals, diastolic dysfunction with preserved systolic function is also predictive of the subsequent development of overt CHF [\n85\n].\nTo date, a number of Doppler echocardiographic studies have been performed in RA patients without clinical evidence of CHF [\n55\n,\n86\n-\n94\n] (Table \n3\n). Although limited by small numbers of patients and, in some cases, failure to provide a non-RA comparator group, these studies are consistent in demonstrating a high prevalence of asymptomatic diastolic dysfunction in the setting of generally preserved systolic function. A correlation between the degree of diastolic dysfunction and RA disease duration was shown in several investigations [\n92\n,\n94\n]. Without longitudinal assessments, however, few conclusions can be made about the long-term effects of RA disease activity on cardiac structure and function or, more importantly, factors influencing the transition from asymptomatic myocardial dysfunction to clinical CHF in RA.\nImpaired diastolic filling is felt to relate physiologically to impairment in relaxation or compliance of the left ventricle, resulting in elevated LV filling pressures and resultant elevated back pressures through the pulmonary circulation, right heart, and beyond [\n95\n]. Histologically, processes that tend to stiffen the myocardium (e.g., hypertrophy, fibrosis, or infiltrative diseases) or reduce compliance (e.g., restrictive pericarditis) can manifest as diastolic dysfunction. We postulate that chronic low-grade myocardial inflammation resulting in fibrosis may predispose patients with RA to diastolic dysfunction (discussed below).\nThe limitations of standard echocardiography, which include poor endocardial definition, lack of inter-observer reproducibility of ejection fraction estimates, and lack of standardization of diagnostic criteria for diastolic dysfunction [\n96\n], often make it difficult to be precise about the diagnosis of diastolic dysfunction. In practice, however, the diagnosis of diastolic CHF is generally based on the finding of typical symptoms and signs of CHF in a patient who is shown to have a normal LVEF and no valvular abnormalities on echocardiography [\n84\n]. Newer noninvasive imaging methods, including contrast echocardiography and cardiac magnetic resonance imaging, have been developed that permit greater precision and accuracy in the assessment of myocardial function. Accordingly, the incorporation of these newer imaging modalities into studies exploring CHF in RA may not only serve to improve diagnostic accuracy, but also provide predictive power and insights into the underlying pathophysiologic mechanisms of disease.\nBiomarkers associated with congestive heart failure risk\nCardiac natriuretic hormones\nRecently, the measurement of circulating levels of brain natriuretic peptide has become available as a means of identifying patients with elevated LV filling pressures who are likely to exhibit signs and symptoms of CHF. Although the role of cardiac natriuretic hormones in the identification and management of individuals with asymptomatic ventricular dysfunction remains to be fully clarified [\n97\n], elevated serum levels of brain natriuretic peptide and amino-terminal pro-atrial natriuretic peptide have been associated with an increased risk of subsequent CHF in a community-based epidemiologic study [\n98\n]. In one small-scale cross-sectional study, RA patients were found to have higher serum atrial natriuretic peptide levels than healthy, non-RA controls [\n99\n]. Another cross-sectional study suggested that brain natriuretic peptide levels may be elevated in RA patients independent of overt or subclinical myocardial dysfunction [\n100\n]. To date, no studies have been performed in RA patients to establish the role of cardiac natriuretic hormones in either risk stratification or diagnosis of CHF.\nHyperhomocysteinemia\nElevated serum levels of homocysteine have been independently linked to an increased risk of CHF [\n101\n], particularly in women [\n102\n]. Hyperhomocysteinemia may promote the development of CHF through induction of atherosclerosis [\n103\n] and by direct effects on the myocardium leading to myocardial remodeling [\n102\n] (discussed below). In RA patients, homocysteine levels have been shown to be significantly higher than those of matched non-RA controls [\n104\n] and are associated with both markers of inflammation and therapy with methotrexate [\n105\n]. Though folic acid treatment reduces homocysteine levels in RA patients [\n105\n], and combination therapy with methotrexate and folic acid has been recently shown to be associated with a reduced incidence of CVD in veterans with RA [\n106\n], the complex relationship of RA-induced and RA therapy-induced hyperhomocysteinemia to CHF risk in RA has yet to be completely elucidated.\nInflammatory cytokines\nIn patients with overt CHF, levels of inflammatory cytokines (TNF-α, IL-6 and/or TNF-α receptors) are elevated and correlate with the severity of the disease [\n107\n-\n112\n] regardless of etiology of CHF. In patients with no overt CHF or history of ischemic heart disease, those with the highest serum levels of IL-6, C-reactive protein (CRP), and peripheral-blood mononuclear cell TNF-α were shown to have a two- to four-fold higher risk of developing CHF compared to patients with the lowest baseline levels of these cytokines [\n113\n,\n114\n]. In patients with overt CHF, both circulating peripheral-blood mononuclear cells and cells localized to the myocardium, including infiltrating inflammatory cells and cardiac myocytes, have been shown to be the source of the elevated cytokine levels [\n112\n,\n115\n,\n116\n].\nIn the inflamed synovium of the rheumatoid joint, macrophage-derived cytokines such as TNF-α, IL-1 and IL-6 are prominently expressed, and inhibitors of these cytokines, particularly TNF inhibitors, have been proven to be highly successful therapies for RA [\n117\n-\n120\n]. In RA, the inflamed synovium as well as peripheral-blood mononuclear cells contribute to elevated circulating TNF-α (and TNF receptor) levels. To date, however, the potential contribution of the myocardium in RA as a source of local cytokine production has not been investigated.\nOther conditions associated with chronically elevated levels of inflammatory cytokines (e.g., aging, chronic kidney disease, obesity) are also associated with an increased prevalence of CHF [\n121\n,\n70\n]; however, as in RA, the contributions of various non-inflammatory confounders in each of these conditions to the pathogenesis of CHF have not been fully explored.\nClinical studies of TNF inhibitors and congestive heart failure\nThe potent association of inflammatory cytokines with both CHF risk and clinical worsening of existing CHF has prompted speculation that pharmacologic cytokine inhibition might prove an effective treatment for established symptomatic CHF and/or reduce the risk of developing CHF in patients who are potentially at risk for CHF secondary to chronic cytokine excess (i.e., patients with RA and other chronic systemic inflammatory disorders). The unfavorable and unanticipated results of clinical trials investigating the use of anti-TNF-α therapy to treat advanced CHF, however, have raised concerns that TNF inhibitors may actually be harmful to the myocardium. To address this apparent contradiction we next examine the conflicting human clinical experience relating TNF inhibitors to CHF in the context of the available animal data on cytokine-induced CHF.\nUse of TNF inhibitors as a treatment for advanced congestive heart failure\nBoth etanercept, a soluble decoy TNF receptor, and infliximab, a chimeric anti-TNF-α monoclonal antibody, have undergone efficacy and safety evaluations in multicenter, double-blind, placebo-controlled trials for the treatment of patients with advanced symptomatic CHF [\n122\n,\n123\n]. The study designs of these trials ('RENNAISSANCE' (Randomized Etanercept North American Strategy To Study Antagonism Of Cytokines) and 'RECOVER' (Research Into Etanercept: Cytokine Antagonism In Ventricular Dysfunction Trial) [\n123\n] for etanercept, and 'ATTACH' (Anti-TNF-α Therapy Against Chronic Heart Failure) [\n122\n] for infliximab) have been recently reviewed in detail [\n124\n]. The collective results of the trials were generally unfavorable, with RENNAISSANCE and RECOVER halted in June 2001 when an interim analysis revealed that continuation would be highly unlikely to show a statistically significant difference in outcomes between the treatment groups [\n123\n] and ATTACH demonstrating no clinical efficacy of infliximab, but higher rates of hospitalizations and all-cause mortality in patients treated with the highest dose (10 mg/kg) of infliximab compared to placebo [\n122\n].\nThe high-profile and well-publicized nature of these trials, coupled with a 2002 report, using the US Food and Drug Administration's MedWatch post-licensure database for voluntary reporting of adverse events, of new or worsening CHF in 47 of approximately 300,000 patients worldwide treated with infliximab or etanercept (of whom 38 (81%) had no prior history of CHF, and 10 of whom were less than 50 years of age) have led some to conclude that TNF inhibition may exert a detrimental, rather than protective, effect on the myocardium of RA patients. To date, the only available evidence to refute this supposition comes from Wolfe \net al\n. [\n27\n], in which a statistically significant lower rate of self-reported, physician-diagnosed CHF was determined in RA patients receiving treatment with a TNF inhibitor compared to those not treated with TNF inhibitors, even after adjustment for unbalanced clinical characteristics and previous history of CVD (2.8% versus 3.9%, respectively, \nP \n= 0.03). A lower rate of incident CHF in TNF inhibitor treated versus untreated patients was also demonstrated (3.5% versus 4.3%, respectively) when the analysis was limited only to data collected after the Food and Drug Administration warning following the RENNAISANCE, RECOVER, and ATTACH trials, although this difference was not statistically significant. No cases of incident CHF in TNF inhibitor treated RA patients who were less than 50 years of age were found, although three cases of incident CHF were reported in RA patients under 50 years of age who were not treated with TNF inhibitors. As noted above, the diagnosis of CHF in this study was not based on predefined clinical and/or imaging criteria nor was the etiology of CHF (ischemic versus non-ischemic versus other) determined; nonetheless, this study provides tantalizing circumstantial support for the notion that TNF-α contributes to the etiology of CHF in RA. Additional indirect support derives from a recent report [\n125\n] in which the prescription of disease modifying antirheumatic drugs (DMARDs; including TNF inhibitors) was associated with a 30% reduction in hospitalizations for new-onset CHF from a large administrative claims database of RA patients. Considering only TNF inhibitor treated patients, a 50% reduction in CHF hospitalizations was observed.\nTo date, few human investigations into the direct effects of TNF-α or TNF inhibitors on the myocardium have been undertaken. Imaging substudies of non-RA patients with advanced CHF showed no effect of etanercept on LVEF (assessed in 215 subjects who underwent radionuclide ventriculography at baseline and at 24 weeks) in RENNAISANCE [\n126\n] and a modest increase in LVEF (measured by radionuclide ventriculography) despite clinical worsening in infliximab treated patients in ATTACH [\n122\n]. Although studies incorporating direct visualization of myocardial function have yet to be performed in RA patients, clues from animal models of CHF induced by chronic cytokine excess (a setting that may mimic the RA disease state) may serve to explain the apparent contradictions in treatment effects of cytokine inhibition on the myocardium.\nAnimal models of cytokine induced congestive heart failure\nIn vitro \nand animal studies strongly support a mechanistic role for macrophage-derived cytokines, especially TNF-α, in the pathogenesis of CHF, rather than a mere epiphenomenon. Key features of the CHF phenotype, including pulmonary edema, negative inotropy, ventricular dilatation and hypertrophy, endothelial dysfunction, reduced myocardial β-adrenergic responsiveness, and myocyte apoptosis are recapitulated by experimental augmentation of TNF-α [\n127\n-\n129\n]. In a rat model, continuous infusion of TNF-α via an implanted osmotic infusion pump to levels congruent with those found in human CHF, led to a time-dependent reduction in LVEF and development of left ventricular dilatation [\n130\n]. These effects were reversed, at least in part, by removal of the infusion pump or administration of a dimeric TNF receptor antagonist [\n130\n].\nTransgenic murine models of cardiac-restricted overexpression of TNF-α have been generated by coupling the murine TNF-α gene to the murine α-myosin heavy chain promoter [\n131\n-\n133\n]. When expression is extremely robust, the animals die quickly (mean 11 days) of a dilated cardiomyopathy that, on histologic examination, is due to a diffuse inflammatory myocarditis [\n131\n]. With less robust expression of TNF-α, survival is longer (mean time to death approximately 10 months) and the CHF phenotype evolves more gradually, characterized by ventricular hypertrophy and dilatation, interstitial infiltrates and fibrosis, and depressed adrenergic response. These effects were attenuated or blocked by antagonism of TNF-α [\n134\n-\n136\n].\nThese studies strongly support a central role for TNF-α in mediating the processes leading to myocardial dysfunction. An inflammatory myocarditis has also been described in autopsy studies of RA patients (discussed above). It is tempting to speculate that chronic production of cytokines, including TNF-α, may affect the myocardium in RA in either an endocrine (originating in the synovium) or paracrine (produced in the local environment of the progressively failing myocardium) fashion, contributing to subclinical and eventually clinically recognizable ventricular dysfunction (Fig. \n1\n).\nInflammatory pathways and myocardial remodeling\nThe process by which cardiac structure and function adapts to physiologic changes is termed 'myocardial remodeling' and involves the cellular and interstitial changes leading to myocyte hypertrophy, ventricular dilatation, alterations in interstitial collagen superstructure, and interstitial myocardial fibrosis [\n137\n]. This process is mediated primarily through local expression of matrix metalloproteinases (MMPs), particularly MMP-1, MMP-2, MMP-3, and MMP-9, and modulated by expression of tissue inhibitors of matrix metalloproteinases (TIMPs) [\n138\n]. Circulating levels of MMPs are elevated in patients with overt CHF, regardless of etiology [\n139\n-\n141\n], suggesting a common unifying mechanism. Overexpression of MMPs and/or reduced expression of TIMPs are associated with proteolysis of the myocardial extracellular fibrillar collagen matrix and progressive ventricular dilatation [\n142\n,\n143\n]. Selective and non-selective MMP inhibition reverses or blocks the development of the phenotype [\n144\n,\n145\n].\nTNF-α has been shown to be a key regulator of MMP expression in myocardial remodeling [\n135\n,\n146\n]. In transgenic mice with cardiac restricted overexpression of TNF-α [\n146\n], early exposure to elevated TNF-α was associated with an increase in the myocardial zymographic MMP activity/myocardial TIMP (MMP/TIMP) ratio favoring degradation of interstitial fibrillar collagen and development of ventricular dilation and CHF. With aging, however, a shift to increased myocardial TIMP levels and an overall reduction in the MMP/TIMP ratio, an increase in collagen production, and subsequent fibrosis of the dilated ventricle was observed. This later phase was associated with an increase in transforming growth factor-β expression [\n146\n]. This time-dependent effect of TNF-α induced myocardial remodeling suggests that there may be a window of opportunity early in disease during which events leading to myocardial interstitial fibrosis may be prevented [\n147\n]. Importantly, it is this shift from myocardial interstitial degradation to fibrosis that appears to play a key role in the transition from compensated to decompensated CHF [\n148\n]. Moreover, this is supported by the finding that delayed anti-TNF-α therapy, administered at six weeks of age, was able to reverse ventricular dilatation, but not established fibrosis, in a transgenic mouse model of cardiac TNF-α overexpression [\n149\n]. The possibility that enhancing TNF-α expression in late CHF might even be desirable in order to reestablish a favorable MMP/TIMP balance has not been explored.\nRecent work suggests that cardiac structural homeostasis is regulated in part through a balance between membrane-bound and cleaved TNF-α. Normally, membrane bound TNF-α is converted to its soluble form by cleavage with TNF-α converting enzyme (TACE) [\n150\n]. In a line of transgenic mice with cardiac-restricted overexpression of TNF-α that is resistant to cleavage by TACE, concentric hypertrophy without chamber dilatation was observed [\n151\n,\n152\n], whereas mice with overexpression of TNF-α and an intact TACE cleavage site exhibited extracellular matrix degradation and ventricular dilatation [\n151\n,\n152\n]. In humans, increased TACE expression parallels the increase in TNF-α expression associated with dilated cardiomyopathy [\n153\n] and myocarditis [\n154\n]. Little is currently known, however, about the relative amounts or contribution of membrane bound TNF-α to myocardial homeostasis in humans.\nIn summary, animal studies have shown that the processes leading to cardiac myocyte hypertrophy, interstitial fibrillar collagen degradation, mural realignment, and ultimately to dilated cardiomyopathy are induced and/or regulated, at least in part, by TNF-α. The effects of TNF-α on the myocardium are complex, however, with a pathogenic effect early on and a putative protective effect later in disease. This dichotomy has important potential implications for human disease and has preliminary support from available clinical studies of TNF inhibitors in humans, in which patients with advanced CHF have shown no benefit or worsened when treated with anti-TNF-α therapy. In contrast, in patients with RA and no overt CHF, treatment of RA with TNF inhibitors might offer some protection against cytokine induced CHF.\nConclusion\nThe evolution of subclinical myocardial dysfunction to overt CHF is associated with significant morbidity and alarming mortality. Population- and clinic-based epidemiologic studies have suggested that RA patients may be more prone to the development of CHF and more susceptible to CHF-related mortality. While some traditional risk factors for CHF are over-represented in RA patients, they do not appear to account for all of the increased CHF risk observed. Other RA associated factors, particularly the chronic elaboration of inflammatory cytokines, are likely substantial contributors to myocardial dysfunction in RA patients. Additional investigation is needed to clarify both the direct effects of the RA disease process and the effects of RA-directed therapeutics on the myocardium at all stages of disease in order to define appropriate strategies to prevent or attenuate the development of CHF in RA patients.\nAbbreviations\nATTACH = Anti-TNF-α Therapy Against Chronic Heart failure; CHF = congestive heart failure; CVD = cardiovascular disease; IL = interleukin; LV = left ventricular; LVEF = left ventricular ejection fraction; MI = myocardial infarction; MMP = matrix metalloproteinase; OA = osteoarthritis; RA = rheumatoid arthritis; RECOVER = Research into Etanercept: Cytokine Antagonism in Ventricular Dysfunction Trial; RENNAISANCE = Randomized Etanercept North American Strategy to Study Antagonism of Cytokines; RF rheumatoid factor; TACE = TNF-α converting enzyme; TIMP = tissue inhibitor of matrix metalloproteinase; TNF-α = tumor necrosis factor-α.\nCompeting interests\nDr Giles receives grant support from the American College of Rheumatology and the Arthritis National Research Foundation. Dr Bathon receives grant support from the National Institutes of Health, Bristol Myers Squibb, Centocor, Amgen, IDEC/Genentech. Dr Bathon is a consultant to Abbott.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
46
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nHospitalization Rates for Coronary Heart Disease in Relation to Residence Near Areas Contaminated with Persistent Organic Pollutants and Other Pollutants\n\n**Article Abstract:**\n\nExposure to environmental pollutants may contribute to the development of coronary heart disease (CHD). We determined the ZIP codes containing or abutting each of the approximately 900 hazardous waste sites in New York and identified the major contaminants in each. Three categories of ZIP codes were then distinguished: those containing or abutting sites contaminated with persistent organic pollutants (POPs), those containing only other types of wastes (“other waste”), and those not containing any identified hazardous waste site (“clean”). Effects of residence in each of these ZIP codes on CHD and acute myocardial infarction (AMI) hospital discharge rates were assessed with a negative binomial model, adjusting for age, sex, race, income, and health insurance coverage. Patients living in ZIP codes contaminated with POPs had a statistically significant 15.0% elevation in CHD hospital discharge rates and a 20.0% elevation in AMI discharge rates compared with clean ZIP codes. In neither of the comparisons were rates in other-waste sites significantly greater than in clean sites. In a subset of POP ZIP codes along the Hudson River, where average income is higher and there is less smoking, better diet, and more exercise, the rate of hospitalization for CHD was 35.8% greater and for AMI 39.1% greater than in clean sites. Although the cross-sectional design of the study prevents definite conclusions on causal inference, the results indirectly support the hypothesis that living near a POP-contaminated site constitutes a risk of exposure and of development of CHD and AMI.\n\n**Article Body:**\n\nCoronary heart disease (CHD) is the most common, serious, chronic, life-threatening illness in the United States, affecting more than 11 million people (\nSelwyn and Braunwald 2001\n). The major risk factors for CHD (smoking, hypertension, dyslipidemia, diabetes mellitus, male sex, and older age) are well known. However, environmental exposures may also contribute to the risk of development of CHD. Air pollution with particulate matter results in an elevated risk for cardiovascular mortality and an increase in hospitalization rates for cardiovascular diseases (\nBrook et al. 2004\n). In the Kuopio Ischemic Heart Disease Risk Factor Study, \nSalonen et al. (1991\n, \n1992)\n found evidence that copper and iron are risk factors for heart disease and later demonstrated that higher dietary intake of mercury from non-fatty freshwater fish was associated not only with an increased risk of acute myocardial infarction (AMI) but also with CHD mortality, cardiovascular disease mortality, and any cause mortality among eastern Finnish men (\nSalonen et al. 1995\n); the researchers suggested that the mechanism occurs through promotion of lipid peroxidation. \nGuallar et al. (2002)\n also found a direct association between toenail mercury concentration and risk of myocardial infarction. Arsenic exposure is associated with peripheral vascular disease (\nTseng et al. 1996\n). Occupational exposure to dioxins/furans and polychlorinated biphenyls (PCBs) has been correlated with an excess incidence of CHD (\nCalvert et al. 1998\n; \nFlesch-Janys et al. 1995\n; \nGustavsson and Hogstedt 1997\n; \nHay and Tarrel 1997\n; \nVena et al. 1998\n).\nSeveral reports have indicated elevations in rates of various diseases (\nGoldberg et al. 1995\n; \nHall et al. 1996\n) and birth defects (\nCroen et al. 1997\n; \nGeschwind et al. 1992\n) among individuals living near hazardous waste sites. New York has a large number of relatively well-characterized hazardous waste sites, known by location and by the major contaminants present at each site. New York also has an excellent statewide system of reporting diseases diagnosed in every hospitalized patient in state-regulated hospitals, which was available to us on the basis of the ZIP code of residence of each patient for the years 1993–2000. We have matched these data sets to investigate the frequency of hospitalization diagnosis for various forms of CHD with residence in ZIP codes that either contain, or do not contain, hazardous waste sites with persistent organic pollutants (POPs) or other wastes.\nFat-soluble POPs, such as PCBs, dioxins/furans, and persistent pesticides such as dichlorodiphenyltrichloroethane (DDT) are of special concern because of their persistence in both the human body and the environment. This class of compounds bioconcentrate in food and can be ingested, inhaled, or absorbed through the skin. These compounds alter normal functioning of the immune, nervous, and endocrine systems and are carcinogenic (\nCarpenter 1998\n; \nLucier 1991\n; \nVine et al. 2000\n). In previous studies, we demonstrated elevated hospitalization for thyroid diseases, diseases of the genital tract, and endometriosis among hospitalized women residing within 15 miles of three areas of concern (AOCs) in western New York (\nCarpenter et al. 2001\n) and when comparing all ZIP codes containing or abutting POP-contaminated sites with either “other waste” ZIP codes (ZIP codes containing a hazardous waste site but not one containing POPs) or “clean” ZIP codes (ZIP codes that do not contain an identified hazardous waste site) (\nCarpenter et al. 2003\n). \nKudyakov et al. (2004)\n reported a similar elevation in risk of infectious respiratory diseases and chronic bronchitis in POP-contaminated ZIP codes. Residential proximity to PCB-contaminated waste sites is associated with increased risk of giving birth to a low-birth-weight infant, especially if it is a male child (\nBaibergenova et al. 2003\n).\nThere is evidence in animals that PCBs induce lipogenic enzymes (\nBoll et al. 1998\n), that dioxin-like PCBs cause direct damage to endothelial cells (\nToborek et al. 1995\n), and that workers occupationally exposed to dioxins and PCBs have elevated serum lipids (\nCalvert et al. 1996\n; \nStehr-Green et al. 1986\n). Because elevated serum lipids are a major risk factor for CHD, we hypothesized that residency in proximity to POP sites may be associated with increased use of CHD hospital care services. The objective of our study was to examine the potential effect of residential exposure to POPs and non-POP contaminants on hospitalization rates for patients with AMI and other forms of CHD.\nMaterials and Methods\nWe conducted a cross-sectional study of hospital discharge rates. Data on hospital discharges were obtained from the New York Statewide Planning and Research Cooperative System (SPARCS; New York State Department of Health, Albany, NY), which is an administrative database. Like other administrative databases, it contains formalized information derived/abstracted from data sets such as clinical charts. We used SPARCS data from 1993–2000, with some 2.5 million hospital discharge records collected annually. Up to 15 diagnoses and 15 procedures, coded according to the \nInternational Classification of Diseases\n, \n9th Revision\n (\nICD-9; 1992\n), are recorded for every patient discharged from any hospital in New York State, except for federal hospitals. The SPARCS data set does not include data from New York City, which maintains its own hospitalization data. For this reason and because New York City differs from the rest of the state in many other ways, we excluded New York City from this study. Data were collected on all the hospital discharges that contained any of the ICD-9 codes for CHD [410.0–414.9 (ischemic heart disease) and 429.7 (sequelae of myocardial infarction, not elsewhere classified)]. The primary outcome variable was the CHD hospital discharge rate calculated as a number of hospital discharges of patients with a diagnosis of CHD divided by the total population residing in a given area (ZIP code). We analyzed separately data for ICD-9 code 410 (AMI), because AMI is more likely to be a primary diagnosis and is less likely to recur in a single individual.\nEvery SPARCS record contains information on patient’s age, sex, race, source of payment (including the type of health insurance coverage), and the ZIP code of their residence. We used this information to adjust for potential confounders. Income was employed as a proxy measure of socioeconomic status (SES), which is another potential confounder in our study. Data on income (median household income on the ZIP code level) were obtained from the 2000 U.S. Census (\nU.S. Census Bureau 2000\n).\nThe ZIP codes were classified as POPs, other waste, or clean, depending on whether they contained or abutted contaminated sites, where POPs were considered to be PCBs, dioxins/furans, or chlorinated and persistent pesticides. We considered the hazardous waste sites in New York identified by the U.S. Environmental Protection Agency (EPA) (87 National Priority List sites) (\nU.S. EPA 2003\n), the New York State Department of Environmental Conservation (NYSDEC) (865 state Superfund sites) (\nNYSDEC 2004b\n), and the International Joint Commission (six AOCs) (\nU.S. EPA 2004\n), and for each site identified the ZIP code(s) containing or abutting the site and the contaminants listed as being those of primary concern by these agencies. Detailed information on the federal and state Superfund sites, including amounts of contaminants they contain, insofar as that is known, is available on the U.S. EPA website (\nU.S. EPA 2005\nβ); for the National Priorities List sites on the NYSDEC website (\nNYSDEC 2004a\n), and for the AOCs from a different U.S. EPA website (\nU.S. EPA 2004\n). Exclusive of New York City, there were 196 POP ZIP codes, 222 ZIP codes with other-waste sites, and 996 clean ZIP codes. \nFigure 1\n is a map of New York State in which the ZIP codes with POP sites are shown in red, and those with other waste are shown in yellow. We analyzed separately the 78 ZIP codes in the PCB-contaminated portion of the Hudson River (200 miles from Hudson Falls to Manhattan), a National Priorities List site, because we have previously reported, using data from the Behavioral Risk Factor Surveillance System (BRFSS), that in those counties abutting the contaminated portion of the Hudson there is less smoking, more consumption of fruit and vegetables, and more frequent exercise than in the rest of the state (\nKudyakov et al. 2004\n, their \ntable 3\n). In addition, the average family income is greater in the ZIP codes along the Hudson River (\nKudyakov et al. 2004\n, their \ntable 2\n). Thus analysis of this subset of POP sites allows for partial control over the other major risk factors for CHD and AMI. In addition, we attempted to control for the adverse cardiovascular effects of particulate air pollution by use of the reported mean daily levels of 2.5 μm particulates as reported by the NYSDEC from its network of 43 air monitoring stations, with data reported on the NYSDEC website (\nNYSDEC 2004b\n) and \nEnvironmental Defense (2004)\n. Effects of living in contaminated sites on the CHD and AMI hospital discharge rates were assessed using a negative binomial model. All analyses were performed using SAS statistical software (version 8.2; SAS Institute Inc., Cary, NC). GENMOD procedure in SAS was used to perform negative binomial regression.\nResults\nTable 1\n shows the demographics of the populations in each of the three categories of ZIP code for the period 1993–2000. Living in a ZIP code containing or abutting a POP hazardous waste site was associated with a 15% increased frequency of discharge diagnosis of CHD compared with living in a clean ZIP code (\nTable 2\n). Living in a ZIP code with other waste was also associated with a 4% elevated CHD diagnosis, but this was not statistically significant. As expected, CHD discharge rates were higher in men than in women and increased with age. Compared with CHD patients with median household income of < $30,312, those with higher income had lower hospital discharge rates. Coverage by Medicare (the U.S. government program for health care for the elderly) or comprehensive private health insurance, such as Blue Cross, was associated with lower use of in-patient hospital care services compared with Medicaid coverage (the U.S. government program for health care for the poor) or absence of insurance (self-pay). Hospitalization rates differed across racial/ethnic groups. Asians and Pacific Islanders had lower rates than did Caucasians, African Americans, and Native Americans.\nChronic forms of CHD would be expected to be coded often in the SPARCS database as one of the 14 “other diagnoses” (along with other comorbidities) rather than as the “principal diagnosis.” This may result in a bias problem. Nonsevere comorbidities that do not require treatment during the hospital stay may be undercoded, resulting in underestimation of the association between CHD hospitalization rates and exposure (bias toward null). But the relatively high prevalence of CHD in the general population makes it quite a common comorbidity. Higher hospitalization rates for any disease caused by the contaminants of interest would result in higher CHD prevalence among hospitalized patients, resulting in overestimation of the association between pollution and hospital care use by CHD patients.\nTo control for these possible biases, we analyzed the association between the most severe form of CHD (AMI) and ZIP code of residence. AMI is a very serious and often life-threatening disease, and it is less likely to be a comorbidity. \nTable 3\n shows hospital discharge rates for AMI in relation to ZIP code of residence and adjusting for known covariates with negative binomial regression. After adjustment for the confounders, those residing in the areas contaminated with POPs have a significantly greater number of AMI hospitalizations. Residency in a POP-contaminated ZIP code is associated with a 20.0% increase in AMI hospital discharge rates compared with clean sites. The 7% elevation in AMI hospitalization rate in other-waste ZIP codes was not statistically significant.\nAlthough other factors associated with AMI hospital discharge rates were not of primary interest for this study, they can be used for quality control purposes and thus merit careful examination. Male sex and older age are well-known risk factors for AMI and other forms of CHD, and more frequent hospitalizations should be expected in these population groups. Consequently, male sex and older age should be associated with higher hospital discharge rates for AMI. So adequacy of the model describing association between any exposure and AMI hospital discharge rates can be questioned if the model fails to indicate the contribution of sex and age.\nThe hospital discharge rate for AMI among males was about twice that among females, and it increased with age (\nTable 3\n). Compared with the lowest income category, those with higher household income had lower hospital discharge rates. Inequality in health insurance coverage is associated with some difference in hospital care use. Those covered by Medicaid or not insured (self-pay) had lower hospital discharge rates compared with those covered by comprehensive health insurance or by Medicare. Caucasians, African Americans, and Native Americans have higher discharge rates than Asians and Pacific Islanders. These results indirectly support the plausibility of the model.\nThere are other important risk factors for CHD, especially smoking, diet, and exercise. Information at an individual level for these risk factors is not available in our data sets. However, by use of BRFSS, we have county-level information, as reported previously (\nKudyakov et al. 2004\n). In the counties along the 200 miles of the Hudson River that are contaminated with PCBs, there is less smoking, more frequent exercise, and more consumption of fruits and vegetables than in the rest of the upstate region. \nTables 4\n and \n5\n show the rates of hospitalization of residents in the 78 ZIP codes that abut the contaminated portion of the Hudson River for CHD and AMI, respectively. Despite living a healthier life style, residents along the Hudson River were 35.8% more likely to be discharged with a diagnosis of CHD, and 39.1% more likely to be discharged with a diagnosis of AMI. These results are highly significant.\nParticulate air pollution is well documented to be an important risk factor for CHD and AMI. It is difficult to control for local differences in air pollution in an ecologic study such as this, but we have used what information is available from the air monitoring stations operated by the NYSDEC. Of the 43 stations in New York, 20 are outside of New York City, but in only 16 is regular monitoring of 2.5-μm particulates obtained (six in POP ZIP codes, seven in clean ZIP codes, and three in other-waste ZIP codes). The mean 24-hr 2.5-μm particulate levels reported were 11.5 μg/m\n3\n (range, 7.7–13.7) in the POP ZIP codes, 11.1 μg/m\n3\n (range, 10.5–12.2) in the other-waste ZIP codes, and 11.2 μg/m\n3\n (range, 9.5–12.4) in the clean ZIP codes. Although the number of ZIP codes for which mean particulate information is available is small, the information that can be obtained does not suggest that air pollution is a major confounder.\nDiscussion\nThe results of this study are consistent with the hypothesis that exposure to certain environmental contaminants increases the risk of development of CHD and AMI. Those persons residing in POP-contaminated ZIP codes have significantly higher rates of diagnosis of CHD and/or AMI on hospital discharge than do those living in noncontaminated areas. Residency in areas contaminated with other waste is also associated with an elevation in hospital discharge rates, but this relationship did not reach the traditionally used significance level of α = 0.05.\nOthers have reported health effects of living near hazardous waste sites [reviewed by \nVrijheid (2000)\n]. Health Canada demonstrated a statistically significant elevation, relative to the rest of Ontario, in standardized morbidity ratios for a number of different diseases, including reproductive dysfunction, respiratory and gastrointestinal disease, and diabetes, in Canadian AOCs, highly contaminated sites along the Great Lakes as defined by the International Joint Commission (\nElliott SJ et al. 2001\n). Congenital malformations have been found more commonly in residents living near hazardous waste sites in a number of studies (\nCroen et al. 1997\n; \nDolk et al. 1998\n; \nGeschwind et al. 1992\n; \nOrr et al. 2002\n), whereas others have reported elevated incidence of low birth weight (\nElliott P et al. 2001\n) and end-stage renal disease (\nHall et al. 1996\n). Low birth weight is important in two regards: It is a known risk factor for the development of CHD later in life (\nBarker et al. 2002\n), and it has been demonstrated to occur more frequently in infants born to women occupationally exposed to PCBs (\nTaylor et al. 1989\n). Using New York birth registry data, we have previously demonstrated an elevation in rates of low-birth-weight infants (especially males) in residents of PCB ZIP codes after adjustment for other factors, including mother’s age, race, weight, height, and incidence of smoking (\nBaibergenova et al. 2003\n). Using SPARCS data, we demonstrated statistically significant elevation of hospitalization rates for respiratory infectious diseases, especially diseases such as chronic bronchitis (\nKudyakov et al. 2004\n). The fact that we have demonstrated relationships between residence near waste sites and various diseases using two independent registries adds support to the hypothesis that living near such sites constitutes a risk of exposure and disease.\nThe observations reported in this investigation raise two important questions: What is the mechanism(s) involved, and what is the route(s) of exposure? Exposure to PCBs and dioxins is known to increase atherogenic serum lipid levels in both animals (\nLind et al. 2004\n; \nLovati et al. 1984\n) and humans (\nCalvert et al. 1996\n; \nChase et al. 1982\n; \nHu et al. 2003\n). Most likely, these actions are secondary to gene and enzyme induction in the liver resulting from exposure to POPs, which are difficult to metabolize (\nBoll et al. 1998\n). In addition, these contaminants cause direct damage to endothelial cells via oxidative stress (\nChoi et al. 2003\n; \nHennig et al. 2002\n; \nSlim et al. 1999\n). The combination of an elevation in serum lipids with damage to endothelial cells would be expected to increase the risk of cardiovascular disease.\nWith regard to the route of exposure, the present and our previous observations (\nBaibergenova et al. 2003\n; \nCarpenter et al. 2001\n, \n2003\n; \nKudyakov et al. 2004\n) are most consistent with air transport of contaminates, both in vapor phase and particulate bound, being the major route of spread, with inhalation of these semivolatile compounds a major (and underappreciated) route of exposure. Ingestion is usually considered to be the most important route of exposure to POPs, but what people eat is not defined by the ZIP code in which they live. Consumption of contaminated fish is an important route of exposure to PCBs and dioxins, but even persons who engage in sports fishing are not defined by ZIP code of residence. There is increasing evidence that although PCBs and other POPs are not as volatile as some other organic pollutants, they are present in air at high levels around contaminated sites (\nHermanson et al. 2004\n), and they can be absorbed from air and cause biologic effects in animals (\nCasey et al. 1999\n; \nImsilp et al. 2005\n). POPs also bind to particulates, which can spread to nearby residences by air currents and can be either breathed in or unintentionally ingested. Although exposure to some of the contaminants at other-waste sites, especially some metals, is also associated with an increased risk of CHD, the fact that these compounds are not very volatile may explain why we did not find a statistically significant relationship between residence in ZIP codes containing these contaminants and CHD.\nSeveral important confounders could explain these observations, particularly SES and behavioral risk factors. Harmful behavioral patterns and unfavorable environmental exposures associated with development of diseases have higher prevalence among lower social classes. \nWoodward and Boffetta (1997)\n report differences in exposure to environmental factors among different social classes. People of lower SES are more likely than those of higher SES to reside near polluted sites. New sources of pollution are likely to be placed in poorer neighborhoods, and populations of low SES tend to migrate to such disadvantaged areas for economic reasons (\nWoodward and Boffetta 1997\n). However, our results are adjusted for the median household income. Income is a commonly used proxy measure of SES (\nBerkman and Macintyre 1997\n; \nKrieger et al. 1997\n; \nMoss and Krieger 1995\n). Thus, an unequal distribution of socially disadvantaged population as a possible explanation of elevation in hospitalization rates for CHD in residents of POP ZIP codes is unlikely. Our results also control for age, race, and type of health insurance. In the subset of POP sites along the Hudson River, the average family income is higher than in the rest of New York State, yet rates of hospitalization for CHD and AMI are even more elevated than in the rest of the POP sites.\nHealth insurance coverage is also related to SES (\nBlackstock et al. 2002\n; \nBradley et al. 2002\n; \nRogers et al. 2000\n; \nSchneider et al. 2002\n). The effect of health insurance on mortality (lacking insurance is associated with higher mortality) is comparable with effects of education and income (\nFranks et al. 1993\n). For CHD, patients covered by the most comprehensive types of insurance (e.g., Blue Cross) and Medicare had lower rates than did those covered by Medicaid or not insured (self-pay). The opposite was observed for AMI patients (except for the subgroup of the Hudson River area residents): Those covered by the most comprehensive types of insurance and Medicare had higher rates. This probably reflects the fact that the CHD and AMI populations are different, with CHD being more heterogeneous and including AMI. Many of the chronic forms of CHD are not emergencies, and patients with good insurance are more likely to seek help and be diagnosed in the early stages of the disease. As a result, their chances for progression of CHD to more severe forms, such as AMI, are lower. In contrast, those covered by Medicaid or not insured are less likely to seek health care for conditions that are not emergencies. As a result, they present at hospitals with AMI.\nFine particulate air pollution is another well-documented risk factor for cardiovascular disease (\nLaden et al. 2000\n). Although there is no information on particulate levels in every ZIP code, the information available through the network of air monitoring stations in New York does not indicate that fine particulate levels explain the results obtained. However, additional study of air pollution as a possible confounder is warranted.\nOur study is not free from limitations above and beyond the usual limitations of ecologic investigations (\nMorgenstern 1982\n). The SPARCS database contains information on discharges from state-regulated hospitals only. Data from federally regulated hospitals, including those operated under auspices of the Veterans Administration, are not available from the SPARCS database. Also, there is no information in SPARCS on how many times a patient was hospitalized, which prevents us from drawing conclusions on CHD incidence. Measurement of CHD incidence would provide stronger support of a cause–effect relationship between exposure to the pollutants and CHD development than only rates of CHD diagnosis on hospitalization. This is somewhat less of a problem with AMI, because repeated hospitalizations of the same person (i.e., hospitalizations for subsequent myocardial infarction) do not happen often. So to some degree AMI incidence can be approximated by hospitalization rate. A major limitation is that ZIP code of residence is a very crude measure of exposure. ZIP codes are of varying size, and we have not controlled for the location of the waste site within the ZIP code, because we have only the ZIP code of patient residence, not street address. However, if anything, these limitations would be expected to result in an underestimation of the true relationship. Although we have to some extent controlled for behavioral confounders through use of BRFSS data and air pollution through use of data from the network of monitoring stations in New York, neither of these data sets has information at the level of every ZIP code.\nIn summary, we determined that residency in POP-contaminated sites is associated with increased rates of hospitalization for CHD and AMI. Although the cross-sectional design of the study prevents us from making definitive conclusions on causal inference, the results support the hypothesis that exposure to PCBs, dioxins/furans, and/or persistent pesticides as a result of living near a hazardous waste site results in an elevated risk of CHD.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
47
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe role of cardiac troponin I as a prognosticator in critically ill medical patients: a prospective observational cohort study\n\n**Article Abstract:**\n\nIntroduction\nMyocardial injury is frequently unrecognized in intensive care unit (ICU) patients. Cardiac troponin I (cTnI), a surrogate of myocardial injury, has been shown to correlate with outcome in selected groups of patients. We wanted to determine if cTnI level measured upon admission is an independent predictor of mortality in a heterogeneous group of critically ill medical patients.\nMethods\nWe conducted a prospective observational cohort study; 128 consecutive patients admitted to a medical ICU at a tertiary university hospital were enrolled. cTnI levels were measured within 6 h of admission and were considered positive (>0.7 ng/ml) or negative. A variety of clinical and laboratory variables were recorded.\nResults\nBoth cTnI positive and negative groups were similar in terms of age, sex and pre-admission co-morbidity. In a univariate analysis, positive cTnI was associated with increased mortality (OR 7.0, 95% CI 2.44–20.5, p < 0.001), higher Acute Physiology and Chronic Health Evaluation (APACHE) II scores and a higher rate of multi-organ failure and sepsis. This association between cTnI and mortality was more pronounced among elderly patients (>65 years of age). Multivariate analysis controlling for APACHE II score revealed that elevated cTnI levels are not independently associated with 28-day mortality.\nConclusion\nIn critically ill medical patients, elevated cTnI level measured upon admission is associated with increased mortality rate. cTnI does not independently contribute to the prediction of 28-day mortality beyond that provided by APACHE II.\n\n**Article Body:**\n\nIntroduction\nAssessing the severity of illness and outcome of critically ill patients is important as it influences management strategies and resource allocation. Historically, research aimed at determining factors associated with intensive care unit (ICU) mortality focused on individual risk factors and the development of multivariable prediction scores. These investigations consistently suggested the importance of organ system failure as strong predictors of both ICU and hospital mortality [\n1\n-\n4\n]. Over the past decade, several studies indicated that cardiac dysfunction is a frequent and important factor in determining the outcome of critically ill patients [\n5\n,\n6\n]. The pathophysiology of myocardial injury in critically ill patients is believed to be multifactorial, including the underlying disease process, hypoxemia and acidosis as well as therapeutic maneuvers [\n7\n,\n8\n]. It is estimated that as many as 15% of ICU admissions are complicated by some degree of myocardial injury and as many as 85% of patients with sepsis may have raised cardiac troponin [\n5\n,\n9\n]. Elevated serum levels of cardiac troponin I (cTnI), a myocardial regulatory protein of the thin actin filament, are considered highly sensitive and specific indicators of myocardial injury [\n10\n]. Serial measurement of cTnI is routinely used in the evaluation of patients with acute coronary syndromes (ACS) for diagnostic and prognostic purposes [\n10\n-\n12\n]. Several studies have assessed the prognostic value of elevated cTnI in critically ill patients without ACS. While some suggested that cTnI levels correlate with myocardial damage and poor outcome, others could not confirm this association [\n6\n,\n13\n-\n17\n]. Because cTnI elevation reflects organ failure (i.e. myocardial injury) its role as an additional marker of severity of illness and outcome is biologically plausible; however, limited information is available regarding the relative significance of cTnI elevation as an independent predictor of mortality in relation to the Acute Physiology And Chronic Health Evaluation (APACHE) II score. We hypothesized that elevated cTnI will not contribute to the mortality prediction provided by the multivariable APACHE II score. Therefore, we conducted a prospective cohort study in which the main purpose was to determine whether cTnI, measured upon admission, is an independent predictor of mortality in a heterogeneous group of critically ill medical patients.\nMaterials and Methods\nStudy location and population\nThe study was conducted within the medical ICU (MICU, eight beds) of Soroka University Medical Center, Beer-Sheva, Israel, a tertiary university hospital in Israel. All patients admitted to the MICU during a nine-month period (September 2002 to June 2003) were evaluated prospectively. The nursing staff and the physicians providing care for the patients in the MICU were completely blinded to the troponin results. A total of 128 consecutive patients were enrolled in this observational cohort study. All definitions were determined prospectively. The definitions used for sepsis, severe sepsis and organ failure were those used by the Recombinant Human Activated Protein C Worldwide Evaluation in Severe Sepsis (PROWESS) investigators [\n18\n]. Patients diagnosed with ACS, defined as unstable angina, typical chest pain, ischemic ECG changes or cardiogenic pulmonary edema were excluded as well as patients requiring chronic hemodialysis or patients who underwent major surgery during the month preceding admission (in order to exclude peri-operative myocardial injury). The Ethics Committee of the Soroka University Medical Center approved the study protocol prior to its initiation.\nData collection\nOne of the investigators who did not participate in routine patient care made daily rounds in the ICU recording relevant data from patient medical records and the hospital mainframe computer for reports of laboratory and microbiologic data. A complete history and physical examination was recorded on each patient enrolled in the study. APACHE II score was calculated based on the worst values for the first 24 h after ICU admission. Serum levels of cTnI were measured within 6 h of admission. The commercial assay AxSYM Troponin-I (Abbott laboratories, Abbott Park, Illinois, USA), a micro particle enzyme immunoassay, was used to determine cTnI levels. The assay characteristics were as follows: detection limit 0.3 ng/ml; analytical range 0–50 ng/ml; assay coefficient of variation (CV) range 5.2–7.8%. The cTnI cutoff is 0.7 ng/ml with a CV of 10%. Thus any cTnI blood level > 0.7 ng/ml was considered abnormal and indicative of myocardial injury. The primary end point was 28-day mortality. Secondary end points included days on mechanical ventilation, length of stay, and the number of failing organs.\nStatistical analysis\nContinuous variables' data are expressed as mean value ± SD. Bi-variate hypotheses involving continuous variables were tested with a t-test for independent variables with normal distribution and Mann-Whitney test for variables with abnormal distribution. Normality of the data was tested with a one-sample Kolmogorov-Smirnov test to indicate the appropriateness of parametric testing. Categorical variables are expressed as percentage; comparisons between groups were made using the chi square test. Logistic regression analysis was used to identify independent variables associated with death. Variables that were associated with mortality in univariate analysis were considered for inclusion in the model, whereas parameters already incorporated into the APACHE-II score, such as age, creatinine level and mean arterial pressure were not included. Cumulative survival curves were constructed using the Kaplan-Meier method and compared with the log-rank test. Results were considered significant at p < 0.05. Statistical analysis was performed with the SPSS 11.5 statistical package (SPSS Inc. Chicago, IL, USA).\nResults\nA total of 128 patients met inclusion criteria and were evaluated during the study period. Demographic and clinical characteristics of the study patients enrolled are shown in Table \n1\n. The mean age of the study population was 53.9 ± 19 years and 68% were male. There was no significant difference between the cTnI positive and negative groups in terms of background illnesses; ischemic heart disease (20% versus 12%, p = 0.2), chronic obstructive pulmonary disease (COPD; 17% versus 12%, p = 0.43), diabetes mellitus (31% versus 17%, p = 0.08), arterial hypertension (34% versus 26%, p = 0.34) or malignancy (6% versus 3%, p = 0.61). Stratifying the patients according to the absence or presence of cTnI elevation revealed that of the various causes of admission, only sepsis was associated with elevated troponin (p = 0.008). Patients with elevated cTnI had a significantly higher APACHE II score (p < 0.001), required longer duration of mechanical ventilation (p = 0.004) and their mortality rate increased from 9.7% to 42.9% (OR 7.0, 95%CI 2.68–18.3, p < 0.001). Clinical variables upon admission, particularly vasopressor requirement, did not correlate with cTnI levels. Although creatinine levels were higher in the cTnI group, none of the patients required renal replacement therapy.\nTable \n2\n shows demographic and clinical information of the study population stratified according to outcome. Patients who died had higher cTnI levels (p < 0.001), were significantly older (p = 0.001), had greater APACHE II scores (p = 0.001) and longer duration of mechanical ventilation (p < 0.001). In contrast, the cause of admission was not associated with differences in mortality rate. Of the clinical variables evaluated upon admission only mean arterial pressure (p = 0.006), creatinine level (p = 0.004) and vasopressor requirement were significantly associated with higher mortality (p = 0.02).\nAmong elderly (older than 65 years) patients (n = 49) with elevated cTnI levels, the 28-day mortality rate was 10/15 patients (66.7%), while the mortality rate among elderly patients with normal cTnI levels was only 4/34 patients (11.8%). This pattern was observed also in the younger patients, but to a lesser extent. Kaplan-Meier survival analysis in the younger and older age groups is shown in Fig. \n1a,b\n. Log-rank tests for both groups were statistically significant: 0.04 and <0.001, respectively.\nThe results of the multivariate analysis (logistic-regression) are shown in Table \n3\n. The two variables that were included in the final model were cTnI and APACHE II; both highly correlated with mortality in univariate analysis. Elevated cTnI levels were not found to be an independent predictor of mortality regardless of APACHE II score (OR 2.8, 95% CI 0.87–9.2, p = 0.085). Multivariate analysis of the subgroup of patients admitted without sepsis (n = 82) reveals that while APACHE II remained significantly associated with 28-day mortality (OR 1.2, 95% CI 1.03–1.28 per point increment), abnormal cTnI level was not (OR 1.2, 95% CI 0.21–7.1).\nDiscussion\nWe found that in critically ill medical patients, elevated cTnI is associated with increased mortality and longer duration of mechanical ventilation. cTnI does not, however, independently contribute to the prediction of 28-day mortality beyond that provided by APACHE II.\nCardiac troponin I and T are the most specific and sensitive laboratory markers of myocardial cell injury and may be elevated in patients presenting with many conditions other than acute coronary syndrome [\n9\n,\n11\n]. Elevated cTnI levels also correlate with decreased left ventricular function in both coronary and non-coronary patients [\n13\n,\n16\n]. Cardiac dysfunction during sepsis is fairly well documented and has been associated with poor prognosis [\n5\n]. Moreover, a small recent study evaluated the value of brain natriuretic peptide (BNP) plasma levels as a marker of systolic myocardial dysfunction during severe sepsis [\n19\n]. This study suggested that systolic dysfunction is present in 44% of patients with severe sepsis, BNP is useful in its detection and high plasma levels of BNP are associated with poor outcome [\n19\n]. It remains unclear though whether, in this context, elevated cTnI reflects reversible or irreversible myocardial damage [\n7\n,\n9\n]. Our data indicate that in patients over 65 there is a stronger correlation between elevated cTnI and mortality, which can probably be attributed to the extent, and possibly irreversibility, of myocardial damage in this age group. An interesting finding of this study was that most deaths among younger patients occurred within the first five days, whereas in the elderly group the majority of deaths (60%) occurred after this time frame. This data may suggest that younger patients who survive the initial insult do relatively well. Our study, however, was not designed nor powered to address the effect of age on outcome.\nSeveral studies have addressed the prognostic value of elevated cTnI in non-coronary patients. In selected groups such as COPD and hemodyalisis patients, elevated cTnI correlated with poor outcome [\n20\n,\n21\n]. A study in emergency department patients has shown that there is a significant correlation between cTnI elevation and outcome. APACHE II is not provided, however, nor were the patients stratified by cause of admission. Therefore, no comparison between this study and ours could be performed [\n17\n]. Relos \net al\n. [\n22\n], evaluating surgical ICU patients, suggested that moderate elevation of serum troponin I, which are below the threshold required to diagnose overt myocardial infarction, may reflect ongoing myocardial injury in the critically ill and are associated with a higher mortality rate and longer hospital and ICU length of stay. To the best of our knowledge, only one study suggested an independent predictive value of elevated cTnI after controlling for severity of illness assessed by APACHE II [\n23\n]. A strong correlation between mortality and elevated cTnI in critically ill medical patients without coronary disease was shown in this study. The sample size was rather small (58 patients), however, and the majority of patients had sepsis (88%), which limits the interpretation of these results. In contrast to these studies, Kollef \net al\n. [\n6\n] suggested that serial measurements of cTnI do not independently contribute to the prediction of hospital mortality beyond that provided by clinically recognized cardiac dysfunction. Differences in design and patient mix preclude meaningful comparisons between this study and ours. Our observation that cTnI elevation is not an independent predictor of mortality is not surprising because troponin reflects a single system malfunction while the multivariable APACHE II reflects several highly relevant systems in the context of critically ill patients. It is, therefore, unlikely that a single assay will provide an independent additional value beyond that provided by APACHE II. Nonetheless, our finding that cTnI elevation is an important marker of severity of illness and is associated with high mortality rate is still clinically relevant, particularly in view of the fact that the Kaplan-Meier analysis indicates that the discriminative effect of cTnI elevation is evident from the first day.\nThe present study included a relatively small number of patients, limiting the significance of post-hoc subgroup analysis and our ability to identify other independent determinants of early mortality. The fact that the frequency of ischemic heart disease (IHD) was similar among cTnI positive patients and cTnI negative patients supports the assumption that the elevated cTnI in our study should not be attributed to ACS. As we did not systematically perform echocardiography or evaluation of coronary flow in these patients, more objective assessment of coronary anatomy and myocardial function is not available. Therefore, any correlation between cTnI levels, in these patients, and irreversible myocardial dysfunction or ACS remains deductive. As indicated earlier, however, elevated cTnI has been previously shown to correlate with left ventricular function. In our study, cTnI was sampled only once upon admission. Even though the time course and kinetics of cTnI and its relation to outcome may be of interest, the main purpose of our study was to determine whether early cTnI elevation is of clinically relevant importance.\nConclusion\nWe conclude that troponin elevation may be used as an early marker of severity of illness and outcome, particularly in older patients, but it is not an independent predictor of mortality. Additional larger prospective studies will be required to determine if a single serum marker, reflecting myocardial injury, could be established as an independent prognostic tool.\nKey messages\n• \tcTnI is a surrogate of myocardial injury in critically ill medical patients\n• \tcTnI may be used as an early marker of outcome\n• \tThe correlation between elevated cTnI and mortality may be stronger among patients older than 65 years of age\n• \tcTnI does not independently contribute to the prediction of 28-day mortality beyond that provided by APACHE II.\nAbbreviations\nACS = acute coronary syndromes; APACHE = Acute Physiology and Chronic Health Evaluation; BNP = brain natriuretic peptide; COPD = chronic obstructive pulmonary disease; cTnI = cardiac troponin I; ICU = intensive care unit.\nCompeting interests\nThe authors declare that they have no competing interests.\nAuthors' contributions\nDAK performed literature research, contributed to protocol planning, was a primary data gatherer and drafted the manuscript. SC participated in data collection and statistical analysis. VN performed statistical analysis. LB participated in data collection. YA supervised research, planned protocol and edited the article.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
48
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe McKenzie method for the management of acute non-specific low back pain: design of a randomised controlled trial [ACTRN012605000032651]\n\n**Article Abstract:**\n\nBackground\nLow back pain (LBP) is a major health problem. Effective treatment of acute LBP is important because it prevents patients from developing chronic LBP, the stage of LBP that requires costly and more complex treatment.\nPhysiotherapists commonly use a system of diagnosis and exercise prescription called the McKenzie Method to manage patients with LBP. However, there is insufficient evidence to support the use of the McKenzie Method for these patients. We have designed a randomised controlled trial to evaluate whether the addition of the McKenzie Method to general practitioner care results in better outcomes than general practitioner care alone for patients with acute LBP.\nMethods/design\nThis paper describes the protocol for a trial examining the effects of the McKenzie Method in the treatment of acute non-specific LBP. One hundred and forty eight participants who present to general medical practitioners with a new episode of acute non-specific LBP will be randomised to receive general practitioner care or general practitioner care plus a program of care based on the McKenzie Method. The primary outcomes are average pain during week 1, pain at week 1 and 3 and global perceived effect at week 3.\nDiscussion\nThis trial will provide the first rigorous test of the effectiveness of the McKenzie Method for acute non-specific LBP.\n\n**Article Body:**\n\nBackground\nIn Australia, low back pain (LBP) is the most frequently seen musculoskeletal condition in general practice and the seventh most frequent reason for consulting a physician[\n1\n,\n2\n]. According to the Australian National Health Survey, 21% of Australians reported back pain in 2001; additionally, the Australian Bureau of Statistic's 1998 Survey of Disability, Ageing and Carers estimated that over one million Australians suffer from some form of disability associated with back problems[\n1\n].\nLBP poses an enormous economic burden to society in countries such as the USA, UK and The Netherlands[\n3\n]. In the largest state in Australia, New South Wales, back injuries account for 30% of the cost of workplace injuries, with a gross incurred cost of $229 million in 2002/03[\n4\n]. It is expected that most people with an acute episode of LBP will improve rapidly, but a proportion of patients will develop persistent lower levels of pain and disability[\n5\n,\n6\n]. Those patients with chronic complaints are responsible for most of the costs[\n6\n]. Effective treatment of acute LBP is important because it prevents patients from developing chronic LBP, the stage of LBP that requires costly and more complex treatment.\nThere is a growing concern about effectiveness of treatments for LBP, as reflected in the large number of systematic reviews published in the last 5 years addressing this issue. [\n7\n-\n12\n]. Despite the large amount of evidence regarding LBP management, a definitive conclusion on which is the most appropriate intervention is not yet available. A comparison of 11 international clinical practice guidelines for the management of LBP showed that the provision of advice and information, together with analgesics and NSAIDs, is the approach consistently recommended for patients with an acute episode[\n13\n]. Most guidelines do not recommend specific exercises for acute LBP because trials to date have concluded that it is not more effective than other active treatments, or than inactive or placebo treatments[\n8\n]. However, some authors have suggested that the negative results observed in trials of exercises are a consequence of applying the same exercise therapy to heterogeneous groups of patients. [\n14\n-\n16\n]. This hypothesis has some support from a recent high-quality randomised trial in which treatment based on a diagnostic classification system led to larger reductions in disability and promoted faster return to work in patients with acute LBP than the therapy recommended by the clinical guidelines[\n17\n].\nIn 1981, McKenzie proposed a classification system and a classification-based treatment for LBP labelled Mechanical Diagnosis and Treatment (MDT), or simply McKenzie Method[\n18\n]. Of the large number of classification schemes developed in the last 20 years [\n19\n-\n26\n], the McKenzie Method has the greatest empirical support (\ne.g\n. validity, reliability and generalisability) among the systems based on clinical features[\n27\n] and therefore seems to be the most promising classification system for implementation in clinical practice.\nPhysiotherapists commonly adopt the McKenzie Method for treating patients with LBP[\n28\n,\n29\n]. A survey of 293 physiotherapists in 1994 found that 85% of them perceived the McKenzie Method as moderately to very effective[\n28\n]. Nevertheless, a recent systematic review concluded that there is insufficient evidence to evaluate the effectiveness of the McKenzie Method for patients with LBP [\n30\n]. A critical concern is that most trials to date have not implemented the McKenzie Method appropriately. The most common flaw is that all trial participants are given the same intervention regardless of classification, an approach contradictory to the principles of McKenzie therapy.\nThe primary aim of this trial is to evaluate whether the addition of the McKenzie Method to general practitioner (GP) care results in better outcomes than GP care alone for patients with acute non-specific LBP when effect is measured in terms pain, disability, global perceived effect, and persistent symptoms.\nMethods\nThe University of Sydney Human Research Ethics Committee granted approval for this study.\nStudy sample\nOne hundred and forty eight participants with a new episode of acute non-specific LBP who present to GPs will be recruited for the study. A new episode of LBP will be defined as an episode of pain lasting longer than 24 hours, preceded by a period of at least one month without LBP and in which the patient did not consult a health care practitioner[\n31\n]. Participants will be screened for eligibility at their first appointment with the GP according to the inclusion and exclusion criteria.\nInclusion criteria\nTo be eligible for inclusion, participants must have pain extending in an area between the twelfth rib and buttock crease (this may or may not be accompanied by leg pain); pain of at least 24 hours duration; pain of less than 6 weeks duration; and they need to be eligible for referral to private physiotherapy practice within 48 hours.\nExclusion criteria\nParticipants will be excluded if they have one of the following conditions: nerve root compromise (defined as 2 positive tests out of sensation, power and reflexes for the same spinal nerve root); known or suspected serious spinal pathology; spinal surgery within the preceding 6 months; pregnancy; severe cardiovascular or metabolic disease; or inability to read and understand English.\nRecruiting GPs will record the number of patients who are invited to participate, the number who decline to participate, and the number of screened patients who are ineligible and their reasons for declining participation or ineligibility. Written consent will be obtained for each participant.\nSubjects who volunteer to participate and satisfy the eligibility criteria will receive baseline treatment and then be randomly allocated to one of the study groups. To ensure equal-sized treatment groups, random permuted blocks of 4–8 participants will be used[\n32\n]. Randomisation will be stratified by Workcover compensation status. The stratified random allocation schedule will be generated by a person not otherwise involved in recruitment, assessment or treatment of subjects and the randomisation sequence will be placed in sequentially numbered, sealed envelopes. The flow of participants through the study is detailed in Figure \n1\n.\nFigure 1\nFlow of participants through the study. \nLegend: GP – General practitioner; NRS – Numeric pain rating scale; PSFS – Patient-specific functional scale; RMQ – Roland-Morris questionnaire; GPE – Global perceived effect; LBP – Low back pain.\nOutcome measures\nThe McKenzie protocol is thought to promote rapid symptom improvement in patients with LBP[\n33\n,\n34\n] and this is one of the reasons that therapists choose this therapy. Therefore it is important to focus assessment on short-term outcomes. The primary outcomes will be:\n1. Usual pain intensity over last 24 hours recorded each morning in a pain diary over the first week. Pain will be measured on a 0–10 numerical rating scale (NRS). The unit of analysis will be the mean of the 7 measures[\n35\n];\n2. Usual pain intensity over last 24 hours (0–10 NRS) recorded at 1 and 3 weeks[\n35\n];\n3. Global perceived effect (0–10 GPE) recorded at 3 weeks.\nThe secondary outcomes will be:\n1. Global perceived effect (0–10 GPE) recorded at 1 week;\n2. Patient-generated measure of disability (Patient-Specific Functional Scale; PSFS) recorded at 1 and 3 weeks[\n36\n];\n3. Condition-specific measure of disability (Roland Morris Questionnaire; RMQ) recorded at 1 and 3 weeks[\n37\n];\n4. Number of patients reporting persistent back pain at 3 months.\nFollowing the screening consultation in which the inclusion and exclusion criteria are assessed, the GP will supervise the baseline measurement of pain. All patients will then receive an assessment booklet and a pre-paid envelope in which all other self-assessed outcome measures are to be recorded and sealed. One member of the research team will contact patients by telephone within 24 hours of the consultation with the GP in order to give explanations regarding the appropriate form of filling in the assessment booklet. At this time, other baseline outcomes will be recorded and then the patient will be randomised to study groups. The patient will be advised to keep the booklet at home, to seal it into the pre-paid envelope after the final assessment and mail the sealed envelope to the research team. To ensure the proper use of the assessment booklet and to avoid loss of data due to non-returned booklets, a blinded assessor will contact all patients by telephone 9 and 22 days after the consultation with the GP to collect patient's answers from the 1\nst \nweek and 3\nrd \nweek assessments, respectively.\nThe procedure for obtaining outcome data will be followed for all participants, regardless of compliance with trial protocols. At 3 months, data regarding the presence of persistent (chronic) symptoms will be collected by telephone. Participants will be asked to answer the following yes-no question: \"During the past 3 months have you ever been completely free of low back pain? By this I mean no low back pain at all and would this pain-free period have lasted for a whole month\". Those answering \nno\n will be considered to have persistent LBP. Information on additional treatment and the direct costs with low back pain management will also be collected at 3 months.\nA secondary analysis will be performed on predictors of response to McKenzie treatment and prediction of chronicity. This will involve the measurement of participants' expectation about the helpfulness of both treatments under investigation as well as information on the occurrence of the centralisation phenomenon. Expectation will be recorded prior to randomisation according to the procedures described by Kalauokalani et al[\n38\n].\nTreatments\nAll participants will receive GP care as advocated by the NHMRC guideline for the management of acute musculoskeletal pain[\n2\n]. Guideline-based GP care consists of providing information on a favourable prognosis of acute LBP and advising patients to stay active, together with the prescription of paracetamol. Patients randomised to the experimental group will be referred to physiotherapy to receive the McKenzie Method. A research assistant not involved in the assessment or treatment of subjects will be responsible for the randomisation process and will contact therapists and patients to arrange the first physiotherapy session. The McKenzie treatment will be delivered by credentialed physiotherapists who will follow the treatment principles described in McKenzie's text book[\n18\n]. All therapists will have completed the four basic courses taught by the McKenzie Institute International. To ensure the appropriate implementation of the McKenzie's classification algorithm, a training session with a member of McKenzie's educational program will be conducted prior to the commencement of the study. The treatment frequency will be at the discretion of the therapist with a maximum of 7 sessions over 3 weeks. We chose to restrict the McKenzie treatment to a maximum of 7 sessions based on the study of Werneke and colleagues[\n39\n], which concluded that further reductions in pain and function are not expected if favourable changes in pain location are not present until the seventh treatment visit. Treatment procedures from the McKenzie Method are summarised in the Appendix.\nParticipants randomised to the control group will continue their GP care as usual. All participants regardless of intervention group will be advised not to seek other treatments for their low back pain during the treatment period. Physiotherapists will be asked to withhold co-interventions during the course of the trial.\nSeveral mechanisms will be used to ensure that the trial protocol is applied consistently. Protocol manuals will be developed and all involved researchers (GPs, physiotherapists, assessor, and statistician) will be trained to ensure that screening, assessment, random allocation and treatment procedures are conducted according to the protocol. A random sample of treatment sessions will be audited to check that treatment is being administered according to the protocol.\nData analysis\nPower was calculated based on the primary outcome measures (pain intensity and global perceived effect). A sample size of 148 participants will provide 80% power to detect a difference of 1 unit (15%) on a 0–10 pain scale (SD = 2.0) between the experimental and control groups, assuming alpha of 0.05. This allows for loss to follow-up of 15%. This sample size also allows the detection of a difference of 1.2 units (12%) on a 0–10 global perceived effect scale (SD = 2.4).\nData will be analysed by a research member blinded to group status. The primary analysis will be by intention-to-treat. In order to estimate treatment effects, between-group mean differences (95%CI) will be calculated for all outcome measures. In the primary analysis these will be calculated using linear models that include baseline values of outcome variables as covariates to maximise precision.\nDiscussion\nWe have presented the rationale and design of an RCT evaluating the effects of the McKenzie Method in the treatment of acute non-specific LBP. The results of this trial will be presented as soon as they are available.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nLACM, CGM and RDH were responsible for the design of the study. HC was responsible for recruiting McKenzie therapists and she will also participate as a clinician in the trial. LACM and JMc will act as trial coordinators. All authors have read and approved the final manuscript.\nAppendix\nClinical picture and treatment principles according to the McKenzie Method\nThis table summarises the procedures involved in the McKenzie Method (Table \n1\n). For detailed description of all procedures and progressions, refer to McKenzie's text book. This is particularly important for Derangement syndrome since the treatment is extremely variable and complex and the full description of procedures would not be appropriate for the purposes of this paper.\nTable 1\nPostural Syndrome\nClinical picture\nIntermittent back pain under prolonged, static end-range postures (usually flexion); no loss of movement, absence of deformity.\nTreatment\nPatient education and postural correction.\nProcedures\nPatient adopts the posture that produces their symptoms. Physiotherapist instructs patient how to abolish symptoms by correcting the posture and provides explanation on the mechanism that produces pain of postural origin. Attainment of the corrected posture is taught through the use of the \"slouch-overcorrect\" exercise. Patients are taught how to maintain the corrected posture through the use of a Lumbar roll and actively when a lumbar roll can-not be used. Consequences of postural neglect are discussed.\nDysfunction Syndrome\nClinical picture\nIntermittent back pain at premature end-range; radiation only in the case of the dysfunction of an adherent nerve root; partial loss of movement.\nTreatment\nPatient education, postural correction, and stretching of contracted structures.\nProcedures\nPosture correction and repeated end-range movements towards the direction of dysfunction (e.g. extension exercises for extension dysfunction). Ten to 15 stretches are repeated at 2/3-hourly intervals, until the movement loss is restored. Treatment progression may include clinician overpressure and/or mobilisation.\nDerangement Syndrome\nClinical picture\nConstant or intermittent back pain and/or leg pain that moves proximally or distally during repeated movements; variable degree of loss of movement; deformity, paraesthesia, numbness and myotomal weakness may be present. A rapid change in the location of symptoms and in the range of movement is seen.\nTreatment\nReduction of derangement and maintenance of reduction, recovery of function and prophylaxis.\nProcedures\nReduction of derangement is achieved with sustained positions and/or repeated end-range movements. The treatment principle (extension, flexion or lateral) is selected according to the movements that abolish, decrease or centralise symptoms, as well as those that restore mobility and function (e.g. extension principle is adopted when extension centralises symptoms). Patient generated forces are used as the procedure of first choice. The exercises are repeated at home at 2-hourly intervals or as necessary for pain relief. Forces are progressed when the progress plateaus including over-pressures and therapist mobilisation. To ensure the maintenance of the reduction the patient is instructed to avoid aggravating postures or movements. Lumbar supports are used where necessary for the maintenance of lumbar lordosis.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
49
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nLow back pain risk factors in a large rural Australian Aboriginal community. An opportunity for managing co-morbidities?\n\n**Article Abstract:**\n\nBackground\nLow back pain (LBP) is the most prevalent musculo-skeletal condition in rural and remote Australian Aboriginal communities. Smoking, physical inactivity and obesity are also prevalent amongst Indigenous people contributing to lifestyle diseases and concurrently to the high burden of low back pain.\nObjectives\nThis paper aims to examine the association between LBP and modifiable risk factors in a large rural Indigenous community as a basis for informing a musculo-skeletal and related health promotion program.\nMethods\nA community Advisory Group (CAG) comprising Elders, Aboriginal Health Workers, academics, nurses, a general practitioner and chiropractors assisted in the development of measures to assess self-reported musculo-skeletal conditions including LBP risk factors. The Kempsey survey included a community-based survey administered by Aboriginal Health Workers followed by a clinical assessment conducted by chiropractors.\nResults\nAge and gender characteristics of this Indigenous sample (n = 189) were comparable to those reported in previous Australian Bureau of Statistics (ABS) studies of the broader Indigenous population. A history of traumatic events was highly prevalent in the community, as were occupational risk factors. Thirty-four percent of participants reported a previous history of LBP. Sporting injuries were associated with multiple musculo-skeletal conditions, including LBP. Those reporting high levels of pain were often overweight or obese and obesity was associated with self-reported low back strain. Common barriers to medical management of LBP included an attitude of being able to cope with pain, poor health, and the lack of affordable and appropriate health care services.\nThough many of the modifiable risk factors known to be associated with LBP were highly prevalent in this study, none of these were statistically associated with LBP.\nConclusion\nAddressing particular modifiable risk factors associated with LBP such as smoking, physical inactivity and obesity may also present a wider opportunity to prevent and manage the high burden of illness imposed by co-morbidities such as heart disease and type-2 diabetes.\n\n**Article Body:**\n\nBackground\nLow back pain (LBP) is the most prevalent musculo-skeletal condition in rural and remote communities [\n1\n-\n3\n]. Indigenous people in these communities are over-represented in low-skilled, manual jobs and the community-service sector [\n4\n]. As such they are more likely to be exposed to greater manual handling of loads, repetitive strains and risk of musculo-skeletal conditions. Formal reporting of such conditions in the Australian Indigenous community is infrequent [\n1\n]. These occupational factors and resulting LBP may be compounded by lifestyle risk factors including smoking, physical inactivity, and obesity [\n5\n].\nThere is an abundance of literature reporting on the risk factors associated with LBP in the general population [\n6\n]. Known modifiable risk factors for low back pain are lack of fitness, poor health, obesity, smoking, drug dependence, and occupational factors including heavy lifting, twisting, bending, stooping, awkward posture at work and prolonged sitting. Those that are non-modifiable are increasing age, number of children, a previous episode of LBP and major scoliosis [\n6\n]. Within the public health context it is important to prevent injuries and painful conditions by addressing modifiable risk factors [\n7\n-\n9\n].\nAustralian Indigenous communities experience sub-optimal mortality and morbidity rates. As such it has been argued that by adopting a holistic approach and addressing modifiable risk factors associated with LBP, such as smoking, physical inactivity and obesity, the clinical management of co-morbidities such as heart disease and diabetes may also be partially addressed [\n10\n]. Exercise, for example, has been reported as the single most important lifestyle factor for preventing and managing insulin resistance especially among those who are obese [\n11\n,\n12\n] It is also known that once their presenting musculoskeletal condition has been effectively managed, patients are more likely to comply with their practitioner's advice to promote other aspects of their health including weight loss and increased physical activity [\n10\n].\nModifiable risk factors for LBP mentioned above have been further classified as lifestyle (physical inactivity, poor muscle strength, obesity, smoking), and occupational (heavy lifting, twisting, bending, stooping, prolonged sitting, awkward posture at work, previous history of injury to the area) [\n6\n]. These are summarised in Table \n1\n. Where high levels of evidence (Level I evidence) such as meta-analyses or systematic reviews were not available, less rigorous studies (Level II, III and IV evidence) were reported to represent the current levels of knowledge.\nTable 1\nIndividual modifiable risk factors associated with low back pain\nFactors strongly associated with LBP (OR > 1.2-)\nFactors moderately associated with LBP (OR ≥ 1–1.2-)\nLack of fitness/Physical inactivity\nBalague, 1999 [44]*\nFeuerstein, 1999[45] ****\nSmoking\nBalague, 1999[44] *\nFeldmann, 1999[47] ***\nLevangie, 1999[48] ***\nPower, 2001[49] **\nLeboeuf-Yde, 1995[46] *\nObesity\nKoda, 1991[50] ****\nAlcouffe, 1999[51] ****\nWalker, 1999[52] **\nFransen, 2002[53] ****\nWebb, 2003[55] ****\nLeboeuf-Yde, 1999[46] *\nBalague, 1999[44] *\nLevangie, 1999[48] ****\nLecerf, 2003[54] ****\nMirtz, 2005[56] **\nPsychosocial stress\nBalague, 1995[57] ***\nHagg, 1997[58] ****\nJosephson, 1998[60] ****\nAdams, 1999[61] ***\nKrause, 1998[62] ***\nFeuerstein, 1999[45] ****\nBildt, 2000[63] ***\nThorbjornsson, 2000[64] ***\nVingard, 2000[65] ****\nYip, 2001[66] ****\nPower, 2001[67] **\nHarkness, 2003[68] ***\nVan den Heuvel, 2004[69] ***\nBalague, 1999[44] *\nHoogendorm, 2000[59] ***\nPhysical trauma\nHarkness, 2003[68] ***\nBalague, 1999[44] *\nFactors strongly associated with LBP (OR > 1.2-)\nFactors moderately associated with LBP (OR > 1–1.2-)\nAwkward posture (at work)\nKoda, 1991[50] ****\nAlcouffe, 1999[51] ****\nJin, 2000[53] **\nPicavet, 2000[70] ***\nFrequent bending and twisting\nAlcouffe, 1999[51] ****\nHoogendoorm, 2000[59] ***\nVingard, 2000[65] ****\nJin, 2000[71] **\nVan den Heuvel, 2004[69] ***\nPicavet, 2000[70] ***\nHeavy lifting, repetitive lifting\nSuadicani, 1994[72] ****\nMarras, 1995[73] ****\nMagnusson, 1996[74] ****\nSturmer, 1997[75] ****\nKrause, 1998[62] ***\nJosephson, 1998[60] ****\nAlcouffe, 1999[51] ****\nThorbjornsson, 2000[64] ***\nVingard, 2000[65] ****\nHartvigsen, 2001[76] ***\nNahit, 2001[77] ****\nFransen, 2002[53] ****\nHarkness, 2003[68] ***\nJarring, Gripping, vibration, repetitive actions\nBongers, 1993[78] *\nMagnusson, 1996[74] ****\nLevangie, 1999[48] ***\nPope, 1999[79] ***\nJin, 2000[71] *\nProlonged sitting & prolonged standing\nBurdorf, 1994[80] ****\nBongers, 1993[78] **\nThorbjornsson, 2000[64] ***\nHartvigsen, 2000[81] ***\nNB: Only first authors included.\nLegend: \n+ OR: Odds ratio\nLevel I evidence *, Level II evidence **, Level III evidence ***, Level IV evidence****\n• Level I – based on studies such as meta-analyses or systematic reviews of all relevant randomised controlled trials (RCTs);\n• Level II – based on well-designed RCTs;\n• Level III – based on well-designed prospective or case-control analytical studies; and\n• Level IV – based on opinions of respected authorities, clinical experience, descriptive studies and case reports or reports of expert committees.\nAs part of a study investigating the prevalence of LBP in this community [\n3\n], the risk factors known to be associated with LBP and other serious causes of morbidity and mortality were measured. This paper aims to describe the most commonly reported risk factors for LBP in a large rural Indigenous community; and examine their association with reported LBP as a basis for informing the development of a broad health promotion intervention in this community.\nMethods and materials\nDesign\nA cross-sectional self-report survey (Kempsey survey) was conducted to determine the extent of risk factors (Table \n1\n) and their association with LBP in the study community.\nEthics: consent and approval\nParticipating community members completed a consent form that explained the purpose of the survey. Ethics approval was obtained from the Durri Aboriginal Corporation Medical Service (ACMS) Board of Directors and the Human Research Ethics Committee of the University of Newcastle.\nCommunity consultation, collaboration and ownership of the program\nThe Durri Community of Kempsey, NSW, Australia, comprises one of Australia's largest rural Aboriginal communities. The Durri (ACMS) is at the forefront of providing culturally appropriate care, largely via its Aboriginal Health Workers (AHWs). Durri ACMS aims to:\n'make primary health care and education accessible to all members of the community in a culturally appropriate and spiritually sensitive manner, endeavouring to improve not only the health status but also the well-being of the Durri Aboriginal community' [\n13\n].\nDiscussions with a cross section of community members led to the formation of a Community Advisory Group (CAG) (which included representatives from the Durri ACMS, Booroongen Djugun Aboriginal Health Worker College, Hands On Health Australia and the University of Newcastle). The CAG aimed to advise on the development and implementation of the musculo-skeletal prevalence study [\n14\n]. Aboriginal Health Workers were chosen as the study agents because they are recognised as essential in providing culturally appropriate and effective health-care for their communities [\n15\n-\n22\n].\nCommunity consultation occurred throughout the study. This process involved regular discussions with key-informants from the community including AHWs, elders and health professionals. The community was informed of developments via information sheets and the publication of a summary report during the process and at the completion of the study.\nSample\nOur goal was to select a representative cross-sectional sample of the local Aboriginal community of sufficient size to generalise our major findings to the whole local community (population 550). A random sampling procedure stratifying for age and sex was used to derive a representative sample of the local community. The sample size was generated using Epi-Info 6 [\n23\n]. With a population size of 550, the expected frequency of the main variable of interest (low back pain) was estimated at 50%. The value chosen as the farthest acceptable from the real population was 44%. Using these values and a 95% confidence interval, the ideal random sample size calculated was 180. However, we expected that logistically this was unlikely to be achieved, as many of the sample selected were likely to be uncontactable given the transient nature of community residents [\n24\n]. Accordingly, where randomly selected community members were unable to participate, they were replaced using a convenience sampling approach to achieve the required sample size. Although this strategy was not ideal, all attempts were made to attain a representative sample. Participants within the community were selected from persons aged 15-years or older who had been previously identified as Aboriginal (according to the definition of Aboriginal adopted by the Department of Aboriginal Affairs Constitutional Section) [\n25\n]. These participants were recruited by distributing letters inviting them to contact the assisting AHWs at the ACMS. If no response was received within a week, an attempt to contact the person via telephone was made by the assisting AHW.\nProcedure\nThe Kempsey survey included a screening survey administered by Aboriginal Health Workers immediately followed by a clinical conducted by chiropractors blinded to the findings of the screening survey.\nThose who consented to participate were asked to attend the Durri ACMS. If participants found transport to the ACMS difficult, either the research team (including the researcher, the AHW and volunteer chiropractors/chiropractic students) would travel to the participants' homes, or the assisting AHW would arrange for the Durri ACMS bus to provide transportation at no charge.\nScreening survey\nParticipants completed a screening survey previously found to be culturally acceptable and sensitive in measuring musculo-skeletal conditions and associated risk factors in this community. The survey achieved satisfactory measurement agreement (Kappa scores) when compared to a clinical assessment performed by chiropractors (a proxy \"Gold Standard\") [\n22\n]. Although some authors argue that a 'Gold standard' does not exist in many areas of musculo-skeletal practice [\n26\n], standard clinical assessments performed by musculo-skeletal health professionals provide the best available tools for measuring painful and limited ranges of motion and a provisional diagnosis [\n27\n]. The purpose of the screening survey was to identify those who had experienced a musculo-skeletal condition including ache, pain or discomfort. The questionnaire also assessed self-reported limitations to Activities of Daily Living (ADL) imposed by pain.\nParticipants screened by the AHW-administered survey subsequently underwent a clinical examination conducted by four chiropractors previously trained and assessed in standard, clinical assessment procedures according to a procedural manual which outlined the cultural considerations and logistical processes required by researchers. The content of the procedural manual was revised in a two-hour workshop for participating researchers to clarify and standardise study requirements. The exam was based on accepted clinical parameters for conducting musculoskeletal conditions and included the domains of assessment used by teaching institutions [\n28\n]. Thus attempts were made to fulfil content and face validity.\nAssessment\nParticipants attended a clinical assessment immediately following the screening survey to confirm the presence of musculo-skeletal conditions [\n22\n]. Chiropractors and 5th year chiropractic students performed a follow-up clinical assessment (based on clinical assessment parameters used in 1999 at the School of Chiropractic, RMIT University, Victoria, Australia) [\n28\n] to validate the findings reported in the screening questionnaire.\nA positive pain finding in the clinical assessment was derived by practitioner-based examination, including the patient's history of involved site(s) followed by standard orthopaedic and range of motion tests to localise sites of pain and restricted movement. A negative pain finding was indicated by the absence of reported pain and/or restricted orthopaedic and range of motion findings as examined by the practitioner. Trivial LBP was differentiated from important LBP using a Likert scale. High levels of pain were interpreted as those ranging between 6–10 on a Likert scale of 0–10. Only those reporting \"High\" levels of pain were analysed in this study. Further questions related to any musculo-skeletal condition(s) experienced in the last seven days. In particular, probable causes of symptoms, past history, initial episode(s) of symptoms, duration of symptom(s), 'average' severity of symptoms and any associated limitation of daily activities. Also examined were, social routine and work activities, the type of treatment received and any barriers to receiving treatment were sought.\nIn the history component of the clinical assessment, chiropractors once again questioned participants about the presence of musculo-skeletal risk factors (according to the criteria reported in Table \n1\n). Risk factor data were derived in the history component of the clinical assessment by asking questions from a list of modifiable occupational and lifestyle factors. Results for LBP as measured in the clinical assessment were used in the analysis. Clinical findings requiring follow-up treatment, management or referral was also identified.\nHealth workers using a laptop computer entered data on-site into a specifically designed, Microsoft Access database.\nScreening and assessment agreement\nThe questionnaire results were compared to the data from the clinical examination and published in a previous study (Table \n2\n). Eighty-three percent of all participants reporting LBP in the screening survey also tested positive for LBP via the clinical assessment. Sensitivity of the screening survey for LBP was 0.83, specificity 0.63 and Kappa 0.46. Thus the screening survey achieved an adequate level of agreement with the clinical assessment [\n29\n].\nTable 2\nSensitivity, specificity and Kappa for LBP screening survey compared to clinical assessment (n = 189)\nSurvey results\nClinical Assessment\nNegative\nPositive\nTotal\nSensitivity\nSpecificity\nKappa coefficient\nNegative\n43\n21\n64\n0.83\n0.63\n0.46\nPositive\n25\n100\n125\nTotal\n68\n121\n189\nMeasures\nThe main variables of interest from the survey and clinical assessment were:\n• Demographic and other sample characteristics-age, sex, number of children, occupation, weight, and Body Mass Index (BMI).\n• Prevalence of LBP (within the last seven days, according to self report).\n• Pain levels were recorded using a Likert scale where a score of 0 corresponded to no pain and 10 to severe pain.\n• Duration of LBP was categorised as less than/equal to or more than seven weeks.\n• Disability levels were recorded using a Likert scale where a score of 0 corresponded to no disability and 10 to severe disability. Disability was defined as \"how much the condition (ache, pain or discomfort) had affected the participants ability to carry out daily activities (e.g., housework, washing, dressing, lifting, walking, driving, climbing stairs, getting in and out of bed or a chair, sleeping, working, social activities and sport)\".\n• Self-reported modifiable risk factors as described in Table \n1\n (according to a standardised clinical history).\n• Other musculo-skeletal conditions.\nAnalyses\nFrequencies and confidence intervals were reported for characteristics of the sample, prevalence of LBP and reported risk factors for low back pain. Chi-square analyses were performed to test for factors associated with low back pain. Given the number of variables, only significant associations were reported.\nResults\nSample\nThe study was conducted between January 2001 and July 2002. The sample comprised 189 Indigenous people: 80 were selected randomly and the remainder were convenience sampled as described above.\nSample characteristics\nAge and sex\nThe mean age of participants was 44 years ( ± 14.8) and the median age 43 years. The sample comprised 87 males (46%) and 102 females (53%) ranging in age from 15 to 80 years. There were no significant differences in the distribution of males and females in the various age categories (p = 0.35). Gender was comparable with previous ABS census data for Indigenous people in Australia [\n26\n]. Age categories were also similar in breakdown to those described in census data for the entire Indigenous community (Table \n3\n) [\n30\n].\nTable 3\nAge and sex of study participants\nAge category (years)\nMale\nFemale\nTotal\n% Male\n% Female\n% Total\n15 – 25\n20\n20\n40\n23.0\n19.6\n21.2\n26 – 35\n14\n16\n30\n16.1\n15.7\n15.9\n36 – 45\n25\n29\n54\n28.7\n28.4\n28.6\n46 – 55\n13\n10\n23\n14.9\n9.8\n12.2\n56 +\n12\n24\n36\n13.8\n23.5\n19.0\nUnknown\n3\n3\n6\n3.4\n2.9\n3.2\nTotal\n87\n102\n189\n100\n100\n100\nDespite a high consent rate (85% of the randomly recruited sample), the response rate was low (40%) because many members of this highly mobile community were unable to be contacted.\nNumber of children\nApproximately one third (31%) of participants had between two or three children. Thirty percent of participants had no dependent children and 17% had 4–5 children. Of note, 15% had six or more children. These findings are comparable to those of other Indigenous studies [\n5\n]. An Australian Bureau of Statistics (ABS) study reported that Indigenous families tend to be larger than Australian families overall. According to the 1996 Census, approximately 13% of Indigenous families had four or more children compared with less than 5% of other Australian families [\n5\n].\nOccupation\nOccupational demographics of the participants in the study are summarised in Table \n4\n. Approximately one third of the community surveyed were students or unemployed. A significant number of people surveyed were associate professionals, retired workers, involved in home duties or labourers. These data were generally comparable with those reported for Indigenous people by the ABS (2000). However, for males in the Kempsey survey, there were significantly less professionals, managers, tradespersons and transport workers, and more intermediate clerical, sales and service persons, compared to the ABS population. For females there were significantly more professional, and associates professionals (such as Aboriginal Health Workers), and less tradespersons or transport workers as well as many less intermediate clerical, sales and service persons, compared to the ABS population [\n5\n].\nTable 4\nOccupation of study participants according to sex\nOccupation\nMale\nFemale\nTotal\n% Male\n% Female\n% Total\nManagers and Administrators\n5\n3\n8\n5.7\n2.9\n4.2\nProfessionals\n7\n9\n16\n8.0\n8.8\n8.5\nAssociate professionals*\n5\n16\n21\n5.7\n15.7\n11.1\nTradespersons and related workers\n1\n2\n3\n1.1\n2.0\n1.6\nAdvanced clerical and service workers\n3\n2\n5\n3.4\n2.0\n2.6\nIntermediate clerical, Sales and service workers\n3\n2\n5\n3.4\n2.0\n2.6\nElementary Clerical, Sales and Service workers\n2\n6\n8\n2.3\n5.9\n4.2\nLabourers and Related workers\n13\n3\n16\n14.9\n2.9\n8.5\nUnemployed/Student\n38\n28\n66\n43.7\n27.5\n34.9\nHome duties\n1\n16\n17\n1.1\n15.7\n9.0\nRetired\n4\n15\n19\n4.6\n14.7\n10.1\nUnknown\n5\n0\n5\n0.0\n2.6\nTotal\n87\n102\n189\n100\n100\n100\n* Associate Professionals\nBMI\nTable \n5\n shows that 32% of participants were overweight and 39% were obese. Using Body Mass Index (BMI) estimates, 26% (95% CI: 20%–32%) of participants were overweight (BMI = 25.0–29.9) and 45% (95% CI: 38%–52%) were obese (BMI = 30.00). The high prevalence of obesity in this study agrees with national figures demonstrating a greater prevalence of obesity among Indigenous people than non-Indigenous Australians [\n5\n].\nTable 5\nBody Mass Index (BMI) of participants, according to age and sex (n = 189)\nBMI classification\nAge (yrs)\nSex\nNormal\n(%)\nOverweight\n(%)\nObese\n(%)\nUnknown\n(%)\nTotal\n(%)\n15 – 25\nMale\n10\n23%\n7\n14%\n2\n.02%\n0\n0%\n19\n10%\nFemale\n7\n16%\n5\n10%\n9\n12%\n0\n0%\n21\n12%\nTotal\n17\n39.5%\n12\n24%\n11\n14%\n0\n0%\n40\n22%\n26 – 45\nMale\n5\n12%\n13\n26%\n18\n23%\n4\n33%\n40\n22%\nFemale\n14\n33%\n9\n18%\n18\n23%\n5\n42%\n46%\n25%\nTotal\n19\n44%\n22\n44%\n36\n47%\n9\n75%\n86\n47%\n> 45\nMale\n4\n9%\n6\n12%\n13\n17%\n1\n8%\n24\n13%\nFemale\n3\n7%\n10\n20%\n17\n22%\n2\n17%\n32\n18%\nTotal\n7\n16%\n16\n32%\n30\n39%\n3\n25%\n56\n31%\nTOTAL\n43\n100%\n50\n100%\n77\n100%\n12\n100%\n182\n100%\nNote: \nBMI = Weight (kg) divided by square of height (m)\nSelf-Report of LBP within the last seven days\nThe prevalence of all LBP (i.e. including all levels of pain) within the last seven days was 72% (95% CI: 63%–80%) and all LBP lasting seven weeks or longer was 34 % (95% CI: 27%–40%).\nPrevious history of LBP\nPrevious history of LBP was present in 34% (95% CI: 27%–40%) of respondents. A previous history of LBP is known to predispose individuals to recurrent episodes of back pain [\n31\n].\nOther modifiable risk factors for LBP\nSmoking\nSmoking was highly prevalent 46% (95% CI: 38%–53%) in the community, with equal numbers of males and females smoking. Thirty eight per cent (95% CI: 31%–45%) of people smoked between 10–20 cigarettes daily and 8% (95% CI: .04%–11%) smoked more than 20 cigarettes per day. This is consistent with the 2001 National Health Survey (NHS), which found that 51% of Indigenous people aged 18 years or older were current smokers, compared with 24% of non-Indigenous people [\n32\n].\nPhysical inactivity\nSixteen percent (95%CI: 10%–21%) of participants spent no time actively exercising and 35.9% (95% CI: 26%–45%) exercised less than 30 minutes per week. There are no other detailed data available on the levels of physical activity among Indigenous people. However, the 2001 NHS reported that 43% of Indigenous people aged 18 years or older living in non-remote areas were sedentary, compared with 30% of non-Indigenous people [\n32\n].\nPsychosocial stress\nFor those reporting LBP 72% (CI: 65%–78%), the most commonly reported traumatic events included sporting injuries 26.5% (95% CI: 20%–38%), motor vehicle accidents 18% (95% CI: 12%–23%) and work-related trauma 17.5% (95% CI: 12%–22%). There was, however, no association between LBP and physical trauma.\nPhysical trauma\nFor those reporting LBP (66.1% CI: 54%–68%), the most commonly reported traumatic events included sporting injuries 26.5% (95% CI: 20%–38%), motor vehicle accidents 18% (95% CI: 12%–23%) and work-related trauma 17.5% (95% CI: 12%–22%). There was, however, no association between LBP and physical trauma.\nOccupational risk factors\nFigure \n1\n, Modifiable occupational risk factors for musculo-skeletal conditions details reported occupational risk factors for LBP. Common risk factors were adopting awkward postures at work 32% (95% CI: 25%–39%), frequent bending and twisting 29% (95%: CI: 22%–35%) and heavy lifting 26% (95% CI: 20% – 32%). However, there was no association between LBP and occupational risk factors.\nFigure 1\nFigure 1\nFactors associated with reported LBP\nEven though a trend was evident, no statistical association between LBP and the lifestyle factors detailed above. However, more participants reporting high levels of LBP were overweight or obese and obesity was statistically associated with self-reported strain causing reported LBP (χ\n2 \n= 9.02, df = 2 10, p = 0.01). While sporting injuries were not statistically associated with report of LBP in particular, participants reporting sporting injuries experienced between two and four musculo-skeletal conditions (χ\n2 \n= 7.90, df = 2, p = 0.02).\nDiscussion\nThe 72% seven day prevalence of LBP found in the Kempsey survey is greater than similar prevalence levels reported in other rural Indigenous Communities [\n1\n,\n2\n,\n33\n,\n34\n]. In their study, Honeyman and Jacobs [\n2\n] reported a 1-day LBP prevalence for the majority of community members, 68% (95% CI: 61%–74%). The majority of participants in the Kempsey survey also experienced their presenting LBP for seven weeks or more. Thus according to accepted definitions of chronicity [\n35\n], the majority of Indigenous people in this Community were suffering from chronic pain and were therefore, likely to be at greater risk of enduring prolonged disability [\n31\n]. Thirty-four percent of participants also reported a previous history of LBP, which was likely to predispose them to recurrent, future episodes [\n31\n]. Furthermore, trauma particularly that incurred in sporting injuries was associated with multiple musculo-skeletal conditions. Past studies have reported that Indigenous people are more likely to experience transport accidents, intentional self-harm and assault than other Australians with rates approximating three times those of the rest of the Australian population [\n32\n].\nThe findings in this study of higher levels of smoking, physical inactivity and obesity are consistent with those reported by other studies of Indigenous Australians [\n9\n]. Though many of the modifiable risk factors known to be associated with LBP were highly prevalent in this study, none of these were statistically associated with LBP. One explanation for this finding is that the size of the sample, though sufficiently large to demonstrate comparability with ABS findings for demographic categories, may not have been sufficiently large to achieve the statistical power to detect any association between LBP and associated study factors.\nObesity and physical inactivity are the two most important modifiable factors contributing to the development of type 2 diabetes mellitus. These factors were highly prevalent in the community with 26% of subjects overweight, 45% obese and 16% spending no time actively exercising plus a further 35.9% exercising less than 30 minutes per day. Exercising was assessed by self-report according to total time spent exercising ranging from 'No time' to 'More than 10 hours per week'. Obesity in this study was associated with self-reported low back strain. The prevalence of obesity in this community is of concern, first because obesity is an independent predictor of back pain [\n36\n], but more importantly as obesity has a global health impact.\nHealth providers including chiropractors and osteopaths commonly counsel LBP sufferers to lose weight to unload their spines. Weight loss also offers other musculo-skeletal benefits. Females with a BMI of over 25 kg/m2, can, by losing 5 kg (2 BMI units) reduce future onset of knee osteoarthritis by 50% and males by 25% [\n37\n]. Obesity has also been associated with a higher prevalence of work limitations, hypertension, dyslipidemia, type 2 diabetes and the metabolic syndrome in adults of working age [\n38\n]. Furthermore, Australia-wide some 50% of cases of type 2 diabetes are asymptomatic, undiagnosed and persons subclinically undergo progressive macro and micro-vascular changes [\n39\n]. The current findings suggest that screening this population group for evidence of glucose intolerance when reviewing musculo-skeletal conditions such as LBP may be valuable.\nOf those reporting LBP, 72% of participants (CI: 65%–78%) were frequently exposed to \"stressful situations\" in their occupation. However, psychosocial stress outside of the work place was not measured given the cultural sensitivity of this factor according to the CAG. Psychosocial stress in general is a strong predictor of LBP [\n40\n,\n41\n]. If conducted in a culturally appropriate manner, future studies assessing LBP in Indigenous Communities should ideally attempt to also measure psychosocial stress as a potential contributing study factor.\nAnother concurrent health hazard is the high prevalence of cigarette smoking. In addition to the well documented risks of smoking it has been found that compared with matched groups of non-smokers, chronic cigarette smokers are more likely to be insulin resistant, hyperinsulinemic, and dyslipidemic [\n39\n].\nExercise is the most common method of treating LBP in Australia [\n42\n]. In addition it may be the single most important lifestyle factor for both preventing and reversing insulin resistance, particularly among obese individuals [\n12\n,\n13\n]. This suggests a good case for concentrating on general exercise health promotion for Indigenous communities.\nLifestyle interventions incorporated into a culturally sensitive health promotion program could potentially benefit the health and modify the morbidity and mortality of this population group. These results suggest an opportunity to review and address risk factors associated with LBP along with more serious diseases affecting Indigenous people. Addressing modifiable risk factors associated with LBP, such as smoking, physical inactivity, and obesity could significantly contribute to the management of co-morbidities including diabetes and heart disease which so commonly affect Indigenous Australians.\nAn understanding of the modifiable risk factors for LBP identified in this paper also formed the basis for a culturally acceptable musculo-skeletal intervention designed to address the high prevalence of LBP. This involved using a pilot training program for Aboriginal Health Workers (AHWs). The intervention was designed to promote the musculo-skeletal and general health of Indigenous people living in this rural community [\n12\n]. Culturally sensitive approaches to managing musculoskeletal conditions have been successfully implemented in other Indigenous Communities [\n43\n].\nThe Community Oriented Program for the Control of the Rheumatic Diseases (COPCORD) represents the largest, ongoing collaborative attempt to measure the prevalence of musculo-skeletal conditions and risk factors in rural populations throughout the world [\n43\n]. COPCORD has also developed implemented and evaluated culturally sensitive approaches for managing these conditions and their associated risk factors through community-based initiatives with applicability in other Indigenous Communities.\nWe propose that any future musculo-skeletal study or intervention in an Indigenous community be accompanied by a review of the modifiable risk factors associated with LBP and counselling about those factors. This may have a beneficial effect on the overall well being of indigenous communities. Further research should test such a program for efficacy and effectiveness.\nConclusion\nThe disturbingly high prevalence of LBP experienced in this community necessitates a serious response. Managing LBP through health services and addressing the modifiable risk factors through culturally sensitive, health promotion programs will be an important step in addressing the high burden of illness imposed by LBP and other more serious conditions suffered in this community.\nCompeting interests\nDr. Bruce Walker is Editor-in-Chief of \nChiropractic & Osteopathy\n.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
50
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe influence of walking performed immediately before meals with moderate fat content on postprandial lipemia\n\n**Article Abstract:**\n\nBackground\nPostprandial lipemia is an independent risk factor for coronary heart disease. Single bouts of moderate exercise may lower this risk, but the minimum duration of moderate intensity exercise that still lowers postprandial lipemia is not known. We, therefore, performed a dose-response study with a normal, daily life setting, to identify the minimum duration of moderate intensity walking that lowers postprandial lipemia in sedentary, healthy young men.\nMethods\nSixteen men performed three activity trials (30, 60, or 90 min of treadmill walking at 50% of their individual VO\n2\nmax) and a control trial with no physical activity in a repeated measures crossover design. The subjects walked immediately before ingestion of the first of two mixed meals, which were served 3 h apart. The meals had a moderate fat content (0.5 g per kg body mass and 33% of total energy per meal) and a macronutrient composition corresponding to current recommendations. Each meal provided one third of the subject's estimated daily energy requirement. Venous blood samples were taken in the fasted state, and then hourly for 6 h after the first meal to assess the postprandial phase. Postprandial lipemia (the incremental area under the curve (dAUC) of triacylglycerol) was compared with a mixed model analysis and Tukey's adjustment.\nResults\nPostprandial lipemia (dAUC of triacylglycerol) was, compared to the control trial, +2% (P = 1.00), -14% (P = 0.24), and -15% (P = 0.23) in the 30, 60, and 90 min walking trials, respectively.\nConclusion\nModerate intensity walking of 60 and 90 min duration slightly, but insignificantly, reduced postprandial lipemia after two mixed meals with moderate fat content in sedentary, healthy young men, compared to inactivity. Therefore, it should be reconsidered if the acute exercise-induced reduction in postprandial lipemia usually observed in studies using high fat meals is of importance in a real, daily life setting.\n\n**Article Body:**\n\nBackground\nPostprandial lipemia describes the blood triacylglycerol (TAG) content after meal intake, and is an independent risk factor for atherosclerosis and coronary heart disease [\n1\n-\n4\n]. The latter is the leading cause of death in industrialized countries and is rapidly becoming a primary cause of death worldwide [\n5\n]. Interventions that have the potential to attenuate the postprandial lipemic response are, therefore, valuable tools for lowering the risk of cardiovascular diseases.\nEndurance exercise is known to positively influence postprandial lipemia [\n6\n], and endurance athletes show a lower postprandial lipemic response than sedentary people [\n7\n]. However, it seems to be the acute response to single exercise bouts rather than the improved endurance capacity per se that has the favourable effect [\n8\n], because postprandial lipemia increases rapidly with detraining [\n9\n,\n10\n]. Furthermore, the intensity at which endurance exercise is usually performed is rather high, which makes endurance exercise not a very attractive option for reducing the cardiovascular risk for sedentary people.\nA single exercise bout with moderate intensity only was also shown to improve postprandial lipemia when performed immediately before meal ingestion, but usually the exercise duration used was one hour or longer [\n11\n-\n13\n]. Since about 60% of the world's population already does not meet the minimum recommendation of daily physical exercise [\n14\n], which is 30 min of moderate intensity activity on most, preferably all, days of the week [\n15\n], it is unlikely that sedentary people would engage in exercise of long duration. Therefore, it seems important to determine the influence of moderate exercise with shorter duration on postprandial lipemia, but few studies have investigated this exercise mode. We are aware of two studies in which the exercise bouts were performed just before ingestion of a meal and corresponded to an intensity and duration required for health-maintaining physical activity, e.g. moderate intensity exercise with a duration of less than one hour [\n16\n,\n17\n]. Whereas Murphy et al. [\n16\n] found a significant influence of 30 min of brisk walking (60% of maximal oxygen uptake, VO\n2\nmax) on postprandial lipemia in overweight or obese and older subjects, Petridou et al. [\n17\n] found a non-significantly lowered TAG response of 17% after 45 min of cycling at 62% of predicted maximal heart rate in sedentary but otherwise healthy young men.\nIn postprandial lipemia studies, a high fat meal (e.g. 1 g fat per kg body mass, BM) is usually provided to the subjects [\n18\n] to induce a strong increase of postprandial lipemia [\n19\n]. However, such high fat meals do not represent normal meals either in absolute or relative fat content, and do not correspond to the current recommendations about macronutrient composition [\n20\n]. As even 15–30 g of fat already elevate TAG significantly [\n18\n], high fat meals are not a precondition to study postprandial lipemia. In order to obtain information on postprandial lipemia that is relevant to real life, it seems more reasonable to choose normal mixed meals with a moderate fat content, as has been done recently in two studies investigating the influence of exercise on postprandial lipemia [\n17\n,\n21\n]. Additionally, free-living individuals consume sequential meals during the course of the day, but we know of only one study [\n16\n] where more than one meal was provided to the subjects. Since second meal effects of postprandial lipemic responses to mixed meals have been reported [\n22\n], the results of the studies with just one test meal do not accurately reflect real life [\n23\n].\nThe aim of the present study was, therefore, to determine the minimum duration of walking with a moderate intensity that would significantly lower postprandial lipemia in sedentary, healthy young men in a normal, daily life setting. The subjects performed three activity trials (30, 60, or 90 min of treadmill walking at 50% of their individual VO\n2\nmax), and a control trial with no physical activity. Immediately after exercising they ingested the first of two mixed meals, which were served 3 h apart. The meals had a moderate fat content (0.5 g per kg BM and 33% of total energy per meal), a macronutrient composition corresponding to current recommendations [\n20\n], and each one provided one third of the subject's estimated daily energy requirement.\nResults\nExercise sessions\nMean relative oxygen uptake with the 30, 60, and 90 min walking sessions was 49.8 (0.2)%, 50.1 (0.1)%, and 50.0 (0.2)% of VO\n2\nmax, respectively. Data comparing mean metabolic responses between the three exercise sessions are presented in Table \n1\n.\nTable 1\nMetabolic responses during 30, 60, and 90 min treadmill walking in the activity trials\n30 min\n60 min\n90 min\nMean\nSEM\nMean\nSEM\nMean\nSEM\nEnergy expenditure [kJ per exercise session]\n879\na\n46\n1799\nb\n83\n2630\nc\n126\nEnergy expenditure [kJ·min\n-1\n]\n29\n2\n30\n1\n29\n1\nRespiratory exchange ratio\n0.95\na\n0.01\n0.92\nb\n0.01\n0.91\nb\n0.01\nFat oxidation [g per exercise session]\n4\na\n1\n12\nb\n2\n21\nc\n2\nFat oxidation [g·min\n-1\n]\n0.12\na\n0.03\n0.20\nab\n0.03\n0.23\nb\n0.02\nCarbohydrate oxidation [g per exercise session]\n44\na\n3\n80\nb\n6\n110\nc\n6\nCarbohydrate oxidation [g·min\n-1\n]\n1.46\na\n0.11\n1.33\nab\n0.10\n1.22\nb\n0.06\nHeart rate [min\n-1\n]\n122\n4\n125\n4\n127\n3\nHeart rate [% HRmax]\n64\n2\n65\n2\n66\n1\nRating of perceived exertion*\n11.0\na\n0.4\n11.5\nab\n0.4\n11.8\nb\n0.4\nSEM, standard error of the mean; HRmax, maximum heart rate.\n*Borg rating of relative perceived exertion, 6–20 scale.\nSignificant difference between means not sharing a common letter (P < 0.05; n = 15 for respiratory data in 30 and 60 min walking trials; n = 16 for other data).\nBlood chemistry\nThe postprandial TAG profile did not differ statistically between the trials (P = 0.06; Fig. \n1\n). Highest values were observed 5 h after breakfast and were 2.63 (0.28) mmol· L\n-1\n, 2.65 (0.26) mmol· L\n-1\n, 2.47 (0.28) mmol· L\n-1\n, and 2.39 (0.26) mmol· L\n-1 \nwith the control, 30 min, 60 min, and 90 min walking trials, respectively, whereas mean postprandial TAG values (area under the curve (AUC) divided by six) were 1.78 (0.17) mmol· L\n-1\n, 1.82 (0.17) mmol· L\n-1\n, 1.71 (0.18) mmol· L\n-1\n, and 1.71 (0.16) mmol· L\n-1\n, respectively. Compared to the control trial the increase in AUC (dAUC) of TAG was +2% (P = 1.00), -14% (P = 0.24), and -15% (P = 0.23) for the 30, 60, and 90 min walking trials, respectively (Fig. \n2\n). To detect a statistically significant difference in dAUC of TAG between the inactivity and the 60 or 90 min walking trials a sample size of 279 and 182 subjects, respectively, would have been required (Power = 0.80).\nFigure 1\nTriacylglycerol concentration for the inactivity and the activity (30, 60, or 90 min treadmill walking) trials. For better readability the symbols of the different trials at the same time points are slightly staggered. Values are means (standard error of the mean). Overall mixed model analysis with repeated measurements, effect of trial: P = 0.06.\nFigure 2\nIncremental area under the curve (dAUC) for postprandial triacylglycerol (mean, standard error of the mean) for the inactivity and the activity (30, 60, or 90 min treadmill walking) trials. Overall mixed model analysis, effect of trial: P = 0.07.\nInsulin values were highest one hour after breakfast in all trials. A second peak was observed one hour after lunch (Fig. \n3\n). Compared to the control trial postprandial insulinemia (dAUC) was lowered by 9% (P = 0.79), 16% (P = 0.54), and 19% (P = 0.20) for the 30, 60, and 90 min walking trials, respectively (Fig. \n4\n). There was a significantly lower insulin to glucagon ratio one hour after breakfast in the 90 min exercise trial compared to the control trial (P = 0.01). No difference between the postprandial glucose values of all trials either in the profile over time (P = 0.50) or dAUC (P = 0.95) was observed. Profiles of glucose, glucagon, fatty acids (FA), and glycerol are presented in Figure \n5A–D\n.\nFigure 3\nInsulin concentration for the inactivity and the activity (30, 60, or 90 min treadmill walking) trials. For better readability the symbols of the different trials at the same time points are slightly staggered. Values are means (standard error of the mean). Overall mixed analysis with repeated measurements, effect of trial: P = 0.16.\nFigure 4\nIncremental area under the curve (dAUC) for postprandial insulin (mean, standard error of the mean) for the inactivity and the activity (30, 60, or 90 min treadmill walking) trials. Overall mixed model analysis, effect of trial: P = 0.25.\nFigure 5\nConcentrations of glucose (A), glucagon (B), fatty acids (C), and glycerol (D) for the inactivity and the activity (30, 60, or 90 min treadmill walking) trials. For better readability the symbols of the different trials at the same time points are slightly staggered. Values are means (standard error of the mean). Significant differences between means not sharing a common letter (P < 0.05).\nDiscussion\nIn a dose-response study we examined the influence of 30, 60, and 90 min of moderate intensity walking just before meal ingestion to determine the minimum duration necessary to lower postprandial lipemia in sedentary, healthy young men in a normal, daily life setting. Our findings indicate that 60 or 90, but not 30 min of brisk walking induced a modest but statistically insignificant reduction of postprandial lipemia compared to an inactive control.\nThis is in contrast to most of the available literature, because in most studies a reduction of postprandial lipemia after a moderate intensity exercise bout was found [\n11\n-\n13\n,\n16\n]. The main difference between those studies and the current study was the type or number of test meals. Our test meals had only a moderate fat content (0.5 g per kg BM and 33% of total energy per meal) and were composed of ordinary, commercially available food. Additionally, to simulate the course of a normal day we served two meals (breakfast and lunch), each meal providing one third of the subject's estimated daily energy requirement. In three studies with healthy subjects who exercised immediately before ingestion of a meal, a significant reduction in postprandial lipemia was observed after 60 min walking at 60% of VO\n2\nmax [\n13\n], 90 min at 50% of VO\n2\nmax [\n11\n], and 90 min at 65% of VO\n2\nmax [\n12\n] (postprandial lipemia (dAUC) was lowered by 38%, 49%, and 39%, compared to inactivity, respectively). However, in these studies high fat meals were served (95–101 g, 81–92% of total energy). Since in our study the 60 and 90 min walking sessions did not significantly lower postprandial lipemia, we assume that our test meals with the moderate fat content only and the macronutrient composition according to the current recommendations [\n20\n] may have largely contributed to the non-significant response observed.\nBesides the amount of fat, the other macronutrients can also influence postprandial lipemia. Carbohydrates in a mixed meal provoke an insulin response, which plays an important role in the regulation of plasma TAG concentration [\n8\n], e.g. through down-regulating lipoprotein lipase (LPL) activity in skeletal muscle [\n24\n]. This insulin effect is in opposition to the acute effect of exercise (90 min of cycling at 85% of the lactate threshold) that increased muscle LPL activity in the immediate 3 to 4 h after exercise, relative to rest in men [\n25\n]. Consequently, it could also be assumed that in our study the suppressing effect of insulin on muscle LPL activity after the meal intake exceeded the stimulating effect of exercise. However, since according to Gill [\n8\n] a reduction in postprandial lipemia after moderate intensity exercise would be caused rather through decreased very-low-density lipoprotein (VLDL) production than increased TAG clearance, this is not very likely to have been the case. The moderate exercise sessions elevated FA and glycerol levels significantly, but only for a short time. Nevertheless, it seems relevant and worth mentioning, since it has not always been done in previous studies, that in lipemia studies including exercise, the TAG measurements are corrected for glycerol in order not to overestimate TAG values immediately and up to one hour after exercise.\nIn one study where three mixed meals with a fat content (47% of total energy) above the recommendation [\n20\n] were served, 30 min of brisk walking (60% of VO\n2\nmax) performed before breakfast lowered postprandial lipemia significantly [\n16\n]. However, the subjects were overweight or obese and older (34–66 years of age) than in our study (20–30 years). Postprandial lipemia seems to behave differently in healthy, untrained adults of different age groups [\n26\n]. Therefore, the influence of an exercise bout on postprandial lipemia might also be influenced by the age of the subjects, and explain the differing findings of that study and ours.\nMost similar to our study in terms of design as well as investigated population group was the study conducted by Petridou et al. [\n17\n]. In that study, subjects cycled for 45 min at moderate intensity (62% of predicted maximal heart rate) just before ingestion of a meal with a fat content of 0.65 g per kg BM and 35% of total energy. They reported similar results to those in our study, finding also only a modest (-17%) and statistically insignificant effect of the exercise bout on TAG dAUC.\nAlthough postprandial lipemia was not lowered significantly with the exercise session used in this study setting, health benefits due to the exercise bout are nevertheless expected via improved insulin sensitivity, increased energy expenditure, and fat oxidation. Gill et al. [\n27\n] stated that in non-diabetic subjects, the insulin response to dynamic metabolic stress is likely to provide the best indirect measure of insulin sensitivity. In this study, postprandial insulinemia tended to decrease the longer the exercise session lasted, with no difference in glycemia, indicating that tissue sensitivity to insulin might have increased [\n28\n]. Furthermore, physical activity accumulating an energy expenditure of 4200 kJ per week is associated with a 30% reduction of all-cause mortality rates [\n29\n]. Our subjects could reach this weekly amount of energy expenditure by performing, for example, five walking sessions of 30 min, one session of 60 min plus three of 30 min, or one session of 60 min plus one of 90 min. Fat oxidation in these three situations would be 18 g, 23 g, and 32 g per week, respectively, indicating that greater fat oxidation can be obtained when performing fewer but longer activity sessions. Interestingly, five sessions of 30 min equal the current minimum recommendation of physical activity [\n15\n]. None of our subjects had difficulties in accomplishing the exercise bouts and, according to the rating of the Borg scale, they perceived the exercise intensity as light. Thus, this kind of physical activity is absolutely suitable to include in daily living.\nWe conclude that 60 and 90, but not 30 min of moderate intensity walking slightly reduced postprandial lipemia after two mixed meals with moderate fat content in sedentary, healthy young men compared to an inactive control. However, the reduction was not statistically significant. It seems, therefore, that a single exercise session of moderate intensity and with a duration of 90 min or less is insufficient to significantly reduce postprandial lipemia in these subjects in a normal daily life setting, i.e. when normal mixed meals with a moderate fat content are served. However, health benefits can nevertheless be achieved at these exercise intensities through other mechanisms.\nMethods\nThe study was approved by the Ethical Committee of the Swiss Federal Institute of Technology Zurich and was carried out according to a repeated measures cross over design. All participants of the study gave written informed consent.\nSubjects\nSixteen healthy, normal-weighed, sedentary men participated in the study (Table \n2\n). They were non-smokers and all normotriacylglycerolemic and euglycemic according to the classification of the NCEP [\n30\n] and the WHO [\n31\n], respectively. One subject had borderline high values of total cholesterol and low-density lipoprotein (LDL) cholesterol while the others were in the normal range (Table \n3\n).\nTable 2\nCharacteristics of the male subjects (n = 16)\nCharacteristic\nMean\nSEM\nAge [y]\n24.8\n0.8\nHeight [m]\n1.81\n0.02\nBody mass [kg]\n68.9\n1.6\nBody mass index [kg· m\n-2\n]\n21.1\n0.5\nVO\n2\nmax [mL· min\n-1\n· kg\n-1 \nbody mass]\n41.2\n0.8\nMaximum heart rate [min\n-1\n]\n192\n2\nSEM, standard error of the mean; VO\n2\nmax, maximal oxygen uptake.\nTable 3\nFasting biochemical variables of the subjects (n = 16)\nPlasma parameter\nMean\nSEM\nTriacylglycerol [mmol· L\n-1\n]\n1.03\n0.09\nTotal cholesterol [mmol· L\n-1\n]\n3.99\n0.19\nHDL cholesterol [mmol· L\n-1\n]\n1.27\n0.06\nLDL cholesterol [mmol· L\n-1\n]\n2.26\n0.15\nGlucose [mmol· L\n-1\n]\n5.01\n0.08\nInsulin [pmol· L\n-1\n]\n91.3\n5.0\nGlucagon [pmol· L\n-1\n]\n20.2\n1.2\nGlycerol [μmol· L\n-1\n]\n55.4\n3.1\nFatty acids [mmol· L\n-1\n]\n0.43\n0.05\nSEM, standard error of the mean; HDL, high-density lipoprotein; LDL, low-density lipoprotein.\nPreliminary tests\nEach subject performed two preliminary walking tests on a treadmill to determine his fitness capacity. In the first test, which also served to familiarise subjects with the methods of the study, subjects walked twice for approximately 20 min on the treadmill (PULSAR, H-P-COSMOS Sports Medical GmbH, Nussdorf-Traunstein, Germany) at 5 and 6 km· h\n-1\n, respectively, and with an increasing treadmill inclination of 3% every 3 min. The relationship between work rate and oxygen uptake was established in this test and the results were used to determine the work rate in the activity trials resulting in 50% of VO\n2\nmax.\nVO\n2\nmax was determined in the second test. Subjects walked at 6 or 7 km· h\n-1\n, and the treadmill inclination was increased by 5% every 3 min until exhaustion. The test was designed to be finished after 10 to 12 min. VO\n2\nmax was considered to be valid when at least two of the following three criteria were met: 1) respiratory exchange ratio (RER) >1.1; 2) heart rate within 10 beats per min of the predicted maximum (220 beats per min minus age); 3) rating of perceived exertion ≥19 on the Borg 6–20 scale.\nMain trials\nEach subject undertook four randomized trials (one control trial with no activity and three activity trials) at intervals of at least four days. To ensure similar baseline conditions, subjects were only allowed to follow activities of daily life on the two days prior to the test days. On the day preceding the test days, the intake of alcohol and caffeine-containing drinks was limited to at most 1–2 glasses of beer or wine and 2 cups of coffee, or 4 cups of tea, or 1 litre of a caffeine-containing soft drink. Additionally, subjects received a standardized evening meal (spaghetti, tomato sauce, cheese, and apple sauce) to prepare at home, providing 0.2 g fat per kg BM, 2.3 g carbohydrates per kg BM, 0.4 g protein per kg BM, and 53 kJ per kg BM. The subjects arrived at the laboratory by public transport after an overnight fast of at least 12 h. The compliance with the instructions was checked with questionnaires that were filled out by the subjects just after arrival at the laboratory.\nA catheter was placed into an antecubital or forearm vein 20 min after arrival and a fasting blood sample (8.7 mL) was taken. Subjects then walked on the treadmill for 30, 60, or 90 min at 50% of their VO\n2\nmax, depending on the respective trial, or rested in the control trial. During walking, respiration and heart rate (Polar Vantage NV, Polar Electro Oy, Kempele, Finland) were measured continuously. The subjects rated their perceived exertion after every 30 min of exercise on the Borg 6–20 scale. The walking session was briefly interrupted after 30 min (in the 60 and 90 min sessions) and after 60 min (in the 90 min session) to flush the catheter with heparin free saline (NaCl 0.9%, B. Braun Medical AG, Emmenbrücke, Switzerland). In the meantime, subjects were allowed to drink water ad libitum. A second fasting blood sample was taken just after the exercise bout. Breakfast was served shortly after, consisting of commercially available cereals, yoghurt, cream, and chocolate drink providing 0.5 g fat per kg BM, 1.6 g carbohydrates per kg BM, 0.4 g protein per kg BM, and 53 kJ per kg BM. Subjects received lunch three hours after breakfast, consisting of commercially available bread, cheese, chocolate cream, cream, and orange juice providing 0.5 g fat per kg BM, 1.6 g carbohydrates per kg BM, 0.5 g protein per kg BM, and 53 kJ per kg BM. Blood samples were taken every hour for six hours after breakfast to assess the postprandial period. The catheter was flushed with heparin free saline every 30 min to keep it patent. Water was available ad libitum during the postprandial period in the first trial, and the ingested amount was replicated in the following trials. The subjects stayed at the laboratory and pursued only seated activities until the end of the test day.\nIndirect calorimetry and energy expenditure calculations\nOxygen uptake and carbon dioxide production during physical activity were determined using a pulmonary gas exchange system (Quark b2, Cosmed, Rome, Italy). Energy expenditure, fat, and carbohydrate oxidation during physical activity were calculated according to the Weir formula [\n32\n] and a table of the nonprotein respiratory quotient [\n33\n], assuming that the urinary nitrogen excretion was negligible.\nBlood sampling and analyses\nFasting blood samples were analysed for TAG, insulin, glucagon, total cholesterol, LDL cholesterol, high-density lipoprotein (HDL) cholesterol, FA, glycerol, and glucose. Postprandial blood samples were analysed for TAG, insulin, glucagon, FA, glycerol, and glucose. Venous blood was collected into a 7.5 mL EDTA tube for analyses of TAG, insulin, total cholesterol, LDL cholesterol, HDL cholesterol, glycerol, and FA. A protease-inhibitor (Trasylol, Bayer AG, Leverkusen, Germany) was immediately added to an aliquot of the EDTA blood for analysis of glucagon. An additional 1.2 mL EDTA/Fluoride tube was collected for analysis of glucose. The tubes were stored on ice until centrifugation (3700 rpm, 8 °C, 12 min; g = 1800; Omnifuge 2.0 RS, Heraeus Sepatech, Osterode, Germany). After separation of venous samples, aliquots of serum were stored at -80 °C. Analyses were conducted after conclusion of the entire experimental period.\nA baseline fasting blood sample from each subject's first experimental day was analyzed by enzymatic colorimetric methods for TAG, total cholesterol (both Hitachi Modular P system, Roche Diagnostics, Basel, Switzerland), HDL (Cobas Integra800 analyzer, Roche Diagnostics, Basel, Switzerland), and LDL (calculated by the Friedewald formula [\n34\n]).\nAll fasting and postprandial blood samples were analysed for TAG, FA, glycerol, and glucose by enzymatic colorimetric methods, using a centrifugal analyzer (Cobas-Mira, Roche, Basel, Switzerland). Quality control sera (Roche Diagnostics, Basel, Switzerland) were used to ensure accuracy and precision. The TAG values were corrected by subtracting the glycerol values. Insulin and glucagon were analysed in duplicates by radioimmunoassay, using half of the prescribed amount of kit reagents (LINCO Research, St. Charles, Missouri, USA). The centrifugation steps (glucagon: 4200 rpm, 4 °C, 30 min and insulin: 4700 rpm, 4 °C, 30 min) were carried out in a conventional laboratory centrifuge (Varifuge RF, Heraeus Sepatech, Hanau, Germany) and radioactivity was measured using a gamma counter (Cobra II, Packard Gamma Counter, Minnesota, USA).\nData analyses and statistics\nThe AUC and the dAUC TAG were calculated using the trapezoidal method [\n35\n]. The measurement just before meal intake was taken as the base value. Statistical analyses were performed using SAS statistical software (version 8.2 for Windows, SAS institute Inc., Cary, NC, USA). The results of the responses during exercise, AUC, dAUC, and blood measurements at specific time points were compared with a mixed model analysis with Tukey's adjustment. The postprandial responses over time were compared with a mixed model analysis with repeated measurements and Tukey's adjustment. The factors for the analyses were subject, period, and trial. The fasting value before activity was used as an additional factor for the postprandial responses over time. Data are presented as mean and standard error of the mean (SEM). A p-value of less than 0.05 was considered significant.\nAuthors' contributions\nMP was responsible for designing, planning, and accomplishing the study, the analyses of the results, as well as drafting the manuscript. TL participated in the accomplishment of the study and analyses of the blood samples. CW participated in the design and coordination of the study. PCC participated in designing the study, the analyses of the results, and drafting the manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
51
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nAmbient Air Pollution and Atherosclerosis in Los Angeles\n\n**Article Abstract:**\n\nAssociations have been found between long-term exposure to ambient air pollution and cardiovascular morbidity and mortality. The contribution of air pollution to atherosclerosis that underlies many cardiovascular diseases has not been investigated. Animal data suggest that ambient particulate matter (PM) may contribute to atherogenesis. We used data on 798 participants from two clinical trials to investigate the association between atherosclerosis and long-term exposure to ambient PM up to 2.5 μm in aerodynamic diameter (PM\n2.5\n). Baseline data included assessment of the carotid intima-media thickness (CIMT), a measure of subclinical atherosclerosis. We geocoded subjects’ residential areas to assign annual mean concentrations of ambient PM\n2.5\n. Exposure values were assigned from a PM\n2.5\n surface derived from a geostatistical model. Individually assigned annual mean PM\n2.5\n concentrations ranged from 5.2 to 26.9 μg/m3 (mean, 20.3). For a cross-sectional exposure contrast of 10 μg/m3 PM\n2.5\n, CIMT increased by 5.9% (95% confidence interval, 1–11%). Adjustment for age reduced the coefficients, but further adjustment for covariates indicated robust estimates in the range of 3.9–4.3% (\np\n-values, 0.05–0.1). Among older subjects (≥60 years of age), women, never smokers, and those reporting lipid-lowering treatment at baseline, the associations of PM\n2.5\n and CIMT were larger with the strongest associations in women ≥60 years of age (15.7%, 5.7–26.6%). These results represent the first epidemiologic evidence of an association between atherosclerosis and ambient air pollution. Given the leading role of cardiovascular disease as a cause of death and the large populations exposed to ambient PM\n2.5\n, these findings may be important and need further confirmation.\n\n**Article Body:**\n\nA large body of epidemiologic evidence suggests associations between ambient air pollution and cardiovascular mortality and morbidity (\nPeters and Pope 2002\n; \nPope et al. 2004\n). All of these studies focus on events occurring at a late stage of vascular disease processes. The impact of air pollution on the underlying preclinical conditions remains poorly understood. We hypothesize that current levels of ambient particulate matter (PM) up to 2.5 μm in aerodynamic diameter (PM\n2.5\n) may contribute to atherosclerosis, leading to subclinical anatomical changes that play a major role in cardiovascular morbidity and mortality later in life. Animal studies support our hypothesis by showing that inhalation of ambient PM promotes oxidative lung damage, including alveolar and systemic inflammatory responses (\nBecker et al. 1996\n; \nDye et al. 2001\n; \nFujii et al. 2002\n; \nGoto et al. 2004\n; \nSuwa et al. 2002\n; \nvan Eeden et al. 2001\n).\nWe investigated the association between residential ambient PM2.5 and carotid artery intima-media thickness (CIMT) using pre-randomization baseline data from two recent clinical trials conducted in Los Angeles, California (\nHodis et al. 2002\n). CIMT is a well-established quantitative measure of generalized atherosclerosis that correlates well with all of the major cardiovascular risk factors, with coronary artery atherosclerosis, and with clinical cardiovascular events (\nMack et al. 2000\n). It is an established tool for investigating the contribution of long-term exposures such as smoking or passive smoking to subclinical stages of atherosclerosis at any given age (\nDiez-Roux et al. 1995\n; \nHoward et al. 1994\n, \n1998\n). This is the first study to assess the association of atherosclerosis with air pollution.\nMaterials and Methods\nPopulation and health assessment\nWe used baseline health data from two randomized, double-blind, placebo-controlled clinical trials conducted at the University of Southern California Atherosclerosis Research Unit (\nHodis et al. 2002\n). The Vitamin E Atherosclerosis Progression Study (VEAPS) investigated the effects of vitamin E on the progression of atherosclerosis measured by CIMT. The B-Vitamin Atherosclerosis Intervention Trial (BVAIT) focused on the effect of vitamin B supplements on the progression of atherosclerosis (trial in progress). Baseline assessment in both trials included CIMT measured between 1998 and 2003 using the same standardized methods (\nHodis et al. 2002\n; \nSelzer et al. 1994\n, \n2001\n). Recruitment of volunteers occurred over the entire Los Angeles Basin, covering a geographic area of approximately 64,000 km\n2\n.\nEligible subjects for the VEAPS trial (\nn\n = 353) were men and women ≥40 years of age with slightly increased LDL cholesterol (≥3.37 mmol/L) but with no clinical signs or symptoms of cardiovascular disease (CVD) (\nHodis et al. 2002\n). Subjects with diabetes, diastolic blood pressure > 100 mm Hg, thyroid disease, serum creatinine > 0.065 mmol/L, life-threatening diseases, or high alcohol intake were excluded.\nBVAIT (\nn\n = 506) had a similar design to that of VEAPS. Men and women > 40 years of age were prescreened to meet study criteria (fasting plasma homocysteine ≥8.5 μmol/L; postmenopausal for women; no evidence of diabetes, heart disease, stroke, or cancer). Subjects were excluded on the basis of any clinical signs or symptoms of CVD, diabetes or fasting serum glucose ≥140 mg/dL, triglyceride levels ≥150 mg/dL, serum creatinine > 1.6 mg/dL, high blood pressure, untreated thyroid disease, life-threatening disease with prognosis < 5 years, or high alcohol intake.\nThus, our study included “healthy” subjects with biomarkers (elevated LDL cholesterol or homocysteine) that suggested an increased risk of future CVDs (\nn\n = 859). Fifty-eight subjects were excluded in the exposure assignment process because they lived outside the area with PM\n2.5\n data. Three subjects had missing data in at least one of the covariates used in the models. Our total sample consisted of 798 participants.\nHealth measures, including CIMT\nOur main outcome of interest is CIMT. In both trials, high-resolution B-mode ultrasound images of the right common carotid artery were obtained before the intervention (baseline) with a 7.5-MHz linear array transducer attached to an ATL Ultramark-4 Plus Ultrasound System (Ultramark, Bothell, WA). We used this baseline CIMT measurement as the outcome. Details of this highly reproducible method are published (\nHodis et al. 2002\n; \nSelzer et al. 1994\n, \n2001\n). Blood pressure, height, and weight were measured with standard procedures.\nThe baseline questionnaires included an assessment of all major CVD risk factors and covariates, including clinical events, diet, use of prescription medications, physical activity, current and past smoking and passive smoking, and vitamin supplements. Age, education, and other sociodemographic factors were available for each subject. Fasting blood samples were also drawn for lipid measurements. Data used in our analyses were collected with the same tools in both trials.\nExposure assignment\nTo assess exposure we chose a novel approach derived from a geographic information system (GIS) and geostatistics. This method allows for assignment of long-term mean ambient concentrations of PM\n2.5\n to the ZIP code area of each subject’s residential address (\nKünzli and Tager 2000\n). The resulting surface of PM\n2.5\n covered the entire Los Angeles metropolitan area. The surface is derived from a geostatistical model and data from 23 state and local district monitoring stations (during 2000). These monitors are located across the Los Angeles region to characterize urban levels of pollution. To assign exposure, PM\n2.5\n data were interpolated using a combination of a universal kriging model with a quadratic drift and a multi-quadric radial basis function model (\nBailey and Gatrell 1995\n; \nBurrough and McDonnell 1998\n). We averaged the two surfaces based on 25-m grid cells. Examination of errors from the universal model showed that > 50% of the study area had assigned values within 15% of monitored concentrations, whereas 67% were within 20%. The larger errors were on the periphery of our study area, where the density of study participants was the lowest. We linked the ZIP code centroids of each subject with the exposure surface through a geocoding database [\nEnvironmental Systems Research Institute (ESRI) 2004\n]. \nFigure 1\n illustrates the PM\n2.5\n surface with the geolocated ZIP codes. Individually assigned PM\n2.5\n data had a range from 5.2 to 26.9 μg/m\n3\n (mean, 20.3), thus exceeding the range observed across 156 metropolitan areas used in the largest cohort study of air pollution and mortality (\nPope et al. 2002\n). All models were implemented with ArcScript from ESRI (Redlands, CA).\nStatistical analyses\nWe tested the univariate and multivariate associations between CIMT and ambient PM\n2.5\n using linear regression analyses. Extensive residual diagnostics indicated some heteroskedasticity, which was rectified with the natural log-transformed CIMT. We adjusted for factors that were statistically associated with both CIMT and ambient PM\n2.5\n (age, male sex, low education, and low income). Next, we expanded the models using covariates that were associated with either PM\n2.5\n or CIMT, including indicator variables for current second-hand smoke exposure and current and former personal smoking. We then added covariates that play a role in atherosclerosis such as blood pressure, LDL cholesterol, or proxy measures such as reporting treatment with antihypertensives or lipid-lowering medications at study entry. These factors may affect the pathophysiologic pathways linking air pollution exposure and atherosclerosis (\nRoss 1999\n); thus, such models may overadjust the coefficients. We chose this conservative approach to test the sensitivity of the effect estimates under a broad range of model assumptions.\nThere is increasing evidence that host factors such as age, sex, or underlying disease and risk profiles may modify the effects of air pollution (\nPope et al. 2002\n; \nZanobetti and Schwartz 2002\n). Furthermore, the finding of atherosclerosis in PM-exposed rabbits was based on a hyperlipidemic trait (\nSuwa et al. 2002\n). Therefore, we also stratified by sex, age (< 60 years, ≥60 years), smoking status, and lipid-lowering drug therapy.\nResults\nTable 1\n summarizes the main characteristics of the study population and among main subgroups. \nTable 2\n presents the percent change in CIMT in association with a 10 μg/m\n3\n contrast in ambient PM\n2.5\n concentrations for three cross-sectional regression models. The unadjusted model indicates a 5.9% [95% confidence interval (CI), 1–11%] increase in CIMT per 10 μg/m3 PM\n2.5\n. For the observed contrast between lowest and highest exposure (20 μg/m\n3\n PM\n2.5\n), this corresponds to a 12.1% (2.0–23.1%) increase in CIMT. The only covariate with a substantial effect on the point estimate was age, which reduced the effect from 5.9 to 4.3% (0.4–9%) per 10 μg/m3 PM\n2.5\n. This change agrees with the age-related effect modification. Otherwise, effect estimates across the models remained robust, in the range of 3.9–4.3% with \np\n-values from 0.05 to 0.1. To corroborate the exposure–response relationship, we also categorized PM\n2.5\n levels into quartiles. \nFigure 2\n shows the adjusted mean CIMT across these four groups of equal sample size at the mean levels of the covariates (age, sex, education, and income). The trend across the exposure groups was statistically significant (\np\n = 0.041). The unadjusted means of CIMT among these quartiles of exposure were 734, 753, 758, and 774 μm, respectively.\nThe associations between CIMT and PM\n2.5\n were substantially stronger among 109 subjects reporting lipid-lowering medication at study entry, both in men and in women (\nTable 2\n, \nFigure 3\n). The crude effect reached 15.8% (2–31%) per 10 μg/m\n3\n PM\n2.5\n, with adjusted values ranging between 12 and 16%. Despite the small sample size, \np\n-values of all models were mostly < 0.1 and often < 0.05.\nResults also suggest significant age and sex interactions, with much larger effects in women and in the older age group (\nFigure 3\n). Effect estimates in women were statistically significant and typically in the range of 6–9% per 10 μg/m3 PM\n2.5\n. Associations were strongest among women ≥60 years of age (\nn\n = 186), leading to crude estimates of 19.2% (9–31%). Adjusted coefficients ranged from 14 to 19%, being statistically significant in all models and sensitivity analyses.\nAmong never smokers (\nn\n = 502), the effect estimate reached 6.6% (1.0–12.3%). The estimate was small and not significant in current (\nn\n = 30) and former smokers (\nn\n = 265).\nDiscussion\nOur study presents the first evidence for an association between CIMT and long-term exposure to ambient air pollution. As recently reviewed in a statement of the American Heart Association (\nBrook et al. 2004\n) substantial epidemiologic and experimental evidence suggests a contribution of ambient air pollutants on cardiovascular mortality and morbidity. However, these studies focus on acute and subacute effects on cardiac autonomic function, inflammatory or thrombogenic markers, arrhythmia, myocardial infarction, cardiovascular hospital admission, and death. The only outcome considered in long-term air pollution studies has been mortality. The relative risks for acute effects on mortality have been substantially smaller than those observed for long-term associations (\nPope et al. 2002\n; \nSamet et al. 2000\n). As shown previously, cohort studies are capable of capturing acute and chronic effects of air pollution on the course of diseases that ultimately lead to premature death (\nKünzli et al. 2001\n). In contrast, time-series and panel studies investigate only the associations of event occurrence with the most recent exposure (\nKünzli et al. 2001\n). Thus, if air pollution has both acute and cumulative long-term effects, one expects larger mortality coefficients in cohort studies. CIMT reflects long-term past exposure; thus, we provide the first evidence for chronic effects of air pollution on atherogenesis that may in part explain the above mentioned discrepancy between acute and long-term risk estimates (\nPope et al. 2002\n; \nSamet et al. 2000\n).\nThere are several major aspects to be considered in the interpretation of this new finding, mainly the strength in the exposure assignment, the limited evidence for bias, the differences in effects within subgroups, and plausibility.\nExposure assignment\nThe individual residence-based assignment of exposure represents a substantial improvement over most studies that have relied on central monitors or on binary road buffers combined with basic interpolation (\nHoek et al. 2002\n; \nPope et al. 2004\n). As a sensitivity analysis, we used weighted least-squares models with the weights specified as the inverse of the standard errors from the universal kriging model to down-weight estimates with larger error. In addition, we implemented models based solely on the universal kriging estimate. In both instances results were robust and similar to what we found with our main model.\nTime–activity studies show that people spend most of their time in or around home, and our restriction of exposure assessment on residential address captures the most relevant part of exposure (\nLeech et al. 2002\n). PM\n2.5\n generally displays spatially homogeneous distributions across small areas such as neighborhoods and blocks, and as a result, the ambient conditions at the ZIP code centroid likely reflect the levels expected at home outdoors (\nRoosli et al. 2000\n). PM\n2.5\n of outdoor origin will also penetrate indoors, and correlations between long-term outdoor PM concentrations and indoor levels of PM from outdoor origin is high (\nSarnat et al. 2000\n). Exposure to ambient air pollution while working and during commute are not included in our exposure term but are considered to be a relevant source of exposure (\nRiediker et al. 2003\n). Although most likely a random misclassification with biases toward the null, the errors may affect subgroups differently, thus explaining part of the observed interactions.\nIn Los Angeles, no clear trends have been observed in PM\n2.5\n concentrations over the past 5–10 years. The year 2000 surface characterizes the prevailing mean PM\n2.5\n concentrations across several years and can be considered a measure of long-term past exposure. This year also sits in the middle of the baseline recruitment period. Overall, the various limitations in our exposure assignment may add some random error, biasing results toward weaker associations (\nThomas et al. 1993\n).\nWe also assigned ambient ozone to ZIP code centroids. Inclusion of ozone in the models had no impact on the PM\n2.5\n coefficients or the SEs. Ozone and PM\n2.5\n were not correlated (\nr\n = –0.17), and the PM\n2.5\n estimates were not substantially different in low-and high-ozone regions. The estimates of association for ozone were positive but not statistically significant and much smaller than for PM\n2.5\n. This finding must be put in context of the specific challenges in determining long-term exposure to ozone, which are substantially different than in the case of PM exposure. In contrast to PM\n2.5\n from outdoor origin, ambient ozone levels have lower correlations with personal exposure (\nAvol et al. 1998\n; \nSarnat et al. 2000\n, \n2002\n); therefore, the ability to detect effects of ozone will likely be reduced due to greater misclassification.\nBiases\nOur subjects were a nonrandom sample of “healthy” volunteers with above-average education, meeting strict inclusion criteria for the two clinical trials. Although we cannot exclude some systematic selection biases affecting the cross-sectional data, it is unlikely that subjects with preclinical signs of atherosclerosis would have been more likely to volunteer if they lived in more polluted areas. Although the selection of subjects limits the generalization to other populations, we do not expect this to lead to over- or underestimating the cross-sectional associations. The two trials recruited subjects independently; thus, the effects may be compared across trials to evaluate the potential influence of selecting volunteers. The populations differed with regard to age, smoking habits, baseline LDL and treatment, blood pressure, active and passive smoking, and other relevant factors; thus, the PM\n2.5\n coefficients were smaller and were not statistically significant in the VEAPS trial with its younger population. However, after taking these factors into account, the associations with ambient PM\n2.5\n were similar. For example, among elderly women of VEAPS (\nn\n = 70) and BVAIT (\nn\n = 116), the effect estimate was 18.1% (–0.1 to 36.3.%) and 13.6% (2.8–24.4.%), respectively. There is some evidence for larger effects in subjects with cardiovascular risk factors, indicated by prescriptions of lipid-lowering treatment. Our trials excluded subjects with clinically manifest CVDs. Moreover, if air pollution amplifies systemic inflammation among those prone to atherosclerosis, exclusion of subjects with high LDL may be a source of bias. One may expect effect estimates in a less selected, less healthy population to be larger than those reported.\nThe wealth of baseline data from these clinical trials offered the opportunity to control for a broad array of covariates. Apart from the effect of age adjustment, estimates were robust to numerous combinations of covariates, including income, education, active and passive tobacco smoke, cardiovascular prescriptions, vitamin intake, and physical activity. Uncontrolled or residual confounding appears to be an unlikely explanation for these results. Among women, adjustment for hormone replacement therapies did not affect the PM\n2.5\n estimates.\nIn previous studies, we found that spatial autocorrelation in the residuals could affect the size and significance of pollution coefficients (\nJerrett et al. 2003a\n). We investigated spatial autocorrelation of the unstandardized residuals. We assessed autocorrelation with first-order, adjusted first-order, and second-order spatial weight matrices based on nearest neighbor contiguity, but we found no evidence of spatial autocorrelation. This supports the conclusion that the models supply efficient unbiased estimates (\nJerrett et al. 2003b\n). As part of our sensitivity analyses, we also derived PM\n2.5\n surfaces using different interpolations and weighted least squares with weights equal to the inverse of the standard error of the exposure estimate. All approaches produced very similar results.\nEvidence for effect modification\nThe data suggest substantial interactions with age, sex, smoking, and underlying cardiovascular risk factors. Given the reduced sample size among subgroups, the recruitment of volunteers, and the cross-sectional nature of the data, it is difficult to fully explore the causes of the observed modifications of associations and to establish susceptibility profiles. If the exposure misclassifications differed across subgroups, part of the interactions may be explained by differential exposure error. The sex and age difference could also be an artifact due to measurement error in the assigned exposure because time spent in commuting and location of work places may be different in men and women and in the young and elderly. Empirical studies on mobility suggest women have smaller activity spaces than men and younger groups, meaning they tend to spend more time in and around the home (\nKwan and Lee 2004\n), and the same is probably true of the elderly compared with younger groups. Exposure measurement error may be reduced in those spending more time at home, leading to stronger effects (\nThomas et al. 1993\n). Moreover, differences in statistical power may play a role as well; as shown at least for the 25–40-year age range, power to detect effects on CIMT is larger in women than in men (\nStein et al. 2004\n).\nThe finding that those reporting prescriptions of lipid-lowering medications at baseline showed stronger associations of CIMT with PM\n2.5\n merits further investigation. This result agrees with the observed effects of PM on atherosclerosis in experiments conducted in hyperlipidemic rabbits (\nGoto et al. 2004\n; \nSuwa et al. 2002\n). The systemic inflammatory and atherogenic reaction in these rabbits was related to the amount of PM contained in the alveolar macrophages. In our study, being under lipid-lowering therapy is an indicator for risk profiles prone to atherogenesis. Those subjects were mostly men (64%) and, on average, older, more often active or passive smokers, and almost twice as likely to report antihypertensive treatment. The systemic response to ambient PM may amplify and expand the oxidation of LDL cholesterol among these susceptible subjects, consequently contributing to injury in the artery wall (\nGoto et al. 2004\n; \nRoss 1999\n). Investigations of short-term effects of ambient air pollution on mortality also suggest that underlying risk profiles such as diabetes may amplify susceptibility to ambient PM (\nZanobetti and Schwartz 2002\n), and similar findings have been shown with smoking and diabetes mellitus in association with CIMT (\nKarim et al. 2005\n). To clarify the relevance of lipid status, it would be interesting to investigate our hypothesis among cohorts with familial hypercholesteremia (\nWiegman et al. 2004\n; \nWittekoek et al. 1999\n).\nAs shown in \nFigure 3\n, the size of the point estimate was larger among the older subjects. Future research needs to clarify whether air pollution contributes to atherosclerosis only after a certain age or early on. Effects of air pollution on lung development have been observed during adolescence and may be a result of both pulmonary and chronic systemic inflammatory effects (\nGauderman et al. 2002\n); thus, it is conceivable that atherogenic responses may occur early in life. The age dependence of the effects may also be codetermined by genetic factors (\nHumphries and Morgan 2004\n; \nRoss 1999\n).\nWe also observed larger effects in women. If other cardiovascular risk factors such as occupational exposures dominate atherosclerosis in men, we would expect a smaller effect signal and less precision in the estimates among men. We also hypothesize that interactions may reflect biologic causes. If premenopausal women are protected against atherosclerosis by endogenous hormones, loss of hormonal protection would lead to increased vulnerability after menopause (\nKannel et al. 1976\n). This could explain part of the interaction by both age and sex.\nActive and passive smoking did not confound results in either the total sample or among subgroups. Adjustment for active tobacco smoke led to a slight increase in the effect estimate; thus, residual confounding is unlikely to overestimate the effects. However, PM\n2.5\n associations were clearly stronger in never smokers compared with smokers (data not shown). This gradient was also observed in all subgroups with significant PM\n2.5\n associations (\nFigure 3\n). Oxidative and inflammatory effects of smoking may dominate to such an extent that the additional exposure to ambient air pollutants may not further enhance effects along the same pathways. The difference in the effects of PM\n2.5\n in smokers and nonsmokers needs further investigation. The American Cancer Society cohort study does not reveal a clear pattern of a smoking interaction for the association of ambient air pollution and cardiovascular death (\nKrewski et al. 2004\n; \nPope et al. 2004\n). In the Study on Air Pollution and Lung Diseases in Adults (SAPALDIA), associations between air pollution and level of pulmonary function did not differ by smoking status (\nAckermann-Liebrich et al. 1997\n).\nSome U.S. studies indicate effect modification of air pollution by socioeconomic status (SES) with much stronger effects among the less educated (\nPope et al. 2002\n). The cause of this interaction pattern is not well understood. SES status was rather homogeneous in these mostly well-educated volunteers, providing little power to investigate interactions of pollution with SES. If lower SES also positively modifies effects of air pollution on atherosclerosis, our population would provide an underestimate of the health effects in the general population (\nO’Neill et al. 2003\n). Further research on samples representative of the population will be needed to assess whether the high SES in the clinical trials biases the effects toward the null.\nFuture research should focus on identifying factors that determine susceptibility to PM\n2.5\n. We are initiating studies on subjects with inflammatory metabolic syndromes prone to accelerated atherosclerosis such as postmenopausal women, diabetics, or obese or physically inactive people. To corroborate the cross-sectional findings, follow-up studies are ultimately needed to investigate the association of concurrent levels of air pollution exposure with the progression of CIMT.\nPlausibility\nFrom a biologic perspective, our results support the hypothesis that long-term exposure to ambient PM contributes to systemic inflammatory pathways, which are a relevant aspect of atherogenesis (\nRoss 1999\n). The findings indicate a biologically plausible link between the observed acute effects of ambient air pollution on systemic inflammation (\nGlantz 2002\n) and the long-term consequences of sustained vascular inflammation leading to increased atherosclerosis and, ultimately, cardiovascular death (\nHoek et al. 2002\n; \nPope et al. 2004\n). Among susceptible people, this may lead to artery wall lesions similar to those observed in the rabbit model (\nFujii et al. 2002\n; \nSuwa et al. 2002\n). In these hyperlipidemic rabbits, 4-week PM exposure was associated with the progression of atherosclerotic lesions, coupled with an enhanced release of bone marrow monocytes. These precursors of macrophages play an important role in the atherogenic inflammatory responses (\nGoto et al. 2004\n; \nRoss 1999\n; \nSuwa et al. 2002\n). Given the central role of oxidized LDL in the initiation and progression of atherogenesis, suggestions that the plasma of automotive workers with high exposure to traffic exhaust is more susceptible to oxidation is also of interest (\nSharman et al. 2002\n).\nAs a quantitative plausibility check, we compared the size of the PM\n2.5\n effects with effects of other risk factors on CIMT. Using smoking and environmental tobacco smoke (ETS) as a model for air pollution exposure, the size of our estimates appear plausible (\nDiez-Roux et al. 1995\n; \nHoward et al. 1994\n). Associations of ETS and current levels of air pollution with various respiratory outcomes are similar and support the notion of common underlying pathways (\nKünzli 2002\n). Smoking and ETS associate with stiffer and thicker artery walls, reflecting the systemic effect of these exposures (\nHoward et al. 1994\n; \nMack et al. 2003\n). Exposure to ETS was associated with 2–3% thicker intima-media, which approximate the effects observed for a 10 μg/m3 change in PM\n2.5\n (\nDiez-Roux et al. 1995\n; \nHoward et al. 1994\n). Using never smokers without ETS exposure as the referent group in our data, never smokers with ETS at home had 0.9% (–2.7 to 4.5%) thicker artery walls; former smokers’ CIMT was increased on average by 3.4% (0.7–6.3%), and the 30 current smokers had 5% (–1.5 to 11.6%) thicker CIMT. The trend across these four categories of tobacco exposure was statistically significant. As shown in \nTable 1\n, smokers were underrepresented in these volunteers of well-educated participants.\nThe observed percent change in CIMT corresponds to an increase in the thickness of approximately 20–40 μm per 10 μg/m\n3\n contrast in PM\n2.5\n. This difference in CIMT translates into some 3–6% increase in the long-term risk for myocardial infarction (\nO’Leary et al. 1999\n). \nPope et al. (2004)\n reported that long-term exposure to PM\n2.5\n was associated with an 18% (14–23%) increase in ischemic heart disease. Effect sizes reported here concur with these findings, indicating that a fraction of the total effect of ambient PM on cardiovascular mortality may be mediated through sustained long-term effects of air pollution on atherosclerosis (\nKünzli et al. 2001\n). This is in line with the proposed model (\nKünzli et al. 2001\n) in which some of the effects observed in cohort studies must reflect long-term contributions of air pollution to the underlying disease progression, whereas in other cases, air pollution contributes only to triggering of cardiovascular events or death (\nBell et al. 2004\n; \nKünzli et al. 2001\n; \nPeters and Pope 2002\n).\nFrom a biologic and policy perspective, we emphasize that PM\n2.5\n probably serves as a surrogate for the mixture of urban air pollution and constituents of PM. It is premature to conclude that PM\n2.5\n and its constituents are the atherogenic culprit per se. Atherosclerosis results from complex processes that may include a combination of various urban pollutants, host factors, and pathways that ultimately lead to the findings of a CIMT–PM\n2.5\n association.\nIn conclusion, we have presented the first epidemiologic evidence supporting the idea of a chronic vascular response to respiratory and systemic effects of PM exposure. Given the leading role of heart disease as a cause of death in most westernized countries and the growing contribution in developing countries, these findings may be of high public health relevance. Further investigations need to focus on susceptible groups and follow-up of cohorts to investigate the effect of air pollution on the progression of CIMT.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
52
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nAging syndrome genes and premature coronary artery disease\n\n**Article Abstract:**\n\nBackground\nVascular disease is a feature of aging, and coronary vascular events are a major source of morbidity and mortality in rare premature aging syndromes. One such syndrome is caused by mutations in the lamin A/C (\nLMNA\n) gene, which also has been implicated in familial insulin resistance. A second gene related to premature aging in man and in murine models is the \nKLOTHO \ngene, a hypomorphic variant of which (KL-VS) is significantly more common in the first-degree relatives of patients with premature coronary artery disease (CAD). We evaluated whether common variants at the \nLMNA \nor \nKLOTHO \ngenes are associated with rigorously defined premature CAD.\nMethods\nWe identified 295 patients presenting with premature acute coronary syndromes confirmed by angiography. A control group of 145 patients with no evidence of CAD was recruited from outpatient referral clinics. Comprehensive haplotyping of the entire \nLMNA \ngene, including the promoter and untranslated regions, was performed using a combination of TaqMan\n® \nprobes and direct sequencing of 14 haplotype-tagging single nucleotide polymorphisms (SNPs). The KL-VS variant of the \nKLOTHO \ngene was typed using restriction digest of a PCR amplicon.\nResults\nTwo SNPs that were not in Hardy Weinberg equilibrium were excluded from analysis. We observed no significant differences in allele, genotype or haplotype frequencies at the \nLMNA \nor \nKLOTHO \nloci between the two groups. In addition, there was no evidence of excess homozygosity at the \nLMNA \nlocus.\nConclusion\nOur data do not support the hypothesis that premature CAD is associated with common variants in the progeroid syndrome genes LMNA and KLOTHO.\n\n**Article Body:**\n\nBackground\nCAD is the most common cause of death in the developed world and an increasingly important cause of mortality in the developing world. The dominant pathophysiologic paradigm in CAD is that observed in a relatively rare inherited form of atherosclerosis; Familial Hypercholesterolemia caused by mutations in the LDL receptor[\n1\n]. In this condition a primary endocytic abnormality leads, at least partly though excess elevations in LDL cholesterol, to focal endothelial injury, and chronic inflammatory lesions of the arterial wall. Ultimately through plaque rupture and thrombosis there is episodic end-artery occlusion. Importantly, while the later phases of this process appear to be relevant to many forms of CAD, the earliest injury is unknown in most forms of vascular disease precluding truly preventative strategies. Recently the identification of Mendelian forms of coronary disease has suggested that other major pathways may contribute to each stage of the process[\n2\n,\n3\n]. Family history is a major risk factor for premature CAD, but the genetic contributions to common forms of the disease are unknown[\n4\n]. The high prevalence of CAD in older age groups suggests that some forms of atherosclerosis are an integral part of the aging process, and inherited premature aging (or progeroid) syndromes are associated with extensive vascular disease[\n5\n]. The causal genes underlying two such rare Mendelian forms of aging recently have been identified.\nDiscrete mutations in the \nLMNA \ngene have been demonstrated to cause a range of inherited syndromes including a variant of Emery-Dreifus muscular dystrophy, dilated cardiomyopathy with conduction disease and Charcot-Marie-Tooth disease[\n6\n]. The mechanisms of this remarkable pleiotropy are unknown, but have been attributed to discrete functions of different lamin domains in individual tissues. At least two of the syndromes caused by lamin mutations include premature CAD. Some lamin mutations result in Dunnigan's partial lipodystrophy in which CAD is a prominent feature, especially in females. These individuals suffer from an unusual form of insulin resistance, with morphologic abnormalities including hemifacial loss of subcutaneous adipose tissue, as well as hypertension, dyslipidemia and vascular disease. Patients in such families also have elevated CRP levels, and lower leptin and adiponectin levels[\n7\n]. A second aging disorder, Hutchison-Gilford Progeria Syndrome (HGPS), is the result of recurrent \nde novo \nmutations of a single nucleotide in exon 11 of the \nLMNA \ngene have been shown to cause the progeroid disorder)[\n8\n,\n9\n]. HGPS is characterized by extreme 'aging' in multiple tissues with most affected individuals dying from atherosclerotic vascular disease in their late teens. In many cases of HGPS there also appeared to be germ-line loss of the second \nLMNA \nallele, suggesting that somatic mutations at this locus might lead to more common forms of aging, possibly in a tissue-restricted manner. Given the extreme forms of vascular disease seen in these two laminopathies, and the strong association of the metabolic syndrome with CAD we explored the role of \nLMNA \nvariation in premature coronary disease.\nThe second gene implicated in progeria is \nKLOTHO \nencoding a membrane protein of unknown function sharing homology with beta-glucosidases. Targeted deletion of the \nKlotho \nlocus in mice results in reduced longevity, vascular disease, osteoporosis and chronic lung disease[\n10\n]. Recent work has demonstrated impaired angiogenesis and vasculogenesis in these \nKlotho\n-deficient mice[\n11\n]. A role for the ortholog of \nKlotho \nin human aging was suggested by the finding that a specific \nKLOTHO \nallele (KL-VS) which changes amino-acid sense is underrepresented in older age groups. This finding was reproduced in three ethnically distinct groups[\n12\n]. Individuals homozygous for the KL-VS allele were 2.6-fold less likely to survive to 65 years of age or greater. A role for the human \nKLOTHO \ngene in vascular disease also has been suggested by work demonstrating that the same KL-VS allele is associated with increased risk of occult atherosclerosis in a high-risk sample consisting of siblings of individuals with premature CAD. This effect of the KL-VS allele was evident even after adjustment for known risk factors [\n13\n]. We also explored the role of the KL-VS allele in our cohort of subjects with premature CAD.\nPrevious studies of these two aging genes largely have been confined to rare kindreds or cohorts with direct evidence of CAD. We tested the hypothesis that common variants at the \nLMNA \nand \nKLOTHO \nloci were associated with angiographically-defined premature CAD in a case-control association study.\nMethods\nSubjects\nBetween 1999 to 2003, we attempted to recruit serial patients with premature CAD presenting to the Massachusetts General Hospital were recruited. Inclusion criteria were; documented acute coronary syndrome (myocardial infarction or unstable angina) confirmed on coronary angiogram; and age ≤ 50 years for males or ≤ 55 years for females. Exclusion criteria were: logistic difficulties precluding enrollment, history of familial dyslipidemia, type I diabetes, endstage renal disease, a history of recent trauma, sepsis, or previous thoracic irradiation. All patients gave written informed consent prior to study enrollment. A structured interview and physical examination was performed during the initial hospitalization. This included a detailed medical history, careful documentation of cardiovascular risk factors, current and past medications and a comprehensive family history using an instrument which we have previously validated. Hypertension was defined as previous antihypertensive use or a documented untreated systolic blood pressure >140 mmHg or diastolic>90 mmHg. Hypercholesterolemia was defined as an LDL cholesterol >130 mg/dl. Diabetes mellitus was defined as the use of diet, oral hypoglycemic agents or insulin to control blood glucose. Smoking was defined as the regular use of tobacco at any stage in the previous decade. A blood sample for nucleic acid extraction was obtained at enrollment. In parallel, over the same time period a control population was recruited from outpatient referral clinics at Massachusetts General Hospital. These control subjects were free from symptoms suggestive of CAD or ECG abnormalities, and all had undergone transthoracic echocardiography to exclude the presence of subclinical structural heart disease.\nGenetic analyses\nLMNA \ngenotyping\nTo generate representative haplotypes at the \nLMNA \nlocus, we first assembled \nin silico \n35,374 base pairs of reference sequence encompassing the entire coding region of the gene including sequence reported by Lin et al[\n14\n], consensus finished sequence and trace data from the region from the Human Genome Project[\n15\n]. Additional direct sequencing of the relevant genomic regions was performed where necessary. Sequence assembly and analysis was performed using the aid of Vector NTI version 8 (InforMax™). SNPs spanning the \nLMNA \ngene were selected from dbSNP [\n16\n] and the published literature. Selection was based on genomic coverage and where possible on polymorphism information content. In addition, all common (defined as those present in ≥ 5% of the population) SNPs changing amino acid sense were included.\nA combination of TaqMan\n® \nbased assays and direct sequencing was used to type the SNPs in an initial subset of the study cohort. Details of probes and primers are available in Table \n5\n. Allelic discrimination using TaqMan\n® \nwas performed using 5 ng of sample DNA in a 25 μL reaction containing 12.5 μL TaqMan\n® \nUniversal PCR Mix (Applied Biosystems), 300 nM primers, 200 nM TaqMan\n® \nMGB probes (Applied Biosystems). Reaction conditions consisted of preincubation at 50°C for 2 minutes, 95°C for 10 minutes, then cycling for 40 cycles of 95°C, 15 seconds; 60°C, 1 minute. Amplifications were performed in an ABI Prism 7000 machine (Applied Biosystems) for continuous fluorescence monitoring. Direct cycle sequencing was used to type one series of closely linked SNPs as detailed in Table \n5\n.\nFor each \nLMNA \nSNP the allele frequencies were defined and testing for Hardy Weinberg equilibrium was performed. Haplotypes at the LMNA locus were defined using the modified estimation-maximization algorithm implemented in the software package Haploview [\n17\n]. Following confirmation that specific SNPs did not segregate independently but were in linkage disequilibrium with each other, the methods of expectation-maximization-based haplotype frequency estimation and permutation-based hypothesis testing were performed as previously described [\n18\n].\nKLOTHO \ngenotyping\nThe KL-VS allele was typed using modifications of the published conditions[\n12\n]. Sample DNA was amplified by PCR (sense primer 5'-GCCAAAGTCTGGCATCTCTA-3'; antisense primer 5'-TTCCATGATGAACTTTTTGAGG-3') under the following conditions: 95°C for 2 minutes, followed by 35 cycles of 94°C for 30 seconds, 60°C for 30 seconds, and 72°C for 1 minute, followed by a 20 minute 72°C final extension. PCR products were then digested with \nMae\nIII (Roche) at 55°C for 16 hours and electrophoretically separated on a 2% agarose gel. The KL-VS allele is characterized by diagnostic \nMae\nIII restriction fragments of 265 and 185 bp respectively. Allele frequencies were determined by gene counting.\nStatistical analyses\nContinuous variables are presented as means ± SD. Baseline characteristics were compared using the Student's unpaired \nt \ntest for continuous data and the Chi-square or Fisher's exact test for categorical data. Single-locus tests of association between either SNP allele frequencies or SNP genotype frequencies and case-control status were carried out using standard contingency Chi-square tests. Based on the method of Chapman and Nam and assuming an allele frequency of 0.20, our study design has 93% power to detect a difference in allele frequency of 1.8 times or more at α = 0.05 [\n19\n].\nResults\nSubjects\nDuring the study period we enrolled 295 subjects with premature CAD and 145 controls. The premature CAD cohort, as expected, exhibited a higher proportion with diabetes mellitus, hypertension, and smoking (see Table \n1\n). In addition, the premature CAD cohort was younger and more likely to be obese. Self-reported ethnicity was similar between the two cohorts.\nLMNA \ngenotypes\nTwo SNPs (rs3204564 and rs536857) that were not in Hardy Weinberg equilibrium were not included in subsequent analyses. Median spacing of the SNPs was 1,206 bp apart with a range of 146 bp to 7,063 bp (SNPs rs568035 and rs568036 are adjacent to each other). Haplotype analysis revealed the presence of 6 haplotypes, with the most frequent occuring at an overall frequency of 43.8% (see Figure \n1\n and Table \n2\n). Haplotype allele frequencies did not differ significantly between patients and controls. Subsequently each individual SNP was tested independently for association with premature CAD. No significant difference in allele frequency for any SNP in the \nLMNA \ngene was observed between the control and patient groups (see Table \n3\n). In analyses adjusting for age, BMI, gender, hypertension, diabetes mellitus, statin use, and smoking history we did not observe any significant associations.\nKLOTHO \ngenotypes\nPrevious studies have documented the heterozygote carrier frequency for the KL-VS allele to be between 20 to 30% and the homozygosity frequency to be between 1 to 4% [\n12\n]. The allele distribution is very similar in our patient and control cohorts, and no significant difference in allele frequencies was observed between these groups (see Table \n4\n). The frequency of the KL-VS allele was 14.0% in patients with premature CAD compared to 18.2% in the control population (p = 0.09).\nDiscussion\nWe hypothesized that common variation at the \nLMNA \nor \nKLOTHO \nloci might result in typical forms of coronary disease in the absence of progeroid syndromes. We tested not only the hypothesis that alleles of \nLMNA \nor \nKLOTHO \nwould be associated with premature CAD (a population enriched for inherited contributions), but also pre-specified that such premature vasculopathy might be associated with an excess of homozygosity at the \nLMNA \nlocus. Our data suggest that, within the constraints of the current study, there is no association between common variation in the aging genes \nLMNA \nor \nKLOTHO \nand rigorously defined premature CAD. Further, there was no evidence of excess homozygosity at the \nLMNA \nlocus, rendering a somatic \"two-hit\" mechanism at this locus less likely as a potential cause of CAD. These data contradict previous findings in smaller studies and emphasize the difficulties intrinsic to such genetic association studies.\nPossible explanations for contradictory findings\nGenetic association studies relating common or \"complex\" phenotypes in large patient cohorts may be the only method capable of unraveling small population-wide genetic effects, but these studies prove difficult to reproduce and are of limited utility in defining causation [\n20\n-\n24\n]. Several intrinsic limitations of genetic association approaches contribute to the disparity between our results and previous studies of the \nLMNA \nand \nKLOTHO \nloci including the low prior probability of any observed association, population stratification, and varying degrees of linkage disequilibrium with neighbouring genes [\n20\n,\n25\n]. One of the most difficult potential confounders is underlying etiologic heterogeneity, magnified by the relatively low resolution of many traditional clinical phenotypes[\n24\n]. Clearly, not all CAD is caused by the same mechanism, and there is variation in the biologic behaviour of the various syndromes, ranging from occult chronic ischemia through to ischemic sudden death. The heritable basis for each of these components in the \"spectrum\" of CAD may be quite distinct. This phenotypic heterogeneity remains an important issue despite our rigorous use of coronary angiographic diagnoses. Our control population was older and had a male predominance, both known cardiovascular risk factors. The patient population had a higher prevalence of diabetes mellitus, hypertension, and smoking. This is not unusual as most patients with CAD already have documented cardiovascular risk factors [\n26\n], and it is conceivable that many 'risk factors' are actually manifestations of subclinical forms of vascular disease. By excluding patients presenting with undifferentiated chronic stable CAD we hoped to minimize the phenotypic heterogeneity. Nevertheless, it remains possible that the progeroid genes we have studied are associated with a particular subset of CAD, but not with premature disease presenting as acute coronary syndromes.\nAdditional factors also may explain our findings. Our study would not have detected somatic mutations present only in the vessel walls. While this is relatively unlikely given the common progenitors shared by hematologic and endothelial lineages, mutations restricted to more differentiated cells may not be detectable. The association between the \nKLOTHO \ngene and premature atherosclerosis seen in the study by Arking, et al.[\n13\n] may reflect a chance relationship between reduced survival from other causes and a common trait, but by studying acute syndromes we may have selected a distinct subset of disease in which the effects of \nKLOTHO \nhave been diluted.\nStudy limitations\nOur study has several intrinsic limitations. The control population did not undergo invasive clinical testing to definitively exclude CAD, but nonetheless had extensive non-invasive evaluations including echocardiography. The genotype frequencies observed suggest that the current study is adequately powered to detect a risk ratio of 1.8 or more [\n22\n], but would be unlikely to detect smaller population wide effects or large effects from rare alleles. The contributions of rare alleles would be better addressed using a family based strategy[\n27\n].\nFuture genetic studies in CAD\nAssociation studies remain controversial and our current study demonstrates some of the problems encountered with this approach. Despite rigorous phenotyping, detailed haplotyping and adequate power to detect a genetic effect of similar magnitude to that seen in previous studies of CAD, we did not see any significant differences in genetic architecture between our study and control populations. We have therefore demonstrated that genes associated with the progeroid syndrome are not likely to have a major effect on the development of premature atherosclerosis, despite a clear biological rationale.\nIn spite of the heterogeneity of CAD, insights from rare Mendelian variants have proven broadly applicable. The identification of new pathways through such familial forms of CAD will contribute to our understanding of all forms of vascular disease[\n2\n,\n3\n]. Linkage based family analyses are likely to yield more robust results than association studies and we believe increasingly will be used in future studies on the genetics of CAD. Some disorders undoubtedly result from more common ancient alleles, and understanding the basic haplotype structure of the human genome will facilitate their identification[\n28\n]. However, the genetic dissection of common conditions will require much more finely textured phenotypes than those traditionally employed in clinical medicine[\n24\n].\nConclusion\nCommon variants in aging syndrome genes previously implicated in CAD are not associated with rigorously defined premature acute CAD. This negative finding may reflect the specific phenotypes tested and highlights one of the major limitations of genetic association studies, the phenotypic heterogeneity of most 'common' diseases.\nAbbreviations\nCAD-coronary artery disease\nLMNA-lamin A/C\nHGPS-Hutchison Gilford Progeria Syndrome\nSNP-single nucleotide polymorphism\nConflict of interest\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nAFL was involved in the study design, carried out the molecular genetic studies, participated in the sequence analysis and drafted the manuscript. SK, PTE, CUC, SYS, BE and CAM, participated in the recruitment of subjects. CAM and COD participated in the design of the study and performed the statistical analysis. CAM and COD conceived of the study, and participated in its design and coordination and helped to draft the manuscript. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
53
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe effect of motor control exercise versus placebo in patients with chronic low back pain [ACTRN012605000262606]\n\n**Article Abstract:**\n\nBackground\nWhile one in ten Australians suffer from chronic low back pain this condition remains extremely difficult to treat. Many contemporary treatments are of unknown value. One potentially useful therapy is the use of motor control exercise. This therapy has a biologically plausible effect, is readily available in primary care and it is of modest cost. However, to date, the efficacy of motor control exercise has not been established.\nMethods\nThis paper describes the protocol for a clinical trial comparing the effects of motor control exercise versus placebo in the treatment of chronic non-specific low back pain. One hundred and fifty-four participants will be randomly allocated to receive an 8-week program of motor control exercise or placebo (detuned short wave and detuned ultrasound). Measures of outcomes will be obtained at follow-up appointments at 2, 6 and 12 months after randomisation. The primary outcomes are: pain, global perceived effect and patient-generated measure of disability at 2 months and recurrence at 12 months.\nDiscussion\nThis trial will be the first placebo-controlled trial of motor control exercise. The results will inform best practice for treating chronic low back pain and prevent its occurrence.\n\n**Article Body:**\n\nBackground\nThe problem of chronic low back pain\nLow back pain is the main cause of work absence and disability in industrialised societies. Approximately 10–20% of patients with low back pain develop chronic pain, defined as pain persisting for more than 3 months. Additional to their pain these patient's health problems typically include reduced physical function and psychological distress[\n1\n]. These patients use more than 80% of health care resources for back problems, and treatment has a low success rate [\n2\n].\nIn 2002, \narthritis and musculoskeletal disorders \nwere announced as the new National Health Priority Area in recognition of the major health and economic burden that these diseases place on the Australian community [\n3\n]. Amongst this group of diseases back pain is both the most prevalent and most costly single disease [\n4\n]. The 2001 National Health Survey revealed that \nchronic back pain \nis the most prevalent illness from the seven National Health Priority Areas [\n5\n].\nThe severity of chronic pain can be described with four hierarchical grades, Grades I–IV, that consider the pain intensity and the degree of disability associated with the pain [\n6\n]. An Australian population-based survey, noted that 22% of respondents reported chronic pain with 39% of respondents classed as Grade I (least severe), 35% as Grade II, 14% as Grade III and 13% as Grade IV (most severe) [\n7\n]. The most common cause of chronic pain was low back pain (45% of cases).\nEffectiveness of treatments for chronic low back pain\nWhile there are a myriad of treatment options for chronic low back pain, there is only one clinical practice guideline for chronic non-specific low back pain: The European Guideline[\n8\n]. This guideline and the relevant Cochrane reviews [\n9\n] provide the most reliable sources of evidence on treatment for this condition. Unfortunately the Cochrane reviews provide fairly bleak reading for both clinicians and patients. Most of the reviews (7/13) concluded that the treatment under review was of unknown value. Five of the thirteen reviews concluded that there was some evidence for the treatment under review however significant limitations for each treatment were noted. These limitations included: no long term effect (e.g. back school); serious side effects (e.g. muscle relaxants); small effect size (e.g. massage); treatment improves outcomes other than pain (e.g. work conditioning) and no information available on patient or dose selection (e.g. behavioural treatment). The European Guideline produced similar conclusions [\n8\n]. In only one Cochrane review, the review of multidisciplinary rehabilitation/functional restoration, did the reviewers conclude that there was strong evidence for the therapy. However the reviewers also noted that these programs were only effective when they included >100 hours of therapy. Because these programs are multidisciplinary they are typically provided in a tertiary setting and because of the amount of time involved they are also very expensive. Accordingly functional restoration is usually reserved for the most severe cases of chronic low back pain.\nThe majority of patients with chronic low back pain has less severe pain (i.e. Grades I–III) and are typically managed in primary care. Not surprisingly clinicians find managing chronic low back pain difficult with qualitative research reporting that therapists' inability to identify effective treatment choices for their patients makes them state clinicians perhaps feel 'helpless' 'disillusioned' and 'pessimistic' [\n10\n]. Studies of patients reveal similar negative feelings and emotions [\n11\n].\nTo address this major problem, we plan to begin a coordinated program of research in which treatments that seem most promising are rigorously evaluated in randomised controlled trials. We define 'most promising treatments' as those that (i) appear to have clinically important effects that are maintained in the long term, (ii) are readily available and of modest cost and (iii) there is biological plausibility for the effect. Exercise therapy is our first candidate for evaluation in this program of research because it satisfies each of these three criteria, however at present trials have reported conflicting results.\nWhile some trials of exercise therapy have reported large, durable and clinically important effects of treatment [\n12\n,\n13\n] others have not [\n14\n]. The uncertainty is reflected in the conclusion of the Cochrane review of exercise therapy: '...there is conflicting evidence on the effectiveness of exercise therapy...' [\n15\n]\nMany factors are likely to have contributed to the inconsistent results across trials. Importantly, interpretation of the results of exercise trials is difficult because most trials have been pragmatic trials, comparing two active treatments delivered in routine practice (e.g. \nexercise \nvs. \nusual medical care \n[\n12\n]; \nexercise \nvs. \nphysiotherapy \n[\n16\n]) These comparisons cannot provide a clear estimate of the effects of exercise treatment because most of the comparison treatments are also of unknown efficacy. Secondly, there has been insufficient appreciation by researchers conducting trials and by reviewers summarising trials of the wide variety of forms exercise can take and also trials do not control the quality of exercise intervention. While exercise is typically regarded as a single class of treatment we believe that this level of conception is inappropriate and analogous to not distinguishing between different classes and doses of drugs when prescribing medication. The types of exercise programs for chronic low back pain vary widely from land-based exercise versus exercise in water to isolated trunk exercise versus a walking program and it is unlikely that all programs are equally effective for all patients. Lastly, methodological quality varies greatly across previous exercise trials, for example in the Cochrane review [\n15\n] the least sound trial attended to none of the nine methodological criteria while the best attended to seven of the nine. Because methodological quality has been shown to affect the results of trials in other areas of health care [\n17\n] it is likely that a lack of rigor has contributed to the inconsistent results.\nIt is not sensible to talk about evaluating the efficacy of exercise without specifying the type of exercise. We have chosen to measure the efficacy of \nmotor control exercise \n(sometimes called specific spinal stabilisation exercise) for chronic low back pain, rather than other forms of exercise, because it is a widely used form of exercise and there is an extensive body of literature that provides a rationale for the mechanism of action. The only way to clearly establish the value of motor control exercise in the management of chronic low back pain is to evaluate the efficacy of this form of exercise therapy in a methodologically sound randomised placebo-controlled trial. Prior to conducting a placebo-controlled trial of exercise we felt that it was prudent to identify the most promising form of exercise that would subsequently be evaluated in the placebo-controlled trial. To do this we conducted a randomised controlled trial where 160 patients were randomised to an 8 week program of either motor control exercise or general exercise[\n18\n].\nThe trial demonstrated that both programs were accompanied by large improvements in pain and disability. Motor control exercise produced significantly better outcomes in the short term, and there was a trend for motor control exercise to produce better outcomes at 6 month follow-up. Accordingly we have chosen to evaluate motor control exercise in the proposed trial. Our choice coincides with the research agenda set by the 2004 European Guideline: \"The effectiveness of specific types of exercise therapy needs to be further evaluated. This includes the evaluation of spinal stabilisation exercises...\" [\n8\n] p 7.\nMotor control exercise: treatment rationale\nThe use of motor control exercise is based on research that has shown that:\n(i) People with low back pain have changes in the strategy for control of the trunk muscles in that activity of the deep muscles is impaired (delayed, less tonic) and these muscles are atrophied[\n19\n,\n20\n].\n(ii) Although all muscles contribute to control of movement and stability of the spine, the deep muscles have a critical role for control of intervertebral motion [\n21\n-\n25\n], but with the potential advantage of allowing dynamic control of the spine.\n(iii) Evidence that people with back pain tend to adopt a strategy for increased stiffness and stability at the expense of spinal function [\n26\n].\n(iv) Non-resolution of changes in the deep muscle system is linked to recurrences of low back pain [\n27\n].\nThe evidence above underpins the primary aim of motor control exercise, which is to re-establish normal control of the deep spinal muscles, reducing the activity of more superficial muscles that tend to stiffen the spine and have increased activity in low back pain, and then maintain normal control during progressively more demanding physical and functional tasks[\n28\n].\nThe key feature of the motor control exercise approach is the training of the deep trunk muscles in isolation \nbefore \nprogressing to demanding tasks that train coordination of the deep and the superficial trunk muscles [\n28\n]. However, unlike functional restoration approaches, training the deep trunk muscles in isolation from the superficial trunk muscles is difficult. In order to teach patients how to contract the deep muscles of the spine, in addition to clinical skills of palpation and observation [\n29\n] physiotherapists need to use technical devices such as pressure monitors, electromyography and ultrasound imaging to provide feedback to the patient.\nThe premise of the motor control approach is that simple functional exercise alone does not re-establish coordination of the trunk muscles. This premise is supported by the finding that the adaptation of these muscles to pain is still present following recovery from an episode of low back pain, when patients have returned to normal functional levels [\n19\n,\n20\n]. Furthermore, recent data confirm that coordination of the abdominal muscles can be restored with training of specific activation of the trunk muscles, but not a simple activation during a sit up task [\n30\n]. Notably, non-resolution of muscle dysfunction is associated with increased back pain recurrence [\n27\n]. Also, asymptomatic people with normal activity levels who are unable to perform a task that is thought to reflect voluntary activation of the deep trunk muscles, are ~6 times more likely to develop back pain than asymptomatic people who are able to perform the same task [\n31\n].\nMotor control exercise: level I and II evidence\nAt present there is no evidence for the efficacy of motor control exercise in the treatment of chronic low back pain. No systematic review of motor control exercise has been published, although one is being completed by our group. While the majority of trials (5 of 8) report that motor control exercise is effective in the management of chronic or recurrent low back pain most (7 of 8) have permitted co- intervention so that the contribution of motor control exercise is unclear. Additionally, all of these previous trials have used other treatments of unknown efficacy as the comparison intervention and so treatment efficacy cannot be measured. For example the earliest trial [\n12\n] reported that motor control exercise is more effective than usual medical care however this result provides an ambiguous estimate of treatment effectiveness because other trials have reported that sham physiotherapy treatments are more effective than usual medical care [\n32\n].\nWe will evaluate the efficacy of motor control exercise in a placebo-controlled randomised controlled trial. The results of our study will be invaluable for more efficacious evidence-based management of patients with non-specific chronic low back pain. Once efficacy is established, we will be able to progress to measuring whether there are additive or multiplicative effects of other treatments that are commonly administered as co-interventions with motor control exercise and thus to being able to make valid recommendations for their use.\nMethods\nOverview of research design\nThe study will be a randomised, blinded, placebo-controlled trial of a motor control exercise program for patients with chronic low back pain. The exercise program will consist of 12 individually supervised half-hour sessions over an 8-week period with treatment outcomes measured at 2 months, 6 months and one year.\nHypotheses\n(i) An 8-week motor control exercise program designed to restore control of the trunk muscles improves pain, disability and global perceived effect in participants with chronic low back pain at 2 months follow-up.\n(ii) The improvements in pain, disability and global perceived effect following motor control exercise are maintained at 6 and 12 months follow-up.\n(iii) At 12 month follow up recurrence is less in the motor control exercise group.\nSubject recruitment\nA total of 154 participants will be recruited into the study. Participants will be screened for suitability for motor control exercise according to usual clinical practice. The screening instruments identify participants who are unsuitable for exercise management of their low back pain because of significant co- morbidity (serious spinal pathology, contraindication to exercise). A clinical assessment will identify patients who we expect would best be managed by a motor control exercise program rather than some other form of exercise or physiotherapy management.\nScreening\nTo screen for serious pathology, the physiotherapist will conduct a diagnostic triage [\n33\n]. Participants in whom serious spinal pathology is suspected will be excluded from the trial and referred to their medical practitioner for review. Potential participants will be screened for contraindications to exercise using the Physical Activity Readiness Questionnaire [\n34\n]. If a volunteer provides a positive response to items 1, 2, 3, 4, 6 or 7, the trial physiotherapist will discuss the case with the referring medical practitioner and if necessary a medical review will be undertaken to exclude any contraindication to exercise as listed in the ACSM guidelines [\n34\n].\nThe clinical assessment used to ensure that the motor control approach is indicated is based on the key text [\n28\n] and is a normal part of clinical assessment of low back pain. The assessment involves evaluation of the motor control strategy during a specific trunk muscle task – drawing in of the lower abdomen while maintaining an isometric contraction of the medial back muscles. The following criteria constitute correct performance of the task:\n1. Moderate and sustained activation (> 10 seconds) of transversus abdominis\n2. Moderate and sustained activation (> 10 seconds) of the lumbar multifidus muscles\n3. Little or no activation of the global trunk muscles\n4. No spinal or rib cage movement.\n5. Normal breathing\nEvaluation of task performance including satisfaction of the above criteria is dependent on the clinical skills of the physiotherapist. Patients who are unable to perform this task correctly will be considered suitable for motor control exercise.\nParticipants will be included if they meet all of the following inclusion criteria:\n• Non-specific low back pain +/- leg pain of at least 3 months duration\n• Currently seeking care for low back pain\n• Aged greater than 18 and less than 80 years\n• Comprehends English\n• Clinical assessment indicates that the subject is suitable for motor control exercise\n• Expects to continue residing in SWSAH region for study duration.\nParticipants will be excluded if they have any of the following:\n• Suspected or confirmed serious spinal pathology (fracture, metastatic, inflammatory or infective diseases of the spine, cauda equina syndrome/widespread neurological disorder)\n• Suspected or confirmed pregnancy\n• Unable to speak English\n• Nerve root compromise (2 of strength, reflex or sensation affected for same nerve root)\n• Spinal surgery\n• Scheduled for major surgery during treatment or follow-up period\n• Any of the contraindications to exercise listed on page 42 of the ACSM guidelines [\n34\n]\n• Any contraindication to pulsed ultrasound or pulsed shortwave.\nSpecific spinal pathology or contraindication to treatment may be suspected based on the results of the screening questionnaire and the Physical Activity Readiness Questionnaire. If the assessor suspects the presence of any pathology or contraindication to treatment, these subjects should be further investigated and medical clearance obtained, if necessary.\nAssessment and allocation\nOutcome measures\nMeasures of outcomes will be obtained at follow-up appointments at 2, 6 and 12 months after randomisation. To maximise attendance at these follow-ups, appointments will be made by phone and then a letter will be sent confirming appointment and a reminder phone call will be made 24 hrs before the appointment. Every attempt (within ethical constraints) will be made to obtain outcome data, regardless of subject's compliance with trial protocols. Follow-up measures will be scored by an investigator who is blinded to group allocation. At 2 months, information about side effects of treatment will be collected from all participants using open-ended questioning.\nFollowing the screening consultation, personal characteristics (age, gender, ethnicity, religion, weight, height, level of education, employment status, doctor's details and contact information) and information about symptoms of low back pain will be collected (eg DASS 21 [\n35\n]; Chronic Pain Grade Questionnaire) The following treatment efficacy variables will be measured at baseline, 2, 6 and 12 months.\n1. Average pain intensity over last week (0–10 scale) [\n36\n-\n38\n]\n2. Patient-generated measure of disability (Patient-Specific Functional Scale) [\n36\n-\n38\n]\n3. Global perceived effect (Global Perceived Effect Scale) [\n36\n-\n38\n]\n4. Condition-specific measure of disability (Roland Morris Disability Questionnaire) [\n36\n-\n38\n]\n5. Recurrence at 12 months\nThe primary outcomes are pain, GPE and PSFS at 2 months and recurrence at 12 months.\nRandomisation\nParticipants will be allocated to treatment group using sealed opaque envelopes. The allocation sequence will be generated by author CM. Participants will be scheduled to receive their first treatment within one week of randomisation.\nInterventions\nContemporary physiotherapy practice in exercise prescription is to assess each patient and to implement the form of exercise that is most relevant to the particular clinical presentation. At present this widely accepted approach relies primarily upon the clinical expertise of the therapist. We have elected to evaluate motor control exercise delivered in this manner because this approach is regarded as contemporary best practice.\nParticipants in each group will receive 12 half hour treatments over an 8-week period, i.e. 2 sessions/week in the first month and 1 session/week in the second month. The treatment sessions are designed to become less frequent over time to encourage independence and continuation of exercise when therapy is complete. This is consistent with current clinical practice.\nThe \nmotor control exercise \nprogram is based on the treatment approach reported by O'Sullivan et al [\n12\n], Richardson et al [\n28\n], and Moseley [\n39\n]. A brief description is provided below.\nAt the first session, participants will be comprehensively assessed and then will be prescribed exercises aimed at improving function of specific muscles of the low back region to be conducted in sessions 2–11. Stage 1 involves the most commonly prescribed exercise aimed at retraining multifidus (a back muscle) and transversus abdominus (a deep abdominal muscle); these exercises will be supplemented with exercises for the pelvic floor muscles, breathing control and control of spinal posture. Participants will be taught how to contract these muscles independently from the superficial trunk muscles [\n28\n,\n40\n]. Physiotherapists will use real-time ultrasound biofeedback to enhance learning of the tasks. When participants are able to perform these exercises, they will be gradually upgraded until the patient is able to maintain isolated contractions of these muscles for 10 seconds, up to a maximum of 10 repetitions, during normal respiration [\n28\n]. When this level of competence has been achieved, patients will be considered ready to progress to Stage 2.\nStage 2 of the approach involves increasing the complexity of the exercise by progressing through a range of functional tasks and exercises targeting coordination of trunk and limb movement and maintenance of trunk stability. The range and progression of exercises is well set-out in clinical texts [\n28\n] and is individualised to the patient based on this presentation. Participants require the ongoing support of a trained physiotherapist to ensure correct performance of the exercises. Session 12 is a discharge session where the patient's progress will be reviewed and patients will be prescribed exercises to continue at home.\nThe \nplacebo \nintervention is 20 minutes of detuned short wave diathermy and 5 minutes of detuned ultrasound for 12 sessions over an eight week period. This attention control will be used because there is no known treatment effect from the detuned machines, but it has been established in previous trials (including one of our own [\n37\n]) that participants view this as a credible treatment. To increase the perceived credibility of the attention control, participants will undergo an examination including routine screening for contraindications at the first consultation and the normal clinical reassessment that would occur with the active forms of these interventions at each subsequent treatment. Each placebo treatment session will be 30 minutes in duration to match the active treatment sessions.\nParticipants in both treatment groups will be asked not to seek other treatments for their chronic low back pain and where possible not to change current medications during the treatment period. Several mechanisms will be used to ensure that the trial protocol is consistently applied. Protocol manuals will be developed and staff will be trained to ensure that screening, assessment, randomisation and treatment procedures are conducted according to protocol. To ensure standardisation across sites we will hold regular meetings with site visits and teleconferencing. An independent researcher will monitor a randomly chosen subset to ensure adherence to assessment, randomisation and treatment procedures.\nIf a participant is concerned about his or her condition during the study, the physiotherapist will screen for potentially serious pathology and, where appropriate, refer the patient to a medical practitioner. The medical practitioner will be asked not to request the participant's group allocation unless it is deemed necessary for medical care. At the completion of the exercise program, patients will be encouraged to continue the home exercise routine demonstrated at the discharge session. Participants will be free to seek other treatment after the experimental period.\nAfter the first treatment session the patient will complete a treatment credibility scale [\n41\n]. At the 8 week follow-up information about side-effects of treatment will be collected using open-ended questioning. At the 12 month follow-up the participants will be asked to rate the helpfulness, understanding and friendliness of therapist and helpfulness of treatment and to nominate which treatment they thought they received. Additionally information about other treatment received for their low back pain during the study period will be sought using open-ended questioning.\nData integrity\nThe integrity of trial data will be monitored by regularly scrutinising data sheets for omissions and errors. Data will be double entered and the source of any inconsistencies will be explored and resolved.\nData analysis\nTreatment efficacy\nIn our primary analysis, we will use a regression model to test for the effect of treatment on outcome at 2, 6 and 12 months follow-up with the baseline value of the outcome entered as a covariate. A treatment effect size will be calculated for each of the follow-up time points and, if there is a statistically significant treatment effect at any time point, we will also calculate number needed to treat (NNT) to achieve pain recovery (pain < 1 out of 10: [\n42\n]) and 95% CI. The recurrence outcome will be analysed with logistic regression.\nPredictor of response to treatment\nWe will include an interaction term baseline DASS-21 depression score × group to the regression analysis to see if the effect of motor control exercise is influenced by the baseline DASS-21 depression score.\nSample size calculations\nWe have designed the study to detect a clinically important difference of 1 unit on the 0–10 pain intensity scale (estimate for SD = 2.00), 1 unit on the 0–10 patient specific functional scale (estimate for SD = 1.8); 1 unit on the 0–10 Global Perceived Effect Scale (estimate for SD = 1.65) and 4 units on the 24 item Roland Morris Disability Questionnaire (estimate for SD = 4.9). We have taken the SD estimates from a trial we completed that recruited a similar patient cohort[\n37\n] With specifications of alpha = 0.05, power = 0.80 a sample size of 77 participants per group is required to detect an effect size of 0.50 SD (the smallest effect size we have specified for the four outcomes). Based on the results of the same trial [\n37\n] we have allowed for 15% non-compliance with treatment, 15% loss to follow-up, and assumed a correlation between baseline and change scores of outcomes of 0.5. Accordingly we will recruit 77 participants per group or 154 participants in total.\nJustification of study design\nPlacebo\nDesigning an appropriate placebo treatment that mimics a physiotherapy exercise program is challenging. The sham interventions used in previous exercise trials do not satisfy the criteria of being both inert (e.g. the use of hot packs) and credible (e.g. allocation to a treatment waiting list). Accordingly, we will use sham electrotherapy as a control. This sham is clearly inert and is regarded as a credible treatment by participants. [\n37\n] To ensure that participants remain unaware of study group, it is necessary to carefully describe the study to patients. In the previous trial where we used sham electrotherapy as a control for exercise, we used the following description:\n'In this trial normal physiotherapy treatment and placebo physiotherapy treatment will be provided. A placebo treatment is a harmless treatment delivered at less than the effective dose. We will not tell you which type of treatment you will receive and it is unlikely that you could distinguish them.'\nTrial staff described the placebo intervention as 'pulsed ultrasound' and 'pulsed shortwave' and explained to patients that they would probably not feel any sensation during treatment.\nControlling bias\nThe trial has been designed to include key methodological features that have been recognised as minimising bias in clinical trials. These features include: true randomisation, concealed allocation, specification of eligibility criteria, blind outcome assessment, patient blinding, blind analysis and intention-to-treat analysis. The nature of the treatments precludes blinding of treatment provider. Trial staff will be trained to ensure consistency of screening, assessment, randomisation and treatment procedures. Participant's perception of the credibility of treatment will be determined after the first treatment [\n41\n]; and at the completion of treatment both assessors and participants will be asked to identify what treatment they think the participant received.\nOutcomes\nMeasures of pain symptoms, disability and generic health status will be taken from the 'core set' of outcome measures for clinical research recently advocated by an international panel of back pain researchers [\n43\n]. The panel considered factors such as reliability, validity and responsiveness before recommending a measure. We have supplemented the back-related disability measure advocated in the core set (Roland Morris) with a patient-generated measure of disability (Patient-Specific Functional Scale) because there is evidence that patient-generated measures of disability are more responsive than condition-specific measures [\n37\n,\n44\n].\nConclusion\nWe have presented the rationale and design of a randomized controlled clinical trial evaluating the effect of motor control exercise versus placebo in patients with chronic LBP. The results of this trial will be published as soon as they are available.\nCompeting interests\nAll author(s) declare that they have no competing interests.\nAuthors' contributions\nCGM, JL, PWH, KMR, GLM, RDH and LOPC were responsible for the design of the study. LOPC and JM will act as trial coordinators. All authors have read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
54
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nManipulative therapy and/or NSAIDs for acute low back pain: design of a randomized controlled trial [ACTRN012605000036617]\n\n**Article Abstract:**\n\nBackground\nAcute low back pain is a common condition resulting in pain and disability. Current national and international guidelines advocate general practitioner care including advice and paracetamol (4 g daily in otherwise well adults) as the first line of care for people with acute low back pain. Non-steroidal anti-inflammatory drugs (NSAIDs) and spinal manipulative therapy (SMT) are advocated in many guidelines as second line management options for patients with acute low back pain who are not recovering. No studies have explored the role of NSAIDs and/or SMT in addition to first line management for acute low back pain. The primary aim of this study is to investigate if NSAIDs and/or SMT in addition to general practitioner advice and paracetamol results in shorter recovery times for patients with acute low back pain. The secondary aims of the study are to evaluate whether the addition of SMT and/or NSAIDs influences pain, disability and global perceived effect at 1, 2, 4 and 12 weeks after onset of therapy for patients with significant acute low back pain.\nMethods/design\nThis paper presents the rationale and design of a randomised controlled trial examining the addition of NSAIDs and/or SMT in 240 people who present to their general practitioner with significant acute low back pain.\n\n**Article Body:**\n\nBackground\nLow back pain is a common condition with lifetime prevalence rates reported between 59 and 84% [\n1\n]. On any given day 12–33% of people report some back pain [\n1\n]. A recent review on the health of Australians placed back problems as one of the three health conditions responsible for the greatest health system expenditure [\n2\n]. Not only is back pain common and costly to the health system but an episode of acute low back pain can be seriously disabling and distressing for the patient. In many cases the patient cannot undertake, or is severely restricted in, normal work and home duties. While it is commonly believed that the majority of people with acute low back pain recover spontaneously within 4–6 weeks a recent systematic review of the prognosis of acute low back pain [\n3\n] did not find evidence of this. On average, people with acute back pain experience substantial improvements in the first month: pain and disability are reduced by 58% of initial values and 82% of patients have returned to work. Further but smaller improvements occur up to three months, after which pain and disability levels remain nearly constant.\nA recent review of international guidelines [\n4\n] for the treatment of acute non-specific low back pain showed clear agreement on the appropriate first line of care. Each guideline recommended that the first line of care should be provision of advice and simple analgesic medicines. Advice includes reassuring the patient of a favourable prognosis, encouraging the patient to stay active and discouraging bed rest. It is recommended that medication should be taken in a time contingent manner and paracetamol (4 g daily) is suggested as first line choice due to its low risk of gastrointestinal side effects in otherwise well adults.\nEach of the guidelines also recommended that if first line management options provide insufficient pain relief then additional therapies could be considered. However, there is no clear agreement on what the second line management options should include or at what time it/they should begin. All the guidelines endorsed the appropriate use of NSAIDs but only some guidelines (8 of 11) endorsed spinal manipulative therapy (SMT).\nResearch to date has primarily addressed the issue of whether SMT and/or NSAIDs are more efficacious than placebo, however, this question does not reflect contemporary evidence-based practice in the management of low back pain. For the practitioner following the available guidelines the salient question is whether either of these two treatments are effective when delivered in addition to first line care universally endorsed in the low back pain treatment guidelines.\nThe recent Australian National Health and Medical Research Council (NHMRC) acute low back pain guidelines 2003 [\n5\n] conclude that there is conflicting evidence in this patient group that spinal manipulation provides greater short term pain relief when compared to placebo. Subsequent to the completion of these guidelines, three systematic reviews evaluating the role of SMT in back pain management have been published [\n6\n-\n8\n]. Each review concludes that spinal manipulation provides a greater reduction in pain and disability than inactive or ineffective therapies, with all trials providing similar estimates for the size and precision of the treatment effect (approximately 18 points of pain relief measured on a 0–100 point scale;95%CI 13–24) [\n6\n].\nThe issue of whether spinal manipulation is more effective than placebo in patients who receive general practitioner (GP) advice and paracetamol as first-line care was not directly investigated in these systematic reviews. However, in the study by Curtis et al [\n9\n] all patients received guideline-based care (advice and paracetamol) with half randomised to also receive a course of spinal manipulative therapy. Furthermore, Curtis et al [\n9\n] reported that a greater proportion of the manipulative therapy group completely recovered after the first visit compared with the control group: 14% versus 6% (P = 0.01). Patients who received more intense manipulative therapy (four or more treatments) had more rapid return to functional recovery (7.8 days) compared with those who received less treatments (11.1 days; P = 0.02). However this study did not include an inactive manipulation intervention and thus it is possible that the results are influenced by intervention bias as a result of the more frequent patient-practitioner contact in the group who received spinal manipulation.\nThe Cochrane Review on the role of NSAIDs in the management of low back pain [\n10\n] located nine studies comparing NSAIDs to placebo and concluded that NSAIDs were effective for short-term symptomatic relief in patients with acute low back pain. Furthermore, the review concluded that there was strong evidence that various types of NSAIDs are equally effective [\n10\n]. Subsequent to this review one study has shown that aceclofenac provides similar results to diclofenac [\n11\n] and another study has suggested temporal differences in analgesia produced by diclofenac pain relief when compared to ibuprofen or placebo [\n12\n]. However, no studies have examined whether the addition of NSAIDs to standard first-line care produced greater benefit than standard first-line care alone or whether there is an additive effect of manipulative therapy and NSAIDs.\nIn summary, there is high quality level I evidence that both SMT and NSAIDs are more efficacious than placebo treatments in patients with acute low back pain who receive no additional care. This evidence is of limited use to GPs managing patients with acute low back pain according to the widely accepted first line care. The most important clinical question is whether NSAIDs and/or spinal manipulation are effective when delivered in addition to the first line of care. At present there is no high quality evidence for this. In 2003, the NHMRC clinical practice guidelines for the evidence-based management of acute low back pain identified the need for research into the use of NSAIDs and spinal manipulative therapy and recommended testing these interventions in well-designed randomised controlled trials (RCTs) with 'advice to avoid bed rest and maintain usual activities' as the appropriate comparator [\n5\n].\nThe primary aim of this study is to investigate whether the addition of SMT and/or NSAIDs to GP advice and paracetamol results in shorter recovery times for patients with significant acute low back pain. The secondary aims of this study are to evaluate whether the addition of SMT and/or NSAIDs to GP advice and paracetamol influences pain, disability and global perceived effect at 1, 2, 4 and 12 weeks for patients with significant acute low back pain.\nMethods\nThis randomised controlled trial will be conducted at approximately 20 general practice clinics and 10 private physiotherapy clinics within Sydney, Australia. Ethics approval has been gained from the University of Sydney Human Research Ethics Committee.\nStudy population\nTwo hundred and forty participants with a new episode of significant acute non specific low back pain who present to GPs will be recruited. GPs will screen potential participants to ensure they satisfy the inclusion and exclusion criteria and will provide participants with an information sheet. The GP will then contact one of the researchers by phone and pass on the patient's contact details. The researchers will then organise an appointment within two days (excluding Sundays) to meet with the participant, formally enrol them in the trial if eligibility is confirmed at which time they will be randomised to a treatment arm of the study.\nInclusion criteria\nTo be eligible for the trial participants must meet all of the following criteria as assessed by the GP:\n• Primary complaint of pain extending in an area between the 12\nth \nrib and buttock crease. This may or may not be accompanied by leg pain.\n• New episode of low back pain. This is defined as an episode which was preceded by a period of at least one month without low back pain where the participant was not consulting a health care practitioner or continuing with medication for their low back pain [\n13\n].\n• Pain of less than six weeks duration.\n• Low back pain severe enough to cause moderate pain and moderate interference with normal work including work outside the home and housework (as measured by adaptations of items 7 and 8 of the SF-36).\n• No known or suspected serious spinal pathology (metastatic, inflammatory or infective diseases of the spine, cauda equina syndrome, spinal fracture).\n• No nerve root compromise evidenced by at least two of the following (i) myotomal weakness, (ii) dermatomal or widespread sensory loss, (iii) hypo or hyper-reflexia of the lower limb reflexes.\n• Not currently taking NSAIDs.\n• Not currently receiving SMT.\n• No spinal surgery within the preceding six months.\n• No history of peptic ulcer.\n• No allergy to aspirin.\n• Not currently receiving anticoagulant therapy.\n• No serious co-morbidities preventing prescription of NSAIDs or paracetamol eg: cardiac, liver or renal failure.\n• No contraindications to SMT or NSAIDs\nEnrolment and baseline measures\nAt the first meeting with the researcher, baseline data will be collected from the participant. This will include contact details, personal details, outcome measures, and variables that will be assessed as predictors of response to treatment. Contact details for both the participant and a friend or relative who does not live with them will be collected to optimise follow up rates. Personal details recorded will include age, length of time symptoms have been present and the number of previous episodes of low back pain. The following baseline measures of outcome will be recorded:\n• Numerical pain rating scale on a 0–10 scale [\n14\n];\n• A back specific disability scale (Roland Morris Disability Scale) [\n15\n];\n• A patient specific measure of disability (Patient Specific Functional Scale)[\n16\n];\nTreatment allocation\nImmediately after completing baseline measures participants will be allocated into treatment groups. Prior to the start of the study a researcher not involved in data collection or analysis will develop a randomisation schedule and produce consecutively numbered sealed opaque envelopes containing each participant's allocation. Randomisation will be performed using randomly permuted blocks of 4, 8 and 12. The researcher will select the next numerical randomisation envelope and open it. This envelope will contain a plastic bottle with the active or placebo NSAIDs which will be given to the participant along with a consumer medicine information sheet for diclofenac. The participant's name will be fixed to the medication. Placebo tablets with an identical shape and colour (including dose form excipients and coating) are dispensed making it impossible for the researchers or participant to differentiate between the active and placebo NSAIDs. The randomisation envelope will also contain a second smaller envelope containing the participant's allocation into active or placebo SMT. The researcher will give this envelope to the treating physiotherapist to open after the researcher has left. The researcher will therefore remain blinded to allocation for the NSAIDs and SMT arms. Treating physiotherapists can obviously not remain blinded to SMT allocation however they will be trained to respond identically to all patients regardless of treatment group except for the treatment provided.\nPatients will be allocated to one of four treatment groups as follows:\n• Control group (placebo NSAIDs and placebo SMT)\n• NSAIDs group (active NSAIDs and placebo SMT)\n• SMT group (placebo NSAIDs and active SMT)\n• SMT and NSAIDs group (active NSAIDs and active SMT)\nTreatments\nAll participants in the study will receive standard care from their GP before baseline and allocation into a treatment group. Standard care in this study will involve advice and paracetamol (1 g four times daily), this being the first line of care advocated in both national and international clinical practice guidelines. Advice will include reassurance of a favourable prognosis and encouragement to avoid bed rest and stay active. Paracetamol will be prescribed at 4 gm per day (Two 500 mg tablets every 6 h). Paracetamol is to be continued at this dosage for a maximum of four weeks. If subjects recover before four weeks (zero or one out of ten pain for seven consecutive days) paracetamol will be stopped. All participants will also receive two follow up visits with their GP, one week and two weeks after their initial visit. At follow up visits GPs will reinforce the initial advice and ensure participants have no adverse reactions to the treatments. GPs will remain blinded to group allocation and instructed not to ask about the physiotherapy management.\nParticipants allocated to receive active or placebo NSAIDs (diclofenac) will be instructed to take them according to an identical schedule. Dosage will be 50 mg bd taken with food for a maximum of four weeks or until the participant has recovered (zero or one out of ten pain for seven consecutive days).\nParticipants allocated to receive SMT will receive treatment two or three times per week (at the therapist's discretion) for a maximum of 12 treatments over four weeks. If the subject recovers (zero or one out of ten pain for seven consecutive days) before four weeks the SMT will be stopped. Patients will receive spinal manipulative therapy according to a treatment algorithm developed by the researchers based on the views of expert clinicians and researchers in the field (\nAdditional file 1\n) [\n17\n-\n20\n]. The algorithm permits and excludes certain physiotherapy treatments. Consistent with contemporary best clinical practice, the physiotherapist will adjust the treatment to the clinical presentation of the patient rather than apply the same treatment to all patients (as per normal clinical practice). The algorithm however is sufficiently prescriptive to allow replication and accurate description of the trial treatment. All participants will be examined by the physiotherapist who will take a standard history and perform a physical examination that will include assessment of active range of lumbar spinal motion, routine tension tests (straight leg raise, passive neck flexion and prone knee bend), neurological examination (reflexes, muscle strength, sensation) when indicated and the application of manually applied postero-anteriorly directed forces to all levels of the lumbar spine. Based on findings from the examination the physiotherapist will initiate what they consider to be an optimal program of SMT within the guidelines of the study (\nAdditional file 1\n).\nSMT will be delivered by physiotherapists who have postgraduate training in manipulative therapy and who regularly use manipulative therapy in their clinical practice. Participating physiotherapists will be supplied with documentation defining their role in the trial and will undergo one hour of training from a researcher who is a physiotherapist. These physiotherapists will have as minimum training a Graduate Diploma in Manipulative Physiotherapy and two years clinical experience using manipulative therapy techniques.\nTherapists will be asked to keep a record of the number of times the participant attended for SMT and details of the treatment including the techniques and dosage. These will be used to ensure compliance with the protocol and to help describe the treatment given in this study.\nPlacebo SMT will be prescribed using exactly the same schedule as active SMT. The placebo therapy used will be detuned ultrasound (US). The detuned US will be performed in a manner that mimics real US around the area involved for 5–12 minutes. Treatment sessions will last for the same time as for active SMT (30–40 minutes for the initial assessment and treatment and approximately 20 min for follow up sessions). Follow ups will include reassessing the participant's history and physical examination findings however no palpation of the spinal joints will be performed after the initial assessment. A re-evaluation of pain or range of motion will be done after the placebo treatment. In this way we will achieve close matching of the active and inactive interventions in terms of treatment duration and patient/therapist contact.\nPatients will be asked not to seek other treatments for their low back pain during the treatment period. In cases where this is unavoidable a record of additional treatments will be kept (and these patients may be excluded from the per protocol but not intention to treat analysis depending on the nature of the treatment). Several mechanisms will be used to ensure that the trial protocol is consistently applied. Protocol manuals will be developed and all involved researchers (general practitioners, manipulative physiotherapists, trial manager and outcome assessors) will be trained to ensure that screening, assessment, random allocation and treatment procedures are conducted according to protocol. An independent researcher will monitor adherence to assessment, randomisation and treatment procedures in a random group of participants.\nAfter four weeks all interventions will cease and participants will be asked not to seek other treatment before the three month follow-up if possible. Participants who do have further treatment will be asked to record the type and amount received.\nOutcome measures\nOutcome measures will be recorded by an assessor blinded to group allocation. Outcome measures will be collected using both a daily pain diary completed by the participants and weekly phone follow-ups for the first four weeks and at three months.\nThe primary outcome is the number of days to recovery, with recovery defined in two ways. Firstly recovery is defined as a pain score of 0 or 1 on a 0–10 pain scale (numerical pain rating scale) that is maintained for seven consecutive days. Secondly recovery is defined as the first day that the patient has a pain score of 0–1 on a 0–10 pain scale. To ensure a precise estimate of the time to recovery, subjects will complete a daily pain diary (completed either first thing in the morning or last thing at night determined by the participant) until recovery. To minimize potential for lost data pain scores from the diaries will be read to the researcher at each of the phone follow ups. The researcher will then transcribe these into a second participant record. Diaries will be kept until the patient has scored 0 or 1 out of 10 for seven consecutive days or for a maximum of three months.\nThe secondary outcomes are pain (numerical pain rating scale) [\n21\n], disability (Patient Specific Functional Scale[\n16\n] and Roland Morris Disability Questionnaire [\n15\n]), global perceived effect and satisfaction/beliefs about treatment [\n22\n]. Secondary outcomes will be recorded at baseline, 1 week, 2 weeks, 4 weeks and 3 months.\nCompliance with physiotherapy will be recorded by the treating physiotherapists. Compliance with the medications will be assessed by collecting unused medications at the end of the treatment period (4 weeks).\nData analysis\nData will be analysed by a statistician who is blinded to group status. The primary analyses will be by intention-to-treat and we will restrict the number of analyses in order to reduce the possibility of Type I errors. For primary outcomes, a p value of <0.05 will be considered statistically significant. For the secondary outcomes a p value of <0.01 will be considered significant.\nFor the primary outcome of days to reach recovery we will use survival curves with a log-rank statistic to assess differences between groups [\n23\n] and, if required, Cox's regression to assess the effects of treatment (group) status on hazard rates for time to recovery. In the primary analysis, number needed to treat (NNT) and the 95% confidence intervals to reach recovery in three months will also be calculated.\nFor secondary outcomes we will use a mixed model with group as a fixed factor. In these analyses, if there is a significant difference in secondary outcomes between treatment groups, we will conduct post-hoc analyses to inspect differences in secondary outcome variables at 1, 2, and 4 weeks and 3 months. We will also test for any additive or multiplicative effects between treatments on the outcome variables\nSample size\nSample size was calculated using equations for survival data. Two hundred and forty participants was determined to provide 80% power to detect a 20% difference in recovery rates between the control and intervention groups with an alpha level of 0.05. These calculations were based on a 50% recovery rate in the control group by three months. These numbers are probably conservative and based on results from our recent prognostic study of over 1000 subjects with acute low back pain. Higher rates of recovery will increase the statistical power. We allowed for 10% loss to follow up.\nConclusion\nWe have presented the rationale and design for an RCT examining the effects of SMT and/or NSAIDs on patients with significant acute low back pain. The primary outcome will be days to recovery and secondary outcomes include pain, disability and global perceived effect at 1 week, 2 weeks, 4 weeks and 3 months. The results of this trial will be available in 2007.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nMH, CM, JL, AM, CC, RD, MS and JM were responsible for the design of the study. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\nSupplementary Material\nAdditional File 1\nDescription of active SMT.\nClick here for file\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
55
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nPatients with suspected acute coronary syndrome in a university hospital emergency department: an observational study\n\n**Article Abstract:**\n\nBackground\nIt is widely considered that improved diagnostics in suspected acute coronary syndrome (ACS) are needed. To help clarify the current situation and the improvement potential, we analyzed characteristics, disposition and outcome among patients with suspected ACS at a university hospital emergency department (ED).\nMethods\n157 consecutive patients with symptoms of ACS were included at the ED during 10 days. Risk of ACS was estimated in the ED for each patient based on history, physical examination and ECG by assigning them to one of four risk categories; I (obvious myocardial infarction, MI), II (strong suspicion of ACS), III (vague suspicion of ACS), and IV (no suspicion of ACS).\nResults\n4, 17, 29 and 50% of the patients were allocated to risk categories I-IV respectively. 74 patients (47%) were hospitalized but only 19 (26%) had ACS as the discharge diagnose. In risk categories I-IV, ACS rates were 100, 37, 12 and 0%, respectively. Of those admitted without ACS, at least 37% could probably, given perfect ED diagnostics, have been immediately discharged. 83 patients were discharged from the ED, and among them there were no hospitalizations for ACS or cardiac mortality at 6 months. Only about three patients per 24 h were considered eligible for a potential ED chest pain unit.\nConclusions\nAlmost 75% of the patients hospitalized with suspected ACS did not have it, and some 40% of these patients could probably, given perfect immediate diagnostics, have been managed as outpatients. The potential for diagnostic improvement in the ED seems large.\n\n**Article Body:**\n\nBackground\nPatients with symptoms of acute myocardial infarction (AMI) or unstable angina pectoris (UA), i.e. an acute coronary syndrome (ACS), are very common in emergency departments (EDs). Because of diagnostic difficulties, a certain \"overadmission\" to in-hospital care for suspected ACS is usually accepted. The size of this overadmission is generally unknown, despite its negative influence on hospital efficiency and resource utilization. In order to reduce unnecessary admission, to optimize disposition of admitted patients and to decrease cost, chest pain units (CPUs) with risk-based diagnostic protocols have been established in many hospitals, primarily in the United States [\n1\n,\n2\n]. These CPUs have been shown to increase the efficiency of patient evaluation with a quality similar to that of traditional EDs [\n3\n,\n4\n].\nFor hospitals with traditional EDs, the benefits of establishing a CPU depend on the quality and outcome of current management, and on patient volume and risk spectrum. Such data are relatively rare, but have been reported from the 1980's from Gothenburg, Sweden [\n5\n,\n6\n], and from the mid-1990's from hospitals in the United States [\n7\n,\n8\n]. The quality of traditional patient management is constantly improving however, with therapeutic and diagnostic advances such as new antithrombotic drugs [\n9\n], ECG decision support software, remote ECG analysis [\n10\n], and the use of new combinations of blood tests for myocardial injury [\n11\n,\n12\n]. With generally improved cardiac care, the patient and risk spectrum in the ED are likely also continuously changing. Therefore, in order to plan and implement improved diagnostic strategies in suspected ACS, new and current data are clearly needed.\nThis study aimed to analyze current characteristics, disposition and outcome of patients with suspected ACS in a traditional ED, and to explore the basis for establishing a CPU. We will report that almost three out of every four patients hospitalized with suspected ACS did not have it, and that some four out of every ten admitted patients could, given perfect immediate diagnostics, have been treated as outpatients.\nMethods\nStudy design\nConsecutive patients presenting with symptoms compatible with an ACS were prospectively included during 10 days from September 26 to October 6, 2000. To reflect the true clinical spectrum of patients, a slightly modified version of the IMIR study criteria [\n13\n] was used for inclusion. Thus, all patients presenting with chest pain or discomfort, dyspnea without obvious pulmonary disease, acute heart failure, arrhythmia of possible ischemic origin and suspected cardiac syncope were included. Informed consent was obtained from all study patients.\nStudy setting and population\nLund University Hospital is a 1200 bed institution with fully public financing that serves a population of some 250,000, has a cardiac intensive care unit (CICU) with 19 beds and an intermediate care ward (ICW) with ECG monitoring at 16 beds. Problems with high bed occupancy have been common in recent years. Both balloon angioplasty (PTCA) and coronary bypass surgery (CABG) are offered 24 hours/day, and ECGs are regularly transmitted from ambulances to the CICU to start thrombolysis or to prepare for direct PTCA on arrival. A traditional ED is in operation with approximately 50 patients per day with problems related to internal medicine. There is no chest pain unit and no systematic diagnostic protocol for patients with suspected ACS. The Siemens Megacart ECG recorders (Siemens-Elema, Solna, Sweden) have the latest Siemens GRI decision support software installed. Serum CKMB mass and Troponin T tests are used for detection of myocardial injury and are available 24 hours.\nStudy protocol\nInclusion was performed by the primary assessing nurse and retrospectively reevaluated by one of the investigators (UE). Risk factors and previous cardiovascular disease were noted on a standard form. Data missing on the forms were collected via patient records or, if ambiguous, via telephone interviews with the patients. To be able to compare initial assessment and outcome, physicians on duty were asked to assign each patient to one of four risk categories based on the suspicion of ACS (modified from [\n5\n]) after history and physical examination, but before blood tests:\nI. Obvious AMI.\n Typical symptoms and ST-elevation with or without Q-waves on the ECG, or LBBB not known to be old.\nII. Strong suspicion of ACS. a.\n Typical symptoms without ST-elevation or Q-wave. \nb.\n Atypical symptoms with ST-T changes or LBBB not previously observed. \nc.\n History of unstable angina regardless of ECG. \nd.\n Acute heart failure or hypotension regardless of ECG. \ne.\n VT/VF or AV-block III.\nIII. Vague suspicion of ACS.\n Unclear symptoms and history, normal or non-ischemic ECG.\nIV. No suspicion of ACS. a.\n No suspicion of ischemic heart disease. \nb\n. Stable angina pectoris.\nEligibility for a potential CPU was estimated among low to moderate risk patients (see Results) with the following commonly used [\n3\n] exclusion criteria: tachy- (>110 bpm) or brady-arrhythmia (<40 bpm) of any sort, bilateral rales above lung bases (as a sign of heart failure), and inability to perform our standard bicycle ergometry stress test on the basis of muscle, joint or motor nerve problems.\nMeasurements\nPatient characteristics in the forms of presenting symptoms, risk factors and cardiovascular history were recorded, as well as the physician's immediate risk estimate, the patient's primary in-hospital bed assignment and the discharge diagnosis. In the immediately discharged, hospitalizations for ACS within 6 months, cardiac ischemic events (AMI and revascularisation) and mortality were monitored by reviewing medical records and by telephone calls to each patient. A diagnosis of AMI was made at a CKMB serum level > 10 μg/l or a Troponin T serum level > 0.06 μg/l in the absence of renal failure, and a typical rise and fall pattern on serial blood testing. Both analyses were performed with sandwich immunoassays using double monoclonal antibodies. For the results to reflect the quality of everyday medical service, there was no retrospective review of discharge diagnoses or risk classification, unless obviously wrong.\nData analysis and statistics\nIn the final analysis, less than 5% of all data were missing. Data are presented as means ± SEM. For statistical comparison, Student's t-test was used except when stated otherwise. Differences were considered significant at P < 0.05.\nResults\nOne hundred and fifty-seven patients with chest pain or other symptoms suggestive of ACS were included during the study period, making up 33% of all those presenting at the ED with internal medicine problems. The included women (n = 90) were on average slightly older than the men (n = 67), 64.4 ± 2.1 vs. 58.1 ± 2.1 years (p = 0.04). Symptoms, risk factors and cardiovascular history are given in table \n1\n. Eighty percent had chest pain or discomfort, 61% had ongoing symptoms in the ED, 42% and 32% had previously established ischemic heart disease in the forms of angina pectoris and AMI respectively, and one out of four had a previous PTCA or CABG. Overweight (body mass index >25) was equally common in men and women (34%).\nTable 1\nCharacteristics of 157 consecutive patients with suspected ACS in the ED of Lund University Hospital and comparison with previous surveys in Gothenburg [\n5\n] and the USA [\n7\n].\n%\nKarlson et al. 1991, n = 7157\nPope et al. 1998, n = 10700\nPain/discomfort, localisation\nChest pain/discomfort\n80\n93*\n76\nLeft arm\n34\nPain/discomfort elsewhere\n30\nPain/discomfort in ED\n61\nOther reason for inclusion\n20\nRisk factors\nFamily history of IHD\n46\nDiabetes\n12\n8\n21*\nSmoking\n17\n33*\nTreated hypercholesterolemia\n28\nOverweight (BMI>25)\n34\nHypertension\n32\n24*\nCardiovascular history\nAngina Pectoris\n42\n39\n37\nMyocardial infarction\n32\n24*\n26\nCABG/PTCA\n25\nIntermittent claudication\n5\nStroke\n8\nHeart failure\n12\n18*\n*P < 0.05 compared with the present data (z-test).\nPhysicians' risk estimates after history, physical examination and ECG, and admittance rates are shown in table \n2\n. At that point in time, a suspicion of ACS remained in 50% of the patients. The higher the judged risk of ACS, the older the average patient.\nTable 2\nRisk classification of patients after initial history, physical examination and ECG, but before blood samples. Modified after [\n6\n]. \nRisk categories\nn\n% of all\nAge (yrs)\n% admitted\n% of men\n% of women\nI.\nObvious AMI\n6\n4\n78.7 ± 3.8\n100\n6\n1*\nTypical symptoms and ST-elevation with or without Q-waves on the ECG, or LBBB not known to be old.\nII.\nStrong suspicion of ACS\n26\n17\n68.6 ± 2.2\n100\n13\n22\na) Typical symptoms without ST-elevation or Q-wave\nb) Atypical symptoms with STT changes or LBBB not known to be old\nc) History of unstable angina regardless of ECG\nd) Acute heart failure or hypotension regardless of ECG\ne) VT/VF or AV-block III\nIII.\nVague suspicion of ACS\n46\n29\n63.7 ± 2.2\n70\n27\n33\nUnclear symptoms and history, normal or nonischemic ECG.\nIV.\nNo suspicion of ACS\n79\n50\n55.0 ± 2.5\n13\n54\n43*\na) No suspicion of ischemic heart disease\nb) Stable angina pectoris\nAll included patients\n157\n100\n60.8 ± 1.5\n47\n100\n100\nACS, Acute coronary syndrome; LBBB, Left bundle branch block; VT/VF, ventricular tachycardia/fibrillation. *P < 0.05 compared to men.\nForty-seven percent of all included patients were admitted, 43% of the men and 53% of the women (n.s.). Primary in-hospital destinations, PTCA rates within 30 days and diagnoses at discharge in the different risk categories are shown in table \n3\n. In those admitted, there were no significant differences in the discharge diagnoses between men and women. Average time to discharge was 3.5 ± 0.4 days (median 2.0 days), and in categories I-IV hospital stays were 7.0 ± 1.4, 4.2 ± 0.8, 2.4 ± 0.4 and 3.0 ± 0.9 days, respectively.\nTable 3\nPrimary in-hospital destinations, PTCA interventions within 30 days of presentation and discharge diagnoses for the 74 admitted patients.\nRisk category\nAdmitted\nPrimary in-hospital destination (%)\nPTCA (%)\nDischarge diagnoses (%)\nW\nICW\nCICU\nTotal\nQMI\nNQMI\nUA\nAP\nCP NUD\nOther\nTotal\nI\n6\n-\n17\n83\n100\n17\n67\n33\n-\n-\n-\n-\n100\nII\n26\n-\n67\n33\n100\n30\n-\n11\n26\n22\n22\n19\n100\nIII\n32\n3\n81\n16\n100\n2\n-\n6\n6\n9\n34\n44\n100\nIV\n10\n50\n50\n-\n100\n0\n-\n-\n-\n10\n40\n50\n100\nAll\n74\n7\n68\n25\n100\n6\n5\n9\n12\n13\n28\n32\n100\nW, general ward; ICW, intermediate care ward; CICU, cardiac intensive care unit; PTCA, ballon angioplasty; QMI, Q-wave myocardial infarction; NQMI, non-Q-wave MI; UA, unstable angina pectoris; AP, stable angina pectoris; CP NUD, chest pain, unspecific.\nPatients with ACS as the discharge diagnose\nOf the 74 patients admitted, only 19 (26%) were diagnosed with an AMI or UA, i.e. an ACS (table \n3\n). Of these, 4 had Q-wave AMI, 7 non-Q-wave AMI (NQMI) and 8 UA. In risk categories I-III, ACS rates among the admitted patients were 100%, 37% and 12% respectively (table \n3\n). Of those admitted to the CICU (n = 18), the ICW (n = 51) and a regular ward (n = 5), 79%, 8% and 20% had ACS, respectively. There was no in-hospital mortality. A total of 10 patients underwent coronary angiography and 9 PTCA (table \n3\n) within 30 days of presentation, most of them from risk category II. The PTCA rate within 30 days was 43% in the patients with NQMI or UA; FRISC II criteria [\n14\n] for early revascularisation in unstable coronary disease were generally used.\nPatients without ACS as the discharge diagnose\nFifty-five patients (40%) of 138 without ACS were admitted. Of these 55, 17 patients were from risk category II, 28 from category III, and 10 (= all admitted) patients from category IV. Compared with the 19 patients with ACS, the patients without ACS were younger, 59.3 ± 1.7 vs. 70.8 ± 2.8 years (P < 0.05). In risk categories II and III, however, patients with and without ACS were of similar age: 67.4 ± 3.2 vs. 65.1 ± 1.9 years (n.s.). Surprisingly, at presentation 38% of all patients without ACS had pain in the left arm and only 6% of the patients with ACS (P = 0.01, z-test). In fact, in categories II and III no patients with ACS (n = 14) had left arm pain vs. 49% in those without ACS (n = 59; P < 0.01, z-test). Apart from this, there was no difference between patients with and without ACS regarding presenting symptoms, risk factors or history of cardiovascular disease or diabetes.\nOf the 55 patients who were admitted and did not have ACS, at least 20 (37%) did not have any other condition or diagnosis requiring admission. These \"overadmitted\" patients could thus, with perfect immediate diagnostics available, have been immediately discharged from the ED and managed in an outpatient setting.\nPatients discharged from the emergency department\nEighty-three patients were immediately discharged, all of them from risk categories III and IV. These patients were significantly younger than those admitted, 54.7 ± 2.3 vs. 67.4 ± 1.7 years (p < 0.001), more seldom had previous angina pectoris (30% vs. 54%, P < 0.01, z-test) or had a history of CABG or PTCA (16% vs. 33%, P < 0.05, z-test). No significant difference as to presenting symptoms between admitted and discharged patients was observed. During a 6 month follow-up, none were hospitalized with UA or AMI and only patient died; from lung cancer. One patient underwent a CABG planned from before the index visit.\nEligibility for a possible chest pain unit\nNine patients in category II had a normal or definitely non-ischemic ECGs at presentation, and only one of them had an ACS (UA). These 9 patients, together with all 32 admitted patients in risk category III were reviewed for CPU eligibility. At presentation, 8 (20%) of these 41 patients had tachy- or brady-arrhythmia, 2 (5%) had rales to indicate heart failure and 9 (22%) were unable to perform our standard bicycle stress test, and were therefore considered unsuitable for a CPU. A total of 29 patients (71%) did not meet any of these exclusion criteria and would thus be eligible for a CPU.\nDiscussion\nThe present survey includes data from 157 consecutive patients presenting at the ED of Lund University Hospital during ten days. Patient characteristics, ED physicians' estimates of risk of ACS, primary destinations in the hospital and discharge diagnoses are reported. Corresponding data from Sahlgrenska Hospital in Gothenburg, Sweden [\n5\n,\n6\n], and from several hospitals in the United States [\n7\n,\n8\n] have previously been reported. Judging by the number of patients with direct chest pain (80%), the inclusion criteria in this study was likely broader than in the Gothenburg study [\n5\n] but similar to those in the more recent American study [\n7\n]. Accordingly, the ACS rate among those admitted seemed higher in Gothenburg, probably being about 30–40%, than in the United States (23%) and in the present investigation (26%). Also, more patients seemed to develop an AMI in Gothenburg (at least 20%) than in the present (15%) and the American study (12%), which also perhaps could be explained by the use of older and less specific markers of myocardial injury (serum aspartate aminotransferase and creatine kinase), and/or an improved in-hospital therapy for unstable angina since the Gothenburg study.\nThe physicians' initial suspicion of ACS seemed to be a good predictor of patient outcome, although the number of observations were small (table \n3\n). As in previous investigations [\n6\n,\n7\n], only a small fraction (26%) of those admitted were diagnosed with ACS. For instance, of those admitted to the ICW, only four patients in 51 (8%) had ACS. In risk categories II and III, 63% and 88% of the admitted patients did not have ACS (table \n3\n). In some cases however, hospitalization might have prevented the development of ACS. For instance, patients in risk risk category II were often treated with aspirin, betablockers, low molecular weight heparin and sometimes also clopidogrel. A surprising finding was that in risk categories II and III no patients with ACS had pain in the left arm compared to 49% in the patients without ACS. We do not have a good explanation for this. The observation challenges prevailing clinical wisdom [\n15\n,\n16\n] and clearly needs to be confirmed in a larger study.\nIn further concert with previous surveys [\n6\n,\n7\n], a large proportion of patients were considered to be at very low risk and were immediately discharged. The discharge rate in the present study (53%) was higher than in Gothenburg and USA (34% in both, P < 0.001, z-test). Most immediate dismissals were correct, since among these patients there were no cardiac events at 6 months. Previous data [\n17\n,\n18\n] indicate that 2(-5)% of all patients with AMI, and more with UA, are erroneously being sent home from the ED, which would here correspond to one or two patients of the 83 discharged.\nTo decrease unnecessary admissions, erroneous discharge and overall cost, dedicated chest pain units (CPUs) have been established in many EDs, principally in the United States [\n1\n,\n2\n]. Randomized controlled trials on the value of these centers are so far very few [\n19\n-\n21\n], but the body of evidence indicates [\n3\n,\n4\n] that CPUs can introduce more effective patient management with a quality similar to that in traditional EDs. Cost savings have been reported per evaluated patient [\n3\n], but not yet at the hospital level. In the CPUs, patients typically undergo serial blood samples for markers of myocardial injury [\n22\n], serial or continuous ECG [\n23\n,\n24\n], echocardiography [\n25\n,\n26\n], exercise testing [\n27\n] and/or myocardial perfusion imaging [\n28\n], according to local practice. Focus in CPUs has been on the evaluation of low to moderate risk patients with a non-diagnostic ECG [\n29\n,\n30\n], which in the present study would probably correspond to all admitted patients in category III and perhaps the 9 patients in category II with normal ECGs. With commonly used exclusion criteria (Methods), almost 3/4 of these patients would be eligible for a CPU, corresponding to about 3 patients per 24 h. The number of patients suitable for a CPU can obviously vary with patient spectrum: In an inner-city ED in Chicago [\n31\n], only about 1/4 of the low-risk patients were considered eligible for a CPU protocol, albeit with the use of somewhat stricter exclusion criteria than here. For instance, 42% were unsuitable for a CPU because of inability to perform a stress test, compared to 22% in the present investigation.\nEven if some of the exclusion criteria would be modified in the present analysis, the number of patients would seem to be at the lower end of what is required for a cost-effective CPU. On the other hand, the current high occupancy and the high false admission rate in the ICW definitely favors the introduction of systematic risk-based accelerated diagnostic protocols in our ED. An attractive option might therefore be to supplement our conventional ED strategy with risk stratification algorithms [\n8\n,\n32\n] and selected investigations such as provocative testing or radionuclide perfusion imaging. In our ED, using the Goldman risk prediction algorithm [\n32\n] would clearly decrease CICU admissions since many of these patients did not meet the Goldman criteria for coronary care unit care: Clearly ischemic ECG and at least two of the following: Acute heart failure, hypotension or symptoms of unstable ischemic heart disease. Regarding perfusion imaging, a review of the patients in the present study suggested that in risk categories II and III, between one and two ED patients would be suitable for myocardial scintigraphy per 24 h, using the inclusion criteria normal ECG, ongoing symptoms, no previous MI and planned admission solely for suspected ACS. If image results would be as expected from the observed clinical courses, almost 8 out of 10 investigated would have had negative images and be candidates for discharge from the ED; The negative predictive value of myocardial perfusion imaging can be expected to be close to 100% in this patient population [\n33\n]. Theoretically, about 15 inpatient days could then be saved during the observation period. Yet another possibility to improve ED efficiency may be to have a general practitioner in the ED to evaluate patients considered to be at very low risk of ACS by e.g. the attending nurse. Patients with very low risk were frequent in the present survey: eighty-seven percent of the patients in risk category IV, corresponding to almost 7 patients per day, were sent home from the ED with no evidence of cardiac events at 6 months.\nLimitations and future questions\nThe present investigation includes a limited number of patients at a single hospital ED, and the results may thus not apply to other hospitals. On the other hand, consecutive patients were analyzed and few data were missing and the conclusions may therefore be reasonably valid for other hospitals of the same type. Other limitations of the present study were that seasonal variation in patient presentation was not considered, and that no serum markers of myocardial injury or ECGs were obtained after discharge. Hence, some cardiac events could have been missed in the follow-up. Whatever the case, the main results and conclusions of this investigation refer to in-patient care and outcome.\nFuture studies should among other things compare modern conventional ED management supplemented by risk prediction algorithms and/or selected investigations such as exercise stress testing [\n27\n] and myocardial perfusion imaging [\n28\n], with the CPU concept strategy. It may well be that improved conventional care will decrease or even eliminate the benefits of establishing dedicated chest pain units.\nConclusions\nThis survey indicates that despite some diagnostic advances in the ED, a large majority of patients hospitalized for suspected ACS from an ED in Sweden do not have it, and that at least 4 out of 10 of these patients can be considered \"overadmitted\". A comparison with older studies suggests that there has been little, if any, improvement over time. With the introduction of new and systematic risk-based diagnostic protocols, many of the now admitted patients could most likely be treated as outpatients, and a few of the admitted could probably get earlier adequate intervention. In the type of ED described in the present study, patient numbers may be too small to establish a CPU. As an alternative, traditional ED diagnostics may be supplemented with risk prediction algorithms and selected special investigations, such as myocardial scintigraphy. This type of strategy and the CPU concept care need to be compared in randomized investigations.\nCompeting interests\nNone declared.\nAuthors' contributions\nUE conceived the study, designed the protocol, collected and analyzed data, and wrote the manuscript. H-JN performed the patient follow-up. AF collected and analyzed data. OT participated in the design of the study and reviewed the manuscript.\nAll authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** definitely relevant"
}
] |
definitely relevant
|
56
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nIntermittent pneumatic compression for prevention of pulmonary thromboembolism after gynecologic surgery\n\n**Article Abstract:**\n\nBackground\nTo investigate the incidence of pulmonary embolism and risk factors for this condition after obstetric and gynecologic surgery, as well as the efficacy of intermittent pneumatic compression.\nMethods\nA total of 6,218 patients operated at Keio University Hospital excluding obstetric or infertility-related surgery and uterine cervical conization were evaluated retrospectively to determine the preventive effect of intermittent pneumatic compression on postoperative pulmonary embolism.\nResults\nPulmonary embolism occurred in 42 patients (0.68%). Multivariate analysis showed that malignancy, blood transfusion, and a body mass index ≥25 kg/m\n2 \nor ≥28 kg/m\n2 \nwere independent risk factors for postoperative pulmonary embolism. A significantly lower incidence of pulmonary embolism occurred in patients receiving pneumatic compression postoperatively versus those without it. Among gynecologic malignancies, endometrial cancer was a significant risk factor for pulmonary embolism.\nConclusion\nPreventive measures, including intermittent pneumatic compression, should be taken to avoid postoperative pulmonary thromboembolism in the gynecology field.\n\n**Article Body:**\n\nBackground\nPreviously, postoperative venous thromboembolism (VTE) did not attract much attention in Japan because its incidence was lower than in the USA and Europe [\n1\n]. However, an increasing number of patients have recently been diagnosed with VTE in Japan along with improved detection thanks to progress in imaging technologies and increasing medical interest in VTE. VTE is associated with pulmonary thromboembolism (PTE), which causes death in nearly 50% of patients if untreated and which appears to be caused by embolism arising from deep venous thrombosis. According to the statistics compiled by the Japanese Ministry of Health, Labor and Welfare, the number of deaths due to PTE increased more than 10-fold from 1951 to 2000 [\n2\n]. However, a recent report estimated the annual number of PTE patients in Japan at 3,492, which is approximately 1/25 of the number in the USA [\n3\n]. Prevention of VTE has been studied intensively in the USA and Europe since the American College of Chest Physicians (ACCP) Consensus Conference was held in 1985. Development of guidelines for the prevention of VTE has been discussed based on high-level evidence, and the seventh ACCP Consensus Statement [\n4\n] and the International Consensus Statement [\n5\n] were published in 2001. Although the incidence of VTE has been rapidly increasing in Japan, there is still a large difference from the incidence in the USA and Europe. Many deaths due to VTE with PTE may be regarded as sudden deaths because clinical diagnosis is difficult; therefore suitable Japanese guidelines for the prevention of VTE were compiled in 2004 [\n6\n].\nThe Japanese Society of Anesthesiologist (JSA) conducted a survey of perioperative PTE in 2003 and reported that there were 4.41 events per 10,000 operations; the number of PTE patients was third highest in the gynecologic field after the orthopedic and gastrointestinal surgery fields [\n7\n]. The incidence of VTE is higher in pregnant women than in non-pregnant women because of hypercoagulability, hypofibrinolysis, platelet activation, venous smooth muscle relaxation by female hormones, and venous compression by the enlarged uterus.\nThere have been few reports on postoperative PTE in the gynecologic field, apart from that by Nicolaids \net al\n. [\n8\n], which indicated that the incidence of PTE was 40–80% higher after extended surgery for malignancy. Therefore, more data about VTE after gynecologic surgery, including that for malignant tumors, are needed. In the present study, we retrospectively investigated the incidence and risk factors for PTE after obstetric and gynecologic surgery performed at Keio University Hospital, and also evaluated the usefulness of intermittent pneumatic compression (IPC) for prevention of postoperative PTE.\nMethods\nA total of 6,218 patients who underwent operations at the Department of Obstetrics and Gynecology, Keio University School of Medicine between January 1995 and December 2003 were analyzed in this study; operations excluded obstetric, infertility-related and uterine cervical conization surgeries. 42 patients were found to have developed postoperative PTE. As a control group, a total of 929 patients who underwent obstetric, infertility-related surgery and uterine cervical conization operations who did not develop PTE in either 1995 (471 patients) or 2002 (458 patients) were selected.\nUnivariate analysis was used to assess the relationship between PTE and risk factors, such as the age, body mass index (BMI), smoking habits, presence/absence of complications (hypertension, abnormal glucose tolerance, heart disease, and collagen disease), operating time, perioperative bleeding, surgical indication (benign or malignant disease), presence/absence of retroperitoneal lymph node dissection, and perioperative blood transfusion. We also investigated the relationship between PTE and risk factors, including the use of IPC, by multivariate logistic regression analysis. The patient pools were analyzed according to the following risk subcategories: age was divided into less than 40 years of age, between 40 and 50 years of age, and greater than 50 years of age; BMI was divided into less than 25 kg/m\n2\n, between 25 and 28 kg/m\n2\n, and greater than 28 kg/m\n2\n; operating time was divided into less than 4 hours, between 4 to 6 hours, and greater than 6 hours; and perioperative blood loss was divided into less than 1000 mL, between 1000 and 2000 mL, and greater than 2000 mL. At our hospital, IPC has been used in patients undergoing gynecologic surgery to prevent postoperative PTE since 1999, before which elastic bandages or stockings were used (both methods were employed during the transition year of 1998).\nSymptomatic PTE patients were further evaluated by electrocardiography, arterial blood gas analysis, chest X-ray examination, or echocardiography. A confirmative diagnosis was made by chest helical computed tomography scan and pulmonary ventilation-perfusion scintigraphy. Furthermore, asymptomatic patients presenting with only a decreased transcutaneous oxygen saturation (SpO\n2\n) were similarly evaluated for confirmative diagnosis.\nResults\nIncidence of PTE\nThe overall incidence of PTE was 0.68% (42/6,218). In patients undergoing surgery for benign diseases, excluding obstetrics and infertility-related surgery, the incidence was 0.32% (10/3,158), while the incidence was 2.21% (32/1,451) in patients undergoing surgery for malignancy apart from uterine cervical conization.\nSymptoms\nSymptoms were present in 27 of the 42 patients who had postoperative PTE, with chest pain and dyspnea occurring in approximately half of them (Table \n1\n). No symptoms were observed in 15 patients who were diagnosed by a decreased SpO\n2\n. PTE was diagnosed at a mean of 2.69 days after surgery.\nTable 1\nSymptoms of PTE\nSymptom\nNo. of patients\nChest pain\n16\nDyspnea\n15\nTachycardia\n3\nChest discomfort\n2\nPalpitations\n1\nHypotension\n1\nCyanosis\n1\nChills\n1\nVomiting\n1\nNo symptoms\n15\nNote: There were 42 patients, but some had multiple symptoms.\nPTE: pulmonary thromboembolism\nRisk factors (Figure \n1\n)\nFigure 1\nPrevalence of risk factors in patients with postoperative PTE. Six factors (malignancy, retroperitoneal lymph node dissection, blood transfusion, hypertension, abnormal glucose tolerance, and heart disease) were significantly associated with PTE.\nWe investigated the association between postoperative PTE and various risk factors, including the surgical indication (benign or malignant disease), perioperative blood transfusion, presence/absence of retroperitoneal lymph node dissection, smoking habits, and presence/absence of complications (hypertension, abnormal glucose tolerance, heart disease, and collagen disease). As a result, postoperative PTE was significantly associated with malignancy, perioperative blood transfusion, retroperitoneal lymph node dissection, hypertension, abnormal glucose tolerance, and heart disease.\nInfluence of age and BMI\nAmong the 42 patients with postoperative PTE, 93% were aged 40 years or older and 69% were aged 50 years or older (Figure \n2-A\n). There was no such bias in the age distribution of the control group, with approximately 30% of the subjects in each age group. Patients with a BMI ≥25 kg/m\n2 \naccounted for 40% of the PTE group versus 15% of the control group (Figure \n2-B\n).\nFigure 2\nDistribution of risk factors in the postoperative PTE and control groups. A, age; B, BMI; C, perioperative bleeding; D, operating time.\nOperating time and perioperative bleeding\nSixty-two percent of patients with postoperative PTE had an operating time of four hours or longer and 36% had a time of six hours or longer (Figure \n2-C\n). In the control group, 21% of patients had an operating time of four hours or longer and 9% underwent operations lasting six hours or longer. In addition, perioperative bleeding was ≥1,000 mL in 45% of PTE patients and ≥2,000 mL in 21%. In the control group, however, perioperative bleeding was ≥1,000 mL in 18% of patients and ≥2,000 mL in 6% (Figure \n2-D\n).\nUnivariate analysis (Table \n2\n)\nTable 2\nResults of univariate analysis\nFactor\nOdds ratio\np value (chi-square)\nAge ≥40 years old\n6.637\n<0.01\nAge ≥50 years old\n4.362\n<0.01\nBMI ≥25 kg/m\n2\n3.718\n<0.01\nBMI ≥28 kg/m\n2\n3.911\n<0.05\nSmoking\n0.809\nn.s.\nHypertension\n3.018\n<0.01\nAbnormal glucose tolerance\n6.285\n<0.05\nHeart disease\n2.951\n<0.05\nCollagen disease\n2.161\nn.s.\nMalignant tumor surgery\n8.327\n<0.01\nRetroperitoneal lymph node dissection\n7.577\n<0.01\nPerioperative bleeding ≥1,000 mL\n3.797\n<0.01\nPerioperative bleeding ≥2,000 mL\n4.252\n<0.01\nBlood transfusion\n7.152\n<0.01\nOperating time ≥4 hours\n5.999\n<0.01\nOperating time ≥6 hours\n5.516\n<0.01\nBMI: body mass index\nn.s.: not significant\nAnalysis by the χ\n2 \ntest showed a significant association between PTE and seven background factors: age ≥40 years, age ≥50 years, BMI ≥25 km/m\n2\n, BMI ≥28 kg/m\n2\n, hypertension, abnormal glucose tolerance, and heart disease. A significant association was also observed with the following seven surgical factors: operation for malignancy, operating time ≥4 hours, operating time ≥6 hours, perioperative bleeding ≥1,000 mL, perioperative bleeding ≥2,000 mL, retroperitoneal lymph node dissection, and perioperative blood transfusion. These variables were also selected as risk factors.\nMultivariate analysis (Table \n3\n)\nTable 3\nResults of multivariate analysis\nFactor\nRisk ratio\n95% CI\np value (chi-square)\nLower\nUpper\nAge ≥40 years old\n2.645\n0.703\n9.946\nn.s.\nAge ≥50 years old\n3.418\n0.926\n12.615\nn.s.\nBMI ≥25 kg/m\n2\n2.718\n1.149\n6.427\n<0.05\nBMI ≥28 kg/m\n2\n3.922\n1.297\n11.863\n<0.05\nSmoking\n1.029\n0.364\n2.913\nn.s.\nHypertension\n0.838\n0.311\n2.259\nn.s.\nAbnormal glucose tolerance\n2.176\n0.675\n7.016\nn.s.\nHeart disease\n1.149\n0.304\n4.345\nn.s.\nCollagen disease\n1.181\n0.199\n7.018\nn.s.\nMalignant tumor surgery\n2.860\n1.083\n7.522\n<0.05\nBlood transfusion\n3.834\n1.683\n8.737\n<0.01\nIPC\n0.396\n0.193\n0.814\n<0.05\nBMI: body mass index\nCI: confidence interval\nIPC: intermittent pneumatic compression\nn.s.: not significant\nBefore performing multivariate analysis, the correlations between variables were investigated by calculating Spearman's correlation coefficients. There were strong correlations between malignancy, retroperitoneal lymph node dissection, operating time, and the amount of perioperative blood loss (data not shown), therefore we selected two of these factors related to surgery (malignancy and blood transfusion) for analysis.\nAs shown in Table \n3\n, multivariate analysis was done for a total of 12 variables, including the use of IPC. Significant associations with PTE were observed in the case of surgery for malignant tumors, blood transfusion, BMI ≥25 km/m\n2\n, and BMI ≥28 kg/m\n2\n, with their risk ratios being 2.860, 3.834, 2.718, and 3.922, respectively. A significantly lower rate of PTE was observed in the patients treated with IPC (risk ratio of 0.396).\nPostoperative PTE and gynecologic diseases\nThirty-two patients among 42 postoperative patients who developed PTE had malignant tumors (76%) compared to an overall rate of PTE development of 2.21% (32/1,451) among all patients undergoing surgery for gynecologic malignancies.\nThere were 16 patients who had endometrial cancer among the 32 PTE patients with malignancy (Table \n4\n). BMI was ≥25 kg/m\n2 \nin 10/16 patients (62.5%) with endometrial cancer, 2/9 patients (22.2%) with ovarian cancer, and 2/6 patients (33.3%) with uterine cervical cancer (Table \n5\n). There was also a significant difference of postoperative PTE between patients undergoing pelvic lymph node dissection alone and those undergoing combined pelvic and para-aortic lymph node dissection, with the incidence being 2.4% (15/636) and 6.2% (13/211), respectively (p < 0.01) (Table \n6\n).\nTable 4\nPostoperative PTE and gynecologic diseases\nMalignant tumors\nNo. of patients\nBenign tumors\nNo. of patients\nEndometrial cancer\n16\nUterine myoma\n3\nOvarian cancer\n9\nUterine adenomyosis\n3\nCervical cancer\n6\nOvarian tumor\n1\nOthers\n1\nCystocele\n1\nUterine myoma/ovarian tumor\n1\nOthers\n1\nTotal\n32\nTotal\n10\nPTE: pulmonary thromboembolism\nTable 5\nMalignancy and BMI in patients with postoperative PTE\nEndometrial cancer\nOvarian cancer\nCervical cancer\nBMI\n<25 kg/m\n2\n6\n7\n4\n25–27 kg/m\n2\n7\n0\n2\n≥25 kg/m\n2\n3\n2\n0\nTotal\n16\n9\n6\nBMI: body mass index\nPTE: pulmonary thromboembolism\nTable 6\nPostoperative PTE and lymph node dissection\nSite\nIncidence of postoperative PTE\nPelvic lymph nodes\n2.4% (15/636)\np < 0.01\n+ Para-aortic lymph nodes\n6.2% (13/211)\nPTE: pulmonary thromboembolism\nOn the other hand, 10 of the 42 patients (24%) who developed PTE had benign disease compared to an overall rate of PTE development of 0.32% (10/3,158) among all patients undergoing surgery for benign gynecologic tumors.\nPatients with uterine myoma and uterine adenomyosis accounted for almost half of these 10 patients (Table \n4\n).\nEffect of IPC\nThere was a significant difference between the incidence of postoperative PTE before and after the introduction of IPC, being 1.19% (23/1,928) versus 0.40% (14/3,525), respectively (p < 0.01) (Table \n7\n).\nTable 7\nProphylaxis for postoperative PTE\n1995–1997\n1998\n1999–2003\nNo prevention\n9\n0\n0\nElastic bandages\n4\n1\n0\nElastic stockings\n10\n4\n0\nIPC\n0\n0\n14\nBefore vs. after introduction of IPC: 1.19% (23/1,928) vs. 0.40% (14/3,525) (p < 0.01)\nIPC: intermittent pneumatic compression\nPTE: pulmonary thromboembolism\nDiscussion\nBased upon a survey conducted by The Japan Society of Obstetrics, Gynecology, and Neonatal Hematology between 1991 and 2000 at 92 medical institutions in Japan, the incidence of postoperative PTE was 0.08% (168/203,058) in all patients undergoing gynecologic surgery, with a breakdown of 0.03% (51/175,448) in patients undergoing surgery for benign disease compared to 0.42% (117/27,610) in patients undergoing surgery for malignant disease.\nThe incidence was approximately 14 times higher in patients undergoing surgery for malignancy than in patients undergoing surgery for benign disease [\n9\n]. The present study retrospectively investigated the incidence of PTE after gynecologic surgery excluding obstetric surgery, infertility-related surgery, and uterine cervical conization, and we found that the incidence of postoperative PTE was 0.68% (42/6,218), which was higher than the average incidence in Japan. This result appears to be attributable to the high percentage of patients with malignancy among those undergoing gynecologic surgery in our hospital, since patients who had malignant disease surgery accounted for 76.5% of the 42 patients with postoperative PTE. The relationship between VTE and malignancy has long been known as Trousseau's syndrome. It has been reported that VTE is caused by release of procoagulant factors from cancer cells and direct damage to venous endothelial cells and that the incidence of PTE is 3–5 times higher in patients with malignancy [\n10\n]. In addition, cancer patients tend to be older and more often have complications, such as hypertension, abnormal glucose tolerance, and heart disease. Furthermore, surgery for malignancy requires a longer operating time, causes more bleeding, and often requires blood transfusion. These were all significant risk factors according to univariate analysis (χ\n2 \ntest) in the present study. In addition, multivariate analysis selected malignancy as an independent risk factor for postoperative PTE along with blood transfusion and BMI (≥25 kg/m\n2 \nor ≥28 kg/m\n2\n). There have been few reports on VTE after gynecologic surgery; Horowitz found that obesity, a long period of immobilization, extensive cancer surgery, trauma, radiotherapy, a past history of VTE, severe varices, diabetes, and heart failure were risk factors of postoperative VTE [\n11\n]. This report is comparable with results of the present study. Our results are also comparable with the ACCP guidelines, which categorize patients ≥40 years old with extensive surgery and malignant tumors as the highest-risk group [\n4\n]. The JSA has also reported that obesity, long-term immobilization, and malignant tumors are risk factors for perioperative PTE, especially in female patients [\n7\n]. Of the 32 patients with postoperative PTE in the present study, 50% had endometrial cancer, which is often associated with obesity, hypertension, and abnormal glucose tolerance.\nEndometrial cancer is increasing relative to cervical cancer in Japan as well as the USA and Europe. Therefore, endometrial cancer appears to be one of the strongest risk factors for postoperative PTE among malignant gynecologic tumors. Thrombosis occurs due to Virchow's triad, namely 1) hypercoagulability, 2) stagnation of blood, and 3) vascular endothelial cell damage. Retroperitoneal lymph node dissection was not identified as an independent risk factor for PTE according to multivariate analysis in the present study. Lymph node dissection may be closely related to the occurrence of VTE since this procedure causes vascular damage and also accumulations of lymph may compress the veins after surgery and cause stagnation of blood. As shown in Table \n6\n, the incidence of postoperative PTE was increased in patients who had both pelvic and para-aortic lymph node dissection.\nRetroperitoneal lymph node dissection is important for the treatment of endometrial cancer, but these findings suggest that it is necessary to carefully consider the performance of lymph node dissection in patients with a number of risk factors as well as the use of postoperative radiotherapy.\nThere are also patients with benign gynecologic disease in whom attention should be paid to the risk of postoperative PTE. Of the 10 patients with benign gynecologic disease in the present series, six were had relatively large uterine tumors, including myoma and adenomyosis. Although age is specified as a risk factor in the ACCP guidelines [\n4\n], neither an age ≥40 years nor an age ≥50 years was identified as a risk factor in the present study. However, multivariate analysis by the χ\n2 \ntest showed a significant difference for patients ≥50 years old (p = 0.0651) in this study, indicating that elderly patients are at increased risk of developing postoperative PTE.\nAs well as minimizing risk factors, it is important to employ adequate preventive measures for VTE in high-risk patients according to the guidelines. Multivariate analysis showed that the risk ratio of patients treated with IPC was 0.396 (p < 0.05), so this technique was an independent preventive factor for postoperative PTE. Our department introduced IPC in 1999, as did other institutions in Japan [\n6\n]. Comparison of the incidence of postoperative PTE before and after the introduction of IPC showed a significant decrease from 1.19% to 0.40%. In addition, the five patients experiencing postoperative PTE in 1998 (transitional period for introduction of IPC) were all managed with other preventive methods. The ACCP guidelines state that IPC reduces the risk of postoperative VTE by 88%, which is superior to the risk reduction rate for low-dose unfractionated heparin (68%) or low-molecular-weight heparin (76%), suggesting that IPC is one of the most useful preventive methods for VTE and PTE [\n5\n].\nThe JSA reported that the incidence of perioperative PTE is 4.41/10,000, with the mortality rate being 18% [\n7\n]. It also reported that 57.7% of PTE was likely to be preventable. In Japan, there is a need to accumulate more evidence-based clinical data, in order to better define the risk factors for VTE and PTE and allow the selection of appropriate preventive methods.\nConclusion\nPreventive measures, including intermittent pneumatic compression, should be taken to avoid postoperative pulmonary thromboembolism in the gynecology field.\nList of abbreviations\nACCP American College of Chest Physicians\nBMI body mass index\nIPC intermittent pneumatic compression\nJSA Japanese Society of Anesthesiologist\nPTE pulmonary thromboembolism\nSpO\n2 \noxygen saturation\nVTE venous thromboembolism\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nNS (Suzuki) and SE were involved in the sequence alignment and drafted the manuscript.\nHN and NS (Suzuki) were involved in writing of method.\nNS (Suzuki) and FK were involved in writing manuscript.\nFK, AH, SE, and HN were involved in analysis of data.\n*** was involved in the sequence alignment.\nNS (Suzuki), FK, and DA were involved in the design of the study.\nNH, AT and NS (Susumu) performed the statistical analysis.\nAH and HT helped to draft the manuscript.\nNS (Suzuki), NS (Susumu) and DA were involved in planning, experimental setup.\nAll authors read and approved the final manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
57
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nPolymorphisms of the Flavin containing monooxygenase 3 (\nFMO3\n) gene do not predispose to essential hypertension in Caucasians\n\n**Article Abstract:**\n\nBackground\nThe recessive disorder trimethylaminuria is caused by defects in the \nFMO3 \ngene, and may be associated with hypertension. We investigated whether common polymorphisms of the \nFMO3 \ngene confer an increased risk for elevated blood pressure and/or essential hypertension.\nMethods\nFMO3 \ngenotypes (E158K, V257M, E308G) were determined in 387 healthy subjects with ambulatory systolic and diastolic blood pressure measurements, and in a cardiovascular disease population of 1649 individuals, 691(41.9%) of whom had a history of hypertension requiring drug treatment. Haplotypes were determined and their distribution noted.\nResults\nThere was no statistically significant association found between any of the 4 common haplotypes and daytime systolic blood pressure in the healthy population (p = 0.65). Neither was a statistically significant association found between the 4 common haplotypes and hypertension status among the cardiovascular disease patients (p = 0.80).\nConclusion\nThese results suggest that the variants in the \nFMO3 \ngene do not predispose to essential hypertension in this population.\n\n**Article Body:**\n\nBackground\nEssential hypertension is the most common reason for adult visits to office-based physicians and for the use of medication [\n1\n-\n3\n]. It is estimated that 24% of the US adult population (70% in persons over 70) and at least 50% of the Irish adult population aged 50 or over are hypertensive[\n4\n,\n5\n]. Ethnic differences exist in the prevalence of hypertension between populations, for example between Africans and Northern Europeans [\n6\n-\n8\n]. Mendelian forms of hypertension resulting from single gene defects are rare [\n9\n-\n11\n]. The major contribution to the etiology of this disorder is proposed to result from the combined effects of genes that modify the response of blood pressure to environmental stresses such as diet and 'environmental susceptibility genes' [\n12\n-\n14\n]. Essential hypertension does not follow a clear pattern of inheritance but exhibits familial aggregation of cases. This multifactorial trait increases the affected individuals' risk of myocardial infarction, stroke and end-stage renal disease, and is one of the leading causes of morbidity and mortality in adults[\n8\n,\n15\n]. Population-wide application of preventative measures and candidate gene analysis to predict modifiable risks in addition to treatment are thus very worthwhile [\n16\n-\n19\n].\nTrimethylaminuria (TMAuria) is an inborn error of metabolism (MIM # 275700) resulting from diminished oxidation of the tertiary amine trimethylamine to trimethylamine N-oxide resulting in a severe body odour in affected individuals. The microsomal NADPH-dependent flavin-containing monooxygenases (FMOs) (E.C. 1.14.12.8) are a family of chemical and drug metabolising enzymes that catalyze the phase 1 oxygenation of a wide variety of nucleophilic heteroatom containing compounds including catecholamines[\n20\n,\n21\n]. \nFMO3\n, a phase 1 drug metabolising gene, is the main liver dependent human isoform[\n22\n]. We and others have shown that recessivity for mutations of \nFMO3 \ncause TMAuria [\n20\n-\n24\n].\nWe have previously noted that a number of patients with TMAuria have idiopathic hypertension [\n21\n,\n22\n]. In addition, Cashman et al [\n25\n] have reported a proposed link in African-American males between hypertension and increased excretion of trimethylamine. We have identified increased excretion of catecholamines in a proband with TMAuria who is homozygous for a deletion of the \nFMO3 \ngene [\n20\n]suggesting a possible association between abnormal catecholamine metabolism and variants of the \nFMO3 \ngene. Endogenous substrates for FMO3 include tyramine and phenylethylamine [\n26\n,\n27\n] and tyramine has a known pressor effect. As high levels of circulating catecholamines contribute to hypertension, it is proposed that polymorphisms of \nFMO3 \ngene could contribute to impaired catecholamine metabolism and hypertension.\nWe have previously described the population frequencies of a number of common polymorphisms of the \nFMO3 \ngene (E158K, V257M, E308G) in a North American population[\n25\n,\n28\n]. Expression studies indicate that the polymorphisms E158K and V257M exhibit decreased tyramine oxidation \nin vitro\n[\n25\n]. We and others have noted that the E308G polymorphism shows a substantial decrease in \nFMO3 \nactivity in the presence of the E158K polymorphism causing mild TMAuria[\n22\n,\n29\n]. While these common polymorphisms exhibit some difference in expression of the functional FMO3 enzyme, this effect is minimal in comparison to that of the null mutations.\nWe hypothesised that common \nFMO3 \npolymorphisms might predispose to essential hypertension. While null alleles in the \nFMO3 \ngene may be too rare to cause any appreciable effect on the population burden of hypertension, prevalent polymorphisms with documented \nin vitro \nevidence of variation in catecholamine metabolism may however potentially associate with and predispose to this condition.\nHerein we report our investigations into a possible association of haplotypes of three polymorphic variants of the \nFMO3 \ngene with the phenotype of blood pressure in an occupational Irish adult population and with presence of essential hypertension in an Irish cardiovascular disease (CVD) population.\nMethods\nStudy populations\nThere were 2 population groups in this study. The first population was recruited from the Allied Irish Bank Phase II (AIB Phase II) study that commenced in 1989 and consists of 387 bank employees (Table \n1\n). Blood pressure was measured every 30 minutes for 24 hours using a validated monitor – the SpaceLabs 90207. The mean daytime and night time systolic (SBP) and diastolic (DBP) values were used for analysis in each case. Hypertension was defined as having daytime blood pressure of 135/85 mm Hg or greater. This group was collected between 1998 and 2002 and was between the ages of 30–70 years. It was noted if individuals consumed more than 2 alcohol-containing drinks per day.\nThe second were a group of 1649 patients with coronary disease (CHD), 1313 of whom were ascertained on the basis of having acute coronary syndromes (ACS) (myocardial infarction (MI) or unstable angina) and 336 as having stable angina (Table \n2\n). MI was defined as chest pain of at least 20 minutes duration, along with previous or current electrocardiogram or serum enzyme changes diagnostic of MI. Unstable angina was defined as chest pain typical of angina occurring at rest or lasting at least 20 minutes and requiring hospitalization in a patient with known coronary artery disease based on a positive stress test or a coronary angiogram. Inclusion criteria for stable angina were chest pain occurring with exercise typical of angina in a patient with known coronary artery disease based on a coronary angiogram or a positive treadmill test. These patients were collected between the years 1999–2002 and were between the ages of 32 and 85 years. They were classified as having a history of hypertension requiring drug treatment or having no history of hypertension.\nInformed consent and ethics approval from the Beaumont Hospital Ethics (Medical Research) Committee was obtained for all samples collected.\nFMO3 \npolymorphism genotyping\nThree single nucleotide polymorphisms in the \nFMO3 \ngene were genotyped in the above populations. These were E158K (G472A), V257M (G769A) and E308G (A923G). The E158K polymorphism was genotyped using the primer GAAGGTGACCAAGTTCATGCTTGGCCTTACCTGGAAAGGACTT for the G allele and GAAGGTCGGAGTCAACGGATTTTTGGCCTTACCTGGAAAGGACT for the A allele. The V257M polymorphism was genotyped using the primer GAAGGTGACCAAGTTCATGCTCAGCCATCTCTGACTGGTTGTACA for the G allele and GAAGGTCGGAGTCAACGGATTAGCCATCTCTGACTGGTTGTACG for the A allele. The E308G polymorphism was genotyped using the primer GAAGGTGACCAAGTTCATGCTGCCTAACGTGAAGGAATTCACAGA for the A allele and GAAGGTCGGAGTCAACGGATTGCCTAACGTGAAGGAATTCACA for the G allele.\nGenotyping was carried out using the Amplifluor™ method by K Biosciences \n. Genomic DNA was isolated from blood. Genotyping was performed in 384-well microplates using a fluorescence resonance energy transfer (FRET)-based genotyping method. Amplification was initiated using allele-specific primers and a common downstream primer. The allele-specific primers were tailed with unique sequences that create corresponding complementary sequences in the two amplicons. In the second round of amplification, quenched Universal Amplifluor™ primers (in a hairpin formation) were used. These primers contain 3' tails that specifically bind to the unique tailed sequences in the amplicons and continue amplification. In the final round of amplification, the action of the DNA polymerase opened up the hairpin structure and the quencher and reporter moieties are spatially separated. The excited reporter moiety emitted either red or green fluorescence, the colour of which depends on which nucleotide is at the polymorphism site. The fluorescence was quantified by a microplate reader and then analysed via an Excel macro to provide genotypes for each SNP. Confirmation of the validation of the mutation detection method was based on the use of known positive DNA controls (which had been sequenced) for the three polymorphisms provided by McGill University (Montreal).\nHaplotype analysis\nHaplotypes for the 3 SNPs were inferred using a maximum likelihood approach and their association with the rank of the various mean blood pressure measurements in the AIB Phase II study group and their association with hypertension in the CVD group was determined using \"haplo.score\", a function written for the statistical package SPLUS 6.0[\n30\n]. This method used score tests for association between a quantitative trait and the haplotypes. The result of the association was given as a haplotype score. The haplotypes score was calculated using a general linear model, which permitted adjustment for age, sex and alcohol consumption.\nStatistical analysis\nThe 2 primary analyses were (1) the association between haplotypes of the 3 SNPs and mean daytime systolic blood pressure in the AIB Phase II study population and (2) the association between haplotypes and the hypertension status in the CVD patients.\nThe secondary analyses included (1) the association between genotypes and daytime systolic blood pressure in the AIB Phase II study, (2) the association between genotypes and hypertensive status in the CVD group, (3) the comparison of genotypic frequencies between the AIB Phase II study group, the hypertensives of the CVD group and the non-hypertensives of the CVD group, (4) the effect of haplotypes on mean daytime diastolic blood pressure, on mean night time systolic blood pressure and on mean night time diastolic blood pressure in the AIB Phase II study group, (5) the association between polymorphisms in the FMO3 gene and cardiovascular disease.\nHaplo.score was used to look for any associations between haplotypes and daytime systolic blood pressure/hypertensive status. We only tested for relatively common haplotypes, and defined as those at an inferred frequency of greater than 5% in the populations. For all of the above analyses, statistical significance was determined when p < 0.05.\nANOVA was used to look for an association between the genotypes and mean daytime systolic blood pressure in the AIB Phase II study group. Both haplo.score and ANOVA were adjusted for age, sex and the number of alcohol units consumed per week.\nChi-squared analysis was used to look for the difference in genotype frequencies between the hypertensive and non-hypertensive patients in the CVD group. Linear regression was then used to adjust for age and sex. Chi-squared analysis was also used to compare genotypic frequencies between the AIB Phase II study group, the hypertensives from the CVD group and the non-hypertensives of the CVD group. Logistic regression analysis was used to predict if any of the SNPs influence the risk of cardiovascular disease, including diabetes, BMI, hypercholesterolemia, smoking status, age and gender in the model. All of the above analyses were repeated stratifying according to gender.\nResults\nThe AIB Phase II population consisted of 387 subjects, 224 (57.8%) of which were male. In comparison to the females, the males had on average higher blood pressure measurements, triglycerides and total cholesterol. Slightly more males in this group were smokers (Table \n1\n).\nThe CVD group consisted of 1649 subjects, 691 (41.9%) of which were classified as having a history of hypertension requiring drug treatment. A greater percentage of those classified as hypertensive also had hypercholesterolemia and diabetes mellitus in comparison to those who were classified as non-hypertensive. As might be expected from a CVD group, most of the subjects were taking medication, with almost the same frequency of hypertensives and non-hypertensives taking each group of medications (Table \n2\n). Blood pressure measurements are only presented to characterise, rather than compare, the groups, since medication is lowering blood pressure in most of the CHD group, but not in most of the AIB Phase II study group.\nThe most notable difference between the AIB Phase II study group and the CVD group is that there were a much greater proportion of current or ex smokers in the CVD group than in the AIB Phase II study group (73% vs. 30.1%).\nThe 3 SNPs were found to be in Hardy-Weinberg Equilibrium. 4 common haplotypes were inferred in the two populations (Table \n3\n), with similar frequencies in the AIB Phase II study group, the hypertensives and in the non-hypertensives of the CVD group. However the haplotype KVG, which is the 2\nnd \nmost frequent haplotype in the AIB Phase II study group, was the 3\nrd \nmost frequent haplotype in the CVD group. However the difference in frequency was only 4%, which is most likely due to chance.\nNo statistically significant associations were found between any of the four common haplotypes and mean daytime systolic blood pressure in the AIB Phase II study (overall p = 0.65, 3 d.f) (See table \n3\n). Nor was this statistically significant when adjusted for age, sex and daily alcohol intake (overall p = 0.729, 3 d.f) (See table \n3\n). Neither did we find any statistically significant associations between any of the haplotypes and hypertension status in all subjects with and without adjustment of sex and age (see table \n3\n). When stratified by gender, there were still no statistically significant associations between any of the specific haplotypes and daytime SBP in the AIB Phase II study (males overall p = 0.91, 3 df and females overall p = 0.61, 3 df) or with hypertension status in the CVD patients (males overall p = 0.59, 3 df and females overall p = 0.82, 3 df). Table \n4\n displays the genotypic frequencies of the 3 SNPs in the AIB Phase II population, in the hypertensives of the CVD group and in the non-hypertensives of the CVD group. When genotypic frequencies were compared among 3 groups, there were no statistically significant differences (E158K p = 0.30, V257M p = 0.47, E308G p = 0.15). There were no statistically significant associations between any of the individual genotypes with daytime SBP in the AIB Phase II study group, even when adjusted for age, sex and daily alcohol consumption (E158K p = 0.91, V257M p = 0.85, E308G p = 0.68).\nThe mean daytime SBP and mean daily alcohol consumption are broken down by genotype in table \n5\n and it is clear that there is not much difference between the genotype groups. Stratifying the analysis by gender, there was still no association between genotypic frequencies in the AIB Phase II study group (females E158K p = 0.92, V257M p = 0.86, E308G p = 0.13, males E158K p = 0.37, V257M p = 0.87, E308G p = 0.38).\nThere was no genotypic difference between hypertensive and non-hypertensive CVD subjects, even after adjustment for age and sex (E158K p = 0.84, V257M p = 0.44, E308G p = 0.91). When this analysis was stratified by gender, still no statistically significant differences are noted (females E158K p = 0.79, V257M p = 0.54, E308G p = 0.29, males E158K p = 0.71, V257M p = 0.22, E308G p = 0.66).\nTesting for any associations between haplotype and daytime diastolic blood pressure, night time systolic blood pressure and night time diastolic blood pressure in the AIB Phase II study yielded no statistically significant associations (Table \n6\n). Likewise it was shown by logistic regression that none of the SNPs were significant predictors for cardiovascular disease when the CVD and the AIB Phase II study groups were compared (E158K z = 0.60 p = 0.55, V257M z = -0.31 p = 0.76, E308G z = 0.49 p = 0.63), though diabetes was found to be a significant predictor.\nDiscussion\nThe observation that a number of patients with TMAuria are hypertensive was the basis to the hypothesis that there may be an association between variants in the \nFMO3 \ngene and hypertension. The FMO3 enzyme has a broad substrate specificity, which includes catecholamines as a minor pathway[\n21\n,\n26\n]. Catecholamines are produced in response to stress and modulate heart rate and blood pressure. Variants of the \nFMO3 \ngene resulting in decreased enzymatic activity could result in decreased catabolism of catecholamines, which impact on blood pressure homeostasis. As catecholamines are at peak levels during the day, we elected to study the association between daytime SBP and variants in the \nFMO3 \ngene as a primary endpoint. In our analysis, we adjusted for alcohol use as tyramine is a substrate for FMO3 oxidation[\n26\n]. The FMO3 enzyme is also modulated by the sex hormones[\n28\n]. Females with moderate to severe TMAuria note exacerbations perimenstrually and it is proposed that decreases in FMO3 enzymatic activity resulting from polymorphisms could also be influenced by hormonal events[\n31\n]. For this reason the analysis was stratified by treating males and females as separate groups.\nIn this study, by constructing haplotypes based on the 3 SNPs, we discovered that none of the haplotypes were statistically significantly associated with either daytime systolic blood pressure in the AIB Phase II study group or with hypertensive status in the CVD group. There was also a lack of association between any of the genotypes of the SNPs with daytime SBP or with hypertension status. Neither did the stratified analyses show any statitically significant associations.\nWhile the definition of hypertension in the CVD population provides a rather arbitrary estimation of hypertension, the 24-hour blood pressure measurements in the AIB Phase II study were carefully controlled. Even so, the results from both groups showed that the variants had no association with blood pressure or hypertension status.\nWhy are \nFMO3 \nvariants maintained in population, and in particular the E158K variant? It is proposed that genes such as \nFMO3\n, a drug and toxin detoxicating gene, may have survived as balanced polymorphisms in an ancient human or primate population to neutralise the effect of harmful exposures[\n32\n,\n33\n]. Evolutionary changes in \nFMO3 \nmay have evolved in different geographic locations to buffer changes in the highly polymorphic drug metabolising genes, which show substantial geographic and ethnic variation. It is possible that 'low penetrance' polymorphisms of \nFMO3 \nalone may not independently affect blood pressure homeostasis but severe loss of function causing mutations may unmask pressor effects of variation in other drug metabolising enzymes previously buffered by \nFMO3\n[\n34\n]. This hypothesis is supported by the observation that only some, but not all, TMAuria patients exhibit hypertensive symptoms. Therefore other common FMO genes may be potential hypertension candidates. There could be identified by typing other FMO genes in TMAuria patients with hypertensive symptoms or by directly assessing the candidate genes in a large study of hypertension.\nConclusion\nIn conclusion, these data indicate that these three polymorphisms of the \nFMO3 \ngene inherited singly or in specific haplotype combinations do not represent an independent susceptibility risk for hypertension as an absolute trait or continuous variable in a representative Irish population.\nAuthors' contributions\nCD carried out the statistical analysis and drafted the manuscript. DCS assisted in the statistical analysis and participated in the study design. AS contributed to the interpretation of the hypertension data and participated in the study design. EOB designed the data collection for the AIB Phase II study and participated in the study design. DML helped draft the manuscript. JKOB led the genotypic analysis component. EPT conceived the study and helped to draft the manuscript. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
58
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nCardiovascular health knowledge and behavior in patient attendants at four tertiary care hospitals in Pakistan – a cause for concern\n\n**Article Abstract:**\n\nBackground\nKnowledge about coronary heart disease (CHD) and its risk factors is an important pre-requisite for an individual to implement behavioral changes leading towards CHD prevention. There is scant data on the status of knowledge about CHD in the general population of Pakistan. The objective of this study was to assess knowledge of CHD in a broad Pakistani population and identify the factors associated with knowledge.\nMethods\nCross sectional study was carried out at four tertiary care hospitals in Pakistan using convenience sampling. Standard questionnaire was used to interview 792 patient attendants (persons accompanying patients). Knowledge was computed as a continuous variable based on correct answers to fifteen questions. Multivariable linear regression was conducted to determine the factors independently associated with knowledge.\nResults\nThe mean age was 38.1 (±13) years. 27.1% had received no formal education. The median knowledge score was 3.0 out of a possible maximum of 15. Only 14% were able to correctly describe CHD as a condition involving limitation in blood flow to the heart. Majority of respondents could identify only up to two risk factors for CHD. Most commonly identified risk factors were stress (43.4%), dietary fat (39.1%), smoking (31.9%) and lack of exercise (17.4%). About 20% were not able to identify even a single risk factor for CHD. Factors significantly associated with knowledge included age (p = 0.023), income (p < 0.001), education level (p < 0.001), residence (p < 0.001), a family history of CHD (p < 0.001) and a past history of diabetes (p = 0.004). Preventive practices were significantly lacking; 35%, 65.3% and 84.6% had never undergone assessment of blood pressure, glucose or cholesterol respectively. Only a minority felt that they would modify their diet, stop smoking or start exercising if a family member was to develop CHD.\nConclusion\nThis is the first study assessing the state of CHD knowledge in a relatively diverse non-patient population in Pakistan. There are striking gaps in knowledge about CHD, its risk factors and symptoms. These translate to inadequate preventive behavior patterns. Educational programs are urgently required to improve the level of understanding of CHD in the Pakistani population.\n\n**Article Body:**\n\nBackground\nCoronary heart disease (CHD) is a major public health concern and accounts for more deaths than any other disease [\n1\n] worldwide. Developing countries were once considered to be less affected by CHD. However, the burden of CHD in developing countries has increased to epidemic proportions [\n2\n]. Furthermore, it is anticipated that within the next fifteen years, CHD will be the leading cause of death in these countries [\n1\n]. The prevalence of cardiovascular risk factors in the Asian population is high [\n3\n]. According to data from the National Health Survey of Pakistan, the prevalence of hypertension and diabetes is approximately 33% and 25% respectively, in persons over the age of 45 years [\n4\n,\n5\n] while the overall prevalence of smoking is 28% in men, going as high as 41% amongst those aged 40 to 49 years [\n6\n]. Furthermore dietary habits in Pakistan are heavily weighed towards the consumption of saturated fats as well as ghee (hydrogenated vegetable oil) [\n7\n]. Knowledge about CVD and its risk factors is an important (albeit not the only) pre-requisite for an individual to implement behavioral changes leading towards CHD prevention. Estimating the knowledge base of the community regarding CHD has important public health applications as it assists in developing targeted educational programs.\nStudies in South Asians (Indians, Pakistanis and Bangladeshis) suggest a very poor degree of knowledge regarding CHD and its risk factors. In the study by Rankin [\n8\n] only a minority (approximately 20%) identified lack of exercise and obesity as a risk factor, while about 30% identified smoking as a factor related to CHD (amongst Pakistanis, this estimate was 14%) and approximately 30% considered dietary fat as a risk factor. Interestingly, only 5% of our respondents mentioned family history of CHD as a risk factor. There is scant data on the level of knowledge about CHD in the population of Pakistan. One prior study [\n9\n] has reported on the very poor awareness about risk factors for CHD in a lower middle-class urban population in Karachi, a major metropolitan city of Pakistan. In this selected population, consisting predominantly of women with a variable degree of formal education, less than 20% were aware of most risk factors for CHD. However, there is paucity of data on the status of knowledge in the broader population of the country, which consists of a much higher proportion of people with lower incomes, rural residency and no formal education. The aim of our study was to assess knowledge of CHD in a more diverse Pakistani population and identify the factors associated with knowledge in this study group. We also aimed to identify attitudes and behaviors regarding CHD prevention.\nMethods\nStudy design\nThis was a multi-center cross sectional study conducted at four tertiary care hospitals in Pakistan. A convenience sample of 810 subjects consisting of attendants of patients (defined as persons accompanying patients to the hospital, usually family members or close relatives) visiting various outpatient departments of these four hospitals were invited to undergo an interview regarding their understanding of what coronary heart disease (CHD) was, risk factors, symptoms and practices related to CHD by trained medical officers. The four hospitals were chosen to enable the study population to pertain to a wide demographic spectrum of Pakistan. These hospitals were as follows: the Aga Khan University Hospital (AKUH) in Karachi is a private hospital that caters to a mixture of middle and upper class patients who (mostly) pay for their care. The Mayo Hospital in Lahore is a public hospital that caters primarily to poor patients who receive free care. The Pakistan Institute of Medical Sciences (PIMS) in a public hospital in Islamabad that caters to patients from a wide area that includes rural as well as urban areas and provides subsidized care. Finally, the Allied General Hospital (AGH) in Faisalabad is a large public hospital in Faisalabad that cares for urban as well as rural patients from central Punjab at nominal costs. The study was approved by each hospital's ethics review body.\nSurvey instrument\nStudy subjects were surveyed using a structured questionnaire that was developed to contain questions on four basic themes: (1) understanding of what CHD was; (2) knowledge of risk factors for CHD – respondents were asked what factors are related with CHD and the direction of the relationship between these factors and CHD was specified; (3) knowledge of the symptoms of CHD; and (4) preventive practices relating to CHD – whether subjects thought CHD was preventable and what preventive practices had they undertaken. The questionnaire was initially developed in English, translated into Urdu, then back-translated into English to check for consistency. The questionnaire, consisting of open-ended questions only, was pre-tested in 20 attendants and revised accordingly. All respondents were surveyed in an identical fashion. All questions were asked in Urdu. Responses to open-ended questions were recorded in English either by selection from a list of predefined answer categories or in writing if the particular response was not listed. Subjects were asked, at each question, whether they wished to add anything to their response, but were not prompted or given hints.\nStudy subjects\nPatient attendants were selected as somewhat reflective of the general population for convenience reasons. Subjects were approached in the outpatients departments of the respective hospitals. If over the age of 18 years and able to give verbal consent, respondents underwent a standard questionnaire based survey. Subjects who were patients, under the age of 18 years, unable to communicate in Urdu (the national language of Pakistan) or were members of the hospital staff were excluded from this study. We estimated that a sample size of 371 would be required to estimate an assumed prevalence of 0.5 of various aspects knowledge about CHD at a confidence level of 95% with an error bound of 0.05.\nDefinitions\nKnowledge was computed as a continuous variable using the cumulative score for each subject based on correct responses to 15 questions (Table \n1\n). Each correct response was assigned one point. Urban dwelling was defined as residence within the geographical bounds of a major metropolitan city (Karachi, Islamabad, Rawalpindi, Faisalabad and Lahore). Rural dwelling was defined as residing outside the major metropolitan cities (most of Pakistan is fairly rural outside the major cities). Formal education was defined as education received in school (but did not include those going to traditional educational institutions or \"madrassa\").\nTable 1\nQuestions on which coronary heart disease knowledge score was computed.\nQuestion\nResponse\nScore\nWhat is CHD?\nBlocked artery\n1\nRisk factors for CHD\nSmoking\n1\nNo exercise\n1\nDietary fat\n1\nStress\n1\nHigh blood pressure\n1\nDiabetes\n1\nFamily history\n1\nAge\n1\nMale gender\n1\nObesity\n1\nCholesterol\n1\nSymptoms of CHD\nChest pain\n1\nDyspnea\n1\nSweatiness\n1\nMaximum Score\n15\nCHD = coronary heart disease.\nStatistical analysis\nAll variables were entered into Statistical Package for Social Sciences (SPSS) version 10. Means and standard deviations were calculated for continuous variables and frequencies for categorical variables. Univariate analysis was performed by simple linear regression to determine the factors associated with knowledge. Univariate covariates with a p value of ≤0.25 were entered into the multivariable model. Multivariable regression using a stepwise technique was conducted to adjust for confounders and determine the factors independently associated with knowledge. The standardized residuals of the regression model were examined for outliers as well as for non-normality and nonlinearity using probability plots and residual plots. A significant level was defined as p < 0.05.\nResults\nApproximately 1000 potential respondents were approached. Eight hundred and ten subjects consented to participate in the study. Complete data were available for 792 subjects. The demographic and clinical characteristics of the study group are shown in Table \n2\n.\nTable 2\nDemographics and Clinical Characteristics of Study Population.\nCharacteristic\nN (%)\nHospital\n AKU\n153 (19.3)\n PIMS\n249 (31.4)\n Mayo\n241 (30.4)\n AGH\n149 (18.8)\nGender\n Male\n558 (70.5)\n Female\n234 (29.5)\nMarital Status\n Single\n†\n202 (25.5)\n Married\n590 (74.5)\nResidence\n Rural\n335 (42.3)\n Urban\n457 (57.7)\nAge\n‡ \n(mean ± SD)\n38.1 ± 13\nAge\n‡ \n(categories)\n ≤30\n277 (35.0)\n 31 – 60\n469 (59.2)\n >60\n46 (5.8)\nSmokers\n314 (39.6)\nMonthly income*\n <3000\n225 (28.4)\n >3000\n567 (71.6)\nEducation\n No formal\n215 (27.1)\n Formal\n577 (72.9)\nFamily Hx of IHD\n373 (47.1)\nPrior Diabetes\n47 (5.9)\nPrior Hypertension\n118 (14.9)\nPrior IHD\n42 (5.3)\nN = number. † includes separated and divorced. ‡ in years.\nAKU = Aga Khan University Hospital. PIMS = Pakistan Institute of Medical Sciences.\nMayo = Mayo Hospital. AGH = Allied General Hospital. SD = standard deviation.\n* in Rupees (1 Rupee = US$ 0.017). Hx = history. IHD = ischemic heart disease.\nSubjects were asked about what they thought CHD meant. Only 14% were able to correctly describe the latter as a condition involving limitation in blood flow to the heart. A variety of other descriptions were offered including a \"malfunction of the heart\" by 35%. Table \n3\n displays the distribution of responses to this question.\nTable 3\nResponses to questions assessing knowledge of coronary heart disease\nResponse count (% of cases)\nWhat is Coronary Heart Disease?*\nArterial blockage\n109 (13.8)\nDo not know\n232 (29.3)\nChest pain\n152 (19.2)\n\"Malfunction\" of the heart\n277 (35.0)\nValve problem\n83 (10.5)\nOther\n142 (17.9)\nWhat are the risk factors for Coronary Heart Disease?*\nDo not know\n162 (20.5)\nSmoking\n253 (31.9)\nNo exercise\n138 (17.4)\nDietary fat\n310 (39.1)\nDietary salt\n26 (3.30)\nStress\n344 (43.4)\nHigh blood pressure\n56 (7.10)\nCholesterol\n59 (7.40)\nDiabetes\n15 (1.90)\nFamily history\n39 (4.90)\nAge\n33 (4.20)\nMale gender\n9 (1.10)\nOverwork\n36 (4.50)\nObesity\n112 (14.1)\nOther\n62 (7.80)\nWhat are the symptoms of Coronary Heart Disease?*\nDo not know\n230 (29.0)\nChest pain\n287 (36.2)\n\"Attack\"\n179 (22.6)\nSweatiness\n116 (14.6)\nPalpitations\n136 (17.2)\nAnxiety\n177 (22.3)\nHeadache\n17 (2.10)\nDyspnea\n193 (24.4)\nOther\n44 (5.60)\n* multiple responses\nParticipants were questioned about risk factors for CHD. As seen in Table \n3\n, the most commonly identified risk factors were stress (43.4%), dietary fat (39.1%), smoking (31.9%) and lack of exercise (17.4%). However about 20% were not able to identify even a single risk factor for CHD (Figure \n1\n). When questioned about the symptoms of CHD, only a minority were able to correctly identify symptoms of chest pain, dyspnea and diaphoresis (Table \n3\n).\nFigure 1\nRisk factors for coronary heart disease identified by study subjects.\nSubjects were questioned regarding preventive practices against CHD. Although nearly three quarters of the study group felt that CHD was preventable (Table \n4\n), preventive practices in this study group were largely lacking.\nTable 4\nPreventive Practices and Attitudes towards coronary heart disease\nResponse count (% of cases)\nIs CHD preventable?\n Yes\n604 (74.3)\n No\n37 (4.70)\n Do not know\n151 (19.1)\nHave you had your blood pressure checked?\n Never have\n275 (34.7)\n Every 2 years\n298 (37.6)\n >2 year intervals\n219 (27.7)\nHave you had your blood sugar checked?\n Never have\n517 (65.3)\n Have at least once\n275 (34.7)\nHave you had your cholesterol checked?\n Never have\n670 (84.6)\n Have at least once\n122 (15.4)\nHave you ever undertaken any preventive practices for CHD*?\n None\n354 (44.7)\n Exercise\n185 (23.4)\n Dietary salt restriction\n39 (4.90)\n Dietary fat restriction\n265 (33.5)\n Weight control\n38 (4.80)\n Stress reduction\n58 (7.30)\n Reduced smoking\n89 (11.2)\n Medications\n16 (2.00)\n Home remedies\n25 (3.20)\n Other\n34 (4.30)\nIf your family member develops CHD, what would you do*?\n Nothing\n72 (11.4)\n Do not know\n104 (16.5)\n See a doctor\n332 (52.7)\n Change my diet\n132 (21.0)\n Start exercising\n50 (7.90)\n Stop smoking\n40 (6.30)\n Reduce stress\n48 (7.60)\n Other\n21 (2.30)\nCHD = coronary heart disease.\n* multiple responses\nKnowledge was assessed in this study as a continuous variable. Responses to 15 questions were scored as correct or incorrect and each respondent received one point for each correct answer (Table \n1\n). The median knowledge score of the study group was 3.0 (range 0–11) out of a possible maximum of 15. Figure \n2\n shows the distribution of knowledge scores in the study group. No participant was able to achieve a score above 11.\nFigure 2\nKnowledge score for coronary heart disease.\nTable \n5\n shows the results of the univariate and multivariable analyses for factors associated with knowledge of CHD, with the respective coefficients (slope of the regression line). In the univariate analysis, factors significantly associated with knowledge included age, gender, education (formal vs. no formal), monthly income (<3000 vs. >3000 Rupees), residence (rural vs. urban), smoking status, family history of CHD and a prior history of diabetes, hypertension or CHD (Table \n5\n). Interestingly, there were also significant differences in the knowledge scores of subjects recruited from different hospitals. In the multivariable analysis factors independently associated with knowledge included age, education, residence, monthly income, family history of CHD, prior history of diabetes and hospital attended. Not unexpectedly, education had the most robust association with knowledge. In the adjusted analysis, gender, smoking and prior history of CHD and hypertension were not associated with knowledge.\nTable 5\nFactors associated with knowledge of coronary heart disease – univariate and multivariable analysis\nN\nMean Knowledge Score\nUnadjusted Coefficient\n8 \n(95% CI)\np value\nAdjusted Coefficient\n8 \n(95% CI)\np value\nAge\n0.01 (0.001, 0.03) \n‡\n0.035\n0.01 (0.002, 0.03) \n‡\n0.023\nGender\n0.008\n0.20\n Female\n234\n3.54\nref\nref\n Male\n558\n3.04\n-0.50 (-0.87, -0.13)\n-0.22 (-0.56, 0.12)\nMarital Status\n0.64\n Single\n202\n3.25\nref\n Married\n590\n3.16\n-0.09 (-0.48, 0.30)\nNA*\nEducation\n<0.001\n<0.001\n No Formal\n215\n1.80\nref\nref\n Formal Education\n577\n3.70\n1.89 (1.54, 2.25)\n1.42 (1.06, 1.77)\nMonthly income \n†\n<0.001\n<0.001\n <3000\n225\n1.88\nref\nref\n >3000\n567\n3.70\n1.82 (1.47, 2.17)\n0.76 (0.40, 1.13)\nResidence\n<0.001\n<0.001\n Rural\n335\n2.21\nref\nref\n Urban\n457\n3.90\n1.69 (1.37, 2.01)\n1.06 (0.75, 1.37)\nSmoking Status\n<0.001\n0.09\n Non smoker\n478\n3.47\nref\nref\n Smoker\n314\n2.75\n-0.728 (-1.07, -0.39)\n-0.27 (-0.57, 0.43)\nFamily Hx IHD\n<0.001\n<0.001\n No\n419\n2.68\nref\nref\n Yes\n373\n3.75\n1.07 (0.74, 1.40)\n0.61 (0.31, 0.91)\nPMH – Hypertension\n<0.001\n0.86\n No\n674\n3.05\nref\nref\n Yes\n118\n3.94\n0.89 (0.42, 1.36)\n0.04 (-0.41, 0.49)\nPMH – Diabetes\n<0.001\n0.004\n No\n745\n3.08\nref\nref\n Yes\n47\n4.85\n1.78 (1.07, 2.48)\n0.96 (0.30, 1.61)\nPMH – IHD\n0.004\n0.28\n No\n750\n3.13\nref\nref\n Yes\n42\n4.21\n1.09 (0.34, 1.84)\n0.37 (-0.31, 1.05)\nHospital\n Mayo\n241\n2.29\nref\nref\n AKU\n153\n3.55\n1.25 (0.78, 1.73)\n<0.001\n0.15 (-0.29, 0.59)\n0.50\n PIMS\n249\n3.45\n1.16 (0.74, 1.57)\n<0.001\n0.42 (0.03, 0.81)\n0.03\n AGH\n149\n3.81\n1.51 (1.03, 1.99)\n<0.001\n1.20 (0.76, 1.64)\n<0.001\n8\ncoefficient = slope of regression line. Values represent change in knowledge (per unit increase in independent variable or with category change compared to reference category)\nCI = confidence interval ‡ for each year increase in age ref = reference category\nHx = history PMH = past medical history IHD = ischemic heart disease\n* not in final model † in Rupees (1 Rupee = US$ 0.017)\nAKU = Aga Khan University Hospital, Karachi. Mayo = Mayo Hospital, Lahore. PIMS = Pakistan Institute of Medical Sciences, Islamabad. AGH = Allied General Hospital, Faisalabad.\nDiscussion\nOur study demonstrates a striking lack of knowledge about CHD amongst patient attendants at four hospitals catering to patients belonging to a wide demographic spectrum. Only 14% of the study group could correctly identify what coronary heart disease was. The majority of subjects were only able to identify up to 2 risk factors, the most commonly identified factors being stress, obesity, dietary fat and smoking. The median knowledge score of the study group was 3.0 out of a possible 15, suggesting a severe lack of awareness about CHD.\nOur findings are consistent with the study by Rankin et al. [\n8\n]. The gaps in knowledge are considerably high compared to what has been reported in Western countries [\n10\n].\nThe relatively poor knowledge about modifiable risk factors for CHD, including smoking (31.9%), obesity (14.1%), lack of exercise (17.4%) and dietary fat (39.1%) in our study population has been seen in other studies on South Asians [\n8\n]. It is possible that the very poor awareness about obesity and lack of exercise are related to their under representation in mass media campaigns as opposed to smoking and dietary fat. Our study highlights a significant lack of knowledge about modifiable risk factors and suggests the need for urgent emphasis on education amongst Pakistanis.\nRespondents in our study appeared to lack sufficient knowledge about the symptoms of CHD. Only 36% knew that chest pain was a symptom of heart disease and a substantial number of subjects gave vague descriptions about possible symptoms of CHD (Table \n3\n). Failure to recognize the symptoms of acute myocardial infarction is associated with delay in seeking medical care [\n11\n] and leads to worse clinical outcomes. Our study suggests a need for educating the public about symptoms of CHD.\nAge appears to have a linear relationship with knowledge in our study. When age was analyzed as a categorical variable, mean knowledge scores progressively increased from the ≤30 year age group (3.06) to the >60 year group (3.93; coefficient 0.76; p = 0.03). This is different to the findings of Potvin [\n10\n] in Canadians where, compared to the age group 18–24 years, the odds ratios for knowledge about risk factors decreased as aged increased, particularly in those aged 65–74 years. One possible explanation could be a very limited emphasis on health education in schools in Pakistan, as a result of which individuals finishing school do so with very little knowledge about CHD. As the years go by, they are likely to accrue knowledge (albeit in small increments). On the other hand, modern school education in the west may involve substantially more time spent on health education; as a consequence younger individuals are likely to be more knowledgeable than the elderly who may not have received such instruction during their schooling years. The finding that knowledge increases with the acquisition of formal education is consistent with other data [\n10\n,\n12\n]. Likewise, the association of income with knowledge has been reported in other studies [\n10\n]. In our study this association was independent of the level of education.\nThere were interesting differences in knowledge score between subjects recruited from the four different hospitals. The mean knowledge score was significantly higher in patients presenting to AGH, a hospital that caters to a substantially poorer, uneducated and rural population compared to AKU and PIMS (Table \n6\n). AGH conducts a large number of public awareness seminars and it is possible that this may be contributing to the higher knowledge scores in patients recruited from that hospital. This potential association between educational seminars for the public and knowledge deserves further investigation.\nTable 6\nKey demographic characteristics of study subjects interviewed from four hospitals in Pakistan.\nAKU N (%)\nMayo N (%)\nPIMS N (%)\nAGH N (%)\nMean age* (SD)\n40.0 (15.9)\n36.1 (11.4)\n40.4 (12.5)\n35.7 (12.1)\nIncome\n†\n <3000\n23 (15.0)\n123 (51.0)\n33 (13.3)\n46 (30.9)\n >3000\n130 (85.0)\n118 (49.0)\n216 (86.7)\n103 (69.1)\nEducation\n No formal\n27 (17.6)\n84 (34.9)\n47 (18.9)\n57 (38.3)\n Formal Education\n126 (82.4)\n157 (65.1)\n202 (81.1)\n92 (61.7)\nResidence\n Rural\n40 (26.1)\n126 (52.3)\n89 (35.7)\n80 (53.7)\n Urban\n113 (73.9)\n115 (47.7)\n160 (64.3)\n69 (46.3)\nAKU = Aga Khan University Hospital, Karachi. Mayo = Mayo Hospital, Lahore. PIMS = Pakistan Institute of Medical Sciences, Islamabad. AGH = Allied General Hospital, Faisalabad.\n* in years; SD = standard deviation\n†Self reported figures (per month in Rupees); estimates may be biased (1 Rupee = US$ 0.017).\nConsistent with the overall poor state of knowledge in our study group, preventive practices were found to be significantly lacking. Although nearly three-fourths of the study group felt that CHD was preventable, over two-thirds had never had their blood pressure checked, and an overwhelming majority had never undergone an assessment of their blood glucose or cholesterol levels. Furthermore, only a minority felt that they would modify their diet, stop smoking or start exercising if a family member was to develop CHD (table \n4\n), consistent with the fact that the vast majority of our study subjects did not identify a family history of CHD as a risk factor for developing CHD in the future.\nOur study is not without limitations. First, the non-probability convenience sampling method introduces selection bias. As samples were taken from four different hospitals in Pakistan representing a wide demographic spectrum, we feel that our study population may be somewhat reflective of the knowledge state of the general population of Pakistan. However, patient attendants may be either less knowledgeable or more informed than the general population. On the one hand, due to more exposure to a medical environment patient attendants may know more about CHD than the general public and therefore, the true knowledge state of the public may be lower. On the other hand, diseased individuals may, in part, be in that state due to the poor knowledge of their household members. Hence, selection of subjects from households of patients risks bias whereby the study subjects may be less knowledgeable than population controls. Second, the use of an open-ended questionnaire introduces the potential of recall bias on the part of the respondents and may underestimate the knowledge state of the study group. Third, computation of a knowledge score based on correct answers to a set of questions is somewhat arbitrary, does not incorporate differential weightage that may be placed on different questions and has not been widely validated. Nevertheless, we feel that this score provides a fair estimate of the degree of knowledge of an individual. Fourth, the majority of study subjects consisted of men. This is partly related to the fact that women in Pakistan are less likely to accompany patients to the hospital; furthermore, when women were approached, if they were accompanied by other male members of the family, the latter would take the lead in answering questions. Thus women are under-represented in this study. Finally, the specialty of the specific outpatient clinic from where respondents were recruited was not recorded and, therefore, not adjusted for in the analysis.\nConclusion\nIn conclusion, this is the first study that has attempted to assess the state of CHD knowledge in a relatively diverse non-patient population in Pakistan. We found striking gaps in knowledge, particularly about the understanding of the nature CHD and its risk factors (physiologic factors like high blood pressure and elevated blood cholesterol in particular). In addition there was an equally significant lack of knowledge about common symptoms of CHD. These deficiencies in knowledge appear to translate into inadequate preventive behavior patterns. Factors significantly associated with knowledge included age, income, education level, residence, a family history of CHD and a past history of diabetes. An interesting association between knowledge and site of recruitment was noted in this study group which may be related to the number of public awareness seminars conducted by the site. This association deserves further investigation. Our study, despite some limitations, should raise strong concerns about the lack of knowledge and awareness about CHD amongst lay persons in Pakistan and should serve as a stimulus for establishing health education programs in the country.\nList of abbreviations\nAKU = Aga Khan University Hospital\nPIMS = Pakistan Institute of Medical Sciences\nMayo = Mayo Hospital\nAGH = Allied General Hospital\nSD = standard deviation.\nCHD = coronary heart disease.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nFHJ, FA, HM, AW, MS, AA conceptualized this study and participated in the study design and manuscript writing and review. FA, HM, AW, MS, AA, MAQ were involved in the data collection process. FHJ performed the statistical analysis. JA, ISK and IH supervised the data collection process and also participated in manuscript review. All authors have read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
59
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nCarbohydrate restriction improves the features of Metabolic Syndrome. Metabolic Syndrome may be defined by the response to carbohydrate restriction\n\n**Article Abstract:**\n\nMetabolic Syndrome (MetS) represents a constellation of markers that indicates a predisposition to diabetes, cardiovascular disease and other pathologic states. The definition and treatment are a matter of current debate and there is not general agreement on a precise definition or, to some extent, whether the designation provides more information than the individual components. We consider here five indicators that are central to most definitions and we provide evidence from the literature that these are precisely the symptoms that respond to reduction in dietary carbohydrate (CHO). Carbohydrate restriction is one of several strategies for reducing body mass but even in the absence of weight loss or in comparison with low fat alternatives, CHO restriction is effective at ameliorating high fasting glucose and insulin, high plasma triglycerides (TAG), low HDL and high blood pressure. In addition, low fat, high CHO diets have long been known to raise TAG, lower HDL and, in the absence of weight loss, may worsen glycemic control. Thus, whereas there are numerous strategies for weight loss, a patient with high BMI \nand \nhigh TAG is likely to benefit most from a regimen that reduces CHO intake. Reviewing the literature, benefits of CHO restriction are seen in normal or overweight individuals, in normal patients who meet the criteria for MetS or in patients with frank diabetes. Moreover, in low fat studies that ameliorate LDL and total cholesterol, controls may do better on the symptoms of MetS. On this basis, we feel that MetS is a meaningful, useful phenomenon and may, in fact, be operationally defined as the set of markers that responds to CHO restriction. Insofar as this is an accurate characterization it is likely the result of the effect of dietary CHO on insulin metabolism. Glucose is the major insulin secretagogue and insulin resistance has been tied to the hyperinsulinemic state or the effect of such a state on lipid metabolism. The conclusion is probably not surprising but has not been explicitly stated before. The known effects of CHO-induced hypertriglyceridemia, the HDL-lowering effect of low fat, high CHO interventions and the obvious improvement in glucose and insulin from CHO restriction should have made this evident. In addition, recent studies suggest that a subset of MetS, the ratio of TAG/HDL, is a good marker for insulin resistance and risk of CVD, and this indicator is reliably reduced by CHO restriction and exacerbated by high CHO intake. Inability to make this connection in the past has probably been due to the fact that individual responses have been studied in isolation as well as to the emphasis of traditional therapeutic approaches on low fat rather than low CHO.\nWe emphasize that MetS is not a disease but a collection of markers. Individual physicians must decide whether high LDL, or other risk factors are more important than the features of MetS in any individual case but if MetS is to be considered it should be recognized that reducing CHO will bring improvement. Response of symptoms to CHO restriction might thus provide a new experimental criterion for MetS in the face of on-going controversy about a useful definition. As a guide to future research, the idea that control of insulin metabolism by CHO intake is, to a first approximation, the underlying mechanism in MetS is a testable hypothesis.\n\n**Article Body:**\n\nIntroduction\nAn association between obesity, diabetes, cardiovascular disease and hypertension has been recognized for some time. Reaven's 1988 Banting lecture is generally considered a turning point in codifying a unifying principle under the name of MetS or Syndrome X (Reviews: [\n1\n-\n7\n]. Although there is no universally accepted definition or mechanism, (Table \n1\n) a rough common denominator is the set of five features: obesity (high body weight, BMI and/or waist circumference), high glucose and insulin levels, low HDL, high TAG and high blood pressure. Involvement of insulin resistance is generally a common feature and a likely causative agent for at least some of the symptoms. A subset of these metabolic markers, the TAG:HDL ratio, has been proposed as a simple marker for identifying insulin resistance [\n8\n]. It has recently been questioned whether the risk attributed to MetS is greater than the sum of the individual symptoms [\n9\n] and, ironically, Reaven has taken the \"Con\" side on a debate on the viability and diagnostic usefulness of the concept [\n10\n,\n11\n]. Nonetheless, there seems little controversy on the inherent potential for risk in the individual components.\nTable 1\nNCEP-ATP III and WHO Definitions of Metabolic Syndrome. Other definitions in references [1], [4] and [90].\nATP III Definition\nAny three or more of the following criteria:\n a) Waist circumference: >102 cm in men, >88 cm in women\n b) Serum triglycerides: ≥150 mg/dL\n c) HDL-cholesterol: <40 mg/dL in men, < 50 mg/dL in women\n d) Blood pressure: ≥130/85 mm Hg\n e) Serum glucose: >110 mg/dL\nWHO Definition\nDiabetes or IFG or IGT or insulin resistance, plus at least two of the following criteria\n a) Waist-to-hip ratio: >0.90 in men, >0.85 in women\n b) Serum triglycerides: >150 mg/dL \nor \nHDL-cholesterol: <35 mg/dL in men and <40 mg/dL in women\n c) Blood pressure: >140/90 mmHg\n d) Urinary albumin excretion rate > 20 μg/min \nor \nalbumin/creatinine ratio >30 mg/g\nIn reading recent reviews of low CHO diets [\n12\n,\n13\n], we were struck by the fact that the symptoms of MetS are precisely the ones targeted by diets that restrict CHO. This effect is not entirely surprising since it has been known that dietary CHO tends to raise glucose, insulin, and TAG and lower HDL and conversely, replacing CHO with monounsaturated fat or with fat and protein improves glycemic control and dyslipidemia expressed as elevated TAG and lowered HDL. Nevertheless, most formal guidelines and clinical papers have not emphasized CHO restriction as a viable approach to treating MetS or the individual components [\n14\n,\n15\n] and although several authors have indicated an association between MetS and CHO restriction in passing [\n5\n,\n13\n,\n16\n,\n17\n] the explicit connection has not been made.\nIn this study we have isolated five features that are common to almost all definitions. Waist circumference is probably the currently preferred measure for obesity, but most of the literature provides data on body mass and we have used that measure. We have collected information in the literature supporting the notion that these symptoms are specifically ameliorated by reduction in dietary CHO, and to the extent that they have been directly compared, low CHO strategies appear to have an advantage over low fat diets or simple calorie reduction. We conclude that response to CHO restriction may be an operational definition for MetS and that a likely mechanism is the control of insulin metabolism. Finally, we side with those who maintain that MetS is a real thing in the sense that the concomitant appearance of several symptoms may provide different recommended strategies than the isolated factors. It is important to point out, however, that MetS is not a disease but a complex of markers and practitioners may decide that LDL or other factors are more important for individual patients and in these cases other therapies will be appropriate. On the other hand, reliance on LDL as a prime indicator must be tempered by the importance of LDL particle phenotypes which, in turn, correlate with TAG and HDL levels, a subset of MetS markers.\nCHO restriction for weight loss\nIt is sometimes stated that MetS is caused by obesity [\n1\n]. In our view, this is only one of several possible theories and would assume that we know the causes of obesity. It is at least plausible that obesity and the features of MetS arise in parallel from disruptions of insulin metabolism (possibly a consequence of high insulin due to chronic high dietary CHO). Also a high prevalence of so called metabolically obese-normal-weight individuals with MetS has long been known [\n18\n]. In any case, it is generally agreed that the first line of attack against MetS or frank diabetes should be reduction in body mass. The method for attaining this weight loss, however, is more controversial. Studies in the literature imply that a low fat diet is a kind of standard although much recent evidence has indicated the value of strategies based on carbohydrate restriction. Whereas low fat diets for calorie reduction can undoubtedly be effective for many people, we feel that they cannot be taken as an established standard; to our knowledge, there has never been a long term study where a low fat diet was instituted in the absence of confounding features such as cessation of smoking and exercise. Also, fat restriction \nper se \ndoes not enhance long-term (one year or longer) weight loss or prevent regain of weight [\n19\n] and the record of compliance is modest at best [\n20\n]. Most important, the fact that, in the obesity and diabetes epidemic, fat consumption went down (for men, the absolute amount) and carbohydrate consumption went up [\n21\n,\n22\n], means that other approaches should be considered. Insofar as isocaloric comparisons have been made, low CHO diets do at least as well, and usually better, than low fat diets (see below). Most striking, in \nad lib\n. trials, subjects on low CHO diets show a spontaneous reduction in calories without any dissatisfaction [\n23\n-\n25\n], a goal that is universally considered desirable but generally recognized as difficult to impose by cognitive admonitions on calorie restriction \nper se \n[\n26\n]. In general, published data support the idea that low CHO diets are at least as effective as other weight reduction methods. Further, experimental results show an improvement in lipid outcomes (discussed below), no damage to normal kidneys [\n27\n], the potentially beneficial rather than deleterious effects of ketone bodies [\n28\n-\n30\n] and the prevalence of strategies based on low glycemic index [\n31\n,\n32\n] or reduction of refined CHO or sweets, all approximations of low CHO diets.\nDespite increased acceptance of low carbohydrate regimens, it is important to point out that there is a tendency to equate any kind of carbohydrate restriction with the popular Atkins diet [\n33\n] and to equate the Atkins diet with a recommendation for high fat and with high saturated fat, in particular. There are, however, many strategies for reducing carbohydrate intake both clinically and in popular diets [\n34\n,\n35\n]. Whereas high fat is permitted on the Atkins diet and other low carbohydrate diets it is not specifically recommended; as noted above, at least three published studies [\n23\n-\n25\n] and much anecdotal evidence suggests that, in practice, the major effect is reduction in carbohydrate intake with limited replacement with either fat or protein. In addition, although a deleterious effect of saturated fat, at least in the absence of CHO control, is established [\n36\n,\n37\n], it has been known since the Seven Countries study [\n38\n] that total dietary fat does not correlate with cardiovascular risk and the two effects should not be confused [\n36\n,\n37\n]. In any case, no particular diet is recommended here; the studies cited include all kinds of interventions, and the underlying rationale is the effect of carbohydrate on insulin. The principle espoused here should be evaluated on this basis.\nIt seems that a prudent statement of the state of affairs would be that, at this point, dieters have many strategies, none perfect, for weight loss and CHO restriction of some kind is one of them.\nCHO restriction and MetS\nOur argument in the following exposition is that a patient presenting with a high BMI or large waist line has several options for weight loss. Many factors, including physician experience, ethnic background, personal taste and genetic profile, will determine the first one to be tried. A patient presenting with high BMI \nand \nhigh TAG may have a clear best strategy because of the known benefit of CHO reduction and the accepted deleterious effect of high CHO intake. Data from the literature suggests that a patient with more than two of the symptoms of MetS or the particular combination of high TAG/HDL ratio should clearly try CHO restriction as a first strategy. Conversely, the patient with high BMI and high LDL might sensibly try a low fat strategy first. We provide a summary of cases in which CHO restriction is beneficial in the treatment of MetS or its individual symptoms. The review is meant to be representative rather than comprehensive but we think that the wide variety of cases studied and the range of conditions against a background of accepted effects of carbohydrate on the relevant parameters, provides a strong case for our thesis. In addition, the generally consistent benefit of CHO restriction allows a possible further basis for identifying the common thread in MetS if such truly exists.\nCHO restriction improves symptoms of MetS\nTable 2 (Table \n2\n) shows the results of single arm studies in which CHO-restricted diets of various compositions and duration were used (for summary of details see, e.g., [\n39\n-\n41\n]). The regimens include very low CHO ketogenic diets (< 50 g/d) and encompasses subjects that were overweight, presented with symptoms of MetS, or were diabetic. It is clear that CHO restriction is effective in relieving these symptoms. Noteworthy is the recent study of Boden [\n23\n] which, while short in duration, carefully measured relevant parameters in patients with diabetes. Patients in this study spontaneously decreased food intake to a substantial degree, were satisfied with the diet, did not show substantial water loss and several were able to reduce or terminate medication.\nTable 2\nCHANGE\nReference\n#\nSubjects\nDuration\nCHO (g/d)\nweight (%)\nHDL (%)\nTAG (%)\nTAG/HDL (%)\nGlucose (%)\nInsulin (%)\nRickman \net al\n. 1974\n1\nNormal Weight Men/Women\n3–17 d\n7\n-4.9\n-11.4\nLaRosa \net al\n. 1980\n2\nObese Men/Women\n8 wk\n6\n-8.3\n-5.7\n-32.6\n-29.9\nPhinney \net al\n. 1980\n3\nObese Men/Women\n6 wk\n<20\n-11.8\n-24\n-16.3\n-57.3\nPhinney \net al\n. 1983\n4\nNormal Weight Men\n4 wk\n<20\n0.2\n0\n-26\n-7.7\n-23.3\nNewbold, 1988\n5\nMen\n3–12 mo\n9.6\n-34.8\n-40.5\nVolek \net al\n. 2000\n6\nNormal Weight Men\n8 wk\n39\n-5.4\n10.0\n-54.9\n-56.9\n-3.4\n-28.0\nSharman \net al\n. 2002\n7\nNormal Weight Men\n6 wk\n46\n-2.8\n11.5\n-33\n-39.9\n-0.2\n-34.2\nMeckling \net al\n. 2002\n8\nObese Women\n8 wk\n71\n-6.1\n4.3\n-40.3\n-4.1\n0.0\nWestman \net al\n. 2002\n9\nObese Men/Women\n6 mo\nAd Lib\n-10.3\n19.2\n-43.1\n-53.6\nDashti \net al\n. 2003\n10\nObese Men/Women\n12 wk\n20 to 30\n-13.4\n8.3\n-50\n-53.9\n-37.1\nHays \net al\n. 2003\n11\nObese Men/Women w/ CVD\n6 wk\nAd Lib\n-5.2\n-2.9\n-39.9\n-38.1\n-7.4\n-30.5\nObese Women PCOS\n24 wk\nAd Lib\n-14.3\n0.4\n-18.5\n-18.8\n5.7\n-49.6\nObese Women Reactive Hypoglycemia\n52 wk\nAd Lib\n-19.9\n3.4\n-13.3\n-33.2\nDashti \net al\n. 2004\n12\nObese Men/Women\n24 wk\n40\n-14.2\n20.4\n-60.4\n-67.1\n-22.6\nBoden \net al\n. 2005\n13\nObese/diabetic men/women\n14 days\n21\n-1.8\n-2\n-35\n-33.8\n-16.0\nImprovement is seen in the absence of weight loss\nSince it is known that weight loss generally improves MetS, it is important to ask whether beneficial metabolic responses to low CHO diets are dependent on weight loss. The question was specifically addressed by Volek's group [\n42\n,\n43\n] in normal-weight men and women encouraged to maintain their weight and by Allick and colleagues in patients with diabetes mellitus type 2 [\n44\n] (Table \n3\n). The studies in normal weight women [\n43\n] and type 2 diabetics [\n44\n], in particular, used a cross-over experimental design removing the confounding effect of group differences. These studies were also well-controlled. In the case of Allick, formula was used and, in the studies by Volek, compliance was documented by measuring elevation of serum and urine ketones, thereby eliminating dietary reporting errors as a confounding factor. Improvement in the TAG/HDL ratio ranged from 40 to 55%. In summary, a low CHO regimen clearly improves MetS relative to low fat diets even in the absence of weight loss.\nTable 3\nCHANGE\nReference\n#\nSubjects\nDuration\nDiet\nCHO (g/d)\nweight (%)\nHDL (%)\nTAG (%)\nTAG/HDL (%)\nGlucose (%)\nInsulin (%)\nSharman \net al.\n2002\n1\nNormal Weight Men\n6 wk\nKetogenic\n46\n-2.8\n11.5\n-33.0\n-39.9\n-0.2\n-34.2\n6 wk\nLow-Fat\n271\n0.5\n0.0\n-5.3\n-5.3\n1.8\n13.0\nVolek \net al\n. 2003\n2\nNormal Weight Women\n4 wk\nKetogenic\n43\n-2.0\n32.0\n-30.2\n-47.2\n-1.9\n11.6\n4 wk\nLow-Fat\n249\n-1.3\n-7.7\n3.8\n0.5\n-5.3\n18.7\nAllick \net al\n. 2004\n3\nType 2 Diabetics\n2 wk\nKetogenic\n0\n0\n23.5\n-43.9\n-55\n-16.9\n-16.7\n2 wk\nLow-Fat\n775\nIn addition to studies in which weight maintenance was a feature of experimental design it is important to consider data reported by Foster [\n45\n] (Figure \n1\n, (Table \n4\n), who compared low CHO and LF diets. It is widely quoted that the low CHO diet is better at 6 months but that there is no difference in the diets at 12 months. However, it has been pointed out [\n12\n] that the particular form of low CHO diet used (Atkins diet) allowed increases in CHO consumption as the trial progressed indicating that it is likely this reintroduction of CHO that predisposes to long-term regain in weight. Most notable in this study, is that the improvement in lipid profile persisted (Figure \n1\n, (Table \n4\n) even after the effect on weight loss disappeared.\nFigure 1\nComparison of features of Metabolic Syndrome on low carbohydrate vs. high carbohydrate diets\n. Data from reference [45].\nTable 4\nCHANGE\nReference\n#\nSubjects\nDuration\nDiet\nCHO (g/d)\nweight (%)\nHDL (%)\nTAG (%)\nTAG/HDL (%)\nGlucose (%)\nInsulin (%)\nDBP (mm Hg)\nBrehm \net al\n. 2003\n1\nObese Women\n6 mo\nLow-CHO\n41–97\n-9.3\n13.4\n-23.4\n-32.4\n-9.1\n-14.8\n-5\nLF\n163–169\n-4.2\n8.4\n1.6\n-6.3\n-4.0\n-23.0\n-1\nSondike \net al\n. 2003\n2\nOverweight Adolescents\n12 wk\nLow-CHO\n37\n-10.7\n8.7\n-40.5\n-45.2\nLF\n154\n-4.1\n4.2\n-5.4\n-9.2\nSamaha \net al\n. 2003\n3\nObese Men/Women\n6 mo\nLow-CHO\n150\n-4.5\n0.0\n-20.2\n-20.2\n-8.6\n-27.3\nLF\n201\n-1.4\n-2.4\n-4\n-1.6\n-1.6\n5.6\nFoster \net al\n. 2003\n4\nObese Men/Women\n1 yr\nLow-CHO\nad lib\n-7.3\n18.2\n-28.1\n-29.5\nLF\nad lib\n-4.5\n1.4\n0.7\n-2.6\nVolek \net al\n. 2004\n5\nOverweight Women\n4 wk\nLow-CHO\n29\n-3.9\n1.3\n-23\n-28.3\n-3.8\n-8.8\nLF\n186\n-1.4\n-8.6\n-11.2\n-4.2\n1.3\n23.2\nSharman \net al\n. 2004\n6\nOverweight Men\n6 wk\nLow-CHO\n36\n-5.6\n-3.3\n-44.1\n-42.3\n-5.8\n-41.5\nLF\n224\n-3.6\n-6.6\n-15\n-8.3\n-5.2\n-28.1\nBrehm \net al\n. 2004\n7\nObese Women\n4 mo\nLow-CHO\n69\n-10.8\n16.3\n-37.3\n-46.1\n-9\nLF\n174\n-6.8\n4.5\n-10.3\n-14.2\n-3\nMeckling \net al\n. 2004\n8\nObese Men/Women\n10 wk\nLow-CHO\n59\n-7.7\n12.2\n-29.4\n-37.1\n-8.0\n-28.7\n-6.1\nLF\n225\n-7.4\n-15.4\n-25.4\n-11.8\n-10.2\n-3.3\n-5\nStern \net al\n. 2004\n9\nObese Men/Women\n1 yr\nLow-CHO\n120\n-3.9\n-2.8\n-28.6\n-26.8\nLF\n230\n-2.3\n-12.3\n2.7\n29.6\nYancy \net al\n. 2004\n10\nObese Men/Women\n24 wk\nLow-CHO\n30\n-12.3\n9.8\n-47.2\n-51.8\n-6\nLF\n198\n-6.7\n-2.9\n-14.4\n-12.1\n-5.2\nAude \net al\n. 2004\n11\nObese Men/Women\n12 wk\nLow-CHO\nad lib\n-6.2\n-2.6\n-23.2\n-21.1\nLF\nad lib\n-3.4\n-7\n-10.5\n-3.8\nSeshadri \net al\n. 2004\n12\nObese Men/Women\n6 mo\nLow-CHO\n113\n(-8.5)\n-2.4\n-7.4\n-40\nLF\n198\n(-3.5 kg)\n-2.4\n-2.3\n11.2\nMcAuley \net al\n. 2004\n13\nObese Women\n8 wk\nLow-CHO\n41\n-6.9\n0.9\n-38.8\n-44.2\n-5.9\n-39.3\nLF\n172\n-4.4\n-6\n-17.5\n-15.1\n-0.1\n-28.4\nMod-PRO\n130\n-5.8\n-4.1\n-33.9\n-31.8\n-3.9\n-24.4\nDansinger \net al\n. 2004\n14\nObese Men/Women\n2 mo\nLow-CHO\n103\n-4.7\n8.8\n-27.6\n-26.20\n-10\n-29.5\nMod-PRO\n158\n-4.6\n4.6\n-34\n-30.50\n-9.3\n-27.7\nLF\n183\n-4.3\n-0.6\n-7.1\n-5.60\n-5.7\n-11\nUltraLF\n230\n-4.9\n-10.9\n-0.6\n8.40\n-3.5\n-7.7\nIn \nad lib\n. comparisons low CHO diets do better than low fat diets for weight loss and MetS\nAt this point, we have established that CHO restriction improves MetS and that this can be independent of weight loss. Weight loss can, of course, occur with low fat diets and we next consider the extent to which one or the other strategy is more effective. (Table \n4\n) summarizes results of several studies in the literature demonstrating that low CHO diets generally do better than low fat diets in \nad lib\n. comparisons. Although there is great variability, a pattern of better responses on very low CHO is evident. It is notable that Samaha et al studied a population in which 39 % had diabetes and 43% had MetS [\n46\n].\nFigure \n1\n shows data from the study of Foster, et al. [\n45\n] and, as noted above, despite the relative similarity in weight loss, the markers of MetS were more favorable in the low CHO arm than the LF arm.\nIn isocaloric comparisons, low CHO diets do better than LF diets for weight loss\nBecause weight reduction is considered the first line of attack in MetS or frank diabetes it is worth considering the record of low CHO diets on this parameter alone. It is generally agreed that the major effect of a low CHO diet is a spontaneous reduction in calories. In studies mentioned above, subjects did not significantly increase fat or protein intake but merely removed CHO from their diets [\n23\n-\n25\n]. Foster and Samaha also attributed the better performance of low CHO arm to decreased caloric intake, although this was not actually measured.\nBeyond spontaneous caloric reduction, however, it has been shown that the macronutrient composition of the diet can affect the efficiency of energy utilization and greater efficacy, the so-called metabolic advantage, of low CHO diets compared to LF diets has been the subject of several reports (Reviews: [\n39\n,\n41\n]. It has long been argued that there must be some mistake because it is physically impossible and would violate the laws of thermodynamics. We have shown this argument is based on misunderstanding of the laws of thermodynamics [\n39\n,\n47\n-\n49\n] and the effect of variable efficiency is now better accepted [\n50\n,\n51\n]. The precise conditions that allow the so-called metabolic advantage to occur are not known although Cornier, \net al\n. [\n51\n] have suggested that those subjects with insulin resistance will show a metabolic advantage on a low CHO diet whereas those who are insulin sensitive do better on low fat. This is consistent with the proposal here, namely that MetS, where insulin-resistance is generally considered a major component, can be defined by the response to CHO restriction. The study of Cornier, \net al\n. [\n51\n] had only a small number of subjects and the low CHO arm was not particularly low (40%) but their theory follows from the general rationale of the effect of CHO on energy efficiency. The factors that determine whether a metabolic advantage can play a role in a CHO restricted diet is unknown but given that the insulin resistance association is reasonable, it would seem that some form of CHO restriction is one of the standard, if not preferred attacks on obesity where MetS is suspected.\nFigure \n2\n shows data from Golay, \net al\n. [\n52\n] This study is widely quoted as an example of how weight loss is independent of macronutrient composition; although the low CHO arm did better in weight loss, this was judged not significant. This may well be an experiment in which metabolic advantage does not occur – the effect is only possible, not required [\n39\n]. It is clear, however, from the figure that there is improvement in TAG and insulin and Golay's conclusion was that \"...considering the greater improvement of fasting blood insulin, the glucose/insulin ratio and blood triglyceride, the low carbohydrate diet (25%) could be more favourable in the long-term [\n52\n].\"\nFigure 2\nPer cent change in response to diet\n. Low carbohydrate (dark blue 25 % CHO) and low fat diets(light blue: 45 % CHO). Data from Golay, et al. [52].\nFigure 3\nEffect of carbohydrate on parameters of Metabolic Syndrome\n. Comparison of 40% CHO (blue) and 55% (red) CHO diets. Data from [54].\nIs this new?\nIn Edgar Allan Poe's detective story The Purloined Letter, the police search the apartment for a missing blackmail note [\n53\n]. In the end, Poe's detective, Auguste Dupin reveals that it had been in plain view on the fireplace all along. The effect of CHO reduction on the symptoms of MetS has, in fact, been visible for some time. In a classic review in 1986, Reaven demonstrated the relative effects of 40% and 55% CHO [\n54\n]. Figure \n3\n shows data from that study: day long glucose, insulin and TAG levels were improved by the low CHO diet. Of interest, is that fasting glucose is not different on the two diets but there is a clear difference in the time course, common to several low CHO interventions (Table \n3\n)). Reaven's experiment suggests that a nutritional approach to MetS is possible by lowering dietary CHO. The experiment should sensibly have spurred research to see whether still lower CHO had further beneficial effect. It took many years, however, before this was done.\nFigure 4\nEffect of diet on plasma glucose\n. Mean plasma glucose concentration before (triangles) and after 5 weeks on control diet (yellow circles: (CHO:fat:protein = 55:30:15)) or 5 weeks on lower carbohydrate diet (blue circles: (20:50:30)). Meal points are Breakfast (B), lunch (L) and dinner(D) plus 2 snacks (S1, S2). Data from reference [57].\nSubstitution of protein for CHO improves MetS\nDespite the evidence from Reaven's experiment, a barrier to progress in understanding the role of CHO restriction was the accepted idea that high fat was unhealthy. At the same time, it was thought that an increase in protein would be deleterious for type 2 diabetics because of the increase in glucose due to gluconeogenesis. Nuttall and Gannon have summarized the history of this problem and work in their lab showed that, in fact, glycemic control was enhanced by a diet that was 40 % CHO, with protein replacing part of the carbohydrate [\n55\n,\n56\n]. Most recently, this group has shown the benefit of a 20 % CHO diet with higher protein [\n57\n]. Results in Figure \n4\n show a pattern similar to Reaven's but much more dramatic. Similar striking differences in the control of insulin and TAG were also demonstrated.\nFigure 5\nChanges in cholesterol/HDL for substitution for fat\n. Fat in the average American diet was substituted with the indicated substances at 10 % of energy. Data from reference [62].\nExplicit low-fat/high CHO interventions exacerbate MetS\nIn the approach taken here, we see dietary fat as playing a largely passive role (not withstanding differences between different fats) and the disposition of dietary fat is controlled by insulin and other hormones that, in turn, depend on dietary CHO which we take as the controlling variable. Thus, characterizing a low CHO diet as high fat [\n58\n,\n59\n] ignores the question about the underlying mechanism; we have recently raised the question of whether \"high fat\" is a meaningful description in the absence of information about CHO [\n60\n]. In the cases we discuss next, the focus is interventions described or designed as low fat. Our point here, however, is that although low fat diets exacerbate the markers of MetS, it is likely the high CHO rather than the fat level that is important.\nA very influential paper by Garg, et al. [\n61\n] describes a four center randomized study of patients with type 2 diabetes receiving glipizide treatment. The study compared diets where monounsaturated fat was substituted for CHO or vice-versa. Because of its importance, we quote from this article. The rationale for the study, according to the authors is that:\n\"Compared with diets rich in saturated fats, low-fat, high-carbohydrate diets are reported to reduce serum low-density lipoprotein (LDL) cholesterol levels. Recent studies, however, suggest the high-carbohydrate diets may accentuate hypertriglyceridemia, reduce serum high-density lipoprotein (HDL) cholesterol concentration, and may even worsen hyperglycemia and/or raise plasma insulin levels.\"\nIn short, the question is whether high CHO diets worsen MetS. The conclusions of the paper state:\n\"The study confirms that HC (high carbohydrate diets) increase plasma TAG levels and increase VLDL-C concentrations in NIDDM patients. In this study the HC diet raised fasting plasma triglyceride levels and VLDL-C concentrations by 24 % and 23 % respectively compared with the HMUF diet. Furthermore, daylong levels of plasma triglycerides were also elevated on the high-carbohydrate diet. Consistent with the results of previous studies, plasma levels of total cholesterol and LDL cholesterol were not different on the two diets in this study. The study, therefore substantiates the fact that high carbohydrate diets offer no advantage in lowering LDL levels in NIDDM patients compared with high-fat diets that are low in saturated fats.\"\nThe general case: substitution of fat for CHO improves MetS\nThe substitution of fat for CHO is, in fact, generally beneficial for MetS. In a recent meta-analysis, Mensink, \net al\n. [\n62\n] showed the effect of substitution of different fat sources or carbohydrate for the fat in the average US diet at 10% of energy. The conclusion was that substitution of carbohydrate had the most unfavorable response on the total cholesterol to HDL ratio, significantly worse than butter or palm oil (Figure \n5\n).\nSummary of review and hypothesis to this point\nWe have summarized work in the literature showing that low CHO interventions improve the markers of MetS in normal subjects, patients with MetS and diabetics. In comparative studies, they are at least as effective as low fat diets for weight loss and, tend to show better improvement in the other markers of MetS. Isocaloric studies similarly support the idea that the markers of MetS respond preferentially to low CHO diets.\nThe state of accepted scientific thinking for the world at large is unknown but we have made the case that it is an acknowledged principle that low CHO diets tend to reduce TAG, raise HDL and improve glycemic control whereas LF/high CHO diets tend to have the opposite effect. Perhaps the strongest indication that such an idea is generally accepted is the paper by Rock, et al [\n63\n] where the effect of low fat diets in cancer patients was studied. To demonstrate compliance with the low fat recommendations, the authors showed increased TAG and reduced HDL levels. These effects were judged not significant enough to cause a risk for CVD but demonstrate that low fat (higher CHO) diets point in that direction.\nWe reiterate that this article is not meant to make recommendations – for which many factors must be considered – but rather to show the association between CHO restriction and improvement in symptoms of MetS. Many low fat interventions have successfully reduced LDL, an established risk factor for CVD. If our hypothesis is correct, however, these same interventions should worsen the features of MetS. To some extent this is established from the principles noted above, but we provide an example from a well done experiment in the literature to support this corollary. Finally, in considering the dialectic of treating MetS with CHO restriction vs. high LDL, with low fat diets, it is important to consider both individual variation and the role of LDL particle size. We consider that last.\nStudies of low-fat diets\nThe most salient feature of the obesity epidemic from the standpoint of food consumption is the dramatic increase in CHO intake and the reduction in fat intake (for men, the absolute amount). To our knowledge, the decreased fat intake has not been accompanied by reduction in the incidence of CVD in unmedicated population. These data suggest that low fat diet recommendations \nper se \nare not likely to help MetS. If the fundamental idea proposed here is correct, then experimental interventions targeting lower fat that concomitantly raise CHO should, in fact, have a deleterious effect on the markers of MetS. Again, one will have to decide if the symptoms of MetS are more important than LDL or total cholesterol which are typically reduced on LF diets in the unmedicated population.\nDelta-1 Study\nThe Delta-1 study is one of the very well done trials involving a large number of participants [\n64\n]. The goal was to determine \"the effects of reducing total fat and saturated fat\" although this is slightly misleading in that only saturated fat was reduced and any reduction in total fat was a consequence of this. The randomized and balanced diets that were compared all contained approximately 15 % of calories as protein. Other macronutrients were as shown in Table \n5\n. (Table \n6\n) shows the outcomes for all groups on lipids in the Delta-1 study. The results indicate that LDL is significantly reduced although only SEM is given so that it is not possible to know the range of responses of subjects. As a group, however, there were step-wise reductions in LDL and HDL going from the average American diet (AAD) to Step 1 to the low saturated fat diet. There is, as well, a corresponding increase in TAG and hence the TAG/HDL ratio. The authors concluded that the reduction in LDL should be associated with 10% to 20% reductions in cardiovascular disease in the population. Other authors have argued, however, that the effect of the 13% higher HDL seen on the AAD might be associated with a 36% reduction in the risk of death from coronary disease or of myocardial infarction [\n65\n]. Again, the purpose here is not to decide on the relative risk attached to different markers but only to point out that the markers for MetS provide another side to the story. An important follow-up in the Delta study to determine HDL subpopulations [\n66\n], showed that the more \nanti\n-atherogenic HDL\n2 \nparticles were, in fact, decreased by reductions in saturated fat.\nTable 5\nMacronutrient composition of diets in the Delta-1 study. Data from reference [64].\nDiet\nCHO (%)\ntotal fat (%)\nSFA (%)\nMUFA (%)\nPUFA (%)\nAverage American diet (AAD)\n48\n34\n15\n13\n7\nStep 1\n55\n29\n9\n13\n7\nLow Saturated Fat\n59\n25\n6\n12\n7\nTable 6\nAve American Diet vs. Step 1\nAve American Diet vs. Low Sat Fat\nGinsberg, \net al\n.,1998 reference [64]\nAAD\nStep 1\ndelta\n% change\npre\npost\ndelta\n% change\nTotal cholesterol\n202.1\n191\n-11.1\n-5.5\n202.1\n183.4\n-18.7\n-9.3\nLDL\n131.4\n122.2\n-9.2\n-7.0\n131.4\n116.9\n-14.5\n-11.0\nTAG (mmol/l) antiln (log)\n85.1\n92.4\n7.3\n8.6\n85.1\n93\n7.9\n9.3\nHDL (mmol/l)\n52.2\n48.5\n-3.7\n-7.1\n52.2\n46.2\n-6.0\n-11.5\nTotal/HDL\n4.1\n4.16\n0.1\n2.2\n4.1\n4.21\n0.1\n3.4\nTAG/HDL (arbitrary units)\n1.6\n1.9\n0.3\n16.9\n1.6\n2.0\n0.4\n23.5\nThe overall conclusion is that \"dietary changes suggested to be prudent for a large segment of the population will primarily affect the concentrations of the most prominent antiatherogenic HDL subpopulation. However, the simultaneous reduction in the atherogenic LDL subpopulation will most likely offset any potential negative effect on cardiovascular risk.\" As noted above, the decision as to \"most likely\" outcome must rest with individual patients and physicians.\nRole of individual responses and LDL heterogeneity\nAs noted in Garg's study, changes in LDL may not be as reliable as changes in other markers. Volek, \net al\n. for example showed that whereas TAG was reduced in almost every subject on a low CHO diet, responses in LDL were highly variable [\n67\n]. The importance of LDL subpopulations has recently been appreciated and, unlike total LDL, changes in specific LDL particles show a consistent pattern with respect to dietary change.\nGreater atherogenic potential is associated with small, dense LDL particles [\n68\n]. Krauss and coworkers have carried out impressive work in defining the variability in different individuals. They identified a genetically influenced pattern (B) in people whose plasma contains small LDL particles. This subpopulation, typically 30 % of the American population, responded to low-fat diets by lowering LDL but the pattern B persisted [\n69\n]. The remaining subpopulation with larger buoyant particles (pattern A) responded to reduction in fat intake by a shift to the more atherogenic pattern B. Thus, for most of the populations studied, replacing dietary fat with CHO leads to a worsening of the LDL size distribution [\n70\n]. In a study described in reference [\n70\n], similar effects were seen when protein was substituted for carbohydrate without significant change in the fat content or composition. As summarized by Krauss, \"This indicates that carbohydrate rather than fat is a major dietary determinant of expression or phenotype B in susceptible individuals.\" Although probably a semantic point, \"susceptible\" is redundant and describing pattern A and B as phenotypes may not be precise: Krauss has summarized how the relative amounts of CHO and fat affect the prevalence of pattern B [\n71\n] and the conclusion is that a strong relation exists between CHO intake (ranging from 40 to 75%) and the prevalence of the pattern B phenotype (Fig \n6\n). In other words, there appears to be a continuous variability in phenotype characterized by sensitivity to CHO and everyone may be susceptible to conversion to pattern B at some CHO/fat ratio. The extrapolated line in Figure \n6\n suggests that a truly low CHO diet might reduce the level of atherogenic subtype to zero. Thus, whereas we have described the dialectic in practical applications as balancing the improvement in MetS with CHO restriction and the improvement in LDL from low-fat diets, focusing on LDL may have some caveats. In general, a growing body of work has shown improvement in LDL pattern switching from high CHO to low CHO diets [\n42\n,\n43\n,\n72\n-\n75\n].\nFigure 6\nPrevalence of pattern B phenotype as a function of the percentage dietary CHO in men. Data from reference [71].\nThe pattern B phenotype rarely occurs in isolation and, our major concern here is that it is metabolically linked to and co-expressed with other characteristics of MetS, particularly elevated TAG and low HDL. Krauss and colleagues reported that switching from a low CHO/high-fat diet (46% fat) to a high CHO/low-fat diet (26% fat) resulted in lowering of LDL, but also a worsening of TAG and HDL when switching to the low fat diet [\n69\n]. In men that were pattern A at a fat intake of 20 to 24%, a further reduction in dietary fat to 10% and CHO to 76% of energy resulted in conversion to B, with continued worsening of TAG and HDL, and no additional LDL-lowering [\n76\n].\nThe TAG/HDL connection\nIn the search for markers for both insulin resistance and predisposition to CVD, recent research has focused on the value of the ratio of TAG:HDL. McLaughlin, et al. [\n8\n] have shown a correlation between insulin resistance as measured by steady-state glucose levels after infusion of glucose, insulin and octreotide (to suppress endogenous insulin secretion). The conclusions of their study were that TAG and HDL were independently related to insulin resistance and the TAG/HDL ratio was the best predictor of insulin resistance. Of importance here is that the results showed that this ratio is comparable to the ATP III criteria for MetS in predicting insulin resistance and \"even better in prediction the LDL phenotype B in two separate populations who were on different diets.\" This is, in fact, only the most recent of several studies (references in [\n8\n]) that have shown a correlation between TAG/HDL and insulin resistance and CVD risk as measured by LDL particle size. Table 2-4 as well as Figures \n2\n and \n5\n indicate that low CHO diets reliably reduce this marker. Inability to recognize this is again due to the separate conditions in which they are measured and the continued emphasis on reducing dietary fat above all else.\nMcLaughlin's analysis [\n8\n] identified a TAG/HDL ratio of ≥ 3.5 as a cutoff for identifying the insulin-resistant patient most at risk for CVD. It is of interest that in Foster's study [\n45\n] described above (Table 3; Figure \n1\n), the average beginning values were 4.6 and 4.3 in the low CHO and low-fat arms, respectively, substantially above this cutoff value. After six months, the low CHO arm had reduced this marker to 3.7 while the LF group showed little change at 4.2. Similarly, in the Delta-1 study, neither the Step 1 diet nor the low fat diet were able to improve the TAG/HDL ratio which was above the threshold value of 3.5 (Table \n6\n)).\nMechanism\nA recent review by Ginsberg [\n77\n] has provided an excellent description of the possible mechanisms and central role of insulin resistance in mediating the dyslipidemia of MetS. In combination with a proposal by Volek [\n13\n] on the mechanism for the reversal of this process, a reasonable understanding of the connection between MetS and CHO restriction is possible.\nA primary target of insulin is hormone-sensitive lipase. Adipocyte insulin resistance, plausibly a down regulation of insulin response due to continued stimulation (from higher dietary CHO), leads to increased lipolysis [\n78\n,\n79\n]. This will lead to greater delivery of fatty acids and an increase in hepatic esterification, and subsequent over production of VLDL, particularly the TAG-rich VLDL1. In combination with impaired plasma TAG clearance, a constant state of hypertriglyceridemia in the postabsorptive and postprandial period occurs. This leads to the exchange of TAG in VLDL for cholesteryl ester in LDL. The resulting TAG-rich LDL particle is a preferred substrate for hepatic lipase and lipoprotein lipase and thereby for generation of small, dense LDL. A similar neutral lipid exchange likely occurs with HDL whereby TAG-rich HDL is hydrolyzed by lipoprotein lipase resulting in the generation of smaller HDL particles that are rapidly removed from the circulation. In this way, elevated TAG resulting from disruption in insulin function, plays a central role in regulating the atherogenic dyslipidemia of MetS.\nAs noted above, Volek, et al. [\n13\n] have reviewed many studies showing that CHO restriction results in significant reductions in postprandial lipemia, and beneficial effects on HDL and intravascular processing of lipoproteins. A key component is what might be called the fatty acid paradox. Whereas insulin resistance is frequently characterized by high fatty acid levels, CHO restriction can improve insulin resistance while raising fatty acids. The latter effect is presumed to be due to lower insulin levels and disinhibition of hormone sensitive lipase. This is accompanied by enhanced cellular fatty acid uptake, mitochondrial transport and increased oxidation. The bias toward fat oxidation over storage reduces hepatic TAG and reduces synthesis and secretion of VLDL.\nDiscussion\nA joint position statement by several organizations recommended \"current dietary guidelines from the ADA, AHA and the NCEP-ATP III.... These recommendations may require modification, however, as new information is generated from additional diet intervention studies [\n80\n].\" Rather than additional studies, however, we provide new information from an evaluation of papers already in the literature that may provide a basis for modification. Data compiled in Figures \n2\n, \n3\n, \n4\n show that low CHO diets improve the symptoms of MetS as defined by five common criteria. We propose that in addition to potential value as therapy, the response to CHO restriction might be considered an operational definition of MetS. Beyond formal categorizing, the idea is consistent with the generally held belief that MetS is intimately involved with some form of insulin resistance. (The importance of other factors such as inflammation are not mutually exclusive). Cornier \net al\n. showed differential benefit of low CHO vs. low fat diets for people with or without insulin resistance [\n51\n]; this study might be thought of as a model for future work to follow this line of thinking. We emphasize that our main point is that an intimate connection between CHO restriction and the complex of symptoms of MetS is seen in the literature of both low CHO studies and low fat (higher CHO) studies. Individual judgment as to the importance of MetS compared to other specific factors or more global assessments such as the Framingham criteria will determine how use is made of this connection. We do believe, however, that ignoring studies on CHO restriction would be unscientific and unproductive.\nHow low is low carbohydrate?\nGoneril\n. What need you five-and-twenty, ten, or five...?\nRegan\n. What need one?\n- William Shakespeare, \nKing Lear\n.\nThe data summarized here suggest that some degree of CHO restriction would provide a first line of attack against the symptoms of MetS. The principle of CHO restriction is that by keeping insulin low, metabolism is biased towards lipid oxidation rather than storage, or the effects of fatty acids on peripheral tissues. Most studies that reported deleterious effects of saturated fat have been carried out in the presence of high CHO and there is a real question whether such effects carry over into hypocaloric conditions or those where insulin is better controlled [\n28\n,\n60\n,\n81\n,\n82\n].\nIn general, whereas current thinking in MetS emphasizes the consequences of insulin resistance, we feel that the role of CHO-induced hyperinsulinemia as a causative factor in generating the initial insulin resistance, dyslipidemia or obesity has been under-appreciated. In any case, there are now many ways to implement CHO restriction ranging from ketogenic diets (less than 50 g/d) to diets based on glycemic index, an indirect method of reducing insulin excursions. The question is how low is low? It is clear that 40% CHO is better than 55% for MetS and there has been some reluctance to go lower even though the studies that have done so show continued improvement. Perusal of Table 2-4 suggests that the lower, the better. Insofar as pattern B is associated with insulin resistance and MetS, examination of Figure \n4\n supports this idea. The barriers to exploring lower CHO diets appears to be continued emphasis on low fat intake although it has been known since Keys's Seven Country study that total fat in the diet does not correlate with cardiovascular risk [\n38\n]. At least as indicated in its popular diet book, the No-Fad Diet [\n83\n], the American Heart Association has removed its limitation on total fat which should open the door to more flexible diet interventions. Since many studies have shown that there is frequently a spontaneous reduction in total caloric intake in very low CHO diets and that CHO removed is not replaced by fat or protein, very low CHO now appears as a far more prudent choice than judged in the past.\nIs this new?\nThe phenomenon of CHO-induced hypertriglyceridemia is long established [\n84\n-\n88\n]. In addition, low fat diets are known to reduce, not only LDL, but also HDL levels. For example, the 2004 recommendations of the American Diabetic Association (ADA) state that \"Low-saturated fat (i.e., 10% of energy) \nhigh carbohydrate \ndiets \nincrease postprandial levels of plasma glucose, insulin, triglycerides \nand, in some studies, \ndecrease plasma HDL cholesterol \nwhen compared in metabolic studies to isocaloric high monounsaturated fat diets.\" This is our conclusion (our italics). We think the ADA statement could have been more clearly worded: \"Substitution of CHO for monounsaturated fat \"increase(s) postprandial levels of plasma glucose, insulin...\" or could have been more comprehensive: \"substitution of CHO or protein for fat increases...\" In other words, it has been known for some time that low fat reduces HDL as well as LDL concentrations as described clearly in the Delta-1 study. Again, Rock's study that used the increase in TAG and decrease in HDL as a marker for compliance to a low fat diet supports the idea as an accepted principle.\nIn combination with the experimentally observed and intuitively obvious reduction in fasting blood glucose and insulin, our proposal for the importance of CHO replacement in the diet hardly seems new. Yet such an idea, to our knowledge has never been made explicit. The primacy of the low fat paradigm in traditional thinking may have played a role in ignoring this obvious correlation. However, we have, in various places, presented or summarized evidence that low CHO diets have a beneficial effect on MetS [\n13\n,\n16\n] but the tight connection proposed here conceptually eluded us. Having raised the question, however, it is now clear that it is perfectly consistent with established knowledge.\nIs MetS useful?\nThe intricacies of the debate among official agencies on the clinical importance of MetS [\n9\n] are beyond the scope of this article. As a first order approximation, however, we are inclined to follow Reaven's strategy in the Point/Counterpoint paper [\n10\n,\n89\n] for assessing the need for the concept of MetS. He describes a patient with a BMI of 27.8 kg/m\n2 \nwho would not conform to the WHO definition of MetS because of acceptable values of glucose, TAG and an HDL level of 37 mg/dL and he points out that if the HDL level fell to 33 mg/dL such a patent would fit a new criteria but would not sensibly be treated in a different way. Under the approach considered here, the patient with the higher HDL would be presented with a number of options for weight loss whereas the patient with lower HDL might reasonably be counseled to CHO restriction as a first strategy. We therefore think that MetS or some combination of markers by any other name would have much more virility than the description of MetS as Methuselah in his amusing Counterpoint [\n87\n]. We also side with the \"Pro\" position on the value for basic research. Reaven raises the critical question: \"How can there be a common etiology for a diagnostic category based on satisfying 3 of 5 arbitrarily defined criteria when any combination of the 3 will define the same phenotype as any other trio of abnormalities.?\" A plausible answer to this question is that if all the markers in MetS are related to hyperinsulinemia and/or insulin resistance, then the relative K\nm\n's for insulin for the different target proteins and different tissues are likely to lead to a variable time course for specific individuals and markers are likely to exceed cutoff at different times for each patient. Appearance of one marker may then be indicative of other still silent conditions.\nRecommendations for the American population\nThe data summarized here suggest that there is value in the definition of MetS and that a nutritional strategy based on CHO restriction might sensibly be the \"default\" diet, the first to be tried, for patients with MetS. In the case of normal weight individuals with MetS, CHO restriction may be the only effective non-pharmacological approach for treating the diversity of symptoms. The choice of any intervention, however, depends on individual assessment of the relative importance of different risk factors and our goal here is the establishment of the close link between CHO restriction and MetS rather than any recommendation.\nThe recent AHA/NHLBI Scientific Statement on Metabolic Syndrome [\n90\n,\n91\n] as well as the ATP III emphasize as the primary target, LDL, a marker that is not considered a feature of MetS and that may not even be high in many patients with MetS. Whereas nutritional recommendations are quite general (reduce weight, increase exercise), these reports emphasize a low fat diet (although limiting simple sugars). We think this is inconsistent and we have made the case that a low fat diet, if high in carbohydrate, seems to be widely accepted as raising TAG, lowering HDL and worsening glycemic control, seemingly the wrong thing for MetS. We also disagree with the assertion in the AHA/NHLBI statement that most low CHO diets are high in saturated fat. This statement is undocumented and, as noted in the introduction, essentially equates all reduced carbohydrate approaches and does not seem to distinguish between total and saturated fat. Even if it were true the statement avoids the question of the effect of saturated fat in the presence of low CHO or hypocaloric diets [\n60\n,\n81\n,\n82\n,\n92\n]. In practical terms, a recommendation to reduce saturated fat on low CHO diets might be more helpful than blanket prohibition. In addition, the AHA/NHLBI report [\n90\n] presents the rationale for low CHO as the effect on appetite. Whereas this may be a component, it has been stated many times, and is part of basic biochemical education [\n16\n,\n93\n-\n96\n], that the rationale of CHO restriction is the control of metabolism by insulin regulation. The effects described above clearly support this. Although we think that, within the framework of MetS, some recommendations can be made, in the end we are probably in agreement with Reaven's judgment that \"What is required is less advice and more information [\n54\n].\"\nQuestions raised\nThe data summarized here leave little room for doubt that the generally accepted deterioration in HDL and TAG levels with low fat diets and the established improvement in glycemic control with CHO restriction are part of a more general picture. The hypothesis that response to CHO restriction (because of the effect on insulin) is the defining feature of MetS is the proposed generalization. This idea raises several questions.\nIs there a threshold level of CHO restriction that is necessary to elicit improvements in MetS? What is the effect of replacing the calories lost from CHO with protein or with fat, and in what proportion? How does this compare to not replacing them at all?\nDoes excessive CHO consumption \ncause \nMetS in susceptible individuals?\nWhat is the relative risk in addressing MetS with CHO restriction compared to low fat diets for reduction in LDL? That is, what is the relative risk of high LDL vs. the symptoms that comprise MetS?\nWhat is the role of genotype in determining the response to CHO restriction?\nSummary\nFive symptoms common to most definitions of MetS are those that are reliably improved by CHO restriction. Carbohydrate restriction is one strategy for weight loss but, in addition, improves glycemic control, insulin levels, TAG and HDL levels even in the absence of weight loss. We suggest that response to CHO restriction may, in fact, be an operational definition of MetS. Its underlying basis would rest on the idea that the features of MetS are associated with a disruption in insulin metabolism which is strongly influenced by dietary CHO. The extent to which this definition is useful may depend on its application by individual practitioners. Experimental studies that follow its lead or conversely disprove its fundamental premise should advance our understanding of obesity, diabetes and CVD. Dismissing CHO restriction without evidence, or expressing \"concerns\" rather than offering data will probably be less productive.\nAbbreviations\nAdult Treatment Panel (ATP III), American Diabetes Association (ADA), American Heart Association (AHA), Average American diet (AAD), carbohydrate (CHO), low fat (LF), Metabolic Syndrome (MetS), National Cholesterol Education Program (NCEP), triacylglycerol (TAG), World Health Organization (WHO)\nCompeting interests\nThe author(s) declare that they have no competing interests.\nNote\nTable 2 - Effect of carbohydrate restriction on markers for Metabolic Syndrome \n(See Table \n2\n)\nData shown in bold indicate improvement in marker, plain, worsening. References:1. [97]; 2. [24]; 3. [98]; 4. [99]; 5. [100]; 6. [101]; 7. [42]; 8. [102]; 9. [103]; 10. [104]; 11. [74]; 12. [105]; 13. [23].\nTable 3 - Effect of carbohydrate restriction on markers for Metabolic Syndrome under conditions of constant body mass \n(See Table \n3\n)\nData shown in bold indicate low CHO shows greater improvement in markers for MetS than LF; plain, LF is better. Table reference 3 shows the ratio of low CHO to LF. References: 1. [42]; 2. [43]; 3. [44].\nTable 4 - Comparison of low CHO vs. LF diets on markers for Metabolic Syndrome \n(See Table \n4\n)\nData shown in bold indicate low CHO (or mod-PROT) shows greater improvement in marker than LF; plain, LF is better. Experiment in reference [106] was carried out for a longer time period but diets became very similar. References:1. [107]; 2. [113]; 3. [46]; 4. [45]; 5. [108]; 6. [72]; 7. [109]; 8. [110]; 9. [111]; 10. [112]; 11. [73]; 12. [75]; 13. [59]; 14. [106].\nTable 6 - Outcomes of the Delta-1 study \n(See Table \n6\n)\nData from reference [64]. bold indicates improvement in the parameter from Step 1 or low Saturated Fat diet compared to AAD; plain indicates worsening of parameter compared to AAD.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
60
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe Vital Link Between Chronic Disease and Depressive Disorders\n\n**Article Abstract:**\n\nIntroduction\nChronic diseases have assumed an increasingly important role in public health research and intervention. Without treatment, depressive disorders characteristically assume a chronic course and are expected, by 2020, to be second only to heart disease in the global burden of disease. Thus, understanding the relationship between depressive disorders and chronic disease appears vital to public health assessment and health care delivery.\nMethods\nArticles for review were primarily identified by a Medline search emphasizing the subject headings \nmental disorders\n or \ndepression\n crossed with selected chronic diseases and conditions including asthma, arthritis, cardiovascular disease, cancer, diabetes, and obesity.\nResults\nMental illnesses — most specifically, depressive disorders — were associated with increased prevalence of chronic diseases. This association between depression and chronic disease appears attributable to depressive disorders precipitating chronic disease and to chronic disease exacerbating symptoms of depression. The complex interrelationship between depressive disorders and chronic disease has important implications for both chronic disease management and the treatment of depression.\nConclusion\nDepressive disorders assume an important role in the etiology, course, and outcomes associated with chronic disease. Multivariate community-based research and intervention fostering the detection and treatment of depressive disorders is needed, as is further examination of the role exerted by mental illnesses other than depression in the pathogenesis of chronic disease.\n\n**Article Body:**\n\nIntroduction\nRecent research indicates that seven out of 10 office visits to a primary care practitioner concern chronic diseases (\n1\n). As the management of chronic diseases has assumed an increasingly vital role in health care delivery, recognition of the importance of depressive disorders has also grown. By 2020, depression is expected to be second only to heart disease as a source of the global burden of disease (\n2\n). As chronic disease and depressive disorders are increasingly recognized as major impediments to health, understanding the connection between them becomes of utmost importance to providing quality health care.\nDespite the growing recognition of the importance of both chronic disease and depressive disorders to the health of individuals and communities, research examining their interrelationship has been the subject of surprisingly little empirical review. A Medline search for literature reviews emphasizing both chronic disease and depression yielded only two publications. These articles addressed factors germane to health-service costs (\n3\n) and individual characteristics precipitating the onset of depressive disorders subsequent to the development of chronic disease (\n4\n). While raising important concerns, previous reviews were deliberately limited in scope and did not generally address disease-specific variables potentially underlying the associations between depressive disorders and a number of chronic diseases. To better address this issue, we reviewed the research literature examining the relationships between depressive disorders and prevalent chronic diseases that are also of programmatic relevance to the work of the Centers for Disease Control and Prevention.\nMethods\nArticles included in this review were primarily identified through a Medline search of the terms \nmental disorders\n or \ndepression\n crossed with the chronic diseases and conditions asthma, arthritis, cardiovascular disease, cancer, diabetes, and obesity. These chronic diseases were selected because they have been identified as highly prevalent and as major sources of morbidity and mortality among U.S. adults. Studies included for review were generally limited to empirical investigations that provided definitional or diagnostic criteria for both depression and relevant chronic diseases and that featured a specified time course.\nResults\nAsthma\nNearly 50% of asthma patients may suffer from clinically significant depressive symptoms (\n5\n), which have been, in part, attributed to the stress of having a chronic illness (\n6\n). In particular, persons with asthma who experience disruptive symptoms, such as dyspnea and nighttime awakening, are at increased risk for major depression (\n7\n). The presence of depression among persons with asthma assumes particular gravity because increased depressive symptoms have been associated with poorer asthma outcomes (\n8\n), such as impaired voluntary activation of the diaphragm (\n9\n). In clinical samples of children and adolescents, asthma has been associated with the presence of an anxiety disorder (\n10\n) and with anxious depressive symptoms among youth with moderate and severe persistent asthma (\n11\n).\nIt appears that the symptoms — rather than the diagnosis — of asthma are associated with depression or anxiety (\n12\n): 87.5% of persons with frequent asthma attacks manifest psychopathology, compared with 25% of persons with less frequent attacks (\n13\n). Similarly, among persons whose asthma is difficult to control, psychopathology — primarily anxiety and depressive symptoms — was associated with more frequent visits to primary care providers and emergency departments and with more hospitalizations (\n14\n). Psychological morbidity is associated with poor adherence to medication regimens (\n15\n), and mothers of children with asthma are at risk for increased depressive symptoms (\n16\n). Early assessment and intervention addressing depressive disorders improves treatment adherence and outcomes and may also decrease mortality (\n17\n).\nCognitive behavioral therapy (CBT) — in which the individual is instructed to monitor and challenge self-negating thoughts — has yielded a significant decrease in asthma symptoms and depression (\n18\n). Likewise, physical inactivity has been speculated to augment the strength of the association between perceived stressors and depression in persons with asthma, suggesting that exercise may ameliorate this association and decrease the likelihood of depression in this population (\n19\n).\nArthritis\nDepression and/or anxiety are among the most commonly reported concerns by persons with arthritis (\n20\n). Screening of patients with arthritis revealed that depression was associated with activity restriction, further suggesting that nonpsychiatric physicians should be aware of the mental health status of patients with chronic illnesses (\n21\n). Persons with arthritis experiencing arthritis-based disability (\n22\n) and the recurrence of arthritic symptoms (\n23\n) reported greater depression. Research on adolescents and young adults with arthritis has found that functional status is significantly correlated with depression, self-esteem, and loneliness (\n24\n); significantly greater depression was reported among those experiencing more severe symptoms (\n24\n).\nResearch on the Arthritis Self-Management Program found that participation in this intervention had a positive effect on perceptions of self-efficacy, communication with physicians, fatigue, anxiety, pain, and depression (\n25\n). A randomized trial of an intervention designed to improve mood (antidepressant medications and/or six to eight sessions of psychotherapy) improved depression and fostered improvements in functional status and quality of life (\n26\n). CBT has proven particularly effective in ameliorating depressive symptoms when initiated early in the course of rheumatoid arthritis (\n27\n) and when tailored to the concerns reported by persons with rheumatoid arthritis, such as fatigue or mood (\n28\n). Similarly, antidepressant medication has been associated with significant improvements in both psychological status and health status in persons with rheumatoid arthritis (\n29\n).\nRest and inactivity were previously considered to be reasonable therapeutic approaches in the management of osteoarthritis until it was recognized that physical inactivity contributed to disability and impaired functioning. Subsequent research suggests that a tailored program of aerobic or resistance-based exercise may be an important component of self-managing osteoarthritis (\n30\n). Aerobic exercise has been found to both ameliorate depressive symptoms and to reduce disability and pain among persons with arthritis (\n31\n).\nCardiovascular disease\nDepressive disorders have been associated with risk factors for cardiovascular disease (CVD), such as smoking and physical inactivity (\n32\n), and mental illness, in general, has been associated with increased mortality due to CVD (\n33\n). In general, persons who are depressed are much more likely to develop coronary artery disease (\n34\n), and meta-analyses reveal that the relative risk for developing heart disease in individuals with depression or depressive symptoms is approximately 1.6 times greater than among nondepressed persons (\n35\n,\n36\n), which is more than the risk conferred by passive smoking (\n36\n). A stronger effect size was reported for clinical depression than for depressive symptoms, suggesting the presence of a dose-response relationship (\n35\n). Depression has been positively associated with the metabolic syndrome among women (but not men) younger than 40 years (\n37\n), suggesting that early detection and treatment of depression may potentially forestall the risk of cardiovascular disease among women.\nDepression or depressive symptoms are also predictive of stroke (\n38\n): persons with significant depressive symptoms are approximately twice as likely as those with few depressive symptoms to have a stroke within 10 years (\n39\n). Moreover, depression is associated with an increased risk for stroke morbidity and mortality (\n40\n).\nIn addition to being a predictor of stroke, depression commonly develops after a stroke, especially after a stroke affecting the left hemisphere of the brain (\n41\n). More than half of patients experiencing a stroke report depressive symptoms within 18 months of having a stroke (\n42\n). Post-stroke depression has been associated with impairments in response to rehabilitation (\n43\n) and with increased mortality up to two years following the stroke (\n44\n). Antidepressant treatment of post-stroke depression is warranted and, in addition to alleviating depression, may foster recovery of cognitive function (\n45\n) and significantly increase survival (\n46\n).\nDepressive disorders also appear related to the occurrence of heart attack, or myocardial infarction (MI). Persons with a history of major depression are more than four times as likely to have an MI than those with no history of depression (\n47\n), and high levels of depressive symptoms are associated with an increased risk of MI (\n48\n).\nApproximately one in six persons who have experienced an MI suffer from major depression, and at least twice that many experience significant depressive symptoms (\n49\n). Patients who have had an MI and are also depressed have more medical comorbidities (\n50\n) and cardiac complications (\n51\n) and are at greater risk for mortality (\n52\n) than their nondepressed peers. Increased mortality is also evident in persons who had an MI and who manifest very low levels of depressive symptoms (\n53\n), underscoring the importance of mental health to physical health outcomes.\nPersons with depression following an MI are less likely to adhere to recommended lifestyle and behavioral changes, potentially increasing their risk for subsequent cardiac events (\n54\n). This is particularly unfortunate because cardiac rehabilitation has been found to improve depressive symptoms (\n55\n). However, the use of a specific class of antidepressant medications — the selective serotonin reuptake inhibitors (SSRIs) — may, in addition to their beneficial effect on depression, exert antiplatelet effects protecting against MI (\n56\n). In addition to being safer in overdose (\n57\n), SSRIs are also less likely to induce arrhythmia than other classes of antidepressant medications (\n58\n). It has further been concluded that the combination of CBT with an SSRI is frequently the most effective treatment of depression in persons with CVD (\n59\n).\nCancer\nEstimates of the prevalence of psychiatric disorders among persons with cancer vary widely, depending on the type of cancer and its clinical stage. Previous research indicates that nearly 50% of patients newly admitted to a cancer center met diagnostic criteria for a psychiatric disorder. Adjustment disorders — distress related to a specific precipitant — comprised 68% of these diagnoses, although many of those diagnosed reported anxiety or depression as a central symptom (\n60\n). Among cancer patients judged terminally ill, 53% met psychiatric diagnostic criteria, with delirium — a fluctuating change in cognition and disturbance in consciousness — being the most frequently diagnosed disorder (\n61\n).\nIn addition to delirium, cancer patients also suffer from depression and anxiety (\n62\n); 21% of cancer patients are reported to be depressed (\n63\n). Depression assumes particular significance in the care of individuals with cancer, because it has been associated with a desire for hastened death among terminally ill cancer patients (\n64\n), and increased depressive symptoms are inversely related to survival (\n65\n). Of cancer patients in an intensive care unit who were assessed as being at high risk for hospital death, 40% reported depression (\n66\n), suggesting that diagnosis and treatment of depression are inadequate. Strikingly, among cancer patients undergoing chemotherapy and experiencing anemia-related fatigue, improved hemoglobin levels have been reported to reduce depressive symptoms (\n67\n), further suggesting the importance of physical health to mental health status.\nA previous survey of psychotropic prescription practices at five major oncology centers revealed hypnotics to be the most widely prescribed drugs, with antidepressants comprising only 1% of psychotropic prescriptions (\n68\n). Subsequent research, however, has indicated an increase of antidepressant use in community cancer care, with 19.2% of breast, 11% of colon, and 13.7% of lung cancer patients receiving antidepressants during a two-year interval (\n69\n).\nDespite the observation that both antidepressants and psychotherapy are effective in treating depression in patients with cancer, research on antidepressant pharmacotherapy and psychotherapy among persons with cancer has been characterized as largely lacking randomized placebo-controlled trials (\n70\n). Moreover, antidepressant prescription has been found to be associated with factors not specifically related to psychopathology, such as patient age or the presence of pain (\n69\n), and some speculate that most depressed patients with cancer do not need medication (\n71\n). This belief, however, may reflect the misconception that depression is a \"natural\" response to cancer and does not merit systematic diagnosis and treatment (\n72\n).\nResearch suggests that depression in persons with cancer is amenable to treatment. Among cancer patients with a life expectancy of at least 12 months, CBT has been associated with significantly decreased depressive symptoms across a four-month interval (\n73\n). CBT has also been associated with decreased pain, reduced symptomatic distress (\n74\n), and subsequent improvement in cellular immune function (\n75\n).\nAdoption of a depression screening program and antidepressant algorithm by oncologists resulted in significant improvements in mood and quality of life among cancer patients (\n76\n). Similarly, a placebo-controlled trial of antidepressant medication in advanced cancer patients demonstrated that antidepressant therapy decreased depressive symptoms and improved patient assessments of quality of life (\n77\n). In addition to reducing the risk of depression, data suggest that physical activity may also decrease the risk of colon, breast, and lung cancer (\n78\n).\nDiabetes\nElevated rates of depression have consistently been associated with diabetes (\n79\n), with results of a meta-analysis indicating depression is twice as prevalent among persons with diabetes than it is among persons without diabetes (\n80\n). While it has been proposed that depressive symptoms may be a risk factor for the development of diabetes, this association is most pronounced at high levels of depressive symptoms and, interestingly, only observed among persons with less than a high school education (\n81\n). These findings suggest that factors associated with low socioeconomic status may contribute to the development of diabetes among persons with substantial depressive symptoms.\nComorbid depressive symptoms or depression among persons with diabetes have been associated with adaptation to the illness (\n82\n), diabetic-related complications (\n79\n), unemployment (\n83\n), and illness intrusiveness, a construct defined as the degree to which diabetes disrupts valued activities and interests (\n84\n). As is true in the general population, depression was more prevalent among women than among men with diabetes (\n80\n,\n85\n) and among younger adults (\n85\n). Depressive symptoms are more likely to persist among persons with multiple diabetic-related complications and those with less than a high school education (\n79\n). In a prospective community-based study, baseline depressive symptoms were positively associated with fasting insulin levels and physical inactivity (\n86\n). A diagnosis of diabetes and self-reported depression were positively associated with sedentariness in both bivariate and multivariate analyses (\n87\n). Compared with their nondepressed peers, patients with diabetes who were diagnosed with depression were more likely to report frequent overeating of sweets and high-fat foods and were less satisfied with their ability to adhere to a diabetic diet away from home (\n88\n).\nDespite the availability of measures to screen for depression, it is estimated that less than 25% of those with depression are diagnosed and treated (\n89\n). This is particularly disconcerting because the treatment of depression appears to be associated with improved glycemic control (\n90\n). Furthermore, because depression is associated with diabetic complications (\n91\n), treatment of depression may also reduce diabetes-related disability. Compared with their nondepressed peers, persons with diabetes and depression have higher ambulatory-care use and fill more prescriptions. Total health expenditures for persons with diabetes and depression were 4.5 times higher than for those without depression: $247 million compared with $55 million (\n85\n).\nResearch has revealed that both CBT (\n90\n) and antidepressant pharmacotherapy (\n92\n) are associated with decreased severity of depression among persons with diabetes and with improved glycemic control. Thus, in addition to preventing needless suffering, the treatment of depression among persons with diabetes offers the added promises of substantial financial savings and improved medical care of these individuals.\nObesity\nSeveral studies have indicated an association between psychopathology, including depressive symptoms, and high body mass index (BMI), or obesity. The relationship between obesity and psychopathology differs among men and women, with a BMI ≥30 among women associated with nearly a 50% increase in the lifetime prevalence of depressive disorders compared with nonobese women (\n93\n). In contrast, while BMI has not been found to be related to measures of mental well-being among men, abdominal obesity or a high waist/hip ratio has been associated with an increased prevalence of both depressive symptoms (\n94\n) and antidepressant medication use (\n95\n).\nAlthough it is important to note that most overweight or obese persons do not suffer from mood disorders (\n96\n), significant positive associations have been reported between BMI and depressive symptoms (\n97\n). It has been posited that a common pathophysiology may underlie both obesity and depression. The neurotransmitters serotonin and norepinephrine are involved in regulating both mood and body weight and, logically, in the treatment of both depression and obesity (\n98\n). Antidepressant medications available before the development of SSRIs frequently induced weight gain; newer agents generally do not stimulate appetite, thus making them potentially useful in depressed patients who do not wish to gain weight (\n99\n).\nPrevious longitudinal research has examined the relationship between depressive symptoms or psychological well-being and weight gain. Women who were either normal weight or overweight at baseline and who had experienced a recent weight gain scored lower on a measure of psychological well-being than women who had not gained weight (\n100\n). Similarly, persons who were overweight and depressed at baseline demonstrated a significantly increased likelihood of subsequent weight gain relative to those who were not depressed. Among the highest quintile of baseline BMI, this relationship was stronger among women (with an odds ratio of 2.2) than men (with an odds ratio of 1.3) (\n101\n).\nCognitive behavioral interventions have been useful in managing obesity, largely by modifying eating behaviors and dietary choices in addition to decreasing psychological distress and sedentariness (\n102\n). In addition to fostering weight loss, CBT has been found to improve self-reported mental health among obese persons (\n103\n). However, psychosocial difficulties have been associated with weight gain following initial weight loss among obese individuals who had received CBT (\n104\n), with long-term CBT compliance being particularly low among persons with binge-eating behaviors (\n105\n).\nStrikingly, children and adolescents with major depressive disorder appear to manifest an increased risk for subsequently becoming overweight (\n96\n), suggesting that both depressive disorders and their treatment are relevant to the prevalence of obesity. The relationship between obesity and depressive disorders thus appears to be reciprocal, with advances in the recognition and treatment of each of these diseases potentially fostering improved mental and physical health.\nDiscussion\nResearch examining the association between depressive disorders and chronic disease suggests that timely diagnosis and treatment of psychiatric disorders could greatly affect the impact of chronic disease. The presence of mental illness may be an important contributor to the etiology of chronic disease. Thus, the promotion of mental health would likely result in reducing a considerable proportion of the burden of chronic disease. Similarly, the presence of depressive disorders often adversely affects the course and complicates the treatment of chronic disease. It is important to remember that untreated depressive disorders characteristically assume a chronic course (\n106\n), thereby adding to the burden of chronic disease in their own right. Multivariate investigation of the associations among depressive disorders, chronic disease, and a variety of medical and sociodemographic characteristics would provide valuable insights into contemporary notions of health and quality of life.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
61
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nFlecainide overdose – support using an intra-aortic balloon pump\n\n**Article Abstract:**\n\nBackground\nFlecainide is an antiarrhythmic agent which is being used increasingly for the management of super-ventricular arrhythmias. Overdose with flecainide is frequently fatal with mortality reported as high as 22% due to arrhythmias, myocardial depression and conduction defects leading to electro-mechanical dissociation and asytole. Supportive measures are often required during the case and previously have included inotropes, extracorporeal membrane oxygenation and cardiopulmonary bypass.\nCase presentation\nA 47 year old lady presented to the emergency department with a four hour history of severe central chest pain. Her ECG showed atrial fibrillation and broad QRS complexes with a sine wave appearance. She had a past history of paroxysmal atrial fibrillation and significant psychiatric history. Following thrombolysis for a presumed myocardial infarction she developed cardiogenic shock with severely impaired left ventricular function. An intra-aortic balloon pump was inserted and coronary angiography demonstrated normal coronary arteries. With inotropic support she improved over 48 hours, with both her QRS duration and left ventricular function returning to normal. Biochemical testing following her discharge demonstrated significantly elevated levels of flecainide.\nConclusion\nThe use of an intra-aortic balloon pump is a useful supportive measure during the acute phase of flecainide overdose associated with severe myocardial depression.\n\n**Article Body:**\n\nBackground\nFlecainide is an increasingly used class 1C antiarrhythmic drug used for the management of both supra-ventricular and ventricular arrhythmias. It causes rate-dependent slowing of the rapid sodium channel slowing phase 0 of depolarisation [\n1\n] and in high doses inhibits the slow calcium channel. Flecainide also slows conduction in all cardiac fibres, increasing conduction times in the atria, ventricles, atrio-ventricular node and His-Purkinje system and can cause myocardial depression.\nCase presentation\nA 47 year old lady presented to the emergency department with a four hour history of severe central chest pain radiating to the neck. She had a significant psychiatric history with multiple episodes of self harm and had previously been hospitalised with behavioural problems. The patient had a history of multiple admissions with cardiac sounding chest pain, all with normal ECG and cardiac troponin levels. An outpatient stress nuclear perfusion scan was normal. The patient also had a history of arterial hypertension and paroxysmal atrial fibrillation and was managed on a combination of amitriptyline, losartan, amlodipine and flecainide. During this admission she repeatedly denied taking an overdose.\nOn admission to the emergency room the patient was unresponsive with a GCS of 6. She rapidly regained consciousness but remained slightly drowsy. Pupil response was normal. Her pulse was 70 bpm and blood pressure 60/40 mmHg. The 12-lead ECG (figure \n1\n) revealed atrial fibrillation with a broad QRS complex (320 ms) with a sine wave appearance. An ECG had been performed 4 weeks previously and was normal. She had normal serum potassium (4.1 mmol/l). The presentation with chest pain led to a presumptive diagnosis of an acute myocardial infarction and she was treated with thrombolysis with intravenous alteplase. Ten minutes later there was a significant change in her ECG (figure \n2\n). Inotropic support was instituted with dobutamine and subsequently with adrenaline to maintain her blood pressure. She remained hypotensive with poor urine output and was transferred to the regional cardiothoracic unit for further management. Blood was taken for paracetamol, salicylate levels which were normal. Flecanide levels were requested. Blood gases showed pH 7.37, pCO2 6.1kPa, pO\n2 \n11.7, bicarbonate 25.3 mmol/l\nFigure 1\n12-lead ECG on admission.\nFigure 2\n12-lead ECG after thrombolysis.\nOn arrival at our institution, transthoracic echocardiography revealed global moderate impairment of left ventricular function. Emergency coronary angiography was performed demonstrating normal epicardial coronary arteries and left ventriculography confirmed the echocardiography findings. An intra-aortic balloon pump was inserted with a rapid improvement in haemodynamics. Over the following 48 hours the patient was weaned from the inotropes and the intra-aortic balloon pump was removed. During this period her QRS duration gradually returned to normal (figure \n3\n) with left axis deviation and first degree heart block (which was present 12 months previously). Repeat echocardiography demonstrated normal left ventricular function.\nFigure 3\n12-lead ECG after treatment.\nFollowing discharge her flecanide levels were returned as 2340 μg/l (normal therapeutic range 200–700 μg/l) at 24 hours post admission.\nDiscussion\nThe mortality of overdose with class 1C agents has been reported as high as 22% compared to less than 1% for all drug overdoses [\n2\n]. In such cases fatal outcome is often related to the progression of conductions disturbance to electromechanical dissociation and asytole. Although less common, ventricular arrhythmias may occur and are frequently unresponsive to electrical cardioversion [\n3\n]. Other features may occur due to impaired tissue perfusion including hypoxia, metabolic acidosis, coma and convulsions. Hypotension can occur within minutes of a significant flecainide overdose, and subsequent reduction in hepatic and renal flow leading to prolongation of the duration of toxicity.\nThe proarrhythmic effects of flecanide may be related to flecainide promoting re-entry in ventricular tissue [\n4\n]. Worsening of existing ventricular arrhythmias or the onset of new ones can occur in up to 30% of patients [\n5\n]. Flecainide depresses cardiac contractility especially in patients with underlying impairment of function.\nThe management of an overdose includes supportive measures and specific pharmacological agents. The benefit of activated charcoal is uncertain but this may be considered within the first hour of ingestion [\n8\n]. Hemodynamic support may be required including the fluid replacement, inotropes and an intra-aortic balloon pump as in this case. Both extracorporeal membrane oxygenation and cardiopulmonary bypass have been used in cases of severe overdose [\n6\n,\n7\n] but the use of intra-aortic balloon pump has not previously been described.\nSodium bicarbonate is recommended for a metabolic acidosis that persists despite correction of hypoxia and adequate fluid resuscitation [\n8\n]. Following administration of intravenous sodium bicarbonate QRS narrowing has been reported and also termination of ventricular tachycardia. [\n9\n]. Ventricular arrhythmias may be difficult to cardiovert electrically and both lidocaine and amiodarone have been used successfully in such cases [\n3\n,\n10\n]. Cardiac pacing may be required but ventricular capture may be poor [\n3\n].\nConclusion\nFlecainide overdose is frequently fatal and supportive measures including the use of intra-aortic balloon pumping may be required for severe myocardial depression that may occur during the acute phase.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nJT, AM and PB drafted the manuscript. NW made final alterations to manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
62
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nMönckeberg's sclerosis – is the artery the only target of calcification?\n\n**Article Abstract:**\n\nBackground\nSince its first description, Mönckeberg's sclerosis has only been related to arterial media calcification, being listed among the primary diseases of the vessels.\nCase presentation\nWe report here a clinically and histologically confirmed case of Mönckeberg's sclerosis in which the patient presented with massive areas of soft tissue calcifications in the pharynx and larynx. Polysomnographic parameters showed severe obstructive apnea refractory to nasal continuous positive airway pressure. Clinical and laboratory findings excluded concomitant endocrine or rheumatological diseases.\nConclusion\nOur data provide a new insight about Mönckeberg's sclerosis, i.e., the fact that the etiopathogenic process involved in the phenomenon of calcification may not be restricted only to the arteries, but may occur in the entire organism. Further studies of the etiopathogenesis of this disease are needed.\n\n**Article Body:**\n\nIntroduction\nMönckeberg's sclerosis (MS) is a degenerative and apparently non-inflammatory disease in which the media of small and medium-sized muscular arteries becomes calcified independently of atherosclerosis. Since the condition does not involve primarily the intimal layer of the artery, the lumen is kept open by the rigid media and, therefore, luminal narrowing is not a direct consequence [\n1\n-\n4\n]. Recent studies, however, have demonstrated that MS is a risk factor for cardiovascular disease and peripheral artery obstruction [\n1\n,\n4\n,\n5\n]. The exact etiopathogenesis of this process is far from being understood, but is frequently related to glucose intolerance, aging, male gender, autonomic neuropathy, osteoporosis and, chronic renal failure[\n6\n,\n7\n]. It commonly occurs in peripheral arteries of the lower limbs where it is seen as \"rail tracking\" on incidental plain radiographs[\n1\n,\n8\n].\nTo the best of our knowledge, soft tissue calcifications have never been described in such disease, especially in association with obstructive sleep apnea (OSA). We report here a patient with classic MS who presented severe OSA due to calcinosis of the pharynx.\nCase report\nA 63-year-old Brazilian woman was referred to the hospital with a 20-year history of an increasing size of the anterior portion of the neck associated with progressive exertional dyspnea, nighttime snoring and coughing, dysphagia of solids and daytime sleepiness. She had no history of hypertension, cigarette smoking, alcohol ingestion, weight loss, fractures or fever. Her medical history was significant for intermittent claudication.\nPhysical examination showed a thin woman (body mass index of 17 kg/m\n2\n) with a hard, irregular, painless, mobile tumoration on the anterior surface of the neck. No lymph nodes were palpable and hoarseness was evident. There was no craniofacial abnormality. The results of oral cavity, thyroid, cardiopulmonary and abdominal examination were unremarkable. The femoral arteries appeared to be thickened and pulses were frail although there were no signs of acute limb ischemia.\nPelvic and lower extremity roentgenograms showed dense, \"rail tracking\" femoral artery calcification associated with near-total obstruction of these vessels confirmed by translumbar aortography (figure \n1\n). A neck X-ray and computed tomography evidenced grossly calcified areas of soft tissue in the topography of the pharynx and larynx. Direct laryngoscopy confirmed exophytic calcic deposits in the left pyriform sinus (figure \n2\n and \n3\n). No other images of abnormal calcifications were found at any other sites, such as the arms, lung, heart, aorta or abdomen. A bone scintigram showed increased uptake of \n99 m\nTc-methylene diphosphate in the calcified femoral arteries and on the anterior surface of the neck (figure \n4\n). Right hip and lumbar spine bone densitometry evidenced supportive findings of osteoporosis. Chest X-ray revealed mild enlargement of cardiac area associated with ectasic thoracic aorta; pulmonary aspects were normal. Doppler echocardiography revealed mild pulmonary hypertension (39 mmHg) associated with mild left atrium and moderate left ventricle enlargement; there was a diffuse left ventricle hypokinesia associated with an ejection fraction of 32% (indirectly measured by echocardiography). Also, there was an eccentrical left ventricular hypertrophy, severe mitral and tricuspid regurgitation. There was no abnormality in the right ventricle. Cineangiocoronariography was attempted to directly analyse any coronary disease as a possible cause of these abnormalities, but the rigidity of femoral and brachial arteries impeded the insertion of the catheter.\nFigure 1\nA\n. Pelvic and lower extremity radiograph shows extensive calcification of the femoral arteries. \nB. \nTranslumbar aortography shows near-total obstruction of the femoral arteries.\nFigure 2\nA. \nNeck radiograph evidences grossly calcified areas of soft tissue in the topography of the oropharynx. \nB. \nDirect laryngoscopic examination shows exophytic calcic deposits in the left pyriform sinus (arrow).\nFigure 3\nTransverse slices of CT showing multiple coarse calcifications scattered by oropharynx \n(A)\n, hypopharynx \n(B) \nand larynx \n(C)\n. \nD. \nSagittal plane appearance.\nFigure 4\nBone scintigram shows increased uptake of \n99 m\nTc-methylene diphosphate in the calcified femoral arteries and on the anterior surface of the neck.\nSleep variables obtained from polysomnography were indicative of severe OSA (table \n1\n) with an apnea/hypopnea index of 51.6 per hour (40.9 apnea episodes/h), 89% of which occurred together with bradycardia and extra beats. Minimal oxygen saturation was 88%. The spirometric study demonstrated mild obstructive airway disease with no responsiveness after bronchodilator test. Also, there was a moderate decrease in the pulmonary diffusion capacity (Collins GS Plus Modular System, Warren E Collins Inc. Braintree, MA).\nTable 1\nDiagnostic values of sleep and respiratory variables obtained by polysomnography\nSleep and respiratory variables\nPatient\nExpected values\nSleep efficiency (TST*/TRT† %)\n58\n>80\nStage 1 (%)\n10,7\n≤_9\nStage 2 (%)\n74,4\n≤_60\nStage 3–4 (%)\n7,4\n10–25\nStage REM (%)\n7,5\n10–25\nMean oxygen saturation(%)\n92\n>96\nMinimal oxygen saturation (%)\n88\n93–95\nApnea/Hypopnea index (/hour)\n51,6\n< 5\nApnea index (/hour)\n40,9\n<5\nMean duration of apneas (seconds)\n30\n10\nTime spent with SaO2 <90%(min)\n2\n-\nTotal sleep time; † Total recording time.\nExcept for the impaired fasting glucose state (fasting blood glucose of 117 mg/dl), there were no other biochemical abnormalities concerning calcium, phosphate, magnesium, creatinine and parathyroid hormone. Clinical and laboratory findings excluded any kind of rheumatologic disease such as dermatomyositis, scleroderma or systemic lupus erythematosus. Biopsy specimens from the pharynx and temporal artery revealed soft tissue calcification and medial artery calcinosis, respectively (Figure \n5\n).\nFigure 5\nA. \nTemporal artery biopsy shows circumferential calcic deposits in the media (detail) (H&E stain). \nB. \nA pyriform sinus biopsy shows soft tissue calcification (arrows) (H&E stain).\nContinuous positive airway pressure (CPAP) tritation for treatment of such obstructive sleep apnea has been tried twice on different occasions, but the patient has complained of extreme discomfort (she could hardly sleep during the procedures). A pressure of 10 cm H\n2\nO was reached during some short periods of sleep with a very low effect on the frequency of episodes of apnea. So, with the aim of stopping further vascular and soft tissue calcification, intravenous dissodic pamidronate was administred (60 mg IV diluted in 250 mL of saline solution once a day for 1 day).\nDiscussion\nMönckeberg's sclerosis commonly occurs in otherwise healthy elderly patients independently of atherosclerosis. After 35 years of disease, 94% of all diabetic patients present arterial calcification[\n9\n]. This is usually an incidental finding during lower limb radiographic examination, although involvement of renal and coronary vessels has been described [\n3\n]. The cause of medial calcinosis remains unclear, but some insights into the etiopathogenic process have been provided by isolated studies. Shanahan \nel al \n[\n10\n] proposed that a loss of expression of certain proteins related to the inhibition of calcification could be the causative factor. These proteins are Gla protein, osteoprotegerin, fibrillin I and carbonic anhydrase (all produced by vascular smooth muscle cells). Byts \net al\n. [\n11\n] pointed out that medial calcification can be a consequence of various metabolic changes triggered by a necrobiotic injury installed in the vessel wall.\nSince its first description in 1903 [\n3\n], MS has only been related to media calcification of small-to-medium-sized arteries, being listed among the primary diseases of the vessels. Calcic involvement of soft tissues has never been described in MS patients. In our case the pharynx involvement was strong enough to produce severe obstructive sleep apnea and the symptoms were clearly associated with the massive tumoral growth of the anterior portion of the neck.\nObstructive sleep apnea results from repetitive episodes of pharyngeal occlusion during sleep which reverse with arousal, thus inducing sleep fragmentation, a low amount of slow wave sleep (stages 3 and 4 non-REM sleep) and a low amount of REM sleep with consequent daytime somnolence [\n12\n]. Sleep apnea causes repetitive episodes of hypoxia, hypercapnia and reoxigenation that can lead to a variety of physiological processes including pulmonary hypertension and other vascular consequences[\n13\n]. Our patient had a confirmed increase in pulmonary arterial pressure that could not be entired explained by the OSA syndrome. Probably it has been worsened by the concomitant left ventriculat disfunction. The exact cause of the cardiac disfunction could not be widely investigated, but OSA is an important contributor.\nGenerally, the pathogenesis of upper airway obstruction involves anatomic and neurological components. Obesity, age, male sex, positive family history and alcohol consumption are well known as major risk factors for this disorder in adults. Narrowing may occur at one or more sites in an unstable upper airway due to anatomical partial obstruction as a result of developmental delay, craniofacial abnormalities and neurologic diseases[\n13\n]. Our patient was a non-alcoholic, very slim woman (as judged by a body mass index of 17 kg/m\n2\n) with no family history of similar disorders.\nThe massive calcification areas of the pharynx were confirmed by radiological images, laryngoscopic visualization and a biopsy of the exophytic lesion in the pyriform sinus which revealed areas of soft tissue calcification. We excluded metastatic and dystrophic calcification in the light of the histological appearance of the lesion and the absence of malignancy and of rheumatologic or endocrine diseases.\nA lower limb X-ray evidenced the classic \"rail tracking\" appearance of MS described by other authors [\n1\n,\n4\n] and a temporal artery biopsy confirmed the intense media calcinosis. The concomitant atherosclerotic process involving the intima layer of the femoral arteries explained the intermittent claudication and weak pulses presented by this patient. Both OSA and MS are recognized as causative factors of atherosclerosis[\n1\n,\n13\n]. Additionally, our patient presented low bone mineral density, and this finding supports recent evidences showing association between arterial calcification and osteoporosis[\n14\n,\n15\n].\nAs can be seen in figure \n3\n, the amount of airway obstruction caused by the grossly calcified tissue could be the answer for the discomfort related to CPAP titration. In face of the difficulties related to this approach, tracheostomy was thought to solve this problem. However, the risk of triggering even more tissue calcification secondary to tissue damages discouraged the realization of this procedure.\nAlternatively, treatment with intravenous dissodic pamidronate was attempted to stop the phenomenon of calcification and prevent further airway obstruction. This drug has the property to attach to hydroxyapatite crystals preventing both vascular and soft tissue calcification[\n16\n]. Additionally, it worked as a treatment for osteoporosis presented by the patient.\nAlthough one can argue about the possible role of upper airway obstruction in intensifying the local deposition of calcium in the soft tissue of the pharynx, the diagnosis of MS was well documented in this case. The present report provides a new insight about this disease, i.e., the fact that the etiopathogenic process involved in the phenomenon of calcification may not be restricted only to the arteries, but may involve the entire organism.\nConclusion\nMonckeberg's sclerosis is a primary disease of the arteries. However, the present case report raises extensive questions about the etiopathogenic process involved in MS, since this is the first report of soft tissue calcification related to this disease. Further investigations of the etiology and pathogenesis of this disease are needed.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nGAS and JABM were responsible for the initial evaluation and management of the patient. GAS was also responsible for the realization and interpretation of polysomnography. CEBC, FAP and FJAP were the responsible for the investigation and the diagnosis of Mönckeberg's sclerosis. All authors have equally contributed in the preparation and revision of the manuscript. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
63
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nRapid screening for glucose-6-phosphate dehydrogenase deficiency and haemoglobin polymorphisms in Africa by a simple high-throughput SSOP-ELISA method\n\n**Article Abstract:**\n\nBackground\nMutations in the haemoglobin beta-globin \n(HbB) \nand glucose-6-phosphate dehydrogenase \n(G6PD) \ngenes cause widespread human genetic disorders such as sickle cell diseases and G6PD deficiency. In sub-Saharan Africa, a few predominant polymorphic variants of each gene account for a majority of these deficiencies. Examining at a larger scale the clinical importance of these independent genetic disorders, their possible association with malaria pathogenesis and innate resistance, and their relevance for antimalarial drug treatment, would be easier if an accurate screening method with limited costs was available.\nMethods\nA simple and rapid technique was developed to detect the most prominent single nucleotide polymorphisms (SNPs) in the \nHbB \nand \nG6PD \ngenes. The method is able to detect the different haemoglobin polymorphisms A, S, C and E, as well as G6PD polymorphisms B, A and A- based on PCR-amplification followed by a hybridization step using sequence-specific oligonucleotide probes (SSOPs) specific for the SNP variants and quantified by ELISA.\nResults\nThe SSOP-ELISA method was found to be specific, and compared well to the commonly used PCR-RFLP technique. Identical results were obtained in 98% (haemoglobin) and 95% (G6PD) of the tested 90 field samples from a high-transmission area in Tanzania, which were used to validate the new technique.\nConclusion\nThe simplicity and accuracy of the new methodology makes it suitable for application in settings where resources are limited. It would serve as a valuable tool for research purposes by monitoring genotype frequencies in relation to disease epidemiology.\n\n**Article Body:**\n\nBackground\nSickle cell disease and glucose-6-phosphate dehydrogenase (G6PD) deficiency are widespread inherited, but independent, human genetic disorders affecting millions of people [\n1\n-\n3\n]. Whereas G6PD deficiency is an x-linked enzymopathy and among the most common genetic disorder in humans [\n3\n], sickle cell disease is a common and severe haemoglobinopathy, caused by sickling haemoglobin [\n2\n]. The cytoplasmic G6PD enzyme is expressed in all tissues and is essential for the capacity of cells to withstand oxidative stress. Individuals with lowered levels of the G6PD enzyme are more susceptible to develop acute haemolytic anaemia [\n4\n]. Apart from childhood death, patients with sickle cell diseases suffer from diverse clinical conditions including anaemia, infarctions and other variable painful crisis throughout life [\n5\n].\nThe disorders arise from single nucleotide point mutations in the haemoglobin beta-globin (\nHbB\n) and glucose-6-phosphate dehydrogenase (\nG6PD\n) genes, resulting in single amino acid substitutions. Despite the fact that more than hundred allelic variants have been described for each polymorph gene-locus, only a few reach high frequencies and, thus, become of clinical importance [\n1\n,\n3\n].\nIn sub-Saharan Africa, G6PD is essentially a tri-allelic polymorphism. G6PD (B) is the most common allele with normal enzymatic activity; G6PD (A) is associated with a single amino acid substitution at codon (c) 126 where Asn is changed to Asp (N126D), causing around 85% of the normal enzymatic activity. The G6PD (A-) deficiency allele has a single amino acid substitution at c68 from Val to Met (V68M), always in conjunction with the N126D mutation [\n6\n]. The G6PD (A-) variant has only around 12% of normal enzymatic activity with frequencies of 5–25% of the affected population in sub-Saharan Africa [\n7\n]. Although most individuals with the G6PD (A-) polymorphic variant are asymptomatic, acute haemolytic anaemia can manifest in hetero- and homozyogte females as well as hemizygote males under oxidative stress of the red blood cells [\n7\n]. This condition can be induced by infections, anti-inflammatory agents and chemotherapeutics, including anti-malarials such as sulphadoxine-pyrimethamine, lapudrine-dapsone or primaquine, making it of importance to know the G6PD status of individuals receiving drug treatment [\n4\n].\nThe most prevalent polymorphic variants of the \nHbB \ngene consist of the normal gene (HbA) in which SNPs in the same amino acid position give rise to either the sickle haemoglobin S, (HbS, Glu to Val at c6 (E6V)) or the common west-African haemoglobin C (HbC, Glu to Lys at c6 (E6K)). A third SNP at position 26 creates the Southeast-Asian haemoglobin E (HbE, Glu to Lys (E26K)) variant, which is not found in Africa [\n1\n]. Apart from several other abnormal haemoglobin gene-combinations, such as beta-thalassaemia, sickle cell disease is found in individuals with homozygote HbSS (sickle cell anaemia) and heterozygote SC genotypes, whereas the inheritance of two C-alleles (HbCC) or one A plus one C or S allele (HbAS and HbAC) give rise to phenotypes associated with limited pathology [\n1\n]. Both haemoglobin S, C and E confer some degree of protection against severe malaria [\n8\n-\n10\n]. In sub-Saharan Africa, HbS gene frequencies exceed 25%, resulting in a widespread, but unequal distribution of the HbAS sickle cell trait [\n2\n].\nThe procedures for diagnosing sickle cell anaemia and G6PD deficiency includes the sickling test, haemoglobin electrophoresis [\n1\n,\n11\n] and enzymatic diagnostic assay [\n13\n]. Current approaches also deploy DNA-analysis using PCR-restriction fragment length polymorphism (RFLP) [\n9\n,\n14\n-\n16\n], allele-specific oligonucleotide hybridization [\n10\n,\n17\n] or dot-blot hybridization analysis of the appropriate PCR-amplified fragments [\n18\n]. However, these techniques can have difficulties in detecting heterozygotes and discerning false-negatives and false-positives thereby hampering specificity and sensitivity [\n19\n]. Furthermore, the methods are relatively laborious, technically demanding and expensive, and may, therefore, be inappropriate for screening large numbers of samples in resource-poor settings.\nHere, a method for screening human populations for the different haemoglobin polymorphisms A, S, C and E as well as the G6PD polymorphisms B, A and A- by use of PCR and sequence-specific oligonucleotide probes (SSOPs) to detect the various SNPs and visualized in an ELISA system, is described and evaluated. The methodology is accurate and simple and would be applicable at laboratories with limited facilities.\nMethods\nSamples and DNA-extraction\nBlood samples from 90 children under the age of five years, living in Mkokola village in North-Eastern Tanzania, collected on filter paper during a cross-sectional survey in March 2004, were used for validation of the method. Informed consent was obtained from parents or guardians of the study participants and the study protocol was ethically approved by the Tanzanian National Institute of Medical Research.\nDNA samples of two donors with HbCC and HbAS genotypes and two donors with G6PD (A-), genotypes 68 MM (homozygote for 68 mutation) and G6PD (A), genotype 68VM/126ND (heterozygote for both mutations), respectively, served as positive controls. DNA extracted from volunteering Danish blood donors were used as controls for wildtype HbAA and G6PD (B) (68VV/126NN). Two samples from the villages Kwemasimba and Tamota in neighbouring areas were identified by the RFLP technique to be HbSS-type and HbAC-type, respectively, and were used as controls in comparison with the SSOP-ELISA technique. DNA was extracted from segments of bloodspots on filter paper in 96-well plate format by a Chelex-100 method described previously [\n20\n].\nPCR conditions\nPrimers, as described in Mombo et al. [\n16\n], were used to amplify a 919 bp fragment of the \nG6PD \ngene covering the two mutation sites at codon 68 and 126. The \nHbB \ngene was amplified by primers as described in Modiano et al. [\n9\n] to produce a 358 bp fragment covering the mutation sites at codon 6 and 26. Both reverse primers were biotinylated at the 5'-end by the supplier (MWG Biotech, Ebersberg, Germany).\nOne μl of DNA-extracted samples were amplified in 20 μl of PCR reaction mixture consisting of 0.2 mM of each dNTP, 2 μM of each primer-set, 1 unit of DNA Qiagen HotStart polymerase (Qiagen, Albertslund, Denmark), Qiagen buffer containing 2.5 mM MgCl\n2\n.\nThe PCR conditions for both the \nG6PD \nand \nHbB \ngene were 15 minutes of incubation at 94°C, followed by 45 amplification cycles of denaturation at 94°C for 30 seconds, annealing at 60°C for 30 seconds and elongation at 72°C for 90 seconds (60 seconds for the \nHbB \ngene), before the final elongation at 72°C for 10 minutes. The reactions were performed in 96-well PCR plates on a DNA thermal cycler (MJ Research, Albertslund, Denmark). A fraction of the PCR products were visualized by electrophoresis on a 1,5% agarose gel for 30 minutes for conformation of the amplification.\nDetection methods\nSSOP-ELISA\nOligonucleotide-probes of 18 bases covering the mutation sites were designed and 3'-end conjugated with digoxigenin (MWG Biotech, Ebersberg, Germany) (Table \n1\n). The detection of the SNPs were performed according to [\n21\n], with slight modifications. In brief, the amplified PCR products were diluted 1:2 in dH\n2\n0, denatured at 95°C for 5 minutes and kept at 4°C until use. 2 μl of the PCR products, conjugated with biotin, were added to streptavidin-coated (1 μg/ml PBS) ELISA plates (Maxisorp; Nunc, Roskilde, Denmark) containing 100 μl PBS with 0.05% Tween-20 and incubated for one hour at room temperature. The bound PCR-products were incubated with 8 nM of either probe in tetra-methyl ammonium chloride (TMAC; Sigma Aldrich, Seelze, Germany) solution (3 M TMAC, 50 mM Tris, pH 8.0, 0.1 sodium dodecyl sulfate, 2 mM EDTA, pH 8.0) at 53°C with shaking for an hour, followed by 2 × 10 minutes. TMAC-washing at temperatures set to 62°C for the haemoglobin probes and 65°C for the G6PD probes, respectively. The plates were incubated with peroxidase-conjugated anti-digoxigenin antibody (Roche Diagnostics, Mannheim, Germany) 1:1000 in PBS with 0.05% Tween-20 at room temperature for one hour, thereafter visualised by \no\n-phenylene-diamine (OPD) (Dako, Glostrup, Denmark). The reaction was stopped with H\n2\nSO\n4\n, before measuring the optical density (OD) at 492 nm. Between each step, the ELISA plates were washed three times in PBS with 0.05% Tween-20. As the OD values of positive and negative controls changed between experiments, probably due to differences in strength of the probe binding, no fixed cut-off value could be specified; thus, for each SNP test, assay-specific cut-off values were defined.\nTable 1\nSequences of the digoxigenin-conjugated sequence-specific oligonucleotide probes (SSOPs). The SSOP-ID named the sequences used in detection of the haemoglobin and G6PD single nucleotide polymorphisms (SNPs).\nSSOP ID\nSSOP sequence\n1\nNucleotide substitution\nAmino acid substitution\nHbB\nHbA-6:\n5' TGACTCCTGAGGAGAAGT\nHbS-6:\n5' TGACTCCTG\nT\nGGAGAAGT\nA18T\nE6V\nHbC-6:\n5' TGACTCCT\nA\nAGGAGAAGT\nG17A\nE6K\nHbA-26\n5' TTGGTGGTGAGGCCCTGG\nHbE-26:\n5' TTGGTGGT\nA\nAGGCCCTGG\nG77A\nE26K\nG6PD\n68V\n5' CACCTTCATCGTGGGCTA\n68M\n5' CACCTTCATC\nA\nTGGGCTA\nG202A\nV68M\n126N\n5' GCCACATGAATGCCCTCC\n126D\n5' GCCACATG\nG\nATGCCCTCC\nA376G\nN126D\n1\n: Letters in bold indicate the nucleotide-substitutions\nRestriction fragment length polymorphism (RFLP)\nIn order to validate the method, comparative RFLP analyses were performed on similar PCR products used for the SSOP-ELISA technique. The 919 bp PCR fragment of the \nG6PD \ngene was digested with restriction enzyme NlaIII, which permits discrimination of the 68V and 68M genotypes [\n16\n], and BsmI, which allows discrimination of the 126N and 126D genotypes. The 358 bp fragment of the \nHbB \ngene was digested with restriction enzyme MnlI and DdeI for discrimination of the different haemoglobin polymorphisms, according to [\n9\n]. All digestions were carried out for a minimum of three hours, at 37°C for NlaIII, DdeI and MnlI, and 65°C for BsmI according to manufacturer's instructions, and resolved on 2–2.5% metaphor agarose gels (Medinova, Glostrup, Denmark).\nResults\nSpecificity of the genotyping assay\nIn order to assess the capacity of the SSOP-ELISA technique to correctly detect HbB and G6PD SNPs, control DNA samples from individuals with known HbAA, HbCC, HbSS, HbAC and HbAS genotypes together with G6PD (68VV/126NN), (68VM/126ND) and (68MM/126DD) genotypes, were used to optimize the screening method.\nUsing the control samples, all SSOPs identified with high specificity the appropriate SNPs in the DNA. The difference in OD-values between the cut-off value and the positive reactions (Δ-OD) was always higher than 2.0 for the haemoglobin samples and higher than 1.5 for the G6PD samples (Figure \n1\n). A sample from an individual with the HbE mutation was not available, and therefore it was not possible to test the specificity of the HbE-26 probe. However, the probe HbA-26, specific for the normal genotype at c26, recognized the all samples with OD values above 2.0 (data not shown). The reaction intensity was equally strong in samples where each probe detected one allele (heterozygote and hemizygote) or two identical alleles (homozygote).\nFigure 1\nMean reactivity (OD value) and 95% confidence intervals in ELISA-SSOP assay of samples with known genotype. \nPanel a) shows genotyping results of the \nHbB \ngene (genotypes AA, AS, CC, AC, SS) using probes reacting with HbA, HbS and HbC, respectively. Panel b) and c) shows genotyping results for G6PD for samples from individuals with the indicated genotypes using probes against 68V, 68M, 126N and 126D, respectively. All experiments were performed 4 times.\nThe procedure was optimized to different TMAC washing temperatures for the different probes, reaching an optimum specificity of 62°C and 65°C for HbB and G6PD probes, respectively. However, with slight decrease in specificity, both assays could be performed using a TMAC washing temperature in the range of 62–65°C. Although weak results could be obtained by applying the probes and PCR-products together at 53°C, saving one hour of the duration of the procedure, the strongest and most specific results were obtained by separating the PCR-product and probe incubations (one hour each). Similar, attempts to combine the two amplifications in one PCR-reaction (multiplex) also reduced the specificity and intensity of both PCR products. The cheaper and less hazardous tetramethylbenzidine (TMB) performed as well as OPD in the detection step.\nSSOP-ELISA versus the RFLP method\nTo test the SSOP-ELISA technique on samples from the field, DNA was extracted from filter paper blood spots collected from 90 children living in a Tanzanian village. The assay was able to screen these samples for the three haemoglobin and two G6PD SNPs during one day and determine the genotype frequencies (Table \n2\n). The majority of the 90 samples were amplified by PCR, except three for the \nHbB \ngene and six samples for the \nG6PD \ngene. Of the PCR-amplified samples, the majority reacted with the SSOPs with a signal-to-background OD value above 1.0. As expected, no samples with HbC or HbE were identified in the village. Twelve individuals carried one HbS allele and had the HbAS genotype, corresponding to a prevalence of 14% of the sickle cell trait. The majority the individuals, 86% (75/87), carried the normal HbAA genotype.\nTable 2\nHbB \nand \nG6PD \ngenotype frequencies for children living in a Tanzanian village and analysed by the SSOP-ELISA method.\nHbB Genotype\nNumbers (87)\na\nG6PD Genotype\nNumbers (84)\na\n68 Status\n126 Status\nDeduced Phenotype\nb\n68–126\nAA\n75 (86%)\nVV-NN\nc\n51 (61%)\nWildtype\nWildtype\nG6PD B\nSS\n0\nVV-DD\nd\n8 (10%)\nWildtype\nMutant\nG6PD A\nAS\n12 (14%)\nM-D\ne\n6 (7%)\nMutant\nMutant\nG6PD A-\nAC\n0\nVM-ND\n10 (12%)\nSingle Mutant\nSingle Mutant\nG6PD A\nCC\n0\nVV-ND\n8 (9%)\nWildtype\nSingle Mutant\nG6PD A\nSC\n0\nVM-DD\n1 (1%)\nSingle Mutant\nMutant\nG6PD A\nNo PCR-product\n3\nNo PCR-product\n6\na\n: Numbers refer to the remaining individuals from the field with amplified PCR-product\nb\n: Phenotype of the G6PD trait was not measured, but deduced based on the genotype\nc\n: Out of the 51 individuals, 30 were males with the V-N genotype\nd\n: Out of the 8 individuals, 5 were males with the V-D genotype\ne\n: All 6 individuals were males hemizygote for M-D genotype\nFor G6PD, 61% (51/84) had the (68VV/126NN) normal genotype (G6PD B variant), whereas 20% (17/84) had the 68M mutation. These individuals could be divided into 6 (7%) with the deficient genotype (68M/126D – only hemizygote males), having the G6PD (A-) variant, and 11 (13%) which were heterozygote for the 68M mutation (10 with 68MV/126ND and 1 with 68MV/126DD) genotype having the G6PD (A) variant.\nTo verify the genotypes determined by the SSOP-ELISA assay, the PCR-products were processed by the RFLP method, which currently is commonly used for genotyping. For HbB, control and field samples gave identical results in 98% (88/90) of the cases. A minor disagreement was found in two samples typed as AS and AC, respectively. The samples had weak positive signals for the S and C probes close to the cut-off OD value of 0.3 in the SSOP-ELISA method. The restriction digestion analysis typed the samples as HbAA and not AC or AS.\nAmong 87 samples amplified for G6PD, there was 95% (83/87) and 97% (84/87) concordance between the two methods for the 68 and 126 mutation, respectively. Four samples with positive signals for 68V, showed weak signals with OD values between 0.2 and 0.5 for the 68M probe. Two of these were typed as 68MV by the RFLP method, whereas the two remaining were typed as 68VV. Another three samples, initially considered containing the 126D allele, typed as either 126DN or 126NN by the RFLP method. Ten samples (6 for the 68 mutation and 4 for the 126 mutation) with clear-cut OD values by the SSOP-ELISA method were difficult to interpret by the RFLP method due to ambiguous band-separation and band-resolution even after repeating the restriction digests. Comparisons of the results with the different methods are shown in Table \n3\n.\nTable 3\nComparison of results obtained with the SSOP-ELISA (horizontal) and RFLP (vertical). The single nucleotide polymorphisms (SNPs) in the \nHbB \ngene (top) and \nG6PD \ngene (bottom) were targeted using DNA extracted from control samples and 90 individuals from the field.\nHbB\nSSOP-ELISA\nRFLP\nHbAA\nHbAS\nHbSS\nHbAC\nHbCC\nNo PCR prod.\nHbAA\n74\n1\n1\nHbAS\n11\nHbSS\n1\nHbAC\n1\nHbCC\n1\nNo PCR-prod.\n3\nG6PD\nSSOP-ELISA\nRFLP\n68V\n68M\n68MV\n126N\n126D\n126DN\nNo PCR prod.\n68V\n64\n2\n68M\n5\n68MV\n2\n8\n126N\n50\n1\n126D\n14\n126ND\n2\n16\nNo PCR-prod.\n6\nInconclusive\n4\n2\n2\n2\nDiscussion\nTo allow large-scale screening of clinically important point mutations associated with G6PD deficiency and haemoglobinopathies, to be applied in resource-poor settings, a simple high-throughput SSOP-ELISA method was developed as an alternative to the conventional RFLP-method. Our new SSOP-ELISA method proved to be highly accurate in detecting the different SNPs of both the \nHbB \nand \nG6PD \ngenes, with signal-to-background differences in OD values greater than 2.0 in most cases. Thus, with only a minimum discordance between the results obtained by the RFLP and SSOP-ELISA methods, the SSOP-ELISA technique confirmed to be an efficient alternative to the RFLP method. Although the SSOP-ELISA originally was developed for detecting \nPlasmodium falciparum \nhaplotypes related to anti-malarial drug resistance, the technique has been shown to be adapted to analyse human genotypes as well. The results clearly showed that the OD values were not reduced in samples with two different SNPs a (heterozygote) compared to samples with two identical alleles (homozygotes). All individuals classified as heterozyogtes by the SSOP-ELISA were females, as expected.\nThe chosen PCR-products have the advantage of covering three important SNPs in the \nHbB \ngene and two important SNPs in the \nG6PD \ngene. The single PCR product from the G6PD gene covers both mutations, whereby amplification of two fragments, as has been done previously, is avoided [\n18\n,\n22\n]. The probes used were all designed to surround the SNP in question and only in the case of the 68M SNP, additional probes were designed to optimise a suitable binding reaction. In contrast, the PCR-RFLP methodology is dependent on recognisable restriction sites around the SNP, limiting the choice of size of the PCR fragment and binding of the primers. The SSOP-ELISA method also has the advantage of not relying on laborious electrophoresis work. Ambiguous results were more frequently observed with the RFLP method, caused by either incomplete enzymatic digestion of PCR fragments or inaccurate gel-resolution and band separation. The generation of ELISA-based OD values removes much of the conjecture over gel results, and a simple spreadsheet can be used for data analysis to identify samples, which need confirmation by the RFLP method. With duration of approximately 3 hours for the PCR amplification step followed by 4 hours for the SSOP-ELISA detection, 90 samples can easily be screened for both haemoglobin and G6PD genotypes or 180 samples for either haemoglobin or G6PD, during one day. Apart from being accurate and rapid, the technique is also relatively cheap as costs pr. sample analyzed and DNA extracted approximately is 1$.\nFrom a practical point of view, setting up and running this new method only requires the use of relatively cheap equipment: a PCR thermal cycler, an incubation oven and an ELISA reader. These are increasingly becoming commonplace in many settings, also in laboratories in resource-poor settings in Africa. At this stage, the SSOP-ELISA technique has already been established at sites in Tanzania for the routine monitoring of molecular markers of \nPlasmodium falciparum \ndrug resistance. The method can be adapted to other areas where different mutations predominate and even modified into a higher throughput system with access to more advanced and expensive equipment. In African populations, screening for the V68M mutant only will suffice, if the intention is solely to assess symptomatic G6PD deficiency [\n15\n,\n22\n].\nThe fact that this method is only able to detect specific SNPs, limits its use to monitoring already known genotypes, and sequencing analysis will be needed to identify unknown molecular markers or other variants of G6PD deficiency. Although by far the largest proportion of individuals with G6PD deficiency have the 68MM genotype, making it unlikely that a person in sub-Saharan Africa without the V68M mutation would be G6PD deficient [\n12\n], it is important to consider that ethnically different populations, e.g. with Arabic influence, could harbour other G6PD deficient variants (e.g. the Arabic G6PD\nmed \nvariant) [\n12\n], and that rare deficiency mutations (G680T and T968C) could be present [\n7\n].\nLimited access to and delayed diagnosis of sickle cell diseases and G6PD deficiency in tropical Africa may hamper prevention of severe illness and consequently lead to increases in morbidity and mortality [\n5\n]. Efficient high-throughput screening methods, as described here, may help to map the distribution of these inherited disorders and, thus, contribute as an epidemiological tool to characterize disease patterns. Molecular epidemiology of genes promoting or protecting against disease, including malaria, is important when large-scale interventions are planned, e.g. studies on malaria immunity, vaccine trials and drug trials.\nConclusion\nHere, a simple screening method is described, detecting, at molecular level and with limited costs, the most important human haemoglobin and G6PD polymorphisms associated with malaria. This assay represents a useful tool for analysing the relation between various combinations of these major genotypes and a variety of epidemiological factors in particular malaria immunity, incidence and severity. The method has proved to be accurate and rapid and will be beneficial at research institutions in resource-poor settings in Africa.\nAuthors' contributions\nAE conceived of the study, performed the experiments and wrote the manuscript. MA, CD, LV, JL, IB, ML and TT participated in manuscript preparation and design of the study. ML and JL supervised collection of samples. All authors read and approved the final manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
64
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nRural Community Knowledge of Stroke Warning Signs and Risk Factors\n\n**Article Abstract:**\n\nIntroduction\nRapid identification and treatment of ischemic stroke can lead to improved patient outcomes. Public education campaigns in selected communities have helped to increase knowledge about stroke, but most data represent large metropolitan centers working with academic institutions. Much less is known about knowledge of stroke among residents in rural communities.\nMethods\nIn 2004, 800 adults aged 45 years and older from two Montana counties participated in a telephone survey using unaided questions to assess awareness of stroke warning signs and risk factors. The survey also asked respondents if they had a history of atrial fibrillation, diabetes, high blood pressure, high cholesterol, smoking, heart disease, or stroke.\nResults\nMore than 70% of survey participants were able to correctly report two or more warning signs for stroke: numbness on any side of the face/body (45%) and speech difficulties (38%) were reported most frequently. More than 45% were able to correctly report two or more stroke risk factors: smoking (50%) and high blood pressure (44%) were reported most frequently. Respondents aged 45 to 64 years (odds ratio [OR] 2.44; 95% confidence interval [CI], 1.78–3.46), women (OR 2.02; 95% CI, 1.46–2.80), those with 12 or more years of education (OR 1.96; 95% CI, 1.08–3.56), and those with high cholesterol (OR 1.68; 95% CI, 1.17–2.42) were more likely to correctly identify two or more warning signs compared with respondents without these characteristics. Women (OR 1.48; 95% CI, 1.07–2.05) and respondents aged 45 to 64 years (OR 1.35; 95% CI, 1.01–1.81) were also more likely to correctly identify two or more stroke risk factors compared with men and older respondents.\nConclusion\nResidents of two rural counties were generally aware of stroke warning signs, but their knowledge of stroke risk factors was limited.\n\n**Article Body:**\n\nIntroduction\nPublic health efforts to promote stroke awareness and the need to seek urgent treatment have assumed a new importance in the years since the publication of a major clinical trial showing decreased short-term disability and improved outcomes for patients experiencing an ischemic stroke after thrombolytic therapy (\n1\n). Prehospital barriers to prompt treatment for ischemic stroke include the lack of awareness of stroke warning signs in patients and family members, underuse of 911 emergency medical services (EMS), and long distances to tertiary-care facilities that provide diagnostic and treatment services (\n2\n-\n5\n). These barriers can lead to delayed presentation to the emergency department and to ineligibility for time-dependent treatment. Achieving increased use of thrombolytic therapy within the three-hour window in one community required a multilevel intervention to influence the knowledge and behavior of the public, the response of EMS, and the coordination of diagnostic and treatment facilities at the hospitals (\n6\n,\n7\n).\nFrom a public health perspective, an important component for the success of stroke interventions is to improve public knowledge about stroke, particularly focusing on individuals at high risk and their family members and caregivers. Public education campaigns in selected communities have been effective in increasing the level of knowledge about stroke, but most data have come from large metropolitan centers working with academic institutions (\n7\n,\n8\n). Much less is known about basic knowledge of stroke symptoms, risk factors, and the need for urgent intervention among residents in rural communities that are relatively isolated from major metropolitan centers.\nWe conducted a telephone survey in two rural counties in Montana in 2004. This report describes the level of awareness of stroke warning signs and risk factors and the public perception of the need to call 911 EMS for stroke in residents aged 45 years and older.\nMethods\nSetting\nThe population for this study included residents living in Cascade and Yellowstone counties, which include the cities of Great Falls (Cascade County) and Billings (Yellowstone County). The 2000 census population for Cascade County was 80,357 (\n9\n). Fourteen percent of the population was aged 65 years and older and 23% was aged 45 to 64 years. The majority of residents were white (91%) or American Indian (4%). The 2000 census population for Yellowstone County was 129,352. Thirteen percent of the Yellowstone County population was aged 65 years and older, and 23% was aged 45 to 64 years. Similar to Cascade County, the majority of residents were white (93%) or American Indian (3%). Both Cascade and Yellowstone counties are classified as rural counties — Cascade County has a population density of 29.8 persons per square mile, and Yellowstone County has a population density of 49.1 persons per square mile. These communities are served by three tertiary-care hospitals that provide comprehensive stroke diagnostic and treatment services. These facilities provide services for large multicounty areas that extend across state boundaries.\t\t\t\t\nTelephone survey\nFrom February 2004 through April 2004, the Montana Department of Public Health and Human Services conducted a random-digit–dial telephone survey of adults aged 45 years and older living in Cascade (n = 400) and Yellowstone (n = 400) counties. Eligible persons living in households with more than one eligible respondent were randomly selected. A trained interview team using computer-assisted telephone interviewing software conducted the survey. The survey was field tested to detect potential problems with questions or answer categories and then revised as needed. A total of 3520 calls were made as part of the survey. Of these calls, 1002 (28%) were nonworking numbers, 754 (21%) were households with no eligible respondent, 426 (12%) were not private residences, and 252 (7%) were no answer/answering machine or busy. Of the remaining calls to persons in eligible households (n = 1086), 800 (74%) were completions, 224 (21%) were refusals, 39 (4%) were unable to complete due to communication/language barriers, and 23 (2%) were not completed because the eligible respondent was not available during the interviewing period. Up to 15 attempts were made to complete unanswered calls.\nThe survey included questions on the warning signs and risk factors for stroke, use of 911 EMS, previous diagnoses of risk factors for stroke, and demographic information. Open-ended questions adapted from Pancioli et al were used to assess respondents' knowledge of the warning signs and risk factors for stroke (\n2\n). Respondents were prompted to name up to three warning signs and three risk factors for stroke. Respondents were asked four questions adapted from Yoon and colleagues to identify what they would do if they witnessed someone having a stroke or if they experienced sudden stroke warning signs including numbness, paralysis, and speech problems that would not go away (\n10\n). Respondents were also asked a series of questions from the Behavioral Risk Factor Surveillance System Survey to identify if they had a history of heart attack, angina, coronary heart disease, stroke, transient ischemic attack (TIA), atrial fibrillation, diabetes, high blood pressure, or high cholesterol and if they currently smoked cigarettes (\n11\n). Respondents who reported a history of a heart attack, angina, or coronary heart disease were classified as having a history of heart disease. Female respondents who had been told only that they had gestational diabetes were not categorized as persons with a current diagnosis of diabetes. Respondents who reported that they smoked cigarettes every day or some days were categorized as current smokers.\nBased on current recommendations from national organizations (\n12\n-\n15\n), we considered the following as established warning signs for stroke: dizziness, difficulty understanding speech or slurred speech, severe headache, problems with vision, weakness on one or both sides of body or face, numbness on one or both sides of body or face, trouble walking, loss of balance, or lack of coordination. We considered high blood pressure, high cholesterol, smoking, diabetes, heavy alcohol use, history of heart disease, and history of stroke or TIA to be established stroke risk factors.\nData analyses\nData analyses were completed using SPSS V11.5 software (SPSS Inc, Chicago, Ill). Chi-square tests were used to compare differences in respondent knowledge of two or more warning signs, two or more risk factors for stroke, and use of 911 EMS by age, sex, and history of stroke risk factors. Multiple logistic regression analyses were conducted to identify demographic and self-reported risk factors independently associated with knowledge of warning signs and risk factors for stroke.\nResults\nThe mean age of respondents (N = 800) was 61 years (range 45 to 95); 60% were female; 96% were white; 2% were American Indian; and 93% reported 12 or more years of education. Ten percent reported a history of atrial fibrillation; 6% reported a history of diabetes; 37% reported a history of high blood pressure; 31% reported a history of high cholesterol; 17% currently smoked cigarettes; and 40% were former smokers. Eight percent reported a history of heart disease, and 6% reported a history of stroke or TIA. Overall, 80% reported one or more risk factors for stroke, and 56% reported two or more risk factors for stroke.\nNumbness on any side of the face or body (45%) and speech problems (38%) were the most frequently reported established warning signs for stroke (\nTable 1\n). Fewer respondents reported vision problems (18%) or difficulty walking (11%). Overweight (56%), smoking (50%), and high blood pressure (44%) were the most frequently reported risk factors for stroke (\nTable 1\n).\nThe majority of respondents (70%) could identify two or more warning signs for stroke (\nTable 2\n). Women (75%) were more likely than men (62%) to identify two or more established warning signs for stroke, and respondents aged 45 to 64 years (76%) were more likely than those aged 65 years and older (59%) to identify two or more established warning signs for stroke. Just under half of the respondents (45%) could identify two or more established risk factors for stroke. Respondents aged 45 to 64 years (48%) were more likely to identify two or more established risk factors for stroke compared with those aged 65 years and older (40%).\nAdjusting for multiple factors using logistic regression analyses, women, individuals aged 45 to 64 years, those with 12 or more years of education, and individuals with a history of high cholesterol were more likely to identify two or more established warning signs for stroke compared with respondents without these characteristics (\nTable 3\n). Women and respondents aged 45 to 64 years were more likely to identify two or more established risk factors for stroke compared with men and with respondents aged 65 years and older.\nOverall, the majority of respondents (76%) indicated they would call 911 EMS if they witnessed someone having a stroke (\nTable 4\n). There were no differences by age, sex, or years of education in the proportion of respondents who indicated they would call 911 if they witnessed someone having a stroke (data not shown). When asked what they would do if they were experiencing sudden difficulty speaking, numbness, or weakness or paralysis, 43% to 49% of individuals indicated they would call 911. Depending on the symptom, 17% to 23% indicated they would go to the hospital, 14% to 19% would call their doctor, 11% to 18% would call their spouse or a family member, and 3% to 5% would do something else (\nTable 4\n). Respondents aged 65 years and older were more likely than respondents aged less than 65 to indicate they would call 911 if they experienced sudden difficulty speaking (49% vs 42%, \nP\n = .04), numbness (50% vs 40%, \nP\n = .006), or weakness or paralysis (55% vs 45%, \nP\n = .004). There were no differences by sex or years of education in the proportion of respondents who indicated they would call 911 if they experienced any of these warning signs (data not shown).\nDiscussion\nThe majority of respondents from these rural counties were aware of the established warning signs for stroke, and awareness was higher in women, younger respondents, those with a higher level of education, and those with a history of high cholesterol compared with respondents without these characteristics. Interestingly, respondents with a history of other major stroke risk factors (e.g., high blood pressure) were no more aware of the warning signs compared with respondents without these conditions. Overall, fewer respondents were aware of the established risk factors for stroke. We also found that the majority of respondents would call 911 if they thought someone was having a stroke, but less than half would call 911 if they were experiencing stroke warning signs.\nIndividuals responding to the survey lived in communities that are typical of many communities across the United States, where health care for a large region is centered in a nearby town. Awareness of established stroke warning signs and risk factors was higher than awareness levels reported in other community surveys (\n10\n,\n16\n,\n17\n). In 1999, only 30% of adults surveyed in Michigan identified two or more warning signs correctly, and 34% identified two or more risk factors correctly (\n17\n). In 2000, more than 40% of respondents in Cincinnati, Ohio, identified two or more warning signs for stroke, and 32% identified two or more established risk factors for stroke (\n16\n). A study of adults living in an urban area of Australia in 1999 found that 26% of respondents to a telephone survey identified two or more warning signs for stroke, and 50% identified two or more risk factors for stroke (\n10\n).\nOur findings on what respondents would do if they witnessed someone having a stroke or if they were experiencing warning signs of stroke are comparable to previous studies from Australia and Michigan (\n10\n,\n17\n). In Australia, 67% of respondents would call an ambulance if they witnessed someone having a stroke, while less than half of respondents would call an ambulance if they were experiencing sudden stroke warning signs (45% difficulties with speech, 38% numbness/weakness, 35% weakness or paralysis). In Michigan, however, 79% indicated they would call 911 if someone was having a stroke.\nThere are a number of limitations to this study. First, the survey does not reflect the experience of residents without telephones. Second, self-reported information regarding risk factors for stroke is subject to recall bias. Previous studies, however, have found that self-reported risk factors for cardiovascular disease are reported reliably (\n18\n,\n19\n). Third, respondents were asked unaided questions to assess respondent knowledge of the warning signs and risk factors for stroke. Some previous studies assessing awareness of stroke warning signs used aided questions and found higher levels of knowledge than the levels found in this study (\n20\n). It is possible that unaided questions may underestimate the awareness of the warning signs of stroke, and aided questions may overestimate awareness. Fourth, this study was conducted in a rural non-Hispanic white population, and there may be significant variation in awareness of stroke warning signs and risk factors in other geographic and racial and ethnic communities in the United States. \nOur findings about stroke awareness in rural communities are important because they are similar to studies published from academic centers working in urban areas (\n10\n,\n16\n,\n17\n). This effort, however, represents a collaboration between a state public health agency and several regional health care systems not only to understand the levels of stroke awareness in two communities at baseline but also to promote community awareness and increased use of EMS and to define regional approaches for prompt stroke treatment in cooperation with the stroke referral centers in these counties. Based on the findings reported here, the Montana Cardiovascular Health Program and these partners have developed and implemented a multifaceted intervention to increase community awareness of the warning signs of stroke and the need to use 911 adapting strategies that have been shown to be successful (\n8\n,\n21\n).\nIt is reassuring that levels of community awareness and knowledge about stroke in rural settings are not markedly different from levels found in urban environments. Others have shown that multifaceted interventions to increase community awareness, use of EMS, and availability of prompt diagnosis and treatment can succeed (\n7\n,\n8\n). Strategies to reduce barriers to prompt stroke treatment may be somewhat different across large frontier areas compared with urban environments. Cooperative efforts between public health agencies, communities, and prehospital and acute care systems, however, can build on the published experience of others to understand and improve knowledge about stroke warning signs and risk factors as part of broader public health interventions targeted to stroke prevention and treatment. In the United States, public health programs are only beginning to develop partnerships and work toward developing and documenting successful interventions in a wide variety of settings. This report represents the beginning of efforts to meet the challenges in rural communities in Montana and across many rural areas.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
65
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nDifferential Susceptibility to Hypertension Is Due to Selection during the Out-of-Africa Expansion\n\n**Article Abstract:**\n\nHypertension is a leading cause of stroke, heart disease, and kidney failure. The genetic basis of blood pressure variation is largely unknown but is likely to involve genes that influence renal salt handling and arterial vessel tone. Here we argue that susceptibility to hypertension is ancestral and that differential susceptibility to hypertension is due to differential exposure to selection pressures during the out-of-Africa expansion. The most important selection pressure was climate, which produced a latitudinal cline in heat adaptation and, therefore, hypertension susceptibility. Consistent with this hypothesis, we show that ecological variables, such as latitude, temperature, and rainfall, explain worldwide variation in heat adaptation as defined by seven functional alleles in five genes involved in blood pressure regulation. The latitudinal cline in heat adaptation is consistent worldwide and is largely unmatched by latitudinal clines in short tandem repeat markers, control single nucleotide polymorphisms, or non-functional single nucleotide polymorphisms within the five genes. In addition, we show that latitude and one of these alleles, \nGNB3\n (G protein β3 subunit) \n825T,\n account for a major portion of worldwide variation in blood pressure. These results suggest that the current epidemic of hypertension is due to exposures of the modern period interacting with ancestral susceptibility. Modern populations differ in susceptibility to these new exposures, however, such that those from hot environments are more susceptible to hypertension than populations from cold environments. This differential susceptibility is likely due to our history of adaptation to climate.\n\n**Article Body:**\n\nIntroduction\nA majority of people in industrialized countries will develop high blood pressure or hypertension. By one estimate, 90% of middle-aged and elderly people living in the United States can expect to become hypertensive [\n1\n]. The burden is not equally shared, however. In the United States, hypertension occurs earlier, more often, and with greater severity among people of African compared to European descent [\n2\n]. A portion of this greater burden may be due to greater genetic susceptibility to hypertension in some populations. Here we argue that hypertension susceptibility is ancestral and that a portion of differential susceptibility is due to differential exposure to selection pressures during the out-of-Africa expansion.\nHypertension Susceptibility Is Ancestral\nEnhanced salt and water avidity and vascular reactivity, key components of hypertension susceptibility, may have been adaptive in our ancestral African environment characterized by a hot, wet climate and salt scarcity [\n3\n–\n7\n]. Effective heat dissipation is essential in hot environments and is achieved most efficiently through evaporative heat loss [\n8\n]. As a result, humans have an unmatched capacity to sweat, being able to achieve a sweating rate of 2 l/h [\n9\n]. Sweating, however, can lead to loss of large amounts of salt and water [\n8\n]. Large salt losses due to sweating, combined with low salt availability in tropical climates [\n3\n], made a robust salt appetite and renal sodium conservation essential for survival. In support of this hypothesis, humans and non-human primates from tropical climates have enhanced salt and water avidity [\n3\n,\n10\n–\n12\n]. Another consequence of the reliance on sweating for heat dissipation is diurnal volume depletion [\n13\n]. During periods of low blood volume, increased arterial tone and force of cardiac contraction maintain blood pressure and ensure organ perfusion. Therefore, genetic variation that enhances arterial and cardiac contractility may have conferred a survival advantage in the environmental context of early human evolution.\nDifferential Susceptibility to Hypertension May Be Due to Differential Exposure to Selection Pressures during the Out-of-Africa Expansion\nOriginating in Africa some 100,000 to 200,000 y ago [\n14\n,\n15\n], our species has since expanded out of Africa to inhabit the rest of the world. As populations expanded out of Africa, the primary thermodynamic requirement shifted from heat dissipation to heat conservation and selection for salt and water avidity, and cardiovascular reactivity lessened. As a result, people who are adapted to colder regions have diminished vascular reactivity [\n16\n,\n17\n] and salt avidity, and as a consequence actually produce more sweat during heat stress than equatorial populations [\n18\n,\n19\n]. This difference in volume avidity and vascular reactivity is a physiologic source of differential susceptibility to hypertension and may be a consequence of differential exposure to selection pressures since the out-of-Africa expansion. In support of this hypothesis, two groups have recently demonstrated evidence of selection in two genes that influence blood pressure. \nAGT\n (angiotensinogen) and \nCYP3A5\n (cytochrome P450 3A5) have single nucleotide polymorphisms (SNPs) with functional alleles that influence salt avidity and blood pressure. For both genes the allele that increases salt avidity is the major allele among populations near the equator. By contrast, the allele that decreases salt avidity has risen to high frequency outside of Africa, probably due to selection [\n20\n,\n21\n].\nDo populations differ in hypertension susceptibility? Is the difference in susceptibility due to selection? What are the implications for worldwide variation in blood pressure? In order to address these questions, we first identified functional alleles in five genes that affect volume avidity and cardiovascular reactivity. The identified genes and SNPs include \nAGT\n (angiotensinogen) \nG-217A\n and \nG-6A, GNB3\n (G protein β3 subunit) \nC825T, ADRB2\n (β2 adrenergic receptor) \nG47A\n and \nG79C, ENaCα\n (epithelial sodium channel α) \nA-946G,\n and \nENaCγ\n (epithelial sodium channel γ) \nA-173G.\n These SNPs were chosen based on experimental evidence that variation at each affects gene expression or function. We then determined worldwide variation in heat adaptation as defined by prevalence of the allele that increases volume avidity or cardiovascular reactivity. Finally, we determined the effect of ecological factors and hypertension susceptibility, as measured by the \nGNB3 825T\n allele frequency, on worldwide variation in blood pressure.\nResults\nHeat Adaptation Is Strongly Associated with Latitude, Temperature, and Precipitation\nAmong the 53 populations represented in the Foundation Jean Dausset-Centre d'Etude du Polymorphisme Humain (CEPH) Human Genome Diversity Project (HGDP) (\nFigure 1\n), populations at low latitudes or in hot, wet climates, have a high prevalence of heat-adapted alleles, whereas populations at high latitudes or in cold, dry climates, have a low prevalence of heat-adapted alleles (\nFigure 2\n). For example, among populations within 10 degrees of the equator, 74%, on average, of the genetic variants are heat adapted. However, only 43% of the variants are heat adapted among populations within 10 degrees of the Arctic Circle. Across all populations, the association of heat adaptation with climate is strong, graded, and continuous.\nFigure 1\nWorldwide Distribution of the 53 Populations of the CEPH Human Genome Diversity Cell Line Panel\nFigure 2\nHeat Adaptation Is Strongly Associated with Absolute Latitude, Temperature, and Precipitation among the 53 Populations of the CEPH HGDP Cell Line Panel\nIn order to assess the significance of the association between heat adaptation and latitude, we compared the worldwide distribution of the functional, heat-adapted alleles with the distribution of a set of 404 multiallelic short tandem repeat markers (STRs) and a set of 42 biallelic control SNPs. No STR or SNP allele had as strong an association with latitude as the functional alleles \nAGT −6A\n or \nGNB3 825T\n (\nFigure 3\n). Only one STR and two control SNPs were more strongly associated with latitude than \nENaCα −946G\n and only seven STRs and eight control SNPs were more strongly associated with latitude than \nENaCγ −173G\n or \nADRB2 47A/79c\n.\nFigure 3\nHistogram of β Coefficients for the Association of Absolute Latitude with Functional Genotypes, Neutral STR Markers, and Control SNPs for the 53 Populations of the CEPH HGDP Cell Line Panel\nIf selection were responsible for the latitudinal cline in susceptibility, then the association should be strongest at the functional allele and decrease in a graded fashion at SNPs increasingly distant from the functional site. Therefore, we assessed the correlation between SNPs in and around each gene with latitude (\nFigure S1\nA–E). In \nAGT, GNB3, ADRB2,\n and \nENaCγ,\n the strength of the correlation is greatest at the SNPs with the functional alleles and decreases in a graded fashion at SNPs increasingly distant from the SNP with functional alleles. In \nENaCα,\n the strength of the correlation of \n-946G\n with latitude is second only to the closest neighboring SNP. Therefore, the latitudinal cline in heat adaptation is largely unmatched by latitudinal clines in STRs, control SNPs, or non-functional SNPs within the five genes.\nPopulations have experienced opposing selective gradients during the out-of-Africa expansion. Initially, heat-adapted African populations expanded northward, undergoing selection for cold adaptation. Subsequently, cold-adapted north Asian populations expanded southward into the Americas, undergoing selection for heat adaptation. Are latitudinal clines in heat adaptation similar in different regions of the world despite opposing directions of migration? The strength of the association of heat adaptation with latitude is similar among populations west of the Himalayas compared to populations in Asia (\nTable 1\n). Importantly, Native Americans, who are recently descended from cold-adapted north Asian populations [\n22\n,\n23\n], have a high percentage of heat-adapted alleles matching the level observed in African and Asian populations living at similar latitudes (see \nFigure 2\n, \nTable 1\n). This level of heat adaptation has occurred over the past 12,000 to 30,000 y and has been achieved despite the fixation of one SNP for the cold-adapted allele (\nENaCγ −173A\n, Figure S2).\nTable 1\nAssociation of Heat Adaptation with Absolute Latitude in Three Different World Regions among the 53 Populations of the CEPH HGDP Cell Line Panel\nAlthough the association of heat adaptation with climate is consistent across regions, the relative contribution of each variant to heat adaptation varies. For example\n, AGT −6A, GNB3 825T, ADRB2 47A/79C,\n and \nENaCα −946G\n contribute to worldwide variation in heat adaptation (Figure S2). In contrast, \nENaCγ −173G\n makes a smaller contribution to worldwide variation and \nAGT −217A\n does not contribute. In Africa, however, \nENaCγ −173G\n and \nAGT −217A\n are strongly associated with heat stress, which incorporates the combined effect of temperature and precipitation (\nR\n2\n = 0.99 \np\n < 0.001, \nR\n2\n = 0.72 \np\n = 0.02, respectively; \nFigure 4\n). The heat-adapted alleles are common among the rainforest-adapted Mbuti and Biaka pygmies and less common among groups living on the savanna such as the San. Furthermore, no STR or SNP allele had as strong an association with heat stress as \nENaCγ −173G\n in Africa (\nFigure 5\n). Only three STRs and one control SNP allele were more strongly associated with heat stress than \nAGT −217A\n in Africa\n.\nFigure 4\nHeat Adaptation, \nAGT G-217A,\n and \nENaCγ\n Are Strongly Associated with Heat Stress in Africa\nFigure 5\nHistogram of β Coefficients for the Association of Heat Stress with Functional Genotypes, Neutral STR Markers, and Control SNPs for the Seven African populations of the CEPH HGDP Cell Line Panel\nThe ancestral African environment was characterized by a hot, wet climate and salt scarcity. Therefore, functional alleles that maximize adaptation to heat may be ancestral [\n24\n]. In the case of \nAGT G-6A\n and \nENaCγ,\n the heat-adapted, functional alleles are ancestral (\nTable S1\n). For \nAGT G-217A, GNB3, ADRB2,\n and \nENaCα,\n however, the heat-adapted alleles are derived. Therefore, although a portion of hypertension susceptibility is ancestral, salt avidity and cardiovascular reactivity were likely magnified during early human evolution prior to the out-of-Africa expansion of anatomically modern humans. Increasing aridification in East Africa and subsequent adaptation to savannah may have driven the magnification of salt avidity and cardiovascular reactivity in early \nHomo\n.\nGNB3 C825T\n and Latitude Are Strongly Associated with Worldwide Variation in Blood Pressure\nIf selection shaped our susceptibility to hypertension through ecological variables that correlate with latitude, then latitude and the associated functional alleles should have a measurable effect on worldwide variation in blood pressure. In order to test this hypothesis, we investigated the extent to which latitude and hypertension susceptibility contribute to worldwide blood pressure variation using data from INTERSALT, an epidemiologic study of blood pressure in 52 populations around the world. We estimated the population frequency of \nGNB3 825T\n for 35 INTERSALT populations using data from HGDP and the literature (\nTable S2\n).\nAmong the 35 INTERSALT populations with allele frequency data, latitude explained 47% of the worldwide variation in blood pressure (\nTable S3\n). With an increase of one degree of latitude north or south, population-average systolic blood pressure increased by 0.3 mmHg. When \nGNB3 825T\n was included in the analysis, we were able to explain 64% of worldwide variation in blood pressure (\nTable 2\n, \nFigure 6\n). With each 1% increase in \nGNB3 825T\n allele frequency, blood pressure increased 0.19 mmHg. When body mass index (BMI) was added to the model, 74% of the variation in mean systolic blood pressure was explained. The addition of sodium excretion, BMI, or alcohol intake did not diminish the effect of latitude and \nGNB3 825T\n on blood pressure variation (data not shown).\nTable 2\nMultivariate Models Describing the Association of Traditional and Nontraditional Risk Factors with Systolic Blood Pressure (mm Hg) among 35 INTERSALT Populations with Allele Frequency Data\nFigure 6\nResidual Plot Demonstrating the Association of \nGNB3 825T\n with Systolic Blood Pressure after Adjustment for Latitude among 35 INTERSALT Populations with Matching Genotype Data\nThe strong association of latitude and \nGNB3 825T\n frequency with worldwide blood pressure variation is partly due to the use of population-level data in this analysis. Latitude represents a number of ecological factors that affect blood pressure, such as temperature and humidity. Likewise, \nGNB3 825T\n represents a number of functional alleles that influence hypertension susceptibility. For example, those populations in HGDP that have a high prevalence of the \nGNB3 825T\n allele also have a high prevalence of heat-adapted alleles at other SNPs (correlation of \nGNB3 825T\n with heat adaptation = 0.82). At present we are unable to assess the impact of other alleles on blood pressure in INTERSALT, because frequencies for other functional alleles were available for only a few INTERSALT populations. It is highly likely, however, that these and other unmeasured hypertension susceptibility alleles that correlate with latitude contribute to the predictive strength of \nGNB3 825T\n.\nGNB3 825T\n frequency is not associated with blood pressure until after adjustment for latitude (\nTable 3\n, \nFigure 7\n). Likewise, the association of latitude with blood pressure increases when \nGNB3 825T\n is included in the model. When the association between two variables is increased by a third, the third variable is said to negatively confound the relationship between the other two. Therefore, \nGNB3 825T\n and latitude negatively confound each other in their relationship with blood pressure. Negative confounding occurs because at low latitudes, blood pressure tends to be low and \nGNB3 825T\n frequency tends to be high, whereas at high latitudes blood pressure tends to be high and \nGNB3 825T\n frequency tends to be low. Therefore, in unadjusted analyses, the effect of \nGNB3 825T\n on blood pressure is counterbalanced by the effect of latitude on blood pressure. When the counterbalancing effect of latitude is removed through adjustment, however, \nGNB3 825T\n is strongly associated with blood pressure. Likewise, after adjustment for \nGNB3 825T,\n the association of latitude with blood pressure is strengthened as well.\nTable 3\nEpidemiologic Models Describing the Relationships among Absolute Latitude, \nGNB3 825T,\n and Systolic Blood Pressure among 35 INTERSALT Populations with Genotype Data\nFigure 7\nEpidemiologic Model Relating Absolute Latitude and Population-Average \nGNB3 825T\n Frequency with Each Other and with Population-Average Systolic Blood Pressure among 35 INTERSALT Populations with Matching Genotype Data\nThe β coefficients represent those in the models listed in \nTable 3\n.\nWhat is the source of this negative confounding? As discussed above, other functional alleles may contribute to the effect of \nGNB3 825T\n on blood pressure. These alleles would be positive rather than negative confounders, however, decreasing rather than increasing the association of \nGNB3 825T\n with blood pressure. The observed negative confounding is more likely the result of natural selection. As populations migrated to higher latitudes during the out-of-Africa expansion, population-average blood pressure increased. Natural selection favored those not in the upper range of blood pressure and \nGNB3 825T\n frequency decreased. The population-level effect is that average \nGNB3 825T\n frequency is negatively correlated with latitude. In addition, depending on time elapsed and the efficiency of natural selection, blood pressure will tend not to vary by latitude or genotype, because across populations, the effect of \nGNB3 825T\n balances the effect of latitude. Therefore, the observed interdependence of latitude, \nGNB3 825T,\n and blood pressure is likely due to natural selection.\nDiscussion\nWe have shown that populations differ in susceptibility to hypertension and provide compelling evidence that this differential susceptibility is due to differential exposure to selection pressure since the out-of-Africa expansion. The most important selection pressure was climate, which produced a latitudinal cline in susceptibility. Consistent with this hypothesis, latitude and hypertension susceptibility as determined by the presence of the \nGNB3 825T\n allele explains a large portion of worldwide variation in blood pressure.\nA growing body of evidence suggests that selection has shaped genetic susceptibility to several common diseases [\n3\n–\n7\n,\n20\n,\n21\n,\n25\n]. As reviewed by Di Rienzo and Hudson [\n24\n], many alleles that increase susceptibility to hypertension, coronary artery disease, and type 2 diabetes are ancestral, rather than derived. This ancestral susceptibility is consistent with the notion that alleles that were adaptive in our ancestral environment are maladaptive in the current one. As shown here, however, many alleles that increase susceptibility to hypertension are not ancestral, suggesting that hypertension susceptibility was magnified after the divergence of the line leading to \nHomo\n approximately 6 million y ago. Consistent with this idea, many of the features that differentiate humans from non-human primates, such as a tall linear body frame, hairlessness, and an enhanced capacity to sweat, facilitate heat dissipation [\n26\n,\n27\n]. Increasing aridification in East Africa and subsequent adaptation to savannah may have driven the evolution of these heat-adapted features, as well as the magnification of salt avidity and cardiovascular reactivity in early \nHomo\n.\nOriginating in Africa, our species has since expanded out of Africa to inhabit the rest of the world. This exposure to widely divergent ecological conditions may have contributed to human diversification. Recently, Ruiz-Pesini et al. found evidence of selection by latitude in human mitochondrial genes [\n28\n]. This variation may influence the efficiency of oxidative phosphorylation and, therefore, cellular heat production, an important adaptation to external temperature. Comparative physiologists have long recognized the importance of selection by latitude. In 1847, Bergmann [\n29\n] described a latitudinal cline in body size and shape that is common for species with a wide geographic range [\n30\n]. In fact, the association is stronger for humans than for many other species [\n31\n]. Allen described a similar latitudinal cline in limb length such that as latitude increases, limb length decreases [\n32\n]. This association is also found in humans [\n26\n,\n31\n,\n33\n]. Both ecological rules serve to facilitate heat dissipation at the equator by maximizing body surface area to volume ratio and to conserve heat toward the poles by minimizing this ratio. The effectiveness of increased surface area to dissipate heat is further maximized through evaporative heat loss, made possible by increased salt avidity and cardiovascular reactivity. As populations expanded into colder climates, the primary thermodynamic requirement shifted from heat dissipation to heat conservation, and selection for salt avidity and cardiovascular reactivity lessened. Therefore, differential susceptibility to hypertension may be a consequence of ecological selection during the out-of-Africa expansion. Consistent with this notion, Nakajima et al. found evidence of positive selection among populations outside of Africa near one of the SNPs examined in this work, \nAGT G-6A\n [\n20\n]. Similarly, Thompson et al. found evidence of positive selection near another SNP associated with increased salt avidity and hypertension, \nCYP3A5*1/*3\n [\n21\n]. We further demonstrate that latitudinal variation in hypertension susceptibility is not limited to salt avidity and is widespread, involving a functional variant in all five genes examined.\nThe rapidity of physical adaptation to climate is illustrated by the changes in body shape that occurred in Europe over the past 30,000 y. Prior to the Last Glacial Maximum, people with body proportions approximating those of savannah-adapted equatorial groups expanded into Europe. Within 20,000 y, these populations had developed high-latitude body proportions characterized, in part, by a smaller limb length to trunk ratio [\n26\n,\n34\n]. Indeed, the evolution of clinal variation in body size and shape has occurred throughout Eurasia and, to a limited degree, among native populations in the Americas [\n26\n,\n31\n]. Similarly, Native American populations demonstrate a level of salt avidity and cardiovascular reactivity equal to populations at similar latitudes in Africa, despite their recent descent from cold-adapted north Asian populations. This level of heat adaptation has occurred over the course of less than 20,000 y, attesting to the strength of selection by latitude.\nLatitude and hypertension susceptibility, as measured by \nGNB3 825T\n frequency, explain a large portion of worldwide variation in blood pressure. Importantly, the effect of \nGNB3 825T\n is not appreciated until latitude is included in the model. This negative confounding is likely a result of natural selection. As populations expanded north out of Africa, salt avidity and cardiovascular contractility decreased as latitude increased, thereby limiting the upward shift in population-average blood pressure due to latitude. In other words, natural selection acted as a homeostatic mechanism preserving blood pressure by matching genes to environment. This negative confounding by natural selection, as well as the strength of the collective effect of latitude and \nGNB3 825T\n on worldwide variation in blood pressure, are strong evidence that latitude influenced worldwide variation in hypertension susceptibility through selection.\nWhat is the source of the current epidemic of hypertension among industrialized populations? As shown in migration studies, the shift in the population average blood pressure occurs as people migrate into hypertensinogenic environments [\n35\n,\n36\n]. Therefore, the upward shift in blood pressure distribution among industrialized populations is more likely due to a greater burden of exposures such as increased salt intake and obesity than increasing hypertension susceptibility. However, we have shown that populations differ in susceptibility to these exposures. In addition, our analysis suggests that the migration of heat-adapted people to colder climates may contribute to the upward shift in population distribution of blood pressure, especially among members of the African Diaspora. Finally, the evolutionary history of disease susceptibility has important implications for association studies. As described by Di Rienzo and Hudson [\n24\n], protective alleles may be easier to identify than older hypertension susceptibility alleles because protective alleles have risen to high frequency more recently and, therefore, are more tightly linked to nearby markers.\nIn summary, we have shown that differential susceptibility to hypertension is due to differential exposure to selection pressure since the out-of-Africa expansion. The current epidemic of hypertension is due to the new exposures of the modern period, such as higher salt intake, interacting with ancestral susceptibility. However, populations differ in susceptibility to these new exposures such that those from hot environments are more susceptible to hypertension than populations from cold environments. This differential susceptibility is likely due to our history of adaptation to climate.\nMaterials and Methods\nHuman DNA.\nDNA was obtained from the CEPH HGDP panel representing 1,064 people from 53 populations around the world (see \nFigure 1\n). Populations that had undergone recent migration were excluded. Participants were descended from several generations of ancestors who belonged to the same population. The Han samples were divided into two groups, Han from North China and Han from Central China.\nGenes and their functional alleles.\nWe chose seven SNPs with functional alleles in five genes based upon three criteria. First, the gene must influence salt and water avidity or cardiovascular reactivity. Second, variation at the SNP must affect gene expression or function in experimental studies. Third, the minor allele frequency must be greater than 5% worldwide. The selected genes include \nAGT, GNB3, ADRB2,\n and the epithelial sodium channel components \nENaCα\n and \nENaCγ\n (see Accession Numbers and \nTable S1\n). Below is a description of these genes and the evidence for their inclusion in this work.\nAngiotensinogen is the precursor of angiotensin II, which increases arterial tone and salt avidity. The substitution of adenine for guanine in the promoter \n(G-6A)\n increases the gene's transcription rate and is associated with increased angiotensinogen levels and higher blood pressure [\n37\n,\n38\n]. The SNP \nM235T\n was the first molecular variant in \nAGT\n found to have an association with hypertension. However, there are no published experimental data suggesting that the two alleles have differential effects on gene expression or function. Rather, the association of \n235T\n with hypertension is likely due to linkage with \n-6A\n. Therefore, we have not included \n235T\n as one of our heat-adapted alleles. The \nAGT\n promoter has a second SNP with functional alleles, \nAGT G-217A,\n which is associated with hypertension among African Americans [\n39\n,\n40\n]. Substitution of adenine for guanine in transfection studies increases gene transcription and promoter activity induced by glucocorticoids and the \nC/ERB\n family of transcription factors [\n39\n,\n40\n].\nSalt avidity is a function of epithelial sodium channel activity, which is the rate-limiting step in renal sodium reabsorption. Mutations in \nENaC'\ns three subunits \nα, β,\n and \nγ\n (also called \nSCNN1α, β,\n or \nγ\n) are responsible for monogenic forms of hypertension. More common \nENaC\n polymorphisms may be responsible for population differences in salt avidity. Inwai et al. found that the substitution of guanine for adenine in the promoter of the \nENaCα\n subunit \n(A-946G\n, also called \nA2139G)\n increases the promoter activity in a cell-based transfection assay and is associated with hypertension [\n41\n]. The same group found a functional polymorphism in the promoter of the \nENaCγ\n subunit [\n42\n]. The substitution of guanine for adenine at position \n-173\n (\nA-173G\n) increased promoter activity in a similar transfection assay and was associated with higher blood pressure [\n42\n].\nG protein beta3 subunit is one of five distinct β subunits that, in combination with α and γ subunits, form signal-transducing G proteins. G proteins couple cell surface receptors to effectors that generate intracellular signals, thereby regulating many biological functions, including blood pressure [\n43\n]. A \nGNB3\n subunit containing thymine \n(825T)\n rather than cytosine \n(825C)\n at cDNA position \n825\n is associated with a truncated splice variant [\n44\n]. Functional analyses of the splice variant in model systems demonstrate enhanced signal transduction and Gα activation [\n45\n]. In human studies, vasoactive agents such as endothelin-1, angiotensin II, and noradrenaline produce greater vasoconstriction in people with the \n825T\n allele [\n44\n]. In addition, \n825T\n is associated with hypertension in many, but not all, populations ([\n46\n] provides a summary; please see \nTable S1\n for other references).\nThe β2-adrenergic receptor is responsible for catecholamine-mediated vasodilatation. In the setting of volume depletion, excess vasodilatation in response to increased sympathetic tone would compromise blood pressure. Therefore, \nADRB2\n variation that decreases this vasodilatory response would be advantageous in hot environments. Two base pair substitutions, \nA47G\n and \nC79G,\n result in two functional amino acid substitutions, Arg16Gly and Gln27Glu respectively. Both substitutions affect receptor desensitization with prolonged agonist activation in vitro [\n47\n,\n48\n]. In populations, however, only three of the four possible combinations occur, \n47A/79C, 47G/79C,\n and \n47G/79G\n [\n49\n]. Therefore, Dishy et al. investigated the affect of each combination in human subjects and found that \n47A/79C\n was associated with increased desensitization to the vasodilatory affect of isoproterenol [\n49\n]. Similarly, we have assigned one of three possible \nADRB2 A47G C79G\n haplotypes to each HGDP participant. We were able to do so unambiguously because the haplotype \n47A/79G\n does not occur.\nSNP genotyping.\nWe used a previously described 5′ nuclease allele discrimination assay (ABI TaqMan; Applied Biosystems, Foster City, California, United States) for all SNPs except \nM235T\n (rs699). Genotyping for \nM235T\n was performed using template directed extension coupled with detection by fluorescence polarization. Oligonucleotide sequences for all genotyping assays are available upon request.\nThe HGDP-CEPH analysis.\nTo test the hypothesis that populations differ in heat adaptation, we estimated individual level and population level of heat adaptation. In the case of \nAGT, GNB3, ENaCα,\n and \nENaCγ,\n the heat-adapted variants are the alleles that increase sodium avidity or vascular tone. In the case of \nADRB2,\n the heat-adapted variant is the haplotype \n27A/47C,\n which increases receptor desensitization. Individuals were scored for heat adaptation on the basis of the number of heat-adapted variants present divided by the number of possible heat-adapted variants. The total number of possible heat-adapted variants was the number of genotyped SNPs in an individual times two. Population-level susceptibility is defined as the average susceptibility of its members.\nTo test the hypothesis that differential heat adaptation is due to selection during the out-of-Africa expansion, we used linear regression to estimate the association of each functional variant with latitude, temperature, and precipitation. Heat-adapted alleles were hypothesized to be more common at latitudes near the equator and in areas with higher temperature and precipitation. In addition, we combined temperature and precipitation into a single term labeled heat stress. First, both variables were log-transformed to create normal distributions (temperature in degrees Kelvin). Second, we generated units equal to one standard deviation to make a unit increase in each variable comparable to the other. Third, we multiplied the variables together to create the summary variable. Finally, the summary variable heat stress was normalized by dividing by the highest level of heat stress in this dataset to produce a percentage.\nIn order to ascertain whether any observed associations were due to genetic drift or nonspecific selection, we compared variation in functional alleles to worldwide variation in 404 STRs, to variation in 42 control SNPs, and to variation in other nonfunctional SNPs in each gene. First, we used STRs previously genotyped by the Mammalian Genotyping Service using the Marshfield Screening Set #10 (\nhttp://research.marshfieldclinic.org/genetics/sets/combo.html\n). Results from this dataset have been previously reported [\n50\n] and are available online. Because STRs are not biallelic, we determined the major allele at each STR and then the frequency of that allele in each population. Second, we genotyped a set of control SNPs that were approximately frequency matched to the SNPs with functional alleles. From Applied Biosystems Assays on Demand, we chose 42 control SNPs, approximately one per chromosome arm, with a minor allele frequency near 40%. Assay IDs are available upon request. Third, we assessed the correlation between latitude and allele frequencies at polymorphic sites in and around each gene.\nThe INTERSALT data.\nAll phenotypic data were taken from data previously published by the INTERSALT investigators [\n51\n]. INTERSALT was an international study of blood pressure variation among 52 populations performed in the late 1980′s. Approximately 200 men and women aged 20–59 y were recruited from each population, giving a total of 10,079 people in all. Phenotypic data included population mean systolic blood pressure, diastolic blood pressure, and BMI (weight in kilograms divided by height in meters squared). Blood pressure was measured twice with a random zero sphygmomanometer using a standard protocol by trained personnel. Exposure data included population mean 24-h urine sodium excretion and alcohol intake. Height and weight were also measured twice. Participants provided a 24-h urine collection for electrolyte analysis. Using 13 sources, including HGDP and the literature, we were able to estimate \nGNB3 825T\n allele frequency for 35 INTERSALT populations (references in \nTable S2\n). Of the 52 INTERSALT populations, the investigation by Siffert et al. of the worldwide distribution of \nGNB3\n 825T contributed to the allele frequency estimation for 25 populations [\n52\n]. The HGDP contributed information for seven populations, and other population-based sources contributed information for 13 populations. More than one source contributed information for 12 INTERSALT populations. In these cases, the allele frequency estimation for the INTERSALT populations was based on a weighted average of the allele frequency estimates. We were not able to estimate the frequency of other functional alleles in a sufficient number of INTERSALT populations.\nThe INTERSALT analysis.\nWe used linear regression to describe the association of latitude and \nGNB3 825T\n with blood pressure, with and without adjustment for BMI, sodium excretion, and alcohol intake. The study populations were recruited by age and gender strata. Therefore, we did not adjust for these variables.\nIn our analysis of negative confounding, we used linear regression to describe the association of \nGNB3 825T\n with blood pressure, with and without adjustment for latitude, latitude with blood pressure, with and without adjustment for \nGNB3 825T,\n and latitude with \nGNB3 825T.\n In order to generate β coefficients that are comparable, we rescaled the variables such that a one unit change in a variable was equal to a one standard deviation change in the variable.\nSupporting Information\nFigure S1\nAssociation between Allele Frequencies for \nAGT, GNB3, ADRB2, ENaCα,\n and \nENaCγ\n and Absolute Latitude among the 53 Populations of the CEPH HGDP Cell Line Panel\n(A) \nAGT,\n (B), \nGNB3,\n (C) \nADRB2,\n (D) \nENaCα,\n and (E) \nENaCγ.\n The tick bars in the gene diagram represent the region from the first to the last exon. The bar under the diagram represents physical distance corresponding to 5 kb, except for \nADRB2\n where the bar represents 0.5kb. The diamonds represent SNPs. The corresponding histogram bar is indicated by the connecting line.\n(72 KB PDF)\nClick here for additional data file.\nFigure S2\nThe Association of Absolute Latitude with the Functional Genotypes in Five Genes Involved in Blood Pressure Regulation among the 53 Populations of the CEPH HGDP Cell Line Panel\n(55 KB PDF)\nClick here for additional data file.\nTable S1\nThe Selected Genes and Their Functional SNPs\n(34 KB DOC)\nClick here for additional data file.\nTable S2\nPopulation Averages of Phenotype and Allele Frequency Data among the 35 INTERSALT Populations with Estimated \nGNB3 825T\n Allele Frequency\n(91 KB DOC)\nClick here for additional data file.\nTable S3\nUnivariate Models Describing the Association of Traditional and Nontraditional Risk Factors with Population-Average Systolic Blood Pressure (mm Hg) among 35 INTERSALT Populations with Genotype Data\n(30 KB DOC)\nClick here for additional data file.\nAccession Numbers\nThe National Center for Biotechnology Information (NCBI) (\nhttp://www.ncbi.nlm.nih.gov\n) accession numbers for the genes discussed in this paper are \nADRB2\n (GeneID 154), \nAGT\n (GeneID 183), \nGNB3\n (GeneID 2784), \nENaCα\n (GeneID 6337), and \nENaCγ\n (GeneID 6338).\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
66
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nCommon carotid arterial interadventitial distance (diameter) as an indicator of the damaging effects of age and atherosclerosis, a cross-sectional study of the Atherosclerosis Risk in Community Cohort Limited Access Data (ARICLAD), 1987–89\n\n**Article Abstract:**\n\nBackground\nThe effect of age on common carotid artery diameter is unclear for varying atherosclerosis risk levels.\nMethods\nCross-sectional data from the Atherosclerosis Risk in Communities Limited Access Data set were used to estimate the association of age with B-mode ultrasound common carotid artery diameter for three atherosclerosis risk levels. Based on information from clinical examinations, B-mode ultrasounds, questionnaires, blood and other tests, participants were categorized into three groups: pre-existing disease (prevalent stroke and/or coronary heart disease), high risk group (no pre-existing disease, but prevalent diabetes, hypertension, plaques/shadowing, body mass index >= 30, current smoking, or hyperlipidemia), and a low risk group (no pre-existing disease, no plaques/shadowing, and no major elevated risk factors). Multivariable linear regression analyses modeled the common carotid artery diameter relationship with age.\nResults\nAge was positively and significantly associated with common carotid artery diameter after risk factor adjustment in the overall sample, but age had a larger effect among persons with evidence of atherosclerosis (interaction p < 0.05). Each year of older age was associated with 0.03 mm larger diameter/year among persons with pre-existing disease, with 0.027 mm larger diameter/year in the high risk group, but only 0.017 mm/year among the low risk group. Results were qualitatively similar using plaques/shadowing status to indicate atherosclerosis severity.\nConclusion\nThe significant impact of age on common carotid artery diameter among low risk, middle-aged, black and white men and women suggests arterial remodelling may occur in the absence of identified risk factors. The significantly larger impact of age among persons with, compared to persons without identified atherosclerosis or its risk factors, suggests that arterial remodelling may be an indicator of exposure duration.\n\n**Article Body:**\n\nBackground\nBecause of its accessibility, the common carotid artery (CCA) is often evaluated using B-mode ultrasound to assess atherosclerosis severity [\n1\n-\n3\n]. Ultrasound, animal, and anatomic studies indicate arterial diameters are associated with hemodynamic factors [\n4\n-\n7\n] and with vascular damage [\n8\n,\n9\n]. Several studies have suggested that arterial wall area, or arterial diameter in conjunction with wall thickness, may provide useful information for understanding atherosclerosis progression, vascular injury, or vascular vulnerability [\n2\n,\n8\n,\n10\n-\n15\n]. However, the relationship between arterial wall thickness and diameter is not likely to be simple since both physiologic and pathological processes can contribute to diameter differences [\n13\n]. For example multiple factors such as gender [\n16\n], physiologic response to shear stress[\n17\n] as well as plaque characteristics [\n8\n,\n9\n] are known to be associated with arterial diameter. So, many factors could potentially impact the relationship between age and diameter. While many studies have evaluated associations of risk factors or vascular characteristics with arterial diameter [\n8\n,\n9\n,\n11\n,\n18\n-\n23\n], fewer studies have attempted to separate the effects of age and atherosclerosis on arterial diameter. The Bruneck study found that age was related to CCA diameter only in persons within the upper 50\nth \npercentile of wall thickness [\n11\n] while a small study of 69 male subjects screened for the absence of atherosclerosis and its risk factors found that diameter did increase significantly with age [\n13\n].\nThis study extends previous studies of B-mode ultrasound CCA by estimating optimal B-mode ultrasound right CCA diameters (interadventitial distances) within a low-risk subset from a bi-racial population sample of both men and women; by determining whether atherosclerosis severity measures were effect modifiers of the age-CCA diameter relationship; and by estimating the effect of age among diseased, high risk, and low risk populations from the same population sample.\nMethods\nStudy sample\nFor our analyses we used the ARICLAD set provided by the National Heart and Lung Institute (NHLBI) after the institutional review board at the University of Arkansas for Medical Sciences approved the secondary data analysis as having minimal risk to the participants within the Limited Access Data set. The ARIC study was previously approved by review boards at each institution involved in the original study. The ARICLAD is a subset of the ARIC Cohort Study, a population based study of atherosclerotic disease in 15,792 black and non-black men and women, ages 45 to 64, from 4 clinical centers: Jackson, Mississippi; Forsyth County, North Carolina; northwest Minneapolis suburbs; and Washington County, Maryland. Participants from the Jackson center were all black, about 14% of those from the Forsyth center were black, and the other participants were predominantly white (non-black) [\n24\n]. The sampling strategy for the ARIC Cohort Study has been reported previously [\n24\n]. As per NHLBI policy [\n25\n], the ARICLAD set excluded participants whose informed consents were not consistent with release to investigators beyond the original ARIC study, and after \"records with personal identifiers and other variables that might enable individual participants to be identified, such as outliers, dates, and study sites, were removed or otherwise modified\" leaving 15,732 (99.6%) baseline participants. From this set, a computer-generated random sample of 10,000 participants was chosen for a developmental data set, of which 9,109 participants had B-mode ultrasound diameter measurements of the right common carotid artery (CCA).\nB-mode ultrasound\nAt baseline, questionnaires were administered [\n24\n] and fasting blood samples were drawn and processed as previously described [\n26\n]. Trained and certified sonographers at each of the four ARIC clinical centers obtained B-mode ultrasounds of the right and left carotid artery from three carotid segments (CCA, bifurcation, and internal carotid artery) with the participant in a supine position [\n27\n,\n28\n]. Each scan was read at a central reading center to achieve maximal standardization of readings as previously described [\n28\n]. This study evaluated the diameters (inter-adventitial distances) obtained from the \"optimal\" angle of interrogation of the distal 1 cm segment of the CCA (i.e. the 1-cm segment proximal to the dilatation of the carotid bulb). The \"optimal\" angle of interrogation was defined as the longitudinal view that best displayed the Y-shaped origin of the internal and external carotids from the carotid bifurcation and the four interfaces needed to define near and far wall thicknesses [\n27\n]. Since an earlier study had shown coefficients describing the relationship between CCA diameter and risk factors to be essentially the same whether right, left, or both CCA diameters were used [\n29\n], we used the diameters from the right CCA because more data were available.\nDisease and subset definitions\nAnalyses were cross-sectional and evaluated either the cohort sample or cohort subsets that were categorized using baseline characteristics to represent populations with varying prevalence of atherosclerotic disease and its risk factors. The pre-existing disease subset was defined by prevalence of either coronary heart disease (CHD) or stroke at baseline. A high risk subset consisted of persons without prevalent CHD or stroke, but with atherosclerotic plaques/shadowing, diabetes, hypertension, obesity, current smoking, or hyperlipidemia. Prevalent CHD was based on electrocardiographic evidence of a myocardial infarction (MI), self-reported physician diagnosis of a MI, or history of a cardiac procedure at the baseline examination [\n30\n]. An algorithm based on a standardized, validated, stroke symptom questionnaire [\n31\n] and self-reported diagnosis of stroke at baseline was used to identify prevalent stroke. Plaques or calcification (shadowing) of the right or left carotid sites (internal, bifurcation, or common carotid arteries) were identified based on B-mode ultrasound wall shape, texture, and thickness as described previously [\n28\n]. Other major risk factors at baseline were identified as follows: prevalent diabetes (self-reported physician diagnosis, medication within 2 weeks, or fasting blood glucose ≥ 126 mg/dL, or non-fasting blood glucose ≥ 200 mg/dL); hypertension (anti-hypertensive medication within 2 weeks or BP ≥ 140/90); obesity (body mass index ≥ 30, computed as weight in kg divided by height in meters\n2\n); current cigarette smoking status; hyperlipidemia (LDL cholesterol ≥ 160 mg/dL and/or use of cholesterol lowering medication). Cigarette years of smoking were calculated as the product of the average number of cigarettes smoked per day times the number of years smoked. The low risk subset consisted of persons remaining after excluding the pre-existing disease and high risk subsets.\nAn alternative 2-level classification of atherosclerosis severity, based on the presence or absence of atherosclerotic plaques/shadowing, was evaluated in statistical models with and without the first severity variables (pre-existing disease and high risk status) with which there was overlap. These analyses were limited to persons with information on plaques or shadowing at any carotid site (n = 7,381).\nStatistical analysis\nThe analyses were performed using SAS v9.1.2 (SAS Institute Inc., Cary, N.C.). Baseline characteristics between disease severity groups were compared using one-way analysis of variance (ANOVA) and chi-square tests. Multiple linear regression analyses were used to determine both the parameter estimates for age and for atherosclerosis severity variables after adjustment for height, race, and gender (basic adjustment) and after adding statistically significant (p ≤ 0.05) atherosclerotic risk or preventive factors from the following list: body mass index (BMI), hypertension, diabetes, systolic and diastolic blood pressures (SBP and DBP), smoking status, drinking status, usual grams of alcohol consumption per week, LDL and HDL cholesterols, cholesterol lowering medication use, white blood count, and fibrinogen. To test for effect modification, variables representing interaction terms between age, gender, and race with variables for atherosclerosis severity were tested and retained at an alpha of 0.05. Adjustments were to the sample covariate means unless specified otherwise. Age centering was used in conjunction with interaction terms to estimate the effects of atherosclerosis severity at specific ages.\nThe gender-, height-, and age-specific means were estimated with ordinary least squared regression models adjusting for race (to the proportion in the low risk subset). The 5\nth \nand 95\nth \npercentiles around the means were estimated using quantile (percentile) regression available in experimental SAS procedure QUANTREG.\nResults\nOf the 9,109 participants with right CCA diameter B-mode ultrasound measurements, 8,528 participants had adequate information for classification of disease severity and 8,163 participants had data for risk adjustment. Among persons with data from all 6 carotid sites (right or left, internal, bifurcation, and CCA), 36% were found to have plaque or shadowing (evidence of calcification) of at least 1 site. The low risk, high risk, and pre-existing disease groups were comprised of 1,397, 6175 and 591 participants respectively.\nCharacteristics of study population and subsets\nCharacteristics used to define the pre-existing disease, high risk, and low risk subsets varied as expected (Table \n1\n): smoking status, lipid profiles, and BP were most favorable in the low risk group, and heart disease and stroke were present only in the pre-existing group. However, other characteristics varied as well. The mean age, proportion of men, proportion of blacks, white blood count, and fibrinogen values were lowest in the low risk subset and were highest in the pre-existing disease subset except for black race. The low risk subset also had the largest proportion of current drinkers and the lowest ethanol consumption reported by drinkers. The group with pre-existing heart disease or stroke contained a greater proportion of former smokers, former drinkers, diabetics, hypertensive persons, users of cholesterol-lowering medication, and persons with plaques/shadowing, but a smaller proportion of current smokers, current drinkers, never smokers, and never drinkers than the high risk group. The pre-existing disease group also had a less favorable lipid profile (higher LDL and lower HDL), a lower DBP, and higher cigarette years smoked for current smokers than the high risk subset.\nTable 1\nCharacteristics of the cohort sample and the cohort subsets*: pre-existing disease, high risk, and low risk subsets, the Atherosclerosis Risk in Communities Cohort Limited Access Data, 1987–89.\nCohort Sample N = 8163\n‡\nSubsets* of Cohort Sample\nPre-existing Disease\nN = 591\n‡\nHigh Risk\nN = 6175\n‡\nLow Risk\nN = 1397\n‡\np-value\nAge (mean, std)\n54.2 (5.7)\n56.5 (5.3)\n54.4 (5.7)\n52.2 (5.4)\n<0.0001\nMale Gender (%)\n44.8\n64.3\n44.8\n36.7\n<0.0001\nBlack Race (%)\n25.5\n25.5\n28.7\n12.3\n<0.0001\nHeight in cm (mean, std)\n168.5 (9.3)\n170.4 (8.9)\n168.4 (9.3)\n168.0 (9.0)\n<0.0001\nStroke (%)\n2.4\n33.7\n†\n0\n§\n0\n§\nNA\nCoronary Heart Disease\n5.2\n72.2\n†\n0\n§\n0\n§\nNA\nPlaque or Shadowing\n35.7\n52.7\n44.0\n†\n0\n§\n0.0002\nSmoker (%)\n Current\n26.9\n29.6\n32.8\n†\n0\n§\n0.0783\n§§\n Former\n31.8\n43.8\n28.7\n40.5\n Never\n41.3\n26.6\n38.5\n59.5\nCigarette Years for Current Smokers (mean, std)\n681.9 (438.9)\n845.3 (532.4)\n667.7 (427.1)\nN/A\n<0.0001\nDrinker (%)\n Current\n56.3\n48.6\n55.4\n63.4\n<0.0001\n§§\n Former\n19.3\n31.5\n19.1\n14.9\n Never\n24.4\n20.0\n25.5\n21.7\nEthanol g/wk for Current Drinkers (mean, std)\n76.3 (119.1)\n87.8 (125.5)\n81.1 (125.8)\n54.1 (81.9)\n<0.0001\nDiabetes (%)\n11.4\n22.3\n12.9\n†\n0\n§\n<0.0001\nHypertension (%)\n35.5\n54.3\n41.7\n†\n0\n§\n<0.0001\nCholesterol Medication Use (%)\n3.0\n6.5\n3.3\n†\n0\n§\n<0.0001\nBody Mass Index (mean, std)\n27.7 (5.3)\n28.2 (5.4)\n28.3 (5.5)\n†\n24.7 (2.8)\n<0.0001\nSystolic Blood Pressure mm Hg (mean, std)\n121.4 (18.7)\n122.7 (21.6)\n123.5 (19.0)\n†\n111.5 (12.0)\n<0.0001\nDiastolic Blood Pressure mm Hg (mean, std)\n73.7 (11.3)\n72.6 (12.5)\n74.8 (11.5)\n†\n69.6 (8.5)\n<0.0001\nLDL Cholesterol mg/dl (mean, std)\n138.2 (39.5)\n145.2 (39.5)\n142.5 (40.3)\n†\n116.2 (26.0)\n<0.0001\nHDL Cholesterol mg/dl (mean, std)\n51.5 (17.0)\n44.6 (15.9)\n50.4 (16.2)\n59.2 (18.7)\n<0.0001\nFibrinogen (mean, std)\n304.3 (65.3)\n321.9 (72.0)\n308.6 (65.0)\n277.5 (55.5)\n<0.0001\nWhite Blood Count (thousands) (mean, std)\n6.2 (2.1)\n6.7 (3.3)\n6.3 (2.0)\n5.4 (1.5)\n<0.0001\n*Subsets: Pre-existing disease = prevalent CHD or stroke; High risk = absence of pre-existing disease + either diabetes, hypertension, body mass index ≥ 30, current cigarette smoking, LDL cholesterol ≥ 160 mg/dL, use of cholesterol lowering medication, or presence of plaque or shadowing on B-mode ultrasound; Low risk = absence of pre-existing disease and risk factors.\nPercentages may not total to 100% because of rounding.\n‡\nN = maximum possible in the cohort or subsets. For some variables, smaller numbers are available because of missing values.\n†\nVariable levels were used to distinguish between the high risk factor and low risk subsets.\nN/A since smokers were excluded from low risk subset.\n§\nSubset was defined by the absence of the characteristic.\n§§\nComparison of equality of proportions of current smokers and current drinkers between groups.\nAge-diameter relationships: adjustment to study population means\nWhen disease severity dummy variables (pre-existing disease, high risk status) were used as indicators of atherosclerosis severity, the risk-adjusted models retained age, race, height, BMI, current smoker status and cigarette years of smoking, current drinker status and usual ethanol intake, SBP, and DBP, and fibrinogen. When interactions were tested, the age-diameter relationships were not the same among the pre-existing disease, high risk and low risk subsets (p < 0.05 for deviance tests comparing models with and without interaction terms). Therefore, interaction terms (age-high risk status and age-pre-existing disease status) were retained and independent variable betas are shown in Table \n2\n.\nTable 2\nBeta coefficients and 95% confidence intervals (CI) for multivariable linear regression models with CCA diameter as the outcome after adjustment for basic covariates and after adding atherosclerotic risk factors.* Both models included interaction terms allowing determination of effects of age in subsets of varying atherosclerosis severity\n†\n, the Atherosclerosis Risk in Communities (ARIC) Limited Data Set, 1987–1989\nBasic Model N = 8163\nFull Model N = 8163\nBeta (95% CI)\np-value\nBeta (95% CI)\np-value\nMain effects\n Male gender\n0.492 (0.439, 0.545)\n‡\n<0.0001\n0.435 (0.384, 0.486)\n‡\n<0.0001\n Black race/ethnicity\n0.190 (0.149, 0.231)\n‡\n<0.0001\n0.087 (0.044, 0.130)\n‡\n<0.0001\n Height (cm)\n0.020 (0.018, 0.022)\n‡\n<0.0001\n0.023 (0.021, 0.025)\n‡\n<0.0001\n Current smoking\n-\n0.154 (0.107, 0.201)\n‡\n<0.0001\n Current drinking\n-\n-0.038 (-0.075, -0.001)\n‡\n0.0485\n Cigarette years of smoking (in 100's)\n-\n0.019 (0.015, 0.023)\n‡\n<0.0001\n Ethanol (100 grams/week)\n-\n0.039 (0.021, 0.057)\n‡\n<0.0001\n BMI\n-\n0.025 (0.021, 0.029)\n‡\n<0.0001\n Systolic BP\n-\n0.017 (0.015, 0.019)\n‡\n<0.0001\n Diastolic BP\n-\n-0.013 (-0.015, -0.011)\n‡\n<0.0001\n Fibrinogen\n-\n0.0002 (0.0000, 0,0004)\n‡\n0.0335\n Age (1 year of age)\n0.028 (0.020, 0.036)\n†\n<0.0001\n0.017 (0.009, 0.025)\n†\n<0.0001\nAdditional diameter increase per year of age\n Among Diseased Subset\n0.018 (0.004, 0.032)\n§\n0.0139\n0.013 (-0.001, 0.027)\n§\n0.0611\n Among Risk Factor Subset\n0.011 (0.003, 0.019)\n§§\n0.0096\n0.011 (0.003, 0.019)\n§§\n0.0101\n* Basic model independent variables = age, race, gender, height, dummy variables for disease severity, and interaction terms between age-disease severity dummy variables. Full model added variables = BMI, systolic and diastolic blood pressures, current smoker status, cigarette years of smoking in hundreds, current drinker status and grams of ethanol usually consumed per week in 100 g, fibrinogen value.\n‡\nBeta indicates the expected difference in millimeters of CCA diameter associated with the presence of each categorical variable and for each unit increase of continuous variables.\n†\nBeta indicates the expected difference in millimeters of CCA diameter for each year of older age in the low risk subset.\n§-§§\nBetasindicate the expected difference in millimeters of CCA diameter associated with each year of age among the diseased (\n§\n) and risk factor or high risk (\n§§\n) subsets.\nIn basic models (Table \n2\n), men (beta = 0.492) and blacks (beta = 0.19) had significantly larger CCA diameters than women and whites respectively. Height (beta = 0.02) was significantly and positively associated with CCA diameter as well. Adjusting for atherosclerotic risk factors (Table \n2\n, full model) resulted in a reduction of the effect sizes associated with race (beta = 0.087) and gender (beta = 0.435) by approximately 54% and 12% respectively, but did not reduce the effect of height (beta = 0.023).\nIn the basic model, each year of older age was associated with almost 0.03 mm larger CCA diameter (Table \n2\n, age main effect) in the low risk subset, but the age effect was larger among the diseased (main effect + interaction term = 0.046 mm/year) and high risk subsets (main effect + interaction term = 0.039 mm/year) (Table \n2\n). Not shown in the table is that by age 64, CCA diameters were 0.602 mm (SE = 0.077) larger in the pre-existing disease and 0.427 mm (SE = 0.056) larger in the high risk subsets than in the low risk subset prior to risk adjustment (both p < 0.0001). After risk factor adjustment, the betas were markedly reduced but still significant (beta = 0.252 and beta = 0.14 for the pre-existing disease and high risk group respectively, both p < 0.01). Except for current drinking status and DBP, all covariates were positively associated with CCA diameter (Table \n2\n).\nAge-diameter relationships: separate models adjusting to young-age risk levels\nResults were similar when the relationship between age and diameter was determined for each subset in separate analyses (Figure \n1\n). Betas for covariates were determined in linear regression models for each subset. Each stratified analysis was then adjusted to the means/proportions for the covariates of persons who were 45 to 50 years old in the respective subsets. Older age was associated with larger diameters in all subsets regardless of the level of adjustment, but the effect of age was reduced by risk factor adjustment in all subsets (slopes decreased after adjustment). Diameters for the pre-existing disease and high risk groups were larger than the low risk group, regardless of the level of adjustment. After risk factor adjustment, there was little difference between the slopes for the pre-existing disease and high risk groups (pre-existing disease: 0.028 mm/year; high risk group: 0.027 mm/year), but both groups continued to have slightly greater slopes than the low risk group (0.020 mm/year).\nFigure 1\nAge-specific, adjusted B-mode ultrasound common carotid artery diameters for study subsets, ARIC Limited Access data, 1987–89. *Age-specific diameters were estimated for each risk subset using betas determined from stratified models after adjusting for basic variables (race, sex, and height) and after adding risk factors (body mass index, SBP, DBP, current smoker status, usual ethanol intake (gms/week), fibrinogen, and years of smoking). **Adjustment was to the covariate means/proportions of persons age 45 to 50 of each subset. Diamonds indicate pre-existing disease subset; triangles indicate high risk subset; squares indicate low risk subset; Solid symbols indicate basic adjustment and open symbols indicate risk factor adjustment.\nAge-diameter relationships: plaque/shadowing as indicator of atherosclerosis severity\nThe alternative measure of atherosclerosis severity (plaque/shadowing presence or absence) was also found to be an effect modifier of the age-CCA diameter relationship in both basic (p = 0.01) and risk factor adjusted models (p = 0.02). After basic adjustment, age was positively associated with CCA diameter (0.035 mm/year) when plaques were absent (p < 0.0001) and with an additional 0.009 mm/year when plaques were present (p = 0.0145). Risk factor adjustment reduced the effect of age for persons without plaques (beta = 0.021, SE = 0.002, p < 0.0001) and reduced the added age effect found when plaques were present (beta = 0.008, SE = 0.003, p = 0.02).\nModels with plaque/shadowing and disease/risk status\nIn statistical models with basic adjustment but no interaction terms, plaque/shadowing status, and pre-existing disease and high risk status were significantly associated with CCA diameter (p < 0.0001). The addition of risk factors (current smoking status and cigarette years of smoking, drinking status and ethanol consumption, body mass index, fibrinogen, and SBP and DBP) resulted in a loss of significance of pre-existing disease (beta = 0.022, SE = 0.044, p = 0.6) and high risk status (beta = -0.039, SE = 0.028, p = 0.16), but not in plaque status (beta = 0.148, SE = 0.021, p < 0.0001). After adjustment, plaque status remained a significant modifier of the age effect on diameter (p < 0.03).\nEstimates of age-, gender-, and height-specific right CCA diameter\nAge had the smallest impact on the right CCA diameter among the low risk subset. Table \n3\n provides the gender-, height-, and age-specific mean diameters and corresponding percentiles for the low risk subset after adjusting for race. Right CCA diameters were larger for men, for tall persons, and for older persons compared to their respective counterparts.\nTable 3\nThe age-specific means and 5\nth \nand 95\nth \npercentiles for men and women by height categories, adjusted for race* determined from low risk participants of the ARIC Limited Access Data set, 1987–89.\nMen\nHeight <170 cm\nHeight 170–179 cm\nHeight 180+ cm\nAge\nMean Diameter\nDiameter Percentiles\nMean Diameter\nDiameter Percentiles\nMean Diameter\nDiameter Percentiles\n5\nth\n95th\n5\nth\n95th\n5\nth\n95th\n45\n7.45\n6.60\n8.15\n7.59\n6.74\n8.85\n7.84\n6.91\n8.90\n46\n7.48\n6.62\n8.19\n7.62\n6.75\n8.90\n7.86\n6.90\n8.92\n47\n7.51\n6.65\n8.23\n7.65\n6.76\n8.94\n7.88\n6.88\n8.95\n48\n7.53\n6.68\n8.28\n7.69\n6.78\n8.99\n7.90\n6.86\n8.98\n49\n7.56\n6.70\n8.32\n7.72\n6.79\n9.04\n7.92\n6.85\n9.00\n50\n7.59\n6.73\n8.36\n7.75\n6.80\n9.08\n7.95\n6.83\n9.03\n51\n7.61\n6.76\n8.40\n7.78\n6.81\n9.13\n7.97\n6.81\n9.05\n52\n7.64\n6.78\n8.45\n7.81\n6.83\n9.18\n7.99\n6.80\n9.08\n53\n7.67\n6.81\n8.49\n7.84\n6.84\n9.22\n8.01\n6.78\n9.11\n54\n7.69\n6.83\n8.53\n7.87\n6.85\n9.27\n8.03\n6.76\n9.13\n55\n7.72\n6.86\n8.58\n7.91\n6.86\n9.32\n8.05\n6.75\n9.16\n56\n7.75\n6.89\n8.62\n7.94\n6.88\n9.36\n8.07\n6.73\n9.19\n57\n7.77\n6.91\n8.66\n7.97\n6.89\n9.41\n8.09\n6.71\n9.21\n58\n7.80\n6.94\n8.70\n8.00\n6.90\n9.46\n8.11\n6.70\n9.24\n59\n7.83\n6.97\n8.75\n8.03\n6.91\n9.50\n8.13\n6.68\n9.26\n60\n7.85\n6.99\n8.79\n8.06\n6.93\n9.55\n8.15\n6.66\n9.29\n61\n7.88\n7.02\n8.83\n8.09\n6.94\n9.60\n8.17\n6.65\n9.32\n62\n7.91\n7.05\n8.88\n8.13\n6.95\n9.64\n8.19\n6.63\n9.34\n63\n7.93\n7.07\n8.92\n8.16\n6.96\n9.69\n8.21\n6.62\n9.37\n64\n7.96\n7.10\n8.96\n8.19\n6.98\n9.74\n8.23\n6.60\n9.39\nWomen\nHeight <160 cm\nHeight 160–169 cm\nHeight 170+ cm\nAge\nMean Diameter\nDiameter Percentiles\nMean Diameter\nDiameter Percentiles\nMean Diameter\nDiameter Percentiles\n5\nth\n95th\n5\nth\n95th\n5\nth\n95th\n45\n6.82\n6.13\n7.75\n6.93\n6.09\n7.93\n7.15\n6.17\n8.10\n46\n6.84\n6.13\n7.77\n6.97\n6.12\n7.96\n7.18\n6.20\n8.15\n47\n6.86\n6.13\n7.79\n7.0\n6.15\n7.99\n7.21\n6.22\n8.21\n48\n6.88\n6.14\n7.81\n7.03\n6.18\n8.02\n7.25\n6.25\n8.26\n49\n6.90\n6.14\n7.83\n7.06\n6.21\n8.06\n7.28\n6.28\n8.31\n50\n6.93\n6.14\n7.85\n7.10\n6.24\n8.09\n7.31\n6.30\n8.37\n51\n6.95\n6.15\n7.87\n7.13\n6.27\n8.12\n7.35\n6.33\n8.42\n52\n6.97\n6.15\n7.89\n7.16\n6.29\n8.15\n7.38\n6.36\n8.47\n53\n6.99\n6.15\n7.91\n7.20\n6.32\n8.18\n7.41\n6.39\n8.53\n54\n7.01\n6.16\n7.93\n7.23\n6.35\n8.22\n7.45\n6.41\n8.58\n55\n7.03\n6.16\n7.94\n7.26\n6.38\n8.25\n7.48\n6.44\n8.63\n56\n7.05\n6.16\n7.96\n7.30\n6.41\n8.28\n7.51\n6.47\n8.69\n57\n7.08\n6.17\n7.98\n7.33\n6.44\n8.31\n7.55\n6.49\n8.74\n58\n7.10\n6.17\n8.00\n7.36\n6.47\n8.35\n7.58\n6.52\n8.79\n59\n7.12\n6.17\n8.02\n7.39\n6.50\n8.38\n7.61\n6.55\n8.85\n60\n7.14\n6.18\n8.04\n7.43\n6.53\n8.41\n7.64\n6.57\n8.90\n61\n7.16\n6.18\n8.06\n7.46\n6.56\n8.44\n7.68\n6.60\n8.95\n62\n7.18\n6.18\n8.08\n7.49\n6.59\n8.48\n7.71\n6.63\n9.00\n63\n7.20\n6.19\n8.10\n7.53\n6.62\n8.51\n7.74\n6.66\n9.06\n64\n7.23\n6.19\n8.12\n7.56\n6.65\n8.54\n7.78\n6.68\n9.11\n*Diameters adjusted to the same proportion of black participants (13%)\nDiscussion\nThis study provides estimates for the effect of age on the right CCA diameter in both low and high risk populations. As an estimate of optimal right CCA diameters for middle-aged adults, the study provides age-, gender- and height-specific estimates for right CCA diameters from a low risk subset of the ARICLAD. Our findings of a significant, positive association between age and CCA diameter among a low risk population, with a larger effect among persons with atherosclerotic disease or high levels of risk factors, suggest that arterial remodeling may indicate duration of exposure among persons with atherosclerosis or elevated risk factors and duration of \"normal\" stresses among persons with low risk factor levels.\nThat atherosclerosis and atherosclerotic risk factors are associated with arterial diameter is well recognized [\n7\n,\n20\n,\n29\n,\n32\n], and recent studies have suggested arterial remodelling frequently occurs in association with vulnerable plaques [\n8\n,\n9\n,\n14\n]. So, associations between age and arterial diameter may not reflect the contribution of age itself, but instead, an increase in prevalence and/or severity of atherosclerosis or its risk factors with increasing age. The prospective Bruneck study, comprised of a random sample of men and women 40 to 85 years old, found a statistically significant increase in CCA diameter with age for persons in the highest 50\nth \npercentile of wall thickness, but a much smaller and non-significant diameter increase among persons with thinner CCA walls [\n11\n]. Similarly, our study found a larger effect of age on CCA diameter in persons with pre-existing atherosclerotic disease or high cardiovascular risk factor levels compared to low risk persons (e.g. without atherosclerotic disease and with low CVD risk factor levels). In our study, the greater effect of age on the CCA diameter in the higher risk groups was driven by the presence of atherosclerotic plaques. In contrast to the Bruneck study, our study found a significant positive association between age and CCA diameter even in the low risk subset. A number of differences between the studies could explain the discrepant findings: our study evaluated cross-sectional data and the Bruneck study evaluated prospective data; our study was of the right CCA and the Bruneck study combined right and left CCA; different criteria were used to define the low risk groups; and the study populations were different. However, qualitatively, results from the two studies are similar. CCA did increase with age in the Bruneck study low risk group, just not significantly so. Another study evaluated 69 male patients and athletes, aged 16–75, who were selected for the absence of major atherosclerotic risk factors and plaque [\n13\n]. In this convenience sample, age was a strong independent predictor of CCA diastolic diameter. Each ten years of increasing age was associated with a 0.17 mm larger CCA diameter [\n13\n], which is similar to the estimate in persons without atherosclerotic plaques (0.02 mm/year) and identical to the risk factor adjusted estimate from our low risk subset (0.017 mm/year). These findings support an effect for aging that is separate from that of clinically identifiable atherosclerosis and which appears to be relatively uniform in middle aged populations without major risk factors.\nThe significant interactions between both atherosclerosis severity measures and age in models predicting CCA diameter are consistent with age being a marker for length of exposure to the damaging risk factor effects. However, a significant interaction persisted only between age and plaques after adjustment for risk factors suggesting that much of the greater age effect in the pre-existing disease and high risk groups occur because of the effect of atherosclerotic damage evidenced by the presence of plaques.\nThe low risk subset was selected so that subjects had risk factor values lower than those typically used to identify cardiovascular risk. The reduction in the parameter estimate for age's impact on CCA diameter in the low risk group after adjusting for continuous atherosclerotic risk factors, indicates that even risk factor levels not commonly classified as detrimental can impact CCA diameters. This is not surprising given previous findings for BP [\n33\n]. Thus, at least part of the CCA diameter differences seen with older age in this low risk group was likely due to higher (though still normal) atherosclerosis risk factor levels at older ages. The persistence of a significant, positive association between age and CCA diameter in the low risk population, even after adjustment for atherosclerotic risk factors, suggests that damage or weakening of the arterial wall associated with aging also contributes to diameter enlargement. Since the primary goal of the ARIC ultrasound examination was not to identify plaques, we cannot exclude the possibility that some of the CCA diameter enlargement, even in the low risk group, was due to underlying atherosclerosis which was not identified.\nThis difference in diameters among the low risk group and higher risk groups has important implications for defining normal values in general. Since the prevalence of obesity and associated risk factors is high in many populations [\n34\n-\n36\n], using population based samples could result in incorrect estimations of optimal values for CCA diameter and other risk factors influenced by obesity. Thus, persons at risk could be misclassified as being normal, and the possibility of misclassification could be largest in populations with the greatest obesity and risk.\nBecause the study is cross-sectional in design, the associations that were identified do not necessarily indicate a causal mechanism. The division into low risk, high risk and pre-existing disease groups is somewhat arbitrary; and so, results could reflect differences because of the ages represented within the risk groups. However, given that substantial proportions of all age categories 45–49, 50–54, 55–59, and 60–64 were represented within each risk group, age differences are unlikely to be driving the findings. Persons who had missing information leading to their exclusion in the current study were different in a number of ways from the persons available for study. However, since the associations for age and CCA diameter were quantitatively similar to those reported by for a smaller \"normal\" male population and qualitatively similar to those reported in a prospective study [\n11\n,\n13\n], our results are likely to provide reasonable estimates for the differences that would be found in populations with disparate atherosclerotic risk.\nConclusion\nIn conclusion, consistent with our hypothesis and previous studies, our cross-sectional results indicate that persons with pre-existing atherosclerotic disease or atherosclerosis risk factors have larger diameters than persons without those attributes. More importantly, we also found that the impact of each year of older age on CCA diameter was significantly larger among populations with pre-existing cardiovascular disease and among persons with high risk factor levels or plaques compared to those at low risk of atherosclerotic disease and we were able to quantify the expected effect. Future investigations should consider the relationship between age, length of risk factor exposure, diameter, wall thickness, plaque, and disease development to better understand the progression of atherosclerosis and development of cardiovascular disease.\nList of abbreviations\nCCA: common carotid artery\nARICLAD: Atherosclerosis Risk in Communities Limited Access Data\nCHD: coronary heart disease\nMI: myocardial infarction\nLDL: low density lipoprotein\nHDL: high density lipoprotein\nSBP: systolic blood pressure\nDBP: diastolic blood pressure\nNHLBI: National Heart, Lung, and Blood Institute\nAuthors' contributions\nMLE developed the study proposal, performed some analyses and drafted and revised the manuscript.\nZB provided most analyses and provided input into manuscript revisions.\nDJC and GE provided input into the analyses while GE also provided understanding of the ARIC B-mode ultrasound procedures.\nRET, FB, KR, and JLM provided knowledge into the pathogenesis of atherosclerosis and revisions of the manuscripts.\nDisclosures\nThe authors have no conflicts of interest to disclose. Neither the interpretation nor presentation of the data was influenced by personal or financial relationship with other people or organizations.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
67
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nEffects of CPAP on right ventricular myocardial performance index in obstructive sleep apnea patients without hypertension\n\n**Article Abstract:**\n\nObjectives\nObstructive sleep apnoea (OSA) might cause right ventricular dysfunction and pulmonary hypertension. We aimed to determine the effects of nasal continuous positive airway pressure (CPAP) therapy on right ventricular myocardial performance index (MPI) in OSA patients without hypertension.\nMethods\n49 subjects without hypertension, diabetes mellitus, any cardiac and pulmonary disease had overnight polysomnography and echocardiography. In 18 moderate-severe OSA (apnea-hypopnea index ≥ 15) patients, right ventricular free wall diameter (RVFWD) was measured by M-mode, and right ventricular MPI was calculated as (isovolumic contraction time+ isovolumic relaxation time) / pulmonary ejection time using Doppler at baseline and after 6 months CPAP therapy.\nResults\nMean age was 46.5 ± 4.9 year. Patients had high body mass index (BMI: 30.6 ± 4,0 kg/m\n2\n), but there was no change in either BMI or blood pressures after 6 months. Right ventricular end-diastolic and end-systolic diameters were in normal limits at baseline, and did not change after CPAP usage. Baseline RVFWD (7.1 ± 2.1 mm) significantly decreased after CPAP therapy (6.2 ± 1.7 mm, p < 0.001). 15 of patients (83%) had right ventricular diastolic dysfunction at baseline, and it was completely improved in 11 of them (73%) by CPAP usage. Right ventricular global dysfunction was shown in 11 patients (61%) with a high MPI (62.2 ± 9.3%) at baseline; and MPI was significantly decreased after CPAP therapy (47.3 ± 8.4%, p < 0.0001), and it was completely corrected in 4 of them (36%).\nConclusion\nCPAP therapy significantly decreases RVFWD and improves right ventricular diastolic and global functions (MPI) in OSA patients without hypertension.\n\n**Article Body:**\n\nIntroduction\nThe obstructive apneic event is associated with considerable breathing efforts against totally or partially occluded upper airway. Obstructive sleep apnoea (OSA) might lead to cardiovascular complications such as heart failure, left/right ventricular dysfunction, myocardial infarction, arrhythmias, systemic and pulmonary hypertension, that all increase morbidity and mortality [\n1\n-\n10\n]. Early recognition and appropriate therapy of ventricular dysfunction is advisable to prevent further progression to heart failure and death [\n11\n,\n12\n].\nDuring an obstructive apnea, large negative intrathoracic pressures are generated during inspiratory efforts, which increase transmural pressures across the myocardium, thus increasing afterload. An increase in preload and pulmonary congestion may also occur due to increased venous return. The presence of hypoxemia decreases oxygen delivery to the myocardium, which may promote angina and arrhythmias. Also, frequent arousals from sleep lead to increase sympathetic activity. Other responsible mechanisms include impaired vagal activity, increased platelet aggregability, insulin resistance, and endothelial dysfunction with reduced endogenous nitric oxide production [\n13\n]. Continuous positive airway pressure (CPAP) is known to maintain upperairway patency during sleep by increasing transmural pressure of upper airways, and treatment of OSA by CPAP improves cardiac function and quality of life [\n14\n-\n17\n].\nVentricular dysfunction could not be detected clinically, but could just be detected echocardiographically. Myocardial performance index (MPI) reflects both systolic and diastolic functions (global function) of the ventricle [\n18\n,\n19\n]. In the presence of ventricular global dysfunction, MPI increases in contrast to ejection fraction (EF) of the ventricle. MPI is reproducible and a simple non-invasive method for the estimation of ventricular global function.\nIn the present study, we aimed to determine the effects of nasal CPAP after 6 months of therapy on right ventricular MPI in moderate-severe OSA patients without hypertension.\nMethods\na) Study population\n49 subjects admitted to sleep clinic with symptoms of nocturnal snoring and/or excessive day-time sleepiness taken into the study. A detailed sleep and cardiovascular anamnesis of the patients were recorded. Sleep cycle, nutritional status, medications, alcohol usage and family anamnesis were also questioned. Epworth sleepiness scale (ESS) [\n20\n] was questioned to all patients, and patients having high scores (ESS ≥ 10) were taken into the sleep study.\nPhysical examination was performed to all subjects at baseline and at 6 months. Systolic (SBP) and diastolic (DBP) blood pressures were measured in the sitting position on the right arm using a sphygmomanometer (Erka, Germany), after at least 5 min of rest. Hypertension was identified as blood pressure ≥ 140/90 mmHg or being used antihypertensive drugs. Heart rate per minute (HR) was measured in the sitting position, and body mass index (BMI) of the patients were calculated as weight divided to height square (kg/m\n2\n).\nPulmonary function tests (Sensor medics 2400, Netherlands), arterial blood gas analysis (ABL 30, Kopenhagen) were performed to all patients at rest. A 12-leadsurface ECG was taken from every subject, and all of them were in sinus rhythm. Also, all of subjects underwent treadmill exercise test and, the test was normal for each subject.\nSymptoms of nocturnal snoring and/or excessive day-time sleepiness were accepted as inclusion criteria. Exclusion criteria of the study were the presence of 1- any known cardiac and lung disease, 2- hypertension, 3- diabetes mellitus, 4- angina pectoris, 5- atrial fibrillation or any arrhythmias, 6- chronic renal and hepatic diseases, 7- serum electrolytes imbalances.\nb) Polysomnography (PSG)\nAll patients underwent an entire night of diagnostic PSG while breathing room air, followed a second night of PSG with nasal CPAP titration [\n21\n]. The portable, limited sleep study performed with the Emblettadevice [\n22\n], consisted of the following: 1) nasal pressure detectorusing nasal cannulae/pressure transducer system, recording thesquare root of pressure as an index of flow; 2) thoraco-abdominalmovement detection through two piezoelectric belts; 3) fingerpulse oximeter; and 4) body position detection.\nApnea was defined as total obstruction of oronasal airflow ≥ 10 seconds, an hypopnea was defined as decrease of airflow at least 50%, and desaturation was accepted as a decrease of ≥ 4% in oxygen saturation [\n23\n]. Desaturation index (DI) was identified as number of oxygen desaturation events per hour of sleep. In this study, 21 non-hypertensive subjects with AHI ≥ 15 were diagnosed as moderate-severe OSA [\n24\n].\nc) Nasal continuous positive airway pressure (CPAP)\nPatients with severe OSA were prescribed nasal CPAP (Remstarplus, Respironics Corporation; Murrysville, Pennsylvania, USA), including use of a heated humidifier. The CPAP machines were equipped with compliance monitors that measured CPAP use, in order to observe CPAP usage/compliance at home. Routine troubleshooting took place in an effort to maximize compliance with nasal CPAP. Patients were considered to be CPAP compliant if they used CPAP an average ≥ 3.5 h per night at the 6-month follow-up.\nd) Echocardiographic measurements\nEchocardiograms were obtained following the diagnosis of OSA and prior to initiation of CPAP, and at 6 months. All measurements were performed with the subjects in the left lateral decubitus position by M mode, two dimensional (2D), and Doppler ultrasound echocardiography in the morning. The ultrasound equipment used was Contron Sigma Iris with a 2.5-MHz probe. The duration of the examination was at least 20 minutes. The ventricular diameters, volumes and functions were measured according to the recommendations of the American Society of Echocardiography [\n25\n]. Basic measurements of left/right ventricular dimensions in diastole and systole, thickness of interventricular septum (IVS), left ventricular posterior wall (LVPW) and right ventricular free wall diameter (RVFWD) were measured by M-mode technique.\nEarly (E) and atrial (A) trans-mitral/tricuspid maximal flow velocities, the ratio (E/A) and deceleration time (DT) of E was registered. Isovolumetric relaxation time (IVRT) was measured by the continuous wave Doppler technique. The velocity of mitral/tricuspid flow propagation (VPR) was estimated using color Doppler M-mode. The left/right ventricular MPI was calculated as (isovolumic contraction time of left/right ventricle + IVRT of left/right ventricle) / (aortic/pulmonary ejection time) by Doppler.\ne) Statistical analysis\nMeasurements are expressed as mean ± SD. A Wilcoxon test for related measurements was used to compare primary outcome variables of both IVS, LVPW, RVFWD and ventricular functions (LVEF, MPI) at baseline and 6 months. Also, Mc Nemar chi-square test was used for comparison of number of obstructive sleep apnea patients without hypertension according to right ventricular hypertrophy and diastolic or global dysfunctions at baseline (before treatment) and after 6 months of CPAP usage. A p value of < 0.05 was regarded as significant.\nResults\n18 of 21 patients were compliant with CPAP therapy, which we defined as ≥ 3.5 h of nightly use. At the end of the study the mean daily CPAP usage of 18 patients, was 5.6 ± 1.7 h per night. The 3 patients who were non-compliant with nasal CPAP were excluded. So, 14 males (78%) and 4 females (22%) with moderate-severe OSA without hypertension were included in the study. Mean age of patients was 46.5 ± 4.9 year. None of them were using alcohol, and 55% of them were smoking cigarettes. Baseline characteristics of OSA patients were shown in table \n1\n. Study patients had high BMI (mean 30.6 ± 4,0 kg/m\n2\n), however there were no change in either BMI or blood pressures (BP) after 6 months (see table \n2\n). Mean AHI was 50.1 ± 11.6 per h, average O\n2 \nsaturation was 80.1 ± 2.6% and sleep duration with oxygen saturation <90% was 66.4% in the patients (table \n1\n).\nTable 1\nBaseline characteristics of obstructive sleep apnea patients without hypertension at pre-treatment of continuous positive airway pressure (CPAP).\nVariables\nData\nSubjects n\n18\nMean age yrs\n46.5 ± 4.9\nMale n, (%)\n14 (78)\nFemale n, (%)\n4 (22)\nBMI kg/m\n2\n30.6 ± 4,0\nSBP mmHg\n120.3 ± 10.1\nDBP mmHg\n82.0 ± 4.1\nHR pulse*min\n-1\n82.4 ± 13.4\nAHI per h\n50.1 ± 11.6\nDI per h\n37.8 ± 18.0\nMinSatO\n2 \n(%)\n73.8 ± 18.9\nAverageSatO\n2 \n%\n80.1 ± 2.6\n*Sleep duration %\n66.4\nCPAP usage h/night\n5.6 ± 1.7\nCPAP pressure cmH\n2\nO\n11.3 ± 2.5\nData are presented as n, n(%) or mean ± SD. BMI: body mass index, SBP: systolic blood pressure, DBP: diastolic blood pressure, HR: heart rate, AHI: apnea hypopnea index, DI: desaturation index, SatO\n2\n: saturation of nocturnal arterial oxygen, NS: nonsignificant. *SatO\n2 \n< 90%\nTable 2\nBasic characteristics and left ventricular structure and function indices in overall obstructive sleep apnoea patients before and after 6 months of continuous positive airway pressure (CPAP) treatment.\nCPAP treatment\np-value\nOverall (n = 18)\nBefore\nAfter\nBasic characteristics\nBMI kg*m\n-2 \n(<30)*\n30.6 ± 4,0\n31,0 ± 3,5\nNS\nSBP mmHg (<140)*\n120.3 ± 10.1\n119,1 ± 10,2\nNS\nDBP mmHg (<90)*\n82.0 ± 4.1\n81.2 ± 3,8\nNS\nLeft ventricular structure\nLeft atrium mm (19–40)*\n35.1 ± 3.2\n36.0 ± 3.0\nNS\nIVS thickness mm (6–11)*\n10.3 ± 1.1\n10,4 ± 1,0\nNS\nLVPW thickness mm (6–11)*\n10.1 ± 0.8\n10,0 ± 0,9\nNS\nLVEDD mm (37–56)*\n47.1 ± 4.1\n46.1 ± 4.3\nNS\nLVESD mm (19–40)*\n32.2 ± 4.8\n31.8 ± 4.7\nNS\nDiastolic functions\nE/A ratio (>1)*\n1.6 ± 0.1\n1.6 ± 0.2\nNS\nIVRT ms (<100)*\n80.0 ± 12.0\n81.1 ± 12.6\nNS\nDT ms (<220)*\n180.2 ± 16.5\n179.5 ± 16.8\nNS\nVPR cm*s\n-1 \n(>55)*\n89.2 ± 10.6\n88.6 ± 10.3\nNS\nSystolic function\nLVEF % (55–75)*\n64.0 ± 4.9\n64,1 ± 4,7\nNS\nGlobal function\nMPI % (39 ± 5)*\n37.2 ± 6.0\n36.8 ± 5.8\nNS\nData are presented as mean ± SD. *Normal values, BMI: Body mass index, SBP: Systolic blood pressure, DBP: Diastolic blood pressure, IVS: Ýnterventricular septum, LVPW: Left ventricular posterior wall, LVEDD: Left ventricular end diastolic diameter, LVESD: Left ventricular end systolic diameter, E/A: Ratio of early and lately mitral flow velocity, IVRT: Ýsovolumic relaxation time, DT: Mitral deceleration time, VPR: Velocity of mitral flow propagation, LVEF: Left ventricular ejection fraction, MPI: Myocardial performance index of left ventricle, NS: nonsignificant.\nCompliance of CPAP\nThe major reasons for noncompliance were mask discomfort or pressure intolerance. All subjects were offered heated humidity, and efforts were made in all subjects to improve comfort and compliance with therapy. Average CPAP pressure after 6 months of therapy did not change from the initial CPAP pressure that was prescribed (11.3 ± 2.5 cmH\n2\nO and 11.0 ± 2,3 cmH\n2\nO).\nEchocardiographic findings before and after CPAP therapy\nBaseline characteristics and left ventricular structure and function indices in OSA patients before and after 6 months of CPAP treatment were shown in table \n2\n. All echocardiographic left ventricular structural (e.g. IVS, LVPW diameters) and functional (e.g. E/A ratio, LVEF and MPI) parameters were in normal limits, and all of them did not significantly change after 6 months of CPAP therapy in OSA patients without hypertension.\nRight ventricular structure and function indices in the patients before and after 6 months of CPAP treatment were shown in table \n3\n. Although right atrial and right ventricular end-diastolic diameters were in normal limits, and both of them did not significantly change; right ventricular free wall diameter at baseline (7.1 ± 2.1 mm) significantly decreased (6.2 ± 1.7 mm, p < 0.001) after CPAP usage.\nTable 3\nRight ventricular structure and function indices in overall obstructive sleep apnoea patients before and after 6 months of continuous positive airway pressure (CPAP) treatment.\nCPAP treatment\np-value\nOverall (n = 18)\nBefore\nAfter\nRight atrium mm\n23.9 ± 3.0\n23.7 ± 3.2\nNS\nRVFWD mm (5–8)\n7.1 ± 2.1\n6.2 ± 1.7\n0.001\nRVEDD mm (9–26)\n25.4 ± 3.6\n25.0 ± 3.3\nNS\nE-velocity (m/s)\n0.4 ± 0.1\n0.6 ± 0.1\n0.0001\nA-velocity (m/s)\n0.6 ± 0.13\n0.5 ± 0.9\n0.001\nE/A ratio (>1)*\n0,7 ± 0.1\n1.2 ± 0.2\n0.0001\nIVRT ms (<100)*\n106.9 ± 24.0\n91.1 ± 18.6\n0.001\nDT ms (<220)*\n245.5 ± 61.0\n210.2 ± 46.8\n0.001\nVPR cm*s\n-1 \n(>55)*\n41.1 ± 9.9\n60.9 ± 10.2\n0.0001\nMPI % (39 ± 5)*\n62.2 ± 9.3\n47.3 ± 8.4\n0,0001\nData are presented as mean ± SD. *Normal values, RVFWD: Right ventricular free wall diameter, RVEDD: Right ventricle end-diastolic diameter, E- velocity: Early tricuspid flow velocity, A- velocity: Lately tricuspid flow velocity, E/A: Ratio of early and lately tricuspid flow velocity, IVRT: Ýsovolumic relaxation time, DT: tricuspid deceleration time, VPR: Velocity of tricuspid flow propagation, MPI: Myocardial performance index of right ventricle, NS: nonsignificant.\nAlthough patients had right ventricular diastolic dysfunction with an increased mean value of diastolic function parameters such as E/A ratio, IVRT, DT and VPR at baseline; average value of all those parameters significantly decreased by CPAP therapy. Also, right ventricular MPI (62.2 ± 9.3%) was significantly decreased after 6 months of CPAP usage (47.3 ± 8.4%, p < 0.0001), but it did not come to the normal limits, and it still reflected right ventricular global dysfunction (see table \n3\n).\nComparison of number of OSA patients without hypertension according to right ventricular hypertrophy (RVH) and diastolic or global dysfunctions at baseline (before treatment) and after 6 months of CPAP usage was shown in table \n4\n. Three of 18 patients (17%) had RVH, and although RVH had improved by CPAP usage, there was still 3 patients having RVH at the end of 6 months. Fifteen of 18 patients (83%) had right ventricular diastolic dysfunction, and 11 of them (73%) completely improved by CPAP usage. Right ventricular global function (MPI) was shown in 11 patients (61%), and also 4 of them (36%) completely improved by CPAP therapy.\nTable 4\nComparison of number of obstructive sleep apnea patients without hypertension according to right ventricular hypertrophy (RVH) and diastolic or global dysfunctions at baseline (before treatment) and after 6 months of continuous positive airway pressure (CPAP) usage.\nCPAP treatment\np- value\nOverall (n = 18)\nBefore\nAfter\nPatients with RVH n (%)\n3 (17)\n3 (17)\nNS\nDiastolic dysfunction n (%)\n15 (83)\n4 (22)\n0,0001\nGlobal dysfuntion n (%)\n11 (61)\n7 (39)\n0,001\nData are presented as n or n (%), NS: nonsignificant.\nDiscussion\nIn our previous studies, we showed right and left ventricular global dysfunctions in OSA patients with an increased MPI [\n3\n,\n4\n]. Arterial hypertension, obesity, diabetes mellitus and coronary artery disease which often have coexistince with OSA are independent predictors of ventricular dysfunction. On the other hand, it's well known that OSA might cause cardiovascular complications such as heart failure, myocardial infarction, arryhthmias, systemic and pulmonary hypertension which all increase mortality and morbidity [\n1\n-\n10\n]. Continuous positive airway pressure is known to maintain upperairway patency during sleep by increasing transmural pressure of upper airways, and treatment of OSA by CPAP improves cardiac function and quality of life [\n14\n-\n17\n]. In the present study, we aimed to determine the effects of nasal CPAP after 6 months of therapy on right ventricular structure and global function (MPI) in moderate-severe OSA patients without hypertension.\nIn our study, we excluded systemic hypertension, diabetes mellitus, coronary artery disease and any pulmonary diseases including chronic obstructive pulmonary disease, and there were no significant differences in BMI or BPs after 6 months of therapy. Thus, we assessed the ventricular structure and functions (MPI) in uncomplicated (isolated) OSA patients.\nLeft ventricular systolic and/or diastolic functions provide prognostic information in the patients. In our study, left ventricular diameters and both systolic and diastolic functions of all subjects were in normal limits and did not significantly change after CPAP therapy. However, right ventricular free wall diameter significantly decreased after CPAP usage. Eleven of 15 patients having diastolic dysfunction (73%) and 4 of 11 patients having right ventricular global dysfunction (36%) completely improved by CPAP therapy.\nThe relation of OSA to right heart structure and function is controversial. The prevalence of RVH by echocardiography in sleep apnea was ranged from 0 to 71% [\n26\n]. In the present study, 3 of 18 patients (17%) had RVH, and it was significantly improved by CPAP usage inspite of any change in the number of patients having RVH. It has been argued that concomitantchronic pulmonary disorders are required for sleep apnea to causeright heart failure [\n27\n-\n31\n]. However, Sannerand colleagues demonstrated that sleep apnea was independentlyassociated with depressed right ventricular ejection fraction by radionuclideventriculography after adjusting for lung function, age, bodymass index, sex, blood gas analysis, pulmonary artery pressure, and left ventricular ejection fraction [\n32\n]. Hanly and colleagues found no difference in right or left ventricular dimensions betweennonapneic snorers and subjects with OSA [\n33\n].\nThe reasons for the disparate conclusions of the prior studies examining RVH, systolic function, and right ventricular enlargementare not certain. In a study, right atrial and ventricular dimensions, and right ventricular systolicfunction were not found to be significantly different betweensubjects with sleep-disordered breathing and the low respiratory disturbance index subjects, but this study indicated that sleep-disordered breathing was associated with increased right ventricular wall thickness in a general population [\n34\n]. Right atrial and ventricular diameters of our patients without hypertension were in normal limits at baseline, and none of them significantly have changed by CPAP usage.\nIn many studies beneficial effect of CPAP on cardiac functions have been shown [\n35\n-\n37\n]. These may include several factors, such as improved myocardialoxygen delivery, decreased sympathetic activity, left ventriculartransmural pressure, and afterload. In a study, Arabi et al. had proved that systemic hypertension developed in hypoxic situation in normotensive cases, and furthermore they showed a decrease in the adrenergic mediators in patients having CPAP therapy for OSA [\n38\n]. Also, Cloward TV et all. showed a regression of left ventricular hypertrophy by 6 months of CPAP therapy, but not in the left and right atrial enlargement [\n39\n]. Recent placebo-controlled trials have revealed reductions of up to 10 mmHg in systolic and diastolic pressures with CPAP therapy [\n40\n-\n42\n]. However, we did not show any decrease in BPs with CPAP therapy in our non-hypertensive OSA patients. The reason of no change in BP might be due to the small sample size of our study population, and it might depend on totally normotensive patients. In our another study, we showed that CPAP therapy in OSA patients with hypertension did not decrease BPs and heart rates acutely, but reduced the variability of these parameters during sleep [\n17\n].\nDoherty LS, et all. performed a long-term follow-up study of 168 patients with OSA who had begun receiving CPAP therapy at least 5 years previously, most of whom had been prospectively followed up, having been the subject of an earlier report on cardiovascular risk factors in OSA patients with the average follow-up period 7.5 years [\n43\n]. They compared the cardiovascular outcomes of those patients who were intolerant of CPAP (untreated group, 61 patients) with those continuing CPAP therapy (107 patients). Deaths from cardiovascular disease were more common in the untreated group than in the CPAP-treated group during follow-up (14.8% vs 1.9%, respectively; p < 0.009), but no significant differences were found in the development of new cases of hypertension, cardiac disorder, or stroke. Total cardiovascular events (ie, death and new cardiovascular disease combined) were more common in the untreated group than in the CPAP-treated group (31% vs 18%, respectively; p < 0.05). They concluded that their results support a protective effect of CPAP therapy against death from cardiovascular disease in patients with OSA.\nOur study does not clarify the reasons of right ventricular diastolic and global dysfunctions in OSA patients without hypertension. Right ventricular diastolic filling is a complex event that is influenced by several factors, such as right ventricular relaxation, right ventricular compliance, right atrium contraction force and pulmonary artery resistance. Thus, right ventricular dysfunction might be the result of a variety of these impairments. In our study patients, intermittent nocturnal hypoxemia might have caused RVH and/or right ventricular dysfunction, since they had more hypoxic duration in their sleep with the highest percent of sleep duration below 90% of oxygen saturation.\nSince the systolic and diastolic dysfunction frequently coexist, it was shown that a combined measure of ventricular performance with calculation of MPI might be more reflective of overall cardiac dysfunction than systolic or diastolic measures alone. MPI is a simple and reproducible non-invasive method for diagnosis of ventricular global dysfunction in patients with OSA.\nIn the present study, a very noticeable finding is the improvement of right ventricular free wall dimension and global dysfunction with a significantly decreased MPI by CPAP therapy, even if 6 months usage.\nConclusion\nOSA patients, especially having diastolic dysfunction, is in an increased risk of heart failure, since the systolic and diastolic dysfunction frequently coexist. A combined measure of ventricular performance with the calculation of MPI might be more reflective of overall cardiac dysfunction than systolic or diastolic measures alone. CPAP therapy significantly decreases right ventricular free wall thickness and improves global dysfunction with a significantly decreased MPI even if 6 months of CPAP usage. We consider that much longer-term usage of CPAP therapy may achieve complete improvement of right ventricular global dysfunction in patients with OSA.\nStudy limitations\nSmall number of patients in our study population is an important study limitation to determine the effects of CPAP on RVH and right ventricular dysfunction. Also, our sleep clinic population may not reflect the findings in the general community. A larger population of study subjects would be helpful to determine the effects of CPAP on right ventricular structure and function.\nFigure 1\nComparison of right ventricular myocardial performance index (MPI) before and after 6 months CPAP therapy in obstructive sleep apnea patients without hypertension.\nFigure 2\nComparison of right ventricular free wall dimension (RVWFD) before and after 6 months CPAP* therapy in obstructive sleep apnea patients without hypertension.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
68
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nSagittal jaw position in relation to body posture in adult humans – a rasterstereographic study\n\n**Article Abstract:**\n\nBackground\nThe correlations between the sagittal jaw position and the cranio – cervical inclination are described in literature. Only few studies focus on the sagittal jaw position and the body posture using valid and objective orthopaedic examination methods. The aim of this study was to test the hypothesis that patients with malocclusions reveal significant differences in body posture compared to those without (upper thoracic inclination, kyphotic angle, lordotic angle and lower lumbar inclination).\nMethods\nEighty-four healthy adult patients (with a mean age = 25.6 years and ranging from 16.1 to 55.8 years) were examined with informed consent. The orthodontic examination horizontal overjet (distance between upper and lower incisors) was determined by using an orthodontic digital sliding calliper. The subjects were subdivided in respect of the overjet with the following results: 18 revealed a normal overjet (Class I), 38 had an increased overjet (Class II) and 28 had an reversed overjet (Class III). Rasterstereography was used to carry out a three – dimensional back shape analysis. This method is based on photogrammetry. A three-dimensional shape was produced by analysing the distortion of parallel horizontal white light lines projected on the patient's back, followed by mathematical modelling. On the basis of the sagittal profile the upper thoracic inclination, the thoracic angle, the lordotic angle and the pelvic inclination were determined with a reported accuracy of 2.8° and the correlations to the sagittal jaw position were calculated by means of ANOVA, Scheffé and Kruskal-Wallis procedures.\nResults\nBetween the different overjet groups, no statistically significant differences or correlations regarding the analysed back shape parameters could be obtained. However, comparing males and females there were statistically significant differences in view of the parameters 'lordotic angle' and 'pelvic inclination'.\nConclusion\nNo correlations between overjet and variables of the thoracic, lordotic or the pelvic inclination could be observed.\n\n**Article Body:**\n\nBackground\nThe cervical column is in close functional and morphological relationship to structures of the masticatory system [\n1\n,\n2\n]. It is typical that patients revealing a short face morphology show a backward inclination and patients with long face morphology are characterised by a forward inclination of the cervical column [\n3\n,\n4\n]. These findings are recognized by many orthodontic practitioners and the documentation often remains semi – objective and anecdotal. A number of studies used lateral cephalometric radiographs of the head to analyse the posture of the head and neck region (cranio-cervical angles; cervical inclination to horizontal or vertical reference planes) [\n1\n,\n3\n,\n5\n-\n9\n]. Solow et al. analysed 120 Danish male dental students (age 20–30) and revealed low significant correlations between head inclination and craniofacial morphology [\n4\n,\n5\n]. All the cephalometric radiographs in these studies were made in a self-balanced mirror position. Festa et al. [\n6\n] used lateral cephalographs to evaluate the relationship between mandibular length and cervical inclination and could find positive correlations between these parameters in 70 Caucasian women (mean age 27.4 years) with skeletal class II malocclusion. D'Attilio et al. [\n7\n] also revealed a correlation between cervical lordosis and mandibular position, mandibular length, mandibular divergency and overjet. Conversely, some studies dismiss the existence of specific orthopedic findings in patients with different sagittal jaw positions [\n10\n-\n12\n]. Concerning the close functional correlations of the cervical and thoracic spine, the back shape of the thoracic and pelvic region seems to be of interest regarding relationships between sagittal jaw position and body posture [\n12\n]. Michelotti et al. [\n2\n] stated in a review article that there exists some evidence for correlations between jaw position and cervical inclination, however for the lower vertebrae these correlations tend to disappear.\nBased on the results of the cited studies we set up the working hypothesis at the beginning of this prospective study that statistical significant correlations between different sagittal jaw positions and the back shape profile (kyphotic and the lordotic angle) exist. Aim of the presented study was to evaluate statistical significant relationships between the upper thoracic inclination, kyphotic angle, lordotic angle and pelvic inclination in healthy adult patients with different occlusal parameters using rasterstereographic back shape analysis and orthodontic examination.\nMethods\nSubjects\nThe sample of investigated patients comprised 84 healthy adults (54 women, 30 men; mean age = 25.6, range 16.1 – 55.4 years; mean body weight = 69.6; mean height 174.3 cm). 66 subjects were admitted to the Department of Orthodontics, University of Münster for combined orthodontic-orthognathic surgery treatment. The control group was composed of 18 dental students from the University of Münster.\nOf the patients 38 subjects revealed an increased overjet (27 women, mean age = 26.58, SD 6.92; 11 men, mean age = 25.93, SD 6.92), 28 subjects an reversed overjet (13 women, mean age = 23.11, SD 7.23; 15 men, mean age = 24.59, SD 9.55) and the control group of 18 dental students a normal overjet (14 women, mean age = 25.38, SD 6.21; 4 men, mean age = 28.32, SD 5.42).\nNo patients in the study sample showed a history of motor or neurological problems, and there were no subjects who had experienced orthopaedic trauma or had any other diagnosed health problems. The subjects gave their informed consent to the experimental procedure according to the Helsinki criteria and the local Ethics Committee.\nEquipment\na) Orthodontic examination\nOf all subjects alginate impressions of the maxillary and mandibular arch were taken in order to fabricate dental casts oriented in a three – dimensional direction by means of a wax – bite plate. The overjet (sagittal distance between upper and lower incisors) [\n14\n] was measured using an electronic digital sliding calliper (JOCAL, C.E. Johansson, Eskilstuna, Sweden). The subjects were subdivided into three different groups according to the determined overjet: Class I \"normal overjet\" 1 – 3 mm, Class II \"increased overjet\" 4 – 10 mm and Class III \"reversed overjet\" < 1 mm. Patients admitted for combined orthodontic- and orthognathic surgery treatment revealed increased or reversed overjet (Class II and III). Class I was composed of 18 dental students. This classification was carried out according to standard orthodontic classification of sagittal occlusion parameters [\n14\n]. For supplementary differentiation of the overjet the distances were noted in 0.5 mm steps.\nb) Rasterstereographic back shape analysis\nRasterstereography [\n15\n,\n16\n] (Formetric 2, Diers International GmbH, Schlangenbad, Germany) may be classified as a method of 3-D optical surface measurement based on the principles of photogrammetry.\nIt uses a system of horizontal parallel white light lines projected onto the back surface of the patient. Observing this light raster from a direction that is different from the projection reveals shape information from the distortion of the white lines [\n17\n]. The synchronous projection and registration of all light lines in one instant reduces the measurement time of all the surfaces to typically 0.25 sec., therefore this method is the proper choice in back shape measurement. Due to the high accuracy of the measurement of the coordinate data (typically 0.1 mm), rasterstereography allows the application of sophisticated method and the automatic localization of anatomical landmarks on the back surface, like for example, the spinous processus of C7 vertebra (vertebra prominens) or the right and left dimple points in the pelvic region (spinae iliacae posterior superior). On the basis of these landmarks the sagittal back profile is established automatically and a set of shape parameters characterizing the back profile is provided [\n18\n].\nFigure \n1\n shows the outline of a sagittal profile. Along the profile three inflectional points are indicated by open circles – the cervico-thoracic (ICT), the thoraco-lumbar (ITL) and the lumbo-sacral inflection point (ILS). The tangents to the inflectional points span two characteristic angles of the profile – The kyphotic angle (KA) is spanned by the tangent lines in ICT and ITL; in an analogous way the lordotic angle (LA) is spanned by the tangents in ITL and ILS. According to their definition concerning the inflectional tangents, these angles provide maximum angles which are to be measured along the profile. The reproducibility of a single rasterstereographic measurement of the kyphosis and lordosis angle is specified to 2.8° [\n19\n]. Accordingly, the reproducibility of the inclination measurements in respect of the vertical line is expected to 2°.\nThe kyphotic and lordotic angles are relative angles without reference to the vertical line. Two other angles provide orientation data with respect to the vertical line (plumb line); 1) the angle of the upper thoracic inclination (UTI), which is virtually the angle spanned by the vertical and the ICT tangent, 2) the angle of the pelvic inclination (PI), virtually the angle spanned by the vertical and the tangent ILS (Figure \n1\n).\nFor each patient a rasterstereographic recording is taken in a standardized position and posture – the patient stands barefoot in relaxed posture. The positioning with respect to the measurement system was carried out according to the recommendations of the supplier.\nc) Data analysis\nSPSS 12.0 (Lead Tech., Chicago, IL, USA) software was employed to perform the data analysis. The posture parameters involved in the measurements were: UTI, KA, LA and PI. in order to determine the craniofacial morphology, the Angle Classification and the overjet were considered. ANOVA, Scheffé and Kruskal-Wallis procedures were used to test our hypothesis. Level of significance was set at p < 0.05.\nResults\nThe orthodontic examination of the subjects revealed a mean overjet of -2.11 mm (standard deviation 3.72), varying between -10 and 6.0 mm. 18 (21.4%) of the subjects belong, according to their horizontal overjet, to Class I, 38 (45.2) to Class II and 28 (33.3%) to Class III. The measurement data (mean values and SD) for the kyphotic and lordotic angle, the upper thoracic and the pelvic inclination are presented in \nadditional file 1\n. The statistical analysis (ANOVA) of the back profiles in the patients grouped according to their sagittal jaw position does not show any significant differences, neither for the upper thoracic inclination (p > 0.05), the kyphotic angle (p > 0.05), the lordotic angle (p > 0.05) nor for the pelvic inclination (p > 0.05). Likewise, further metric differentiation of the overjet in steps of 0.5 mm showed no significant differences (p > 0.05). No significant correlation between the overjet and the upper thoracic inclination (R2 = 0.022), the kyphotic angle (R2 = 0.011), the lordotic angle (R2 = 0.012) and the pelvic inclination (R2 = 0.02) could be found.\nHowever, the statistical significant differences (Kruskal-Wallis) between the sexes determined in view of the lordotic angle (p < 0.01) and the pelvic inclination (p < 0.01) were revealed. Even with an additional subdivision of the groups (Class I, II and III) confirmed these differences (p < 0.01).\nDiscussion\nThe initial hypothesis of this prospective study stated that patients with different sagittal jaw positions show different back shape curvatures regarding the upper thoracic and the pelvic inclination to a vertical plumb line, the kyphotic angle and the lordotic angle. To test this hypothesis valid information using lateral cephalographs for the analysis of sagittal jaw position and the neutral vertebrae in the radiological Cobb-angle definition might have been used. However, arguments on possible radiation hazards would not justify this attempt. Therefore rasterstereography was established, allowing an examination of the back profile without radiation exposure but providing comparable accuracy and objectivity. It has been shown, that in the sagittal plane exists a reliable correlation between the spinal curvature and the back profile curvature [\n19\n]. The accuracy of the system was tested by Hackenberg et al. [\n20\n,\n21\n] on patients with idiopathic scoliosis after anterior and posterior correction and fusion and showed a good accuracy compared with the anterior-posterior thoracic radiographs. In order to simplify the examination technique Drerup et al. provided four parameters of the sagittal back shape profile to determine back shape in a standardized wise fashion [\n22\n].\nIn literature documentation about significant correlations between the jaw position and the parameters of the body posture often anecdotal and important questions are left unanswered [\n1\n,\n2\n]. The positive correlation between different skeletal facial patterns and the cervical inclination was analysed in a series of studies by Solow et al. and Huggare et al. [\n3\n,\n5\n,\n8\n,\n9\n]. Nobili et al. [\n12\n] used a \"balance platform\" (dynamometric platform for postural oscillation measurement) and revealed positive correlations between the sagittal jaw position and the body posture: the class II malocclusion was correlated to the anterior body posture and the class III malocclusion to the posterior oriented posture. Korbmacher et al. [\n1\n] concluded that studies of correlations between orthodontic and orthopedic findings often lack precise orthopedic measurement methods. Furthermore it was a demand of the same authors to provide prospective clinical trials in close cooperation with orthodontics and orthopaedics. The presented study fulfills this demand because an interdisciplinary team (orthodontists, maxillofacial surgeons, orthopaedic surgeons and biomechanic physicians) analysed the patients in this study. Even more sophisticated methods for orthopedical examination were used.\nThe results of the present study do not show any significant relationships between different sagittal jaw positions and kyphotic or lordotic angle, upper thoracic and pelvic inclination (p > 0.05). These results are in agreement with a critical review of the literature by Michelotti et al. [\n2\n], who postulated that there is some evidence between sagittal jaw position and cervical posture but not to body posture Nevertheless, the pelvic inclination and the lordotic angle show significant differences (p < 0.01) between the examined males and females. This is in agreement with Vialle et al. [\n23\n], Korovessis et al. [\n24\n,\n25\n], Legaye et al. [\n26\n], and Gelb et al. [\n27\n] but contrary to the results of Jackson et al. [\n28\n-\n30\n].\nConclusion\nThe measurement of the body posture by means of rasterstereography is known to provide accurate information on the back shape and the sagittal profile without entailing radiographic strain for the patient. With this system no correlations between the sagittal jaw position and variables of the kyphotic, the lordotic or the pelvic inclination could be found. Further studies are necessary to provide cephalometric measurements of the craniofacial skeleton and to correlate them to the examined parameters used in the present study.\nCompeting interests\nThe author(s) declare, that they have no competing interests.\nAuthors' contributions\nCL carried out the study design and initiated the study, participated in the data collection and drafted the manuscript. GD carried out the orthodontic analysis, datacollection, data processing and the statistical analysis. MS participated in the idea for this study, data collection and rasterstereographic analysis. BD participated in the design of the study and did the programming of the raterstereographic units that were used in this study. Moreover he helped to draft the manuscript. LH participated in its design and coordination and helped to draft the manuscript. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\nSupplementary Material\nAdditional File 1\nDescriptive Statistics and ANOVA results of the Rasterstereographic Back Shape Analysis\n. Descriptive Statistics (mean and SD) of Upper Thoracic Inclination (UTI), Kyphotic Angle (KA), Lordotic Angle (LA) and Pelvic Inclination (LA) for males, females and the total number of patients in Class I (normal overjet), Class II (enlarged overjet) and Class III (reversed overjet); p-values of the ANOVA results (* = statistically significant) among males and females. Missing values: KA (12 measurements) and LA (2 measurements) due to measurement problems.\nClick here for file\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
69
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nRisk factors for traumatic and non-traumatic lower limb pain among preadolescents: a population-based study of Finnish schoolchildren\n\n**Article Abstract:**\n\nBackground\nThe child's lower limb is the most commonly reported musculoskeletal location with pain and also the most commonly injured site in sports. Some potential risk factors have been studied, but the results are inconsistent. We hypothesized that distinction of traumatic from non-traumatic pain would provide a clearer picture of these factors. The aim of this study is to assess factors associated with lower extremity pain and its impact on preadolescents in a population-based cohort.\nMethods\nA structured pain questionnaire was completed by 1756 schoolchildren of third and fifth grades to assess musculoskeletal pain, psychosomatic symptoms, subjective disabilities, school absence and frequency of exercise. In addition, hypermobility and physical fitness were measured.\nResults\nThe knee was the most common site of pain followed by the ankle-foot and thigh. Of the children who reported pain in their lower extremity, approximately 70% reported at least one disability and 19 % reported school absence attributed to their pain during the previous three-month period. Children with traumatic pain had a higher subjective disability index than those with non-traumatic pain (P = 0.02). Age less than 11 years, headache, abdominal pain, depressive feelings, day tiredness, and vigorous exercise were more common in children with lower limb pain than those free of it. In the stratified analysis, younger age was related to both traumatic and non-traumatic pain groups. Vigorous exercise was positively associated with traumatic pain, while subjects with non-traumatic pain had more frequent psychosomatic symptoms.\nConclusion\nRisk factors and consequences of traumatic and non-traumatic lower limb pain are not similar. Traumatic lower limb pain is associated with practicing vigorous exercise and high level of physical fitness, while non-traumatic pain is more correlated with psychosomatic symptoms. These differences might be one of the reasons for the discrepancy of previous research conclusions. The two conditions need to be treated as different disorders in future studies.\n\n**Article Body:**\n\nBackground\nPrevious studies about pediatric pain have consistently found that the lower limb is the most commonly reported musculoskeletal location with pain and has been ranked among the leading general pain symptoms in childhood and adolescence [\n1\n-\n3\n]. The lower limb is also the most commonly injured site in sports [\n4\n] and accounts for a substantial percentage of pediatric rheumatology and orthopedic consultations [\n5\n].\nTwo studies have reported consequences and disabilities related to lower limb pain in schoolchildren, both limited to non-traumatic knee pain. Fairbank et al. found that 18% of children aged 13–17 with knee pain had to stop playing during the past year because of their symptoms. In addition, 22% of girls and 40% of boys needed to visit a doctor [\n6\n]. In a Finnish study [\n7\n], 45% of schoolchildren aged 9–15 reported moderate to severe disability attributed to lower limb pain during past three months. Despite these high figures, less attention has been given to determinants of lower limb pain in children compared to other pediatric pain symptoms. This might be due to a belief that lower extremity pain in children is a transient, self-limiting condition [\n8\n]. Further, the substantial burden of other pain symptoms in adults [e.g. lower back pain [\n9\n] and headache [\n10\n]] has directed research interests in understanding the origin of these symptoms in childhood. However, lower limb pain may limit children's activities and lead to adoption of an inactive lifestyle persisting to adulthood [\n11\n]. Hence, more studies are needed to provide further insight into factors that influence the occurrence of this condition in schoolchildren.\nSome potential determinants of lower limb pain have been studied in children and adolescents, but the results are inconsistent. A positive relationship has been reported between frequency of physical exercise and lower limb pain in most studies [\n6\n,\n7\n], but no correlation was observed in a recent follow-up study [\n11\n]. Similarly, conflicting results have been reported for the predictive role of physical fitness [\n12\n,\n13\n] hypermobility/hyperflexibility [\n11\n,\n14\n,\n15\n] and psychosocial factors [\n16\n,\n17\n]. We hypothesized that distinction of traumatic from non-traumatic pain would provide a clearer picture of the risk factors for lower limb pain.\nThe aims of this study were (a) to determine the prevalence of pain symptoms in different lower limb parts in a population-based sample of preadolescents, (b) to examine the associations of traumatic and non-traumatic lower limb pain with age, sex, hypermobility, frequency of exercise, physical fitness, and psychosomatic factors, (c) to assess school absence and subjective disabilities attributed to traumatic and non-traumatic lower limb pain.\nMethods\nThe initial study took place in Lahti, a town of 94 827 (1995) inhabitants in southern Finland. All the 21 primary schools in town were asked to participate in the survey. Two schools refused and 19 took part in the study. The Steiner school, the hospital school, and the schools for hearing and physically disabled and the mentally handicapped were excluded because some of the methods used in this study were not suitable for their pupils. All pupils from the third and fifth grades participated in the survey except those who were not at school on the day of the study [\n18\n,\n19\n].\nThe study was approved by the Ethics Committee of the Health Care Center of the City of Lahti. The parents were informed about the study by letters in advance. Both the children and their parents had the possibility to refuse enrollment in the survey. The final sample consisted of 1756 preadolescents, of whom 867 were third-grade (mean age 9.8 [SD = 0.4] years) and 889 were fifth-grade (mean age 11.8 [SD = 0.4] years) school children. This population represents 82.9% of all schoolchildren in these grades attending normal or special schools in Lahti (Figure \n1\n). In March 1995, these children completed a pain questionnaire, during a class lesson, to assess lower limb pain during the preceding 3 months and were tested for hypermobility and cardio-respiratory fitness.\nInstruments\n1- Pain questionnaire\nA structured pain questionnaire was designed to assess lower limb pain, as well as other musculoskeletal pain symptoms (neck, upper limb, chest, upper back, lower back, buttock) during the previous three months. Musculoskeletal pain symptoms were classified according to pain frequency (seldom or never, once a month, once a week, more than once a week, almost daily). The 5-level frequency classification was adopted from the questionnaire used in the nationwide survey on health and health-related behaviors in schoolchildren by the WHO [\n20\n]. The body area concerned was indicated on a figure placed next to the question to help the child recognize the named area. Furthermore, the children were asked to mark the exact site of pain in the lower extremity (foot, ankle, leg, knee, thigh and hip). If the child had pain due to a direct trauma (e.g. injured when exercising, fallen down, stumbled), they were asked to indicate the traumatized area on the pain drawing with a different color [\n18\n,\n19\n]. The lower extremity area shown in the picture included the area from the level of the hip joint to the toes anteriorly and the area from the gluteal folds to the toes posteriorly.\nPsychosomatic symptoms (headache, abdominal pain, depressive mood, day tiredness, difficulties in falling asleep, waking up during nights) were asked about with the same frequency categorization as for musculoskeletal pain. Presence of each symptom was defined as occurrence at least once a week. Disability due to pain was assessed by the following questions (A) \ndo you have difficulties in falling asleep because of your pain or does your pain disturb your sleep \n(B) \ndo you have difficulties while sitting during lessons \n(C) \ndo you feel pain if you walk more than one kilometer \n(D) \ndo you feel pain during physical exercise class \n(E) \ndoes your pain interfere with your hobbies\n. A subjective disability index (1 point for each, maximum 5) was calculated from answers to these questions. Absence from school during the preceding 3 months due to pain or aches was asked about through the questionnaire. In addition, the children were asked about the frequency with which they undertook vigorous exercise, for at least half an hour, during the preceding 3 months and were categorized into 3 groups (0–2, 3–4, and 5–7 times a week).\nDuring the questionnaire development, two versions of the questionnaire were tested and the test-retest reliability of the final version in detecting those who have pains at least once a week was excellent (kappa 0.9) [\n18\n]. The concurrent validity of the pain questionnaire was examined by comparing it with interviews of 31 third- and 25 fifth-grade children on the same day of the survey. The agreement between pain questionnaire and interview with similar pain questions was 86% (95% confidence interval [95% CI] 74 to 94%) and kappa was 0.67 [\n19\n].\n2- Hypermobility test\nHypermobility test was conducted using Beighton's method (score 0 to 9) [\n21\n]. A nurse, specially trained for the tests, examined the children during school lessons. No stretching was allowed before the test. Intra-and inter-observer reliability were evaluated earlier with kappa coefficients of 0.75 and 0.78 respectively [\n18\n]. Out of 1756 children included in the analysis, 1637 (93.2%) were examined for hypermobility. School absence on the examination date was the reason for non-participation. We used Beighton score of six as the cutoff point for hypermobility on the basis of the distribution of the results. Children were also categorized into two groups (with and without regional knee hypermobility) in part of the analysis.\n3- Shuttle run test\nThe 20-meter shuttle run test [\n22\n] is an indoor test of maximal performance. It provides a valid and reliable index of cardio-respiratory endurance or maximal oxygen uptake (VO\n2 \nmax) [\n23\n]. It was carried out for all the study subjects excluding children with acute musculoskeletal injury, acute respiratory infection, or other diseases inhibiting maximal physical strain. Children from schools that did not have room for the 20-meter distance required for the test, were also excluded. Out of 1756 children, who were included in the analysis, 1204 (68.6%) underwent the test. Based on the distribution of the results (median 51.1 ml/kg/min), children were categorized into 3 groups according to their VO\n2 \nmax measurements: low (below the 25\nth \npercentile), average (from the 25\nth \ntill the 75\nth \npercentiles) and high (above the 75\nth \npercentile).\nCase definition of lower limb pain\nThose who reported pain in their lower extremity, occurring at least once a week during past three months fulfilled our case definition of lower limb pain. Furthermore, children with lower limb pain were divided into those with traumatic and non-traumatic pain according to whether or not they have reported a direct trauma. The same case definition was used for other musculoskeletal pain symptoms. Descriptive information about these symptoms has been reported earlier [\n19\n].\nStatistical methods\nAssessment of subjective disabilities and school absence due to lower limb pain was limited to those who had the lower limb as the only musculoskeletal pain area (regional lower limb group) to eliminate possible effect of other musculoskeletal pain symptoms. Differences between the two lower limb pain groups (traumatic and non-traumatic) related to their reported subjective pain disability index and school absence were assessed by t-test and Fisher's exact tests, respectively.\nLogistic regression analysis was used to identify factors associated with lower limb pain in preadolescents. The logistic models included the following independent variables: age (below/above 11 years), psychosomatic symptoms (present/absent), frequency of exercise (0–2/3–4/5–7 times a week), Beighton score of hypermobility (below/above six), and VO\n2 \nmax (low/normal/high). For analytic purposes, a new variable was created categorizing all children included in our survey into 2 groups according to the occurrence of musculoskeletal pain in locations other than the lower limb. The logistic models were first fitted with each of the independent variables separately, together with the \"Other musculoskeletal pain symptoms\" variable. A multivariate analysis was then conducted using a stepwise backward elimination method. All independent variables were initially included in the regression equation together with the \"Other musculoskeletal pain symptoms\" variable. Elimination of variables, at each step, was based on the likelihood ratio test at 10% level of significance. Interactions between variables were tested all through the analyses. All statistical analyses were performed using SPSS (for Windows), version 10.0.\nResults\nPrevalence of lower limb pain according to location\nOut of 216 children who had non-traumatic lower limb pain, 95% (N = 205) reported that their pain was diffuse and not limited to one specific lower limb site. On the other hand, only 21% (N = 22) of the traumatic group reported that they had pain affecting more than one lower limb site. The knee was the most commonly reported site for both traumatic and non-traumatic lower limb pain. The thigh was a commonly reported site for non-traumatic pain, while the ankle-foot was a common site for traumatic pain (Table \n1\n). Traumatic injuries were reported by 34% (N = 54) of children with regional lower limb pain, and by 32% (N = 52) of children with combined lower limb pain.\nPain interfering with daily activities\nOut of 158 children who had regional lower limb pain, 70% (N = 110) reported at least one disability attributed their pain, 40% (N = 63) had pain that disturbs walking > 1 km, 30% (N = 47) had pain that disturbs their sleep. In addition, 27% (N = 42) reported that their pain interferes with their physical exercise classes, 18% (N = 28) had their pain interfering with hobbies and 4% (N = 7) reported that their pain interferes with their sitting comfort. School absence due to pain, for one or more days during the preceding 3 months, was reported by 19% (N = 30) of these children who reported frequent pains in their lower extremity.\nFactors associated with lower limb pain\nIn the univariate analysis, children aged 9–10 years had approximately 25% higher risk of lower limb pain compared with those aged 11–13. All psychosomatic symptoms (headache, abdominal pain, and depressive feelings, difficulty falling asleep, day tiredness and waking up during nights) were positively associated with occurrence of lower limb pain. Children who exercised vigorously (5–7 times a week) had approximately twice the risk of lower limb pain compared to those who exercised less than 3 times a week. In the multivariate analysis, age, headache, abdominal pain, depressive feelings, day tiredness, and vigorous exercise remained statistically significant (Table \n2\n).\nSubjective disabilities and school absence related to traumatic and non-traumatic lower limb pain\nChildren with regional traumatic lower limb pain had a significantly higher subjective disability index than children with regional non-traumatic lower limb pain (t = 2.36, P = 0.02). Traumatic pain interfered with daily activities more than non-traumatic pain, with the exception of sleeping. There was no statistically significant difference in school absence between the children with traumatic and non-traumatic pain (Table \n3\n).\nRisk factors for traumatic and non-traumatic lower limb pain\nAll psychosomatic factors were positively associated with lower limb pain in both groups. However, in the multivariate analysis, day tiredness was the only psychosomatic symptom associated with traumatic pain, while headache, depressive feelings and day tiredness were positively related to non-traumatic pain (Table \n4\n). In the univariate analysis, there was a significant gender difference in traumatic pain experience, with males reporting more injury-induced pain in their lower extremity than girls. No relationship was found between physical activity/physical fitness and occurrence of non-traumatic pain in the lower extremity. On the other hand, both Vigorous exercise and high physical fitness were significantly and independently associated with traumatic lower limb pain. Furthermore, a significant synergistic interaction was found between these two factors (p = 0.015). The predictive effect of high physical fitness on occurrence of traumatic lower limb pain was stronger as the amount of exercise performed increased. The odds ratios of high physical fitness on occurrence of traumatic pain increased steadily from 2.13 (95% CI 1.12–4.42) in children who practiced infrequent exercise, to 3.35 (95% CI 1.22–5.88) in children who practiced moderate exercise, to 7.54 (95% CI 0.86–10.72) in children who practiced vigorous exercise. Similar to the crude results, the age of the preadolescents was inversely associated with both traumatic and non-traumatic lower limb pain. Hypermobility was not associated with both traumatic and non-traumatic pain and no statistically significant interaction were found between physical exercise and hypermobility on occurrence of both conditions. However, children with regional knee hypermobility were less likely to have traumatic pain compared to children with normal joint laxity (OR = 0.59 [95% CI 1.22–5.88]).\nDiscussion\nIn our study, the knee was the most common site of pain in the lower limb, followed by the ankle and foot. This is in accordance with previous studies in children and adolescents [\n24\n,\n25\n]. The knee was also the most common location of pain due to a direct trauma, as has been reported previously [\n26\n]. About half the children who had lower limb pain reported pain also in other musculoskeletal location. This figure is substantially higher than the 19% prevalence of musculoskeletal pain in those without lower limb pain. This finding is consistent with previous surveys which have demonstrated frequent co-occurrence of different musculoskeletal complaints [\n12\n,\n27\n].\nOn the basis of our cross-sectional study, lower limb pain – both traumatic and non-traumatic- was more common among the younger age group (less than 11 years old) than among the older age group (from 11 to 13 years old). This contradicts the previous study by Vähäsarja, showing a clear increase in prevalence of knee pain from 4% in the 9–10 olds to 19% in the 14–15 olds schoolchildren [\n7\n]. However, this might be due to the different age distribution of our study population; which is composed of two age groups (9–10 and 11–12 years); and the wide case definition of lower limb pain used in our study (including pain in all lower limb area). More frequent non-traumatic lower limb pain among younger children (aged 9–10 years) is in accordance with the literature suggesting that \"growing pains\" mainly affects children aged 4 to 10 with occasional relapses in teenage years [\n8\n]. In this study, traumatic lower limb pain was more common among boys. Likewise, Smedbraten and co-workers found knee to be the only site in which pain was more common among boys [\n24\n].\nDifficulty in walking long distances was the most common disability, reported by approximately 40% of children with lower limb pain. This is much higher than the 11% reported in a previous study about knee pain in schoolchildren [\n7\n]. However, the minimum distance was not specified in the later study. Disturbances of sleeping was the only disability associated to some extent more closely with non-traumatic than traumatic pain. This suggests that \"growing pains\" constituted a substantial proportion of non-traumatic pain.\nPracticing vigorous exercise was associated with occurrence of non-specific lower limb pain. As mentioned earlier, conflicting results have also been reported about the role of physical exercise in occurrence of lower limb pain in schoolchildren [\n6\n,\n7\n,\n11\n]. we hypothesized that psychosomatic symptoms are associated only with non-traumatic lower limb pain, and that physical exercise is only related to traumatic lower limb pain, and this might be the reason for this conflicting results. As we expected, our stratified analysis showed that practicing vigorous exercise was associated with pain in the traumatic group but not in the non-traumatic group. After adjusting for physical activity and all other baseline predictors in our multivariate analysis, day tiredness was the only significant psychosomatic factor in the traumatic group. Day tiredness might have been a consequence of pain experience rather than had psychological origin. We have used the term \"psychosomatic\" to refer to symptoms that are chiefly considered to be expressions of psychological stress rather than manifestations of organic disorders based on previous research in children [\n28\n,\n29\n]. The same term was used in our previous reports [\n19\n,\n30\n] as well as by other researchers [\n31\n,\n32\n]. However it might be argued that some of these symptoms were manifestations of lower limb pain rather than related to emotional problems in childhood.\nHigh level of physical fitness was independently associated with the occurrence of traumatic lower limb pain and practicing vigorous exercise was a significant effect modifier for this relationship. These results seem to contradict previous findings by Knapik et al. who reported that musculoskeletal injuries in young soldiers were associated with lower aerobic fitness [\n13\n]. However, several factors may prevent a valid comparison between our results and those of the latter study. Firstly, the age groups and the study settings in these studies were different; secondly, Knapik et al. were studying the relationship between physical fitness and all kinds of musculoskeletal injuries, including overuse injuries. Overtraining injury is not caused by a direct trauma but is related to repetitive loading on musculoskeletal structures without sufficient recovery. It must be noted that in the current study we have not collected information about overuse injuries, as we assumed that children would find it hard to understand the exact meaning of such type of injury. We have categorized our children into two groups according to whether or not they have directly traumatized their lower limb area with pain. Children who might have had overuse injuries were not included in the traumatic group, but rather in the non-traumatic group, as they have not indicated a direct trauma to the lower limb in the pain questionnaire. It might be possible that the predictive roles of physical fitness on the development of overuse and traumatic musculoskeletal injuries are different. However, this possible explanation cannot be examined with our data, and hence further research is needed to find out if such a difference really exists.\nOccurrence of traumatic and non-traumatic lower limb pain did not differ between children with and without hypermobility. This is similar to our previous finding [\n19\n], regarding occurrence of musculoskeletal pain in general. However, children with regional knee hypermobility reported significantly less traumatic pain than children with normal joint laxity. This inverse association was not explained by differences in physical exercise frequency between these two groups. These results go well with the previous observations that hypermobility is not associated with increased athletic injuries [\n33\n] and that stretching plays an important role in decreasing the rate of injury [\n34\n]. These studies as well as ours, challenge the recommendation that children with hypermobility should avoid strenuous physical activities.\nThe most important strengths of this study are its population based setting and classifying lower limb pain according to location and association with injuries. In addition, pain interference with the children's daily activities was assessed. Yet, we did not have information about anatomic-structural or psychosocial factors, which might have been linked to occurrence of lower extremity pain in children.\nConclusion\nOur study indicates that risk factors and consequences of non-traumatic and traumatic lower limb pain are not similar. Non-traumatic pain is correlated with headache, recurrent abdominal pain and sleeping problems, while the traumatic pain is associated with practicing vigorous exercise and high level of physical fitness. This dissimilarity is consistent with our previous finding that traumatic lower extremity pain in preadolescents has a more favorable long-term natural course compared to non-traumatic pain [\n35\n]. Including or excluding traumatic injuries in the case definition of lower limb pain in research work investigating its determinants in children will significantly affect the results, and this might be the reason for the discrepancy of previous research conclusions. These two conditions need to be treated as different disorders in future studies.\nDeclaration of interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nDr. Ashraf El Metwally had primary responsibility for data analysis, and writing the manuscript. Dr. Jouko Salminen supervised the design of the study and contributed to the writing of the manuscript. Dr. Anssi Auvinen participated in the analytic framework for the study, and contributed to the writing of the manuscript. Hannu Kautiainen participated in the analytic framework for the study. Dr. Marja Mikkelsson developed the protocol and questionnaire, designed the study, supervised and participated in data collection, and contributed to the writing of the manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
70
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nOverweight and obesity in relation to cardiovascular disease risk factors among medical students in Crete, Greece\n\n**Article Abstract:**\n\nBackground\nRecent data indicate increasing rates of adult obesity and mortality from cardiovascular disease (CVD) in Greece. No data, however, are available on prevalence of overweight and obesity in relation to CVD risk factors among young adults in Greece.\nMethods\nA total of 989 third-year medical students (527 men, 462 women), aged 22 ± 2 years, were recruited from the University of Crete during the period 1989–2001. Anthropometric measures and blood chemistries were obtained. The relationships between obesity indices (body mass index [BMI], waist circumference [WC], waist-to-hip ratio [WHpR], waist-to-height ratio [WHtR]) and CVD risk factor variables (blood pressure, glucose, serum lipoproteins) were investigated.\nResults\nApproximately 40% of men and 23% of women had BMI ≥ 25.0 kg/m\n2\n. Central obesity was found in 33.4% (average percentage corresponding to WC ≥ 90 cm, WHpR ≥ 0.9 and WHtR ≥ 50.0) of male and 21.7% (using WC ≥ 80 cm, WHpR ≥ 0.8, WHtR ≥ 50.0) of female students. Subjects above the obesity indices cut-offs had significantly higher values of CVD risk factor variables. BMI was the strongest predictor of hypertension. WHtR in men and WC in women were the most important indicators of dyslipidaemia.\nConclusion\nA substantial proportion of Greek medical students were overweight or obese, obesity status being related to the presence of hypertension and dyslipidaemia. Simple anthropometric indices can be used to identify these CVD risk factors. Our results underscore the need to implement health promotion programmes and perform large-scale epidemiological studies within the general Greek young adult population.\n\n**Article Body:**\n\nBackground\nOverweight and obesity are recognized as an \"escalating epidemic\" affecting both developed and developing countries [\n1\n,\n2\n]. Obesity and its associated morbidities are leading causes of cardiovascular disease (CVD), type-2 diabetes, some types of cancer and several other health problems [\n3\n]. Recent data show that mortality from CVD is increasing in Greece, in contrast to trends observed in northern Europe and the USA [\n4\n,\n5\n]. Age-adjusted ischaemic heart disease mortality in men aged 45–74 years almost doubled from 1956 to 1978 and the prevalence of myocardial infarction per 100.000 adults aged 30–69 years increased from 230 in 1981 to 349 in 1988 [\n5\n]. This unfavourable trend is partially attributed to increased prevalence of obesity as indicated by existing literature [\n6\n,\n7\n]. Adult obesity levels in Greece are the second highest in Europe, exceeding 25% for men and 35% for women [\n8\n].\nThe childhood roots of adult obesity and also CVD are widely recognized and associated with calls for health promotion targeted at youth [\n9\n-\n11\n]. Recent studies have indicated the presence of increasing trends in overweight and obesity among children and adolescents in Greece [\n6\n,\n12\n], but there is complete lack of data regarding young adult groups. Moreover, although there are many studies on the health status of medical students, a target group of particular interest as they are future physicians, these have mostly tracked the use of alcohol and tobacco [\n13\n,\n14\n]. The occurrence of obesity and other risk factors for coronary heart disease has not been extensively examined, particularly among European medical students.\nThe aim of this descriptive study was to assess the prevalence of overweight, obesity and other CVD risk factors, namely high blood pressure and dyslipidaemia, among University of Crete medical students. We investigated the relationships of four different obesity indices (body mass index, waist circumference, waist-to-hip ratio, waist-to-height ratio) with blood pressure, glucose, serum lipids and lipoproteins. Finally, we examined which of these indices could better predict the presence of such risk factors in this young adult group.\nMethods\nSubjects\nThe survey was carried out within the training framework of the Clinical Nutrition class, which is presented in the third year of the medical course in the University of Crete School of Medicine [\n15\n]. Between the years 1989–2001, all students registered in the third year of their studies (21–49 men and 17–47 women per year) were invited to participate in the study and sign appropriate consent forms. The average annual participation rate was 98.2% (range 95.3–100%). Eighteen students were excluded from the analyses because of missing data on potential confounding variables. The final sample included 989 students (527 males, 462 females), aged 20–40 years (mean age 22, standard deviation [SD] 2) with complete measurements for all variables other than glucose. Blood glucose was available for a sub-sample of 727 students (412 men, 346 women).\nQuestionnaires\nPurpose designed questionnaires were administered to ascertain biographical data, lifestyle behaviours on topics including cigarette smoking and alcohol consumption, and medical and family history of cardiovascular diseases. In order to validate the results multiple crosschecked questions on the same topic were addressed to the participants. Smokers were classified as those who stated smoking more than one cigarette per day for at least three consecutive months. Ex-smokers were defined as those who had not been smoking for the last three consecutive months, and non-smokers as those who did not fall in any of the two previous groups. The questionnaires remained unchanged over the years.\nPhysical characteristics\nA digital scale (Seca) was used to measure body weight (BW) with an accuracy of ± 100 g. Subjects were weighed without shoes, in their underwear. Standing body height (BH) was measured without shoes to the nearest 0.5 cm with the use of a commercial stadiometer with the shoulders in relaxed position and arms hanging freely. Body mass index (BMI) was calculated as BH in kilograms (kg) divided by the square of the BH in meters (m\n2\n). Waist circumference (WC) was measured in the middle between 12\nth \nrib and iliac crest at the level of umbilicus and the hips circumference (HC) at the fullest point around the buttocks. WC (cm) was divided by HC (cm) and BH (m) in order to calculate the waist-to-hip (WHpR) and waist-to-height (WHtR) ratio respectively. Means of replicates were used in all anthropometric measurements, which were carried out by the same faculty members over the years.\nIn order to measure blood pressure, subjects were seated in a chair with their back supported and their arms bared and supported at heart level. Measurement was performed with the student not having ingested coffee or smoked for 30 minutes and after at least five minutes of rest. The appropriate cuff size was used to ensure an accurate measurement. Measurements were taken using a mercury sphygmomanometer applied on the right arm of the participants. First and fifth Korotkoff sounds were recorded for systolic and diastolic readings respectively. Two readings separated by two minutes were averaged. If they differed by more than 5 mmHg, one additional reading was obtained and then averaged.\nBiochemical analyses\nEarly morning ,venous blood samples were drawn for biochemical screening tests, following a 12-hour overnight fast. The blood samples were transferred to the Nutritional Research Laboratory of the University of Crete in tanks containing ice packs so as to maintain a temperature of 3–4°C. Blood was centrifuged and 1.5 mL aliquots were pipetted into plastic Eppendorf tubes. One aliquot was used for blood analysis of triglycerides (TG), total cholesterol (TC) and high-density lipoprotein cholesterol (HDL-C) measurements on the same day of collection, while the other was stored (at -80°C). TG was determined using Fossati's method [\n16\n]. TC was determined by Allain's method [\n17\n]. HDL-C was measured by the heparin-manganese precipitation method [\n18\n] while low-density lipoprotein cholesterol (LDL-C) was calculated as follows: LDL-C = TC - (HDL-C + TG/5) [\n19\n]. The ratio of TC to HDL-C (TC:HDL-C) was calculated. Coefficients of variation for measurement error during 1989–2001 ranged between 4.3 and 12.4% for TC and HDL-C. Blood glucose (BG) levels were measured by the exokinase method, using an auto-analyser AU-640 (Olympus Instruments).\nAssignment of CVD risk factors\nBased on the International Obesity Task Force [\n20\n], convened by the World Health Organization, a subject with BMI of 25.0 to 29.9 kg/m\n2 \nwas defined as overweight; a BMI ≥ 30.0 kg/m\n2 \nwas defined as obese. The WC, WHpR and WHtR measurements were used to determine the extent of central adiposity. For WC, cut-off points of ≥ 90 cm in men and ≥ 80 cm in women were used [\n21\n]. A WHpR ≥ 0.9 in men and ≥ 0.8 in women was considered to represent central obesity [\n21\n], and WHtR values of ≥ 50.0 in either sex were adopted as cut-offs [\n22\n].\nParticipants were classified as having elevated blood pressure if they reported taking anti-hypertensive medication or had a systolic blood pressure (SBP) ≥ 140 mmHg or diastolic blood pressure (DBP) ≥ 90 mmHg. High-normal blood pressure was defined as blood pressure ≥ 130/85 – < 140/90 mmHg. The cut points correspond to the Sixth Joint National Committee on High Blood Pressure criteria for high blood pressure [\n23\n].\nDyslipidaemia was defined as TC ≥ 5.2 mmol/l (200 mg/dl), TG ≥ 1.5 mmol/l (150 mg/dl), LDL-C ≥ 3.4 mmol/l (130 mg/dl), and HDL-C < 0.9 mmol/l (40 mg/dl). These cut-offs correspond to the Adult Panel Treatment III criteria for borderline high TC, TG, LDL-C and low HDL-C levels [\n24\n]. A TC:HDL-C ≥ 4 was also considered a adverse serum lipid profile [\n25\n].\nImpaired fasting glucose was defined as BG ≥ 6.1 mmol/l (110 mg/dl) based on the Report of the Expert Committee on the Diagnosis and Classification of Diabetes Mellitus [\n26\n].\nStatistical analysis\nStatistical analyses were performed using the Statistical Package for Social Sciences (version 8.0, SPSS, Inc) software. Analysis of covariance (ANCOVA) was used to examine for differences in the lipidaemic profiles of men and women, adjusting for the year of examination. The chi-square (χ\n2\n) test (or Fisher's exact test for 2 × 2 data tables) was used for categorical data. Although the set of data was collected over a 13-year-period, we did not examine for time trends since the cross-sectional design of the survey and the small number of participants per year would preclude any definite conclusions. However, in order to account for any possible time effects, the year of examination was included in all statistical analyses as an independent variable.\nThe relationship between obesity and other CVD risk factor variables was first examined with univariate analyses using obesity indices as categorical variables. Average differences in blood pressure, glucose, serum lipids and lipoproteins were calculated using ANCOVA with covariates age, sex, tobacco use and year of examination. Stepwise linear regression techniques were applied to assess the extent to which CVD risk factors depend on the obesity indices considered using the same independent variables. Logistic regression models were applied to calculate odds ratios (OR) for the presence of CVD risk factors after adjustment for age, tobacco use, and year of examination. A level of p < 0.05 was used to indicate statistical significance in all analyses.\nResults\nPrevalence of overweight, obesity, and other CVD risk factors\nThe fasting blood glucose levels and lipidaemic profiles of University of Crete medical students are given in Table \n1\n. Men had significantly higher values of BG (p < 0.001), TG (p < 0.001), LDL-C (p = 0.010) and TC:HDL-C (p < 0.001), and lower values of HDL-C (p < 0.001) than their female counterparts. Table \n2\n presents the distribution of obesity indices, blood pressure, blood glucose, serum lipids and lipoproteins among medical students. The prevalence of overweight or obesity (BMI ≥ 25.0 kg/m\n2\n) was 39.5% in male and 23.3% in female students. Central obesity levels were significantly higher in men than women, using the WC (32.6% vs. 21.9%, p < 0.001) or WHtR (37.6% vs. 12.8%, p < 0.001) cut-offs. Forty eight percent of men and 36.1% of women (p < 0.001, difference between the genders) had blood pressure levels ≥ 130/85 mmHg. A significantly higher percentage of males than females had high TG, LDL-C, TC:HDL-C, or low HDL-C (p < 0.001 for all analyses). Only 10 students (8 men, 2 women) had BG levels ≥ 6.1 mmol/l (110 mg/dl).\nTable 1\nBlood glucose and lipidaemic profiles of University of Crete medical students\nMen\n1\nWomen\n2\nMean ± S.D.\n3\np-value\n4\nBG (mmol/l)\n4.73 ± 0.59\n4.59 ± 0.56\n<0.001\nTC (mmol/l)\n4.65 ± 0.91\n4.63 ± 0.87\nNS\n5\nTG (mmol/l)\n0.83 ± 0.43\n0.66 ± 0.28\n<0.001\nHDL-C (mmol/l)\n1.19 ± 0.30\n1.44 ± 0.35\n<0.001\nLDL-C (mmol/l)\n3.01 ± 0.86\n2.86 ± 0.82\n0.010\nTC:HDL-C\n4.12 ± 1.30\n3.40 ± 1.02\n<0.001\n1 \nN = 527 except for BG analysis where N = 412. \n2 \nN = 462 except for BG analysis where N = 346. \n3 \nStandard deviation. \n4 \nANCOVA (adjusting for the year of examination) for differences between the two genders. \n5 \nNot significant.\nTable 2\nDistribution of obesity indices, blood pressure, glucose, and lipoproteins among University of Crete medical students\nMen\nWomen\nN\n%\nN\n%\np-value\n1\nBMI \n(kg/m\n2\n)\n < 20.0\n30\n5.7\n83\n18.0\n<0.001\n 20.1–24.9\n289\n54.8\n271\n58.7\n 25.0–29.9\n181\n34.4\n92\n19.9\n ≥ 30.0\n27\n5.1\n16\n3.4\nWC \n(cm)\n < 90 (♂) – < 80 (♀)\n355\n67.4\n361\n78.1\n<0.001\n ≥ 90 (♂) – ≥ 80 (♀)\n172\n32.6\n101\n21.9\nWHpR \n(cm/cm)\n < 0.9 (♂) – < 0.8 (♀)\n369\n70.0\n321\n69.5\nNS\n2\n ≥ 0.9 (♂) – ≥ 0.8 (♀)\n158\n30.0\n141\n30.5\nWHtR \n(cm/m)\n < 50.0\n329\n62.4\n403\n87.2\n<0.001\n ≥ 50.0\n198\n37.6\n59\n12.8\nBlood pressure \n(mmHg)\n < 130/85\n272\n51.6\n295\n63.9\n<0.001\n ≥ 130/85 – < 140/90\n185\n35.1\n136\n29.4\n ≥ 140/90\n70\n13.3\n31\n6.7\nBG \n(mmol/l)\n < 6.1\n404\n98.1\n344\n99.4\nNS\n ≥ 6.1\n8\n1.9\n2\n0.6\nTC \n(mmol/l)\n < 5.2\n390\n74.0\n352\n76.2\nNS\n 5.2–6.1\n109\n20.6\n90\n19.5\n ≥ 6.2\n28\n5.4\n20\n4.3\nTG \n(mmol/l)\n < 1.5\n482\n91.4\n453\n98.0\n<0.001\n ≥ 1.5\n45\n8.6\n9\n2.0\nHDL-C \n(mmol/l)\n < 0.9\n76\n14.4\n21\n4.6\n<0.001\n ≥ 0.9\n451\n85.6\n441\n95.4\nLDL-C \n(mmol/l)\n < 3.4\n365\n69.2\n352\n76.2\nNS\n 3.4–4.0\n111\n21.1\n79\n17.1\n ≥ 4.1\n52\n9.7\n31\n6.7\nTC:HDL-C\n < 4\n298\n56.5\n370\n80.1\n<0.001\n ≥ 4\n229\n43.5\n92\n19.9\n1 \nChi-square test (Fisher's exact test where appropriate) for differences between the genders.\n2 \nNot significant.\nRelationships between obesity indices and other CVD risk factors\nThe relationships between blood pressure, glucose, serum lipids and lipoproteins, and obesity indices treated as categorical data are presented in Table \n3\n. Across the four BMI categories, all CVD risk factor variables except BG demonstrated a significant increase. For WC and WHtR, subjects above the selected cut-off points had significantly higher values of SBP, DBP, TC, TG, LDL-C, TC:HDL-C and lower values of HDL-C. High WHpR values were also related to adverse serum lipid profile.\nTable 3\nRelationship between obesity indices and CVD risk factor variables in University of Crete medical students\nSBP \n(mmHg)\nDBP \n(mmHg)\nBG \n(mmol/l)\nTC \n(mmol/l)\nTG \n(mmol/l)\nHDL-C \n(mmol/l)\nLDL-C \n(mmol/l)\nTC:HDL-C\nObesity index\nN\n1\nMean ± S.E.\n2\nBMI \n(kg/m\n2\n)\n < 20.0\n113\n112 ± 1.2\n75 ± 1.0\n4.50 ± 0.06\n4.56 ± 0.09\n0.70 ± 0.04\n1.36 ± 0.04\n2.83 ± 0.09\n3.56 ± 0.13\n 20.0–24.9\n560\n117 ± 0.5\n76 ± 0.4\n4.63 ± 0.03\n4.57 ± 0.04\n0.71 ± 0.02\n1.30 ± 0.02\n2.87 ± 0.04\n3.66 ± 0.05\n 25.0–29.9\n273\n121 ± 0.8\n79 ± 0.6\n4.67 ± 0.04\n4.74 ± 0.06\n0.80 ± 0.02\n1.24 ± 0.02\n3.08 ± 0.06\n4.07 ± 0.08\n ≥ 30.0\n43\n123 ± 1.9\n82 ± 1.5\n4.77 ± 0.10\n4.89 ± 0.15\n1.06 ± 0.06\n1.25 ± 0.06\n3.05 ± 0.15\n4.17 ± 0.21\np-value\n3\n<0.001\n<0.001\nNS\n4\n<0.001\n<0.001\n0.010\n0.018\n<0.001\nWC \n(cm)\n < 90\n5 \n– 80\n6\n716\n116 ± 0.6\n76 ± 0.4\n4.58 ± 0.03\n4.56 ± 0.04\n0.69 ± 0.02\n1.36 ± 0.02\n2.84 ± 0.04\n3.54 ± 0.05\n ≥ 90 – 80\n273\n120 ± 0.9\n79 ± 0.6\n4.64 ± 0.04\n4.74 ± 0.06\n0.89 ± 0.03\n1.19 ± 0.02\n3.05 ± 0.06\n4.13 ± 0.08\np-value\n7\n<0.001\n<0.001\nNS\n0.011\n<0.001\n<0.001\n0.002\n<0.001\nWHpR \n(cm/cm)\n < 0.9\n5 \n– 0.8\n6\n690\n117 ± 0.6\n77 ± 0.4\n4.59 ± 0.03\n4.58 ± 0.04\n0.69 ± 0.02\n1.34 ± 0.02\n2.88 ± 0.04\n3.61 ± 0.06\n ≥ 0.9 – 0.8\n299\n119 ± 0.9\n78 ± 0.7\n4.68 ± 0.04\n4.76 ± 0.07\n0.88 ± 0.03\n1.21 ± 0.03\n3.09 ± 0.06\n4.21 ± 0.09\np-value\n7\nNS\nNS\nNS\n0.019\n<0.001\n<0.001\n0.003\n<0.001\nWHtR \n(cm/m)\n < 50.0\n732\n117 ± 0.5\n76 ± 0.4\n4.59 ± 0.03\n4.54 ± 0.04\n0.69 ± 0.02\n1.34 ± 0.01\n2.83 ± 0.04\n3.57 ± 0.05\n ≥ 50.0\n257\n129 ± 0.9\n79 ± 0.7\n4.64 ± 0.04\n4.81 ± 0.07\n0.88 ± 0.03\n1.25 ± 0.02\n3.09 ± 0.06\n4.12 ± 0.08\np-value\n3\n0.022\n0.001\nNS\n<0.001\n<0.001\n<0.001\n0.001\n<0.001\n1 \nFor BG the sample sizes are: N = 79, N = 408, N = 210, and N = 30 respectively for the BMI categories; N = 527 and N = 200 for the WC categories; N = 508 and N = 219 for the WHpR categories; N = 532 and N = 195 for the WHtR categories. \n2 \nStandard error of the mean. \n3 \nF-statistic from ANCOVA including age, sex, tobacco use, and the year of examination as covariates. \n4 \nNot significant. \n5 \nMale-specific cut-off value. \n6 \nFemale-specific cut-off value. \n7 \nF-statistic from ANCOVA including age, tobacco use, and the year of examination as coviariates.\nPrediction of CVD risk factors using obesity indices\nThe linear regression analyses showed that BMI was the best obesity index predicting SBP and DBP in male students (Table \n4\n). The percentage of the variance of these two measurements explained was <5%. WC was also a significant, though not powerful, determinant of SBP. WHtR could better predict most of the serum lipoproteins, explaining 6.2% of TC, 10.6% of TG, 4.2% of LDL-C and 7.3% of TC:HDL-C variance. WHpR was a significant determinant of HDL-C. The same analyses within the female sample showed also that BMI was the most important predictor of blood pressure, explaining 11.9% of the SBP and 8.4% of the DBP variance (Table \n5\n). WHtR could better predict LDL-C levels, and WC was the most important determinant of TG, HDL-C and TC:HDL-C, predicting 7.9, 7.6 and 10% of their variance respectively. In both genders, none of the obesity indices could significantly predict BG levels.\nTable 4\nRegression analysis of blood pressure, glucose, and lipoproteins on obesity indices in male students\n1\nDependant variable\n2\nobesity indices\nbeta\nadjusted R\n2\nt-statistic\np-value\nSBP\nBMI\n0.266\n0.048\n3.3\n0.001\nWC\n0.485\n0.025\n3.6\n<0.001\nDBP\nBMI\n0.215\n0.049\n4.5\n<0.001\nBG\n__\n__\n__\n__\n__\nTC\nWHtR\n0.217\n0.062\n4.3\n<0.001\nTG\nWHtR\n0.263\n0.106\n5.5\n<0.001\nLDL-C\nWHtR\n0.180\n0.042\n3.4\n0.001\nHDL-C\nWHpR\n-0.255\n0.045\n-5.1\n<0.001\nTC:HDL-C\nWHtR\n0.244\n0.073\n4.7\n<0.001\n1 \nN = 527 except for BG analysis where N = 412. \n2 \nAll four obesity indices, age, tobacco use and the year of examination were initially included in all regression models.\nTable 5\nRegression analysis of blood pressure, glucose, and lipoproteins on obesity indices in female students\n1\nDependant variable\n2\nobesity indices\nbeta\nadjusted R\n2\nt-statistic\np-value\nSBP\nBMI\n0.346\n0.119\n6.6\n<0.001\nDBP\nBMI\n0.288\n0.084\n5.3\n<0.001\nBG\n__\n__\n__\n__\n__\nTC\n__\n__\n__\n__\n__\nTG\nWC\n0.285\n0.079\n5.5\n<0.001\nLDL-C\nWHtR\n0.161\n0.023\n3.0\n0.003\nHDL-C\nWC\n-0.270\n0.076\n-5.2\n<0.001\nTC:HDL-C\nWC\n0.312\n0.100\n6.1\n<0.001\n1 \nN = 462 except for BG analysis where N = 346. \n2 \nAll four obesity indices, age, tobacco use and the year of examination were initially included in all regression models.\nUsing the odds ratios for the prediction of the presence of CVD risk factors, subjects above the selected cut-offs had higher risk for high blood pressure and dyslipidaemia (Table \n6\n). Men with WHtR ≥ 50 had the highest risk for elevated TC (OR 2.26) and LDL-C (OR 1.83). Those with WHpR ≥ 0.9 had significantly higher risk for TG ≥ 1.5 mmol/l (OR 2.51), HDL-C < 0.9 mmol/l (OR 2.03), and TC:HDL-C ≥ 4 (2.78). Women with WHtR ≥ 50 had the highest odds for high DBP (OR 2.33) and LDL-C (OR 2.60), and TC:HDL-C ≥ 4 (OR 5.30). The risk for low HDL-C was significantly higher in female students with WHpR ≥ 0.8. Nevertheless, the odds ratios among the obesity indices differed only slightly and their 95% confidence intervals overlapped.\nTable 6\nRisk for the presence of hypertension and dyslipidaemia according to the obesity status\nOdds ratios (95% confidence interval)\nMen \n(n = 527)\n1\nBMI ≥ 30 kg/m\n2\nWC ≥ 90 cm\nWHpR ≥ 0.9\nWHtR ≥ 50\nSBP ≥ 130 mmHg\n1.81 (0.64–5.10)\n1.24 (0.69–2.23)\n1.62 (0.87–3.02)\n1.37 (0.77–2.43)\nDBP ≥ 85 mmHg\n2.73 (1.13–6.59)\n2\n1.38 (0.84–2.27)\n1.11 (0.66–1.87)\n1.46 (0.90–2.37)\nTC ≥ 5.2 mmol/l\n2.01 (0.80–5.05)\n1.91 (1.18–3.10)\n3\n1.70 (1.01–2.84)\n2\n2.26 (1.40–3.67)\n4\nTG ≥ 1.5 mmol/l\n2.62 (0.80–8.64)\n1.80 (0.83–3.92)\n2.51 (1.11–5.69)\n2\n1.72 (0.78–3.80)\nLDL-C ≥ 3.4 mmol/l\n1.46 (0.55–6.04)\n1.67 (1.04–2.70)\n2\n1.80 (1.09–2.98)\n2\n1.83 (1.14–2.94)\n2\nHDL-C < 0.9 mmol/l\n2.39 (0.94–6.04)\n1.61 (1.00–2.58)\n2\n2.03 (1.23–3.35)\n3\n1.34 (0.84–2.14)\nTC:HDL-C ≥ 4\n2.36 (0.86–6.47)\n2.16 (1.38–3.39)\n4\n2.78 (1.69–4.57)\n4\n2.09 (1.35–3.26)\n3\nWomen \n(n = 462)\n1\nBMI ≥ 30 kg/m\n2\nWC ≥ 80 cm\nWHpR ≥ 0.8\nWHtR ≥ 50\nSBP ≥ 130 mmHg\n2.98 (0.34–26.12)\n0.87 (0.17–4.33)\n1.16 (0.27–4.98)\n0.71 (0.09–6.00)\nDBP ≥ 85 mmHg\n3.15 (0.89–11.13)\n1.77 (0.92–3.41)\n1.26 (0.65–2.41)\n2.33 (1.09–4.96)\n2\nTC ≥ 5.2 mmol/l\n1.34 (0.35–5.16)\n1.49 (0.83–2.68)\n0.98 (0.56–1.72)\n1.53 (0.75–3.12)\nTG ≥ 1.5 mmol/l\n0.01 (0.00–1.53)\n3.80 (0.51–28.13)\n3.44 (0.57–20.67)\n7.19 (0.95–54.49)\nLDL-C ≥ 3.4 mmol/l\n2.35 (0.66–8.42)\n1.97 (1.12–3.47)\n2\n1.32 (0.77–2.26)\n2.60 (1.33–5.07)\n3\nHDL-C < 0.9 mmol/l\n2.77 (0.54–14.26)\n1.98 (0.91–4.29)\n3.33 (1.63–6.79)\n4\n2.83 (1.19–6.73)\n2\nTC:HDL-C ≥ 4\n3.67 (0.99–13.67)\n4.21 (2.35–7.55)\n4\n3.71 (2.14–6.41)\n4\n5.30 (2.66–10.58)\n4\n1 \nLogistic regression models including age, tobacco use, and the year of examination as independent variables. \n2 \np < 0.05, \n3 \np < 0.01, \n4 \np < 0.001\nDiscussion\nIn our survey, a relatively high proportion of University of Crete medical students were overweight (25 ≤ BMI < 30 kg/m\n2\n) or obese (BMI ≥ 30 kg/m\n2\n) (27.6 and 4.3%, respectively). Although the range of definitions complicates comparisons with other studies of young adults or medical students, these percentages are among the highest reported in literature. A recent study in Slovakia showed that 16% of male but only 2% of female medical students had a BMI > 25.0 kg/m\n2 \n[\n27\n]. In a study of male medical students in the US, nearly one-fifth of the subjects had a BMI > 24.7 kg/m\n2 \nand a further 30% were classified as overweight with BMI 22.8–24.7 kg/m\n2 \n[\n28\n]. Another survey at Louisiana State University during 1987–1992 showed that 37% of males and 9% of females were overweight [\n29\n]. Two percent of men but no women had BMI ≥ 30 kg/m\n2\n. The self-reported prevalence of overweight among New Jersey medical students was 35.8% [\n30\n]. A study conducted among 154 medical students in South Africa reported rates of overweight and obesity that were 8.9% and 2.5% respectively for Indian and 19.7% and 4.6% for black students [\n25\n]. Overweight or obesity among black female medical and nursing students was found to be 30.6% [\n31\n].\nCentral obesity levels among medical students varied widely according to the anthropometric index used – a common problem found in similar surveys, as no consensus about the appropriateness of the different obesity indices or cut-off points has been reached [\n32\n,\n33\n]. We adopted the WC and WHpR cut-offs proposed by Dobbelsteyn \net al \n[\n21\n] for Caucasian populations. With regard to WHtR, no established cut-offs exist to this point and our selection was based on the findings of Ko \net al \nwho provided evidence of WHtR ≥ 50 being the most appropriate cut-off for the risk of presence of CVD risk factors in both sexes [\n22\n]. Despite the differences in the observed obesity rates obtained using the different indices, it can be seen that a considerable proportion of medical students were characterized by central fat distribution, about 33.4% of men (this being the average percentage corresponding to WC ≥ 90 cm, WHpR ≥ 0.9 and WHtR ≥ 50.0) and 21.7% of women (the respective percentage in women using cut-offs of WC ≥ 80 cm, WHpR ≥ 0.8, WHtR ≥ 50.0).\nA striking finding of our study was the high prevalence of major CVD risk factors, notably high blood pressure and adverse lipid profile, among University of Crete medical students. The rates of hypertension and dyslipidaemia reported here appear to be much higher than corresponding results of other surveys involving medical students. A study performed among black and Indian medical students in South Africa disclosed rates of high blood pressure (≥ 140/90 mmHg) of 2.5 and 4.2% respectively [\n25\n]. Hypercholesterolaemia (TC ≥ 5.2 mmo/l) and high LDL-C (≥ 3.9 mmol/l) was present in 19.4 and 16.9% respectively for Indian students, and 7.3 and 8.9% for black students. New Jersey medical students reported high DBP, SBP and TC levels at percentages of 4.2, 3.5 and 21.3% respectively [\n30\n]. A survey conducted among medical students at Louisiana State University between 1988 and 1992 reported rates of high SBP that were 4% for both men and women [\n29\n]. Eleven percent of women and 4% of men had DBP > 90 mmHg. The prevalence of high TC during 1991–92 was 18% for men and 31% for women [\n29\n]. Another study among University of California – San Diego medical students during 1986–1989 reported that 6.6% of them had LDL-C ≥ 150 mg/dL (3.9 mmol/l), 20% had TC > 200 mg/dL (5.2 mmol/l) and only 8.7% had high SBP or DBP [\n34\n]. A large cross-sectional survey among first-year medical students in the UK between 1948 and 1968 reported rates of elevated blood pressure that were somewhat higher than those in our study. The authors found that 29.9% of the males had high-normal blood pressure (≥ 130/85 and < 140/90 mmHg) and another 32.0% were hypertensive. The respective percentages for females were 21.8 and 16.9% [\n35\n].\nAssessing the risk for the presence of major CVD risk factors in young adults is of particular importance, since it would allow us to promptly identify persons at high risk for development of clinical CVD later in life. In this context, obesity indices such as BMI, WC, WHpR and WHtR are all considered useful non-invasive anthropometric measurements to provide information on cardiovascular risks. The results of the univariate analysis showed that all four indices were related to higher levels of CVD risk factor variables except for glucose, where no significant associations were observed. One likely explanation for the glucose – obesity index relationships not reaching the 5% level of statistical significance is that our subjects were young adults aged 22 ± 2 years with relatively low BG levels (median 4.6 mmol/l [84 mg/dl] with only 10 subjects having BG ≥ 6.1 mmol/l), compared to the ranges found in older adults [\n36\n,\n37\n]. Another explanation is that as the glucose measurements were available only for a sub-sample of the students. Although the sub-sample with BG measurements was random, any statistical inferences have the inherent limitations of analyses involving sub-samples. Nevertheless, and with regard to other CVD risk factor variables, our findings are in agreement with several studies performed on large cross-sectional samples [\n21\n,\n38\n] but also young adult groups [\n39\n,\n40\n]. There is lack of consistency, however, in the selection of the most useful anthropometric indicators for prediction of CVD risk factors [\n32\n], particularly for young adult populations.\nIn our sample of medical students, aged 20–40 years, both linear and logistic regression analyses disclosed that BMI was a better predictor of elevated blood pressure. Similar results have been reported elsewhere [\n41\n,\n42\n] and evidence suggests that central obesity indices (such as WC) contribute only slightly to be predictive value of BMI [\n43\n]. Our results couple also with those of the Bogalusa Heart Study, where none of the WC, WHpR or WHtR measurements predicted the blood pressure levels of young adults in multivariate models [\n44\n]. Nonetheless, there are many studies with different conclusions [\n21\n,\n22\n,\n45\n].\nCentral obesity indices were mostly correlated with adverse serum lipids and lipoproteins. Several studies conclude that WC might be a superior index predicting the presence of central adiposity and dyslipidaemia [\n21\n,\n46\n,\n47\n]. We found that WC was a strong indicator for abnormal lipid profile within the female sample of medical students, whereas WHtR could better identify men with dyslipidaemia. The latter finding has also been reported by Ko \net al\n, although their study involved Hong Kong Chinese adults aged 37 ± 9 years [\n22\n]. In both genders, the obesity indices could only explain between 2.3% and 11.9% of the variance of the CVD risk factor variables. These low percentages are probably a result of the multifactorial nature of these CVD risk factors.\nConclusions\nThe main findings of this study are summarized as follows: a) a substantial proportion of young Greek medical students were overweight or obese, b) obese students had higher levels of major CVD risk factor variables, namely blood pressure, serum lipids and lipoproteins, and c) BMI was found to be a useful index for the prediction of high blood pressure; WC in women and WHtR in men were also strong indicators for abnormal serum lipids and lipoproteins.\nOur results highlight the necessity to institute effective prevention and health promotion programs in Greece targeting at young age groups. In view of the fact that medical students are not representative of the general population, studies should be extended to the Greek adult population and investigate the presence of obesity and major CVD risk factors and their trends over time.\nCompeting interests\nNone declared.\nAuthors' contributions\nGB performed physical measurements, collected data, and drafted the manuscript. IM performed physical measurements, collected data, and reviewed the manuscript. ML carried out the statistical analysis and participated in data collection. AK conceived of the study and participated in its design, and also performed physical measurements. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
71
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nFrequency and severity of myocardial perfusion abnormalities using Tc-99m MIBI SPECT in cardiac syndrome X\n\n**Article Abstract:**\n\nBackground\nCardiac syndrome X is defined by a typical angina pectoris with normal or near normal (stenosis <40%) coronary angiogram with or without electrocardiogram (ECG) change or atypical angina pectoris with normal or near normal coronary angiogram plus a positive none-invasive test (exercise tolerance test or myocardial perfusion scan) with or without ECG change. Studies with myocardial perfusion imaging on this syndrome have indicated some abnormal perfusion scan. We evaluated the role of myocardial perfusion imaging (MPI) and also the severity and extent of perfusion abnormality using Tc-99m MIBI Single Photon Emission Computed Tomography (SPECT) in these patients.\nMethods\nThe study group consisted of 36 patients with cardiac syndrome X. The semiquantitative perfusion analysis was performed using exercise Tc-99m MIBI SPECT. The MPI results were analyzed by the number, location and severity of perfusion defects.\nResults\nAbnormal perfusion defects were detected in 13 (36.10%) cases, while the remaining 23 (63.90%) had normal cardiac imaging. Five of 13 (38.4%) abnormal studies showed multiple perfusion defects. The defects were localized in the apex in 3, apical segments in 4, midventricular segments in 12 and basal segments in 6 cases. Fourteen (56%) of all abnormal segments revealed mild, 7(28%) moderate and 4 (16%) severe reduction of tracer uptake. No fixed defects were identified. The vessel territories were approximately the same in all subjects. The Exercise treadmill test (ETT) was positive in 25(69%) and negative in 11(30%) patients. There was no consistent pattern as related to the extent of MPI defects or exercise test results.\nConclusion\nOur study suggests that multiple perfusion abnormalities with different levels of severity are common in cardiac syndrome X, with more than 30 % of these patients having at least one abnormal perfusion segment. Our findings suggest that in these patients microvascular angina is probably more common than is generally believed.\n\n**Article Body:**\n\nBackground\nSyndrome X is defined by a typical angina pectoris with normal or near normal (<40% stenosis) coronary angiogram with or without ECG change or atypical angina pectoris with normal or near normal coronary angiogram plus a positive none-invasive test (exercise tolerance test or myocardial perfusion scan) with or without ECG changes [\n1\n,\n2\n]. Patients with coronary artery spasm (Prinzmetal's or variant angina), left ventricular hypertrophy, systemic hypertension, and valvular heart disease are not included in this syndrome [\n3\n]. The term \"Microvascular Angina\" (MVA) includes all such patients with coronary microcirculatory derangements but with normal coronary angiograms irrespective of the presence or absence of exercise-induced ST segment depression [\n4\n].\nThe exact pathophysiological mechanisms underlying this condition are not well understood, and many mechanisms for the chest pain have been suggested. In some studies, microvascular dysfunction has been proposed as the cause [\n4\n-\n7\n] whereas in others, metabolic abnormalities, such as net myocardial lactate production have been demonstrated [\n8\n-\n12\n]. Noninvasive imaging has been used to determine whether ischemia is present or not. Controversial findings have been reported regarding left ventricular function in MVA. Though regional wall motion abnormalities have been reported using stress nuclear techniques, two dimensional echocardiography has not disclosed any segmental contractile dysfunction [\n13\n]. Some studies in which positron-emission tomography (PET) was used have shown abnormal heterogeneity in perfusion [\n14\n,\n15\n] whereas others have shown no abnormality [\n16\n,\n17\n]. However, the possibility of the development of exercise induced ischemia in these patients is supported by the fact that approximately two-thirds of the patients develop regional abnormalities of left ventricular contraction or show an abnormal ejection fraction response (i.e., less than 5% increment) following exercise [\n18\n].\nTl-201 scintigraphy has been employed in the investigation of patients with syndrome X, and often shows regional defects after stress [\n19\n-\n21\n]. However, the physical limitations due to lower energy emission of Tl-201 as a myocardial perfusion agent have long been recognized [\n22\n-\n25\n] yielding inconsistent results [\n19\n,\n26\n]. The development of new and higher energy emission Tc-99m labeled agents, such as Tc-99m MIBI, significantly improved image quality and eliminated false-positives results in Tl-201 SPECT [\n25\n,\n27\n]. Although, in these patients the diagnosis of microvascular involvement as a \"yes-no\" binary outcome may be adequate for further management, however, information on both the presence and extent of coronary artery disease (CAD) are desirable, as both have implications in assessment of prognosis or selection of therapy [\n28\n-\n30\n]. In this study we evaluated myocardial perfusion in syndrome X, using Tc-99m MIBI SPECT.\nMethods\nParticipants and study design\nThe study included 23 females aged 42–58 years (mean 49.86 ± 6.32 [SD] y) and 13 males ranging from 40–59 years (mean, 49 ± 4.61 [SD] y) who had syndrome X. The patients were recruited from the cardiology Clinic at our Hospital from January 2004 to may 2005. This study was approved by the institutional ethics committee of Tehran university of medical science and all patients gave written informed consent.\nAll patients had a previously established diagnosis of syndrome X, according to the following two criteria; 1- typical history of angina (substernal burning, heavy or squeezing feeling, precipitated by exertion or emotion and promptly relieved by rest or nitroglycerin)[\n31\n] and normal coronary angiography (stenosis less than 40%) 2- atypical chest pain (located in the left side of the chest, abdomen, back or arm in the absence of mid-chest sharp, fleeting, recurrent or very prolonged pain unrelated to exercise; not relieved by rest or nitroglycerin but responded to antiacids, or characterized by palpitations without chest pain[\n31\n]) with an abnormal exercise electrocardiogram (0.1 mV horizontal or downsloping ST segment depression of 80 msec after the J point) or myocardial perfusion image and completely normal results on coronary angiography, with no inducible spasm on ergonovine-provocation test. In case of the patients with atypical chest pain, other causes especially gastro-esophageal disorders that can mimic this pattern were excluded. None of the patients had diabetes, hypertension, left ventricular hypertrophy (defined as a value above 35 mm for the sum of the heights of the S wave in lead V1 and R wave in lead V5), valvular heart disease, congestive heart failure (CHF), history of myocardial infarction, mitral valve prolapse, left bundle branch block(LBBB), congenital heart disease (CHD), cardiomyopathy, ejection fraction less than 55% in echocardiography or demonstrated any remarkable change in clinical condition during the investigations. Fifteen out of 36 cases had typical whereas other 21 had atypical chest pain. The patients with syndrome X were taking calcium-channel blockers (10), nitrates (8), hormone-replacement therapy (7), beta-blockers (8), potassium-channel openers (5), or no treatment (1 patient). Some of our patients were on more than one medication.\nMyocardial SPECT imaging & analysis\nPatients fasted overnight and all cardiovascular drugs were discontinued at least 2 days before the study. All patients were asked to exercise on a treadmill under a standard Bruce protocol. At the achieved peak heart rate (more than 85% the age-predicted maximum heart rate), appearance of typical angina and/or positive exercise ECG findings, 20 mCi Tc-99m MIBI as a compact bolus was injected. The exercise test was considered to be positive if there was a horizontal or downsloping ST segment depression more than 1 mm for 80 microseconds after the J point. An intravenous line of normal saline solution, with a 20-gauge cannula was positioned in an antecubital vein. Imaging was performed 15–30 minutes after exercise. On the next day 60 minutes after injection of 20 mCi Tc-99m MIBI, the patients were asked to eat a fatty meal to accelerate hepatobiliary clearance of Tc-99m MIBI. The resting SPECT was performed 90 minutes after Tc-99m MIBI injection. SPECT images were obtained using a double detector system (ADAC Genesys Malpitas, CA, USA) with low-energy, all purpose (LEAP) collimator. For Tc-99m MIBI SPECT, a symmetric 15% window was centered at 140 KeV, and images were acquired into a 64 × 64 computer matrix through a 180° rotation, at an angular interval of 6° from RAO 45° to LPO 45°. Reconstruction was performed by a standard back projection method using a Butterworth Filter for a 64 × 64 matrix image. Acquisition parameters were identical for the rest and stress studies.\nInterpretation was made on the basis of a left ventricular polar-plot segmentation according to the 17-segment model [\n32\n] [Fig \n1\n]. This was done by two observers who had no previous knowledge of the patients' histories, results of exercise ECG, or coronary angiograms. The uptake in each of these segments was assessed as normal, mild (= equivocal), moderate, severe or absent [\n33\n].\nFigure 1\nA. A polar-plot depiction of the left ventricular segmentation according to the 17-segment model. The recommended nomenclature is noted for each segment below. B. The 17-segment model, obtained by three individual short-axis slices as well as one midcavity vertical long-axis slice. A depiction of the coronary artery distribution is also noted.\nCoronary arteriography\nCoronary arteriography was performed with a monoplane imaging system and recorded on conventional 35 mm film. Angiographic images were visually assessed by two readers who were blind to MPI data.\nStatistical analysis\nThe statistical analysis was performed with the use of SPSS version 11.5. Data are presented as the mean ± one standard deviation. Chi square test was also applied. A p value < 0.05 was considered to be statistically significant.\nResults\nThirteen patients out of 36 (36.1%) showed abnormal myocardial perfusion scan. Of the 23 females patients, 9 (39.1%) had abnormal Tc-99m MIBI SPECT and 14 (60.9%) showed normal scan. Of the 13 males 4 (30.8%) showed abnormal and 9(69.2%) cases revealed normal studies. There was no significant difference between two genders (p value > 0.05). Of the 9 positive female patients, 3 (33.33%) cases showed multiple perfusion defects and 6(66.66%) cases revealed single localized perfusion abnormality. Of the 4 males with positive scan 2 (50%) cases revealed multiple and 2 (50%) single perfusion defects. The defects were localized in the apex in 3, the apical segments in 4, the midventricular segments in 12 and in the basal segments in 6 cases. All patients had reversible perfusion abnormality and none of them had transient left ventricular dilation (TLV). The involvement of three vessel territories approximately were the same(LAD;8, RCA;9 and LCX;8). In the cases with multiple perfusion defects, the ischemic pattern was distributed throughout the different segment of myocardium. The detailed data of uptake reduction are shown in table \n1\n and a sample picture is presented [Fig. \n2\n]. Exercise treadmill test (ETT) was performed in this study as a part of the protocol. The results of ETT were positive in 25 (69%) patients and negative in 11(30%). 65% of the results of the exercise ECG were not concordant with perfusion defects found on myocardial perfusion imaging.\nTable 1\nfrequency and percent of MIBI uptake defects and involved segments of coronary vessel territories\nLAD\nLCX\nRCA\nTotal\nNo\n%\nNo\n%\nNo\n%\nNo\n%\nMild\n6\n75\n3\n37.5\n5\n55.5\n14\n56\nModerate\n1\n12.5\n4\n50\n2\n22.2\n7\n28\nSevere\n1\n12.5\n1\n12.5\n2\n22.2\n4\n16\nTotal\n8\n100\n8\n100\n9\n100\n25\n100\nAbbreviation: LAD = Left anterior descending artery, LCX = Left circumflex artery, Rca = Right coronary artery\nFigure 2\nA patient with multiple perfusion defects with different degrees of severity. The upper images are stress phase and lower images are rest or delayed images. There is moderate ischemia in the mid anterolateral and mid inferolateral walls. Also there is severe ischemia in the basal inferior wall. Mild ischemia in the apex, apical septal and basal anterolateral are also noted.\nDiscussion\nInvestigations over the past two decades have not revealed a specific cause for syndrome X. In the presence of normal coronary arteries, many explanations have been put forth to explain myocardial ischemia, including small vessel abnormalities, coronary artery spasm, cardiomyopathy, metabolic abnormalities, misinterpretation of the coronary angiograms, impaired coronary flow reserve, oxyhemoglobin dissociation defects, psychosomatic factors, altered pain perception, increased sympathetic drive, and endothelial dysfunction [\n33\n,\n34\n]. It is now acknowledged that syndrome X most likely encompasses several pathophysiologic diseases. Since the introduction of the term syndrome X, many investigators have used the term with different criteria as to its definition, to create a more homogeneous group of patients. Our results suggest that multiple perfusion defects with different severity and distribution are relatively common in cardiac syndrome X, with the majority of these patients having at least one abnormal perfusion segment. Thus, 36 % of our patients with angina pectoris, who had no evidence of significant organic stenosis on their coronary angiograms, exhibited exercise-induced perfusion defects in their Tc 99m-MIBI scintigrams. In a review of the literature, a number of authors have reported different results when using conventional Tl-201 myocardial perfusion imaging. Berger et al reviewed the exercise Tl-201 scans and clinical data of 41 patients with chest pain and normal coronary arteries (a broad definition of syndrome X). A negative Tl-201 study was the most common finding. Of the 41 patients, 11 (27%) had abnormal exercise Tl-201 scans. Of the 11 patients with abnormal scans, 9 had greater than or equal to 1 cardiac abnormality [\n19\n]. Tweddel et al (1992) studied 100 patients with normal arteriograms (a broad definition of syndrome X) undergoing diagnostic angiography for typical angina. Thallium defects were found in 98 patients (a very high incidence) [\n20\n]. Legrand et al (1985) studied the results of exercise Tl-201 scintigraphy in 18 patients with chest pain and angiographically normal coronary arteries (a broad definition of syndrome X). Regional exercise Tl-201 perfusion was abnormal in three patients [\n21\n]. Chia-Hung et al (1996) reviewed the stress Tc-99m MIBI SPECT results and clinical data of 15 patients with syndrome X. The results of exercise ECG and resting left ventricular ejection fraction (LVEF) were compared with the results of Tc-99m MIBI SPECT. Of these 15 patients, 9 (60%) had a normal Tc-99m MIBI SPECT study and 6 (40%) had an abnormal Tc-99m MIBI SPECT [\n35\n]. Recently Cavusoglu et al (2005) have evaluated the regional distribution and extent of perfusion abnormalities, and the lung to heart (L: H) uptake ratios using exercise thallium-201 SPECT in 31 patients. They showed that perfusion abnormalities are relatively common in these patients. Also patients with perfusion abnormalities have significantly higher L: H ratios during exercise than control patients [\n36\n]. Jonathan et al (2002) performed myocardial-perfusion cardiovascular magnetic resonance imaging in 20 patients with syndrome X and 10 matched controls, both at rest and during an infusion of adenosine. Quantitative perfusion analysis was performed using the normalized upslope of myocardial signal enhancement to derive the myocardial perfusion index and the myocardial-perfusion reserve index (defined as the ratio of the myocardial perfusion index during stress to that at rest). Following adenosine, control group revealed increased myocardial perfusion in subendocardial and subepicardial layers of myocardium but there was only increased perfusion in subepicardium in patients with syndrome X without any detectable change in the subendocardial layer [\n37\n]. In our study, 69 % of exercise tests were abnormal which is similar to the study by Cannon et al (1985) [\n18\n]. In this study, we tried to match coronary anatomy with perfusion segments to localize CAD to the level of small vessels, its potential application being in serial studies, following surgical or percutaneous revascularization interventions, and in patients without an established diagnosis of CAD to identify small sized ischemia or infarctions, not detectable by angiography. Our study suggests that SPECT MPI can be used to identify small perfusion defects pointing to the presence of CAD and also suggests that this procedure may have value in the assessment of the physiological significance of small vessel stenosis not identifiable by coronary angiography. We noticed that the ischemic regions in patients with multiple perfusion defects are distributed in the different myocardial segments as previously reported by other investigators [\n38\n].\nFurthermore, ischemia may not necessarily be localized to an entire myocardial area as in patients with epicardial coronary stenosis.\nIndeed myocardial ischemia may be patchily distributed in small areas of myocardium. In these patients, small areas of hypoperfusion were patchily distributed in different anatomic sites, spreading among nonischemic areas, able to compensate for the dysfunction of adjacent myocardium. This pattern is clearly different from that of patients with coronary artery disease, whereas the hypoperfused areas are clustered in the anatomic regions supplied by the stenotic arteries [\n38\n].\nIn addition, in theses patients inappropriate constriction of prearteriolar vessels may be postulated to be sparse in the myocardium and to be non uniform with the possibility that only a minority of these vessels are intensely constricted. Thus, during increased myocardial activity a focal and spotty myocardial ischemia can result although electrocardiographic signs, metabolism and function are found to be within normal limits. Similarly, a focal increase in myocardial adenosine concentration may cause anginal pain even in the absence of significant myocardial ischemia. Depending on the percentage of involvement of prearteriolar abnormality reduced coronary flow reserve and the presence of detectable myocardial ischemia by nuclear scan may vary widely [\n39\n].\nThe patients in our study had well-characterized syndrome X; however, other conditions may lead to microvascular dysfunction, and similar findings might be found in patients with hypertension, hypertrophic conditions, CHD, CHF, LBBB, MVP, valvular diseases, cardiomyopathy or diabetes. Therefore, we excluded patients with these conditions from our study. Although there is predominance of female to male patients (23/13) referred to our hospital, the scan abnormalities are almost similar in both genders (39% Vs 38%). The prognostic implications of the identification of microvessel disease are uncertain. Although one may expect that, if the total myocardium at risk is small, the patient's prognosis will be favorable, the significance of CAD in multiple branches has not been assessed. Our study did not address the prognostic implications of branch vessel disease, as detected by SPECT MPI. Further studies are needed to follow these patients and determine the prognostic significance of these interesting findings.\nFinally it should be emphasized that our study is not free of drawbacks. Since the sensitivity of SPECT as compared to PET for the assessment of myocardial ischemia is less than optimal, the absence of documented myocardial ischemia does not allow for the exclusion with certainty of cardiac and/or ischemic genesis of anginal pain in those remaining patients, in whom nuclear scan was normal [\n40\n].\nConclusion\nOur results support the concept that the chest pain in patients with syndrome X may be related to myocardial ischemia. Myocardial perfusion defects revealed by scintigraphy in 13 out of 36 (36 %) patients with angina and normal coronary arteriograms, raises the possibility of microvascular angina as the cause of chest pain. The term \"microvascular angina\" is commonly used in these patients; however, the cardiologists should be cautioned when confronting cases with discordant scintigraphic and angiographic findings.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nMS participated in the interpretation of the scintigraphic results. MA participated in its design and coordination, supervised the acquisition process, participated in the interpretation of the scintigraphic results and also participated in writing of this manuscript. ME supervised the acquisition process, interpreted the scintigraphic results and edited the manuscript. MY carried out angiography and interpreted exercise test. AFE supervised the acquisition process. JMM performed the statistical analysis. BFS, DB and AT supervised the acquisition process. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** definitely relevant"
}
] |
definitely relevant
|
72
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nRisk of ischaemic heart disease and acute myocardial infarction in a Spanish population: observational prospective study in a primary-care setting\n\n**Article Abstract:**\n\nBackground\nIschaemic heart disease is a global priority of health-care policy, because of its social repercussions and its impact on the health-care system. Yet there is little information on coronary morbidity in Spain and on the effect of the principal risk factors on risk of coronary heart disease. The objective of this study is to describe the epidemiology of coronary disease (incidence, mortality and its association with cardiovascular risk factors) using the information gathered by primary care practitioners on cardiovascular health of their population.\nMethods\nA prospective study was designed. Eight primary-care centres participated, each contributing to the constitution of the cohort with the entire population covered by the centre. A total of 6124 men and women aged over 25 years and free of cardiovascular disease agreed to participate and were thus enrolled and followed-up, with all fatal and non-fatal coronary disease episodes being registered during a 5-year period. Repeated measurements were collected on smoking, blood pressure, weight and height, serum total cholesterol, high-density and low-density lipoproteins and fasting glucose. Rates were calculated for acute myocardial infarction and ischaemic heart disease. Associations between cardiovascular risk factors and coronary disease-free survival were evaluated using Kaplan-Meier and Cox regression analyses.\nResults\nMean age at recruitment was 51.6 ± 15, with 24% of patients being over 65. At baseline, 74% of patients were overweight, serum cholesterol over 240 was present in 35% of patients, arterial hypertension in 37%, and basal glucose over 126 in 11%. Thirty-four percent of men and 13% of women were current smokers. During follow-up, 155 first episodes of coronary disease were detected, which yielded age-adjusted rates of 362 and 191 per 100,000 person-years in men and women respectively. Disease-free survival was associated with all risk factors in univariate analyses. After multivariate adjustments, age, male gender, smoking, high total cholesterol, high HDL/LDL ratio, diabetes and overweight remained strongly associated with risk. Relative risks for hypertension in women and for diabetes in men did not reach statistical significance.\nConclusion\nDespite high prevalence of vascular risk factors, incidence rates were lower than those reported for other countries and other periods, but similar to those reported in the few population-based studies in Spain. Effect measures of vascular risk factors were mainly as reported worldwide and support the hypothesis that protective factors not considered in this study must exist as to explain low rates. This study shows the feasibility of conducting epidemiological cohort studies in primary-care settings.\n\n**Article Body:**\n\nBackground\nIschaemic heart disease (IHD) is an extremely frequent cause of hospitalisation and death in Spain. This has made it a priority of health-care policy, not only because of its social repercussions, but also because of its impact on the health-care system [\n1\n]. Furthermore, incidence studies conducted in Spain indicate that IHD is a frequent disease, with rates in the order of 200 and 50 new myocardial infarctions p.a. per 100,000 men and 100,000 women respectively [\n2\n-\n8\n]. At an international level, however, these rates are among the lowest in the world, notwithstanding the fact that frequency of exposure to cardiovascular risk factors is no less among Spaniards than it is in other countries [\n9\n,\n10\n]. This phenomenon, known as the French paradox, is also seen in other populations in the Mediterranean area and has been linked to the possible existence of protective factors linked to the Mediterranean diet [\n11\n-\n13\n]. Yet there is little information on the effect of the principal risk factors on risk of coronary heart disease in populations with low rates of IHD morbidity and mortality [\n14\n,\n15\n]. Indeed, it has been postulated that the magnitude of the effect had by the principal cardiovascular risk factors on such populations might be different to that had on populations registering high rates [\n16\n].\nIn addition, the coronary morbidity information available for Spain and for Europe in general, is sparse, only marginally comparable and subject to certain limitations [\n8\n,\n15\n]. A recent review, ordered by the European Commission as part of the Health Monitoring Programme, concluded that cardiovascular disease morbidity data are rarely available in the different countries, and when available, are very rarely comparable [\n17\n]. Moreover, longitudinal studies undertaken in Europe are already out of date and their results on incidence cannot be extrapolated to the present [\n15\n,\n18\n]. In Spain, neither the MONICA-Catalonia study, nor the registers constituting the IBERICA study, allow for the risk associated with exposure to risk factors to be estimated [\n2\n-\n5\n]. Moreover, both studies solely collect information on the incidence of acute myocardial infarction and not on other forms of cardiac ischaemia. The Manresa cohort study was confined to men from a very restricted work setting, whereas, to date, the DRECE study has not reported results on coronary incidence by age and sex [\n6\n,\n7\n].\nPrimary-care settings, mostly in those health systems that as the Spanish one cover the entire population, could be a good alternative to population-based registries to conduct epidemiological studies, as general practitioners are fully qualified and capable for detecting both cardiovascular risk of their patients and coronary events and deaths, and moreover this information is routinely recorded in primary-care clinical practice. This study sought: to describe coronary disease morbidity and mortality across 5 years of follow-up in a cohort of persons attended in a primary-care setting; and to analyse the association between such morbidity and mortality, and subjects' serum cholesterol levels, blood pressure, glucaemia, tobacco use and overweight.\nMethods\nEight primary-care centres in the Province of Zaragoza participated in the study, each contributing to the constitution of the cohort with the entire population assigned by the Spanish National Health Service to each of the participating doctors. In May 1994, a closed cohort of 6262 men and women over the age of 25 years was thus formed. The patients were base-line interviewed and explored after obtaining their informed consent, at the time of requesting some type of service, regardless of the reason for their medical visits. All patients who presented with history of ischaemic heart disease or cerebrovascular accident were excluded. Patients were subsequently followed up on a consultation-on-demand basis until May 1999; during this 5 year period all episodes of fatal and non-fatal ischaemic heart disease were systematically searched and duly registered. On conclusion of the study, all patients who had not attended the primary-care centre in the preceding 9 months were contacted by telephone to identify any possible non-reported events.\nAn ischaemic cardiac event (codes 410 to 414, Ninth Revision of the International Classification of Diseases: ICD-9) was defined as any event diagnosed as acute myocardial infarction, non-Q wave myocardial infarction, unstable angina, angina or coronary angioplasty by the cardiologists' or reference hospitals' reports, or death certificates in the case of sudden deaths. From these, only those cases that fulfilled MONICA diagnostic criteria were classified as AMI (definite or probable). No attempt was made to recode cases according to the new definition of acute coronary syndromes, because the information that would have been needed to do so was not gathered at the time the study was conducted. All events were validated against clinical records. For this study only incident first-ever events were considered; in case of multiple or recurrent events only the first one was considered.\nA total of 138 individuals (2.2%) who could not be followed up after enrolment, were deemed to be lost to follow-up. Consequently, the final cohort numbered 6124 persons (3393 women and 2731 men).\nAt baseline (date of enrolment) and across follow-up, the following information was collected on each patient: sex, age, smoking habit, systolic and diastolic blood pressure, weight and height, total cholesterol, high-density lipoprotein cholesterol (HDL-c), low-density lipoprotein cholesterol (LDL-c), triglyceride and glucose. To standardise the recording of data, the eight researchers used the \"HIPÓCRATES\" clinical-history-management software programme as supplied by the Spanish General Medicine Society (SEMG).\nBiochemical methods were those routinely used in Spanish primary-care system. Blood was extracted after a 10–12 hour fast. Extracted specimens were immediately refrigerated and stored until delivery that same day to the laboratory. Total cholesterol and HDL-cholesterol concentrations were determined by the cholesterol oxidase: p-aminophenazone (CHOD-PAP) method (enzymatic colorimetric test), after separation by precipitation and centrifugation of kilomicrons, VLDL and LDL. LDL concentration was calculated using Friedewald's formula [\n19\n]. Determination of glucaemia was performed using the hexokinase-based GLUCO-QUANT method.\nBlood pressure was measured twice with the subject seated and at rest, using a mercury sphygmomanometer, as per the Hypertension Detection and Follow-up Program Guidelines [\n20\n]. Smoking habit was evaluated by interviewing subjects as to their present and past history of tobacco use. Condition of previous ischaemic event was likewise assessed. We defined: a smoker as any individual who had regularly smoked a minimum of 1 cigarette per day up to two years prior to the study termination date; and a non-smoker as any patient that had never regularly smoked 1 or more cigarettes per day, or had done so more than 2 years prior to the study termination date.\nStatistical analysis\nFrequency of coronary events and coronary and all-cause mortality were calculated by means of incidence and mortality rates per person-years of observation, with the follow-up period defined as the time elapsed from the start of the study to the date of appearance of the event or death, where applicable, or alternatively, from the start of the study to the study termination date (May 1999); in the case of mortality rates, the time was deemed to run until the date of death or termination of the study. Rates were adjusted for age, taking the age distribution of the Standard European population as reference.\nSurvival analysis was used to describe and analyse the experience of coronary morbidity in the cohort, with the Kaplan-Meier method for the univariate analyses and Cox proportional risk regression for the multivariate analysis. In both cases, the association between IHD-free survival and cardiovascular risk factors was evaluated in accordance with pre-established dichotomous categories of risk factors. For each such factor (systolic and diastolic blood pressure, total cholesterol, LDL- and HDL-cholesterol, glucaemia, weight), we took the mean value of the repeated measures obtained across follow-up. The criterion used to define arterial hypertension (AHT) was the Sixth Report of the Joint National Committee, which defined hypertension as systolic blood pressure (SBP) ≥ 140 mm Hg and/or diastolic blood pressure (DBP) ≥ 90 mm Hg [\n21\n]. Hypercholesterolaemia was defined as total cholesterol ≥ 240 mg/dl as per NCEP (ATP II) criteria [\n22\n]. The effect of the LDL and HDL lipoprotein level was jointly assessed by reference to the atherogenic index (LDL/HDL ratio); for the purpose of this index, a cut-off of 3 was used to define the categories. The diagnostic criterion for definition of diabetes mellitus was fasting plasma glucose ≥ 126 mg/dl, as per the ADA recommendations [\n23\n]. Overweight was defined as a Body Mass Index (BMI; weight, expressed in kilograms, divided by the square of the height, expressed in metres) > = 25. Treated patients were classified as exposed when the mean of the repeated measures was above the cut-off values; this way, not controlled patients remained as exposed and controlled patients were classified either as exposed or not exposed depending on the degree of effective control.\nTo avoid overadjustment, overweight was excluded from the Cox model in assessing the effect of diabetes and AHT, and LDL/HDL ratio in measurement of the effect of hypercholesterolemia, since they share the etiological pathway. To avoid potential bias and power shortages due to deletion of cases in complete-case analysis, missing data in covariates were replaced by multiple imputation, with age, sex and coronary disease outcome taken as predictors [\n24\n]. If missing data in a variable were more than 30%, these were not imputed and the variable considered as measured only in a subgroup of the cohort. This occurred in BMI and LDL/HDL ratio variables.\nThe study complies with the World Medical Association Declaration of Helsinki. Due to the non-experimental nature of the research, the study protocol did not need to be submitted for consideration and approval to an ethical review committee.\nResults\nThe general characteristics of the cohort, comprising 6124 patients (44.6% men, 55.4% women) are described in Table \n1\n. A more detailed description has been previously published [\n25\n]. The age range was 25–99 years (mean ± standard deviation 50.4 ± 15 and 52.8 ± 16 in men and women respectively, p = 0.000), with 24% of patients being over 65 and 9% over 75 years of age. The prevalence of the cardiovascular risk factors considered was as follows: 34% of men and 13% of women were current smokers (p = 0.00); 76% and 73% respectively were overweight (p = 0.02); and 33 and 37% respectively were hypercholesterolaemic (p = 0.03). Frequency of arterial hypertension (38% in men, 36% in women) and diabetes mellitus (11%) showed no statistically significant differences between the sexes.\nThe age and gender distributions of the study cohort vis-à-vis those of the Zaragoza general population obtained from official demographic statistics are depicted in Figure \n1\n. These distributions in the study population overlaps that of the general population, with the differences of female (55% vs. 52%) and the 35–64 age group (56% vs. 52%) being slightly over represented in the cohort.\nOver the 5 years of study, the 6124 patients included in the cohort furnished 30,386 person-years of observation (mean ± standard deviation 4.96 ± 0.03 years), with 159 patients (0.02%) with incomplete follow-up due to competing mortality. A hundred and fifty-five first episodes of all forms of ischaemic heart disease were detected (fatal and non-fatal) (Table \n2\n). The crude incidence rates per 100,000 person-years were 650 in men and 403 in women; the age-adjusted rates remained higher for men than for women, with figures of 362 and 191 new cases per 100,000 person-years respectively, and increased with age in both sexes. This incidence pattern -namely, increasing with age, and higher in men than in women- was maintained for acute myocardial infarction alone.\nTwenty-one of the 155 episodes of ischaemic heart disease resulted in death, yielding an age-adjusted IHD mortality rate of 42.5 and 25.8 per 100,000 person-years, for men and women respectively (Table \n2\n). All-cause mortality in this cohort was 5.92 per 1000 person-years (adjusted rate of 3.15 per 1000).\nAll the risk factors considered displayed an statistically significant association with incidence of ischaemic heart disease in the univariate analysis (Figure \n2\n, table \n3\n), the strongest associations being observed for age and overweight. After multivariate adjustments, age, male gender, smoking habit, hypercholesterolaemia and the LDL/HDL ratio remained strongly and consistently associated with risk of suffering ischaemic heart disease after five years of follow-up (Table \n4\n). The positive, significant effect of age, as well as those of cholesterol, LDL/HDL ratio and BMI on risk remained significant when they were taken in a continuous scale. The presence of hypertension, that showed a 24% increase in risk that did not reach statistical significance in the analysis for the hole cohort, was statistically associated with disease in men but not in women. Positive and high relative risks for overweight an smoking in women were almost statistically significant. Lastly, diabetes proved to be associated with disease in women but not in men.\nThere were only three cases of sudden death, two of them presenting symptoms of severe neurological deficit and no chest pain. These contributed to follow up time until the date of death, which was recorded as due to probable stroke.\nThe one single case of sudden death with AMI compatible symptoms was considered as probable AMI, following MONICA criteria. The inclusion or exclusion of this case of the analysis did not modify the results.\nDiscussion\nKnowledge of the magnitude of IHD risk, along with identification of the factors responsible and populations at greatest risk, are fundamental for the planning and assessment of preventive and health-care strategies and identification of specific excess-risk scenarios. There is a dearth of such information in Spain. This study sought to describe the epidemiology of ischaemic heart disease and acute myocardial infarction in a cohort drawn from the population attending primary-care centres.\nEpidemiological studies conducted in a primary care setting can be subject to several limitations, that must be taken into account [\n26\n]. Firstly, this cohort cannot be regarded as representative of the general population but only of those who use primary-care services, although it should be stressed that the Spanish National Health Service covers the entire population and that, according to the Spanish National Health Survey, 80% of the Spanish adult population attends such health centres at least once a year [\n27\n]. In this study, the age and sex distribution of the cohort was very similar to that of the general population, but substantial differences in frequentation to primary care by age and sex have been well described in many studies, so it is likely that detection and exposure classification biases could be present; to minimize this potential biases the study protocol included systematic search of events and exposures during follow-up and at the end of the study period. This systematic approach explains the very low percentage of patients lost for follow-up. Anyway, we must further remark that the study population is not a random sample of general population, so any generalization of the results should be cautious. Furthermore, the cohort is not a sample but the entire population covered by the participant health centres but these were not randomly sampled, this meaning that the results are applicable only to the study population, and of course this population is not representative of other populations.\nClinical trials have demonstrated that effective medical control of vascular risk factors reduces risk, so classifying treated patients as exposed (as has traditionally been done) could have biased the results, mostly when the study was conducted in a medical setting. In the same manner, including treated patients as not exposed would have also introduce a bias because effective control is not always achieved. This potential exposure misclassification derived from medical treatment and control has been approached by taking the mean of repeated measures for arterial pressure, serum cholesterol and glucose, so treated patients were therefore classified as exposed when the mean of the repeated measures was above the cut-off values; this way, not controlled patients remained as exposed and controlled patients were classified either as exposed / not exposed depending on the degree of effective control.\nIn the same way, multiple imputation of missing data was used to prevent biases derived from the aggregation of missing data in different variables when considering them jointly in multivariate analyses [\n24\n].\nThe age-adjusted acute myocardial infarction incidence rates registered in this study are similar to those of the IBERICA study for the general population registers of 7 Spanish regions as a whole, the MONICA-Catalonia, the REGICOR and the IBERICA-Murcia studies [\n2\n,\n4\n,\n5\n,\n28\n]. Nevertheless, it should be borne in mind here that our study targeted an older population, i.e., whereas in the above studies the study population was aged 25–75 years, in our cohort 10% of women and 5% of men were over 75 years old. Still, when this age breakdown was taken into account, the incidence rates in our cohort were almost the same as those found in the general population, despite the fact that this was a medical-settled study. The likelihood of information on events in the cohort being lost is practically non-existent, since the researchers were the designated general practitioners of the patients enrolled, and therefore responsible for their medical follow-up and prescription of drugs in the case of cardiovascular episodes. At all events, on termination of the study all patients who had not attended the primary-care centre in the preceding 9 months were contacted by telephone.\nIn Spain, only two other cohort studies have been conducted to date, aimed at measuring and analysing the risk of IHD, namely the Manresa and DRECE studies, though their results are not entirely comparable vis-à-vis our study or even each other, due to differences in methodology and design [\n6\n,\n7\n]. Taking the above limitations on comparability into account, it can be concluded that the incidence rates registered in the present study do not diverge from those published in Spain until now, and that any differences are attributable to design. This incidence is very high compared to Spanish incidence rates for other chronic diseases, and indeed exceeds the joint incidence of colon, rectal, lung and breast cancer combined [\n29\n]. In the international context, the myocardial infarction incidence rate in this population is very low compared to those reported for non-Spanish populations in the MONICA study [\n2\n] and under-65 mortality is lower than that reported in cohorts included in the SCORE project, though these cohorts were studied 20–30 years ago [\n15\n].\nIHD incidence in this cohort should be interpreted in the light of its level of cardiovascular risk. Compared to the general Spanish population, this cohort registered comparable prevalences of arterial hypertension and diabetes, slightly higher prevalences of overweight and hypercholesterolaemia, and a lower prevalence of tobacco use. The differences in risk profile in studies targeting persons attending primary-care centres is known and has been previously reported [\n9\n]. However, with the sole exception of the low frequency of smoking (34% and 13% among men and women respectively versus 40% and 25% in the general population), the differences in this study are not unduly pronounced, something that would lead one to expect IHD incidence rates to be within the range of those reported by population-based studies in Spain, as is indeed the case.\nAnalysis of the association between cardiovascular risk factors and risk of ischaemic heart disease yields results in line with what was expected, with age, smoking, elevated LDL-cholesterol, hypertension, diabetes and overweight emerging as linked to the risk of suffering an event. This is the first ever cohort study in Spain to show these associations, since previous studies were unable to rule out the null hypothesis for overweight, dyslipaemia or diabetes [\n6\n,\n7\n]. Insofar as arterial hypertension is concerned, the absence of statistical significance in the association among women may be reflecting a better medical control of AHT than among men. Information on treatment and effective control of AHT was not collected in this study, and we believe that further research is needed to identify possible gender differences in AHT awareness, treatment and control in Spain.\nLastly, this study shows the feasibility of conducting epidemiological studies in primary-care settings. Furthermore, the opportunities offered by the primary health care setting were not utilised fully in this study, i.e. treatment information was not recorded when it would have been feasible and desirable. Particular strenghths were found, as the minimization of follow-up and event losses or diagnostic misclassifications. Potential weaknesses, as selection biases due to demographic differences of primary-care frecuentation can been also minimized by an adequate, systematic approach. This systematic approach should also be used to prevent the miss of data, a possibility always present in large cohort studies, moreover with the high work load of primary-care doctors.\nConclusion\nTo sum up, IHD incidence and mortality rates were lower than those reported for other countries and other periods, despite a high prevalence of cardiovascular risk factors, thus confirming similar results reported in other cohort and population-based studies in Spain. Effect measures of vascular risk factors were mainly as reported worldwide and support the hypothesis that protective factors not considered in this study must exist as to explain low rates.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nAM conceived of the study, participated in its design and coordination and helped to draft the manuscript. MJM and RB performed the statistical analysis and interpretation of data and prepared the draft manuscript. JG, HP, VC, MB, MVF, JT, JMC, AM, FH and JB participated in the design of the study, in patients recruitment, follow-up and data collection, and in critical review of the manuscript. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** possibly relevant"
}
] |
possibly relevant
|
73
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nIdentification of pain indicators for infants at risk for neurological impairment: A Delphi consensus study\n\n**Article Abstract:**\n\nBackground\nA number of infant pain measures have been developed over the past 15 years incorporating behavioural and physiologic indicators; however, no reliable or valid measure exists for infants who are at risk for neurological impairments (NI). The objective of this study was to establish consensus about which behavioural, physiologic and contextual indicators best characterize pain in infants at high, moderate and low levels of risk for NI.\nMethods\nA 39- item, self-administered electronic survey that included infant physiologic, behavioral and contextual pain indicators was used in a two round Delphi consensus exercise. Fourteen pediatric pain experts were polled individually and anonymously on the importance and usefulness of the pain indicators for the 3 differing levels of risk for NI.\nResults\nThe strength of agreement between expert raters was moderate in Round 1 and fair in Round 2. In general, pain indicators with the highest concordance for all three groups were brow bulge, facial grimace, eye squeeze, and inconsolability. Increased heart rate from baseline in the moderate and severe groups demonstrated high concordance. In the severe risk group, fluctuations in heart rate and reduced oxygen saturation were also highly rated.\nConclusion\nThese data constitute the first step in contributing to the development and validation of a pain measure for infants at risk for NI. In future research, we will integrate these findings with the opinions of (a) health care providers about the importance and usefulness of infant pain indicators and (b) the pain responses of infants at mild, moderate and high risk for NI.\n\n**Article Body:**\n\nBackground\nAssessment of pain in infants has remained somewhat of an enigma over the past two decades. Although a plethora of infant pain measures has been developed [\n1\n], they are infrequently and inconsistently used in clinical practice. This paucity of assessment is particularly evident in infants who are the most vulnerable; such as those at risk for neurological impairment (NI). Infants at varying levels of risk for NI are exposed to multiple painful procedures during their initial days in the NICU [\n2\n]. Stevens et al [\n2\n], found that during the first day of life, neonates at highest risk for NI experienced the greatest number of painful procedures (e.g., suctioning, heel lances, intravenous starts) compared to lower risk groups and were administered the least amount of opiods [\n2\n]. To appropriately manage these at-risk infants, a reliable and valid approach to assessing pain is required.\nTo address this issue, a comprehensive approach to measurement development taking into account the perspectives of multiple stakeholders such as health care providers from different disciplines, parents and family members needs to be undertaken. Eliciting the perceived importance (in accurately and consistently identifying pain) and clinical usefulness (how feasible and useful the measure is for making decisions concerning pain management) of physiologic, behavioural and contextual indicators that comprise pain measures by experts in infant pain research is an appropriate starting place.\nOnly a few infant pain measures have taken contextual factors, which consist of any factor either known or thought to influence the infant's pain response (such as gestational age, sleep/wake status, severity of illness, that would assist to describe an infant's pain response within a particular context [\n3\n-\n5\n]) into consideration. As no measures have incorporated risk for neurological impairment (NI) as a contextual factor, the results of this study will contribute to our understanding as to whether there is a difference in response based on risk for NI or whether this risk in and of itself should be considered a contextual factor. There is inconsistent evidence on the differences in behavioural and physiological indicators when comparing infants with and without NI. Stevens et al [\n6\n] reported there were differences in facial activity and heart rate variability with the most at risk for NI infants demonstrating the least response following heel lance. Conversely, Oberlander et al [\n7\n] found similar facial and heart rate variability responses to heel lance between groups of preterm infants with and without parenchymal brain injury.\nGenerally, infants with NI may show fewer and less clear emotional responses [\n8\n,\n9\n]. For example, infants with Down's syndrome or asphyxia exhibited cries that were less frequent, less variable in intensity and fundamental frequency (pitch) [\n10\n-\n14\n] and of longer latency from the painful stimulus than cries in infants with no disabilities [\n10\n]. Furthermore, there is speculation that differences in facial musculature, hypotonia, and aberrant neural information programming may affect facial pain responses [\n15\n,\n16\n]. The multidimensional pain response in infants at risk for NI has not been consistently or comprehensively described, and no measure to assess pain in this population has been validated.\nUsing the Delphi method, the aim of this study was to establish consensus amongst infant pain research experts about which behavioural, physiologic and contextual indicators characterized pain in infants at high, moderate and low risk for NI. The ultimate goal is the development of a new measure or validation of an existing measure for acute pain assessment in this population.\nMethods\nStudy participants\nA list of 42 local and international infant pain research experts was generated by the study investigators (who represent diverse levels of expertise in medicine [n = 5], nursing [n = 5] and psychology [n = 2]) and from the International Association for the Study of Pain (IASP) Directory of Members, 2004. To support the content validity of the Delphi exercise and to ensure that the most appropriate experts participated in this process, participants were approached if they had at least 2 years of experience in pain research on assessment and management of infants and young children, had published in peer reviewed pain journals, had presented at major pediatric pain meetings or were known to be involved in current research in pediatric pain. Our goal was to include a multidisciplinary (e.g. nurses, physicians, and psychologists), international sample of approximately 10–15 research experts with broad expertise in pain and pain measurement in infants in this Delphi exercise. Although this sample is small, we were drawing from a very finite number of experts with research in a specialized area and thus it is reasonable given the limited number of eligible participants, time commitment required and limitations of international survey research.\nDelphi survey: expert opinions about managing pain in infants at risk for NI\nA 39- item self-administered survey was developed by the study investigators to include indicators representing infant physiologic, behavioral and contextual pain responses [\n2\n] as well as pain indicators identified by parents and health professionals. This list of indicators was circulated amongst the study investigators (most of whom were infant and pediatric pain experts) to establish face validity. The survey was organized to assess four domains: (a) physical indicators (11 items); (b) facial actions (10 items); (c) vocal behaviour/cry (9 items); (d) infant activity (9 items). The survey was pilot tested for feasibility and content validity with 10 advanced practice nurses from three local neonatal and pediatric intensive care units with expertise in pain assessment and management. The survey was sent electronically to the nurses participating in the pilot study and took approximately 20 to 30 minutes to complete. Based on the pilot study results, minor changes were made to the format of the questionnaire along with the instructions for participants.\nEach survey participant was polled individually and anonymously on the comprehensiveness and accuracy of the list of proposed items. Each item was scored on importance and usefulness of the pain indicator for 3 differing levels of risk for NI (i.e., high risk, moderate risk, low risk), which has been defined and verified by a group of neonatal experts for previous studies by this group of researchers[\n2\n,\n17\n]. The risk cohorts were defined as:\n• High risk cohort: i.e., perinatal asphyxia, IVH [Grade III or IV] or a syndrome or chromosomal anomaly;\n• Moderate risk cohort: i.e., acute disease processes such as persistent pulmonary hypertension of the newborn, severe meconium aspiration, meningitis, hydrocephalus, necrotising enterocolitis;\n• Low risk cohort; i.e., respiratory distress requiring ventilation, sepsis.\nEach item on the survey was scored using a 10 point scale, where a score of 1 = not important/useful at all and 10 = extremely important/useful. \nImportance \nreferred to how vital the pain indicator was in accurately and consistently identifying pain following a painful tissue damaging procedure. \nUsefulness \nreferred to the feasibility (i.e., how easily the pain indicator was to observe and score) and clinical utility (i.e., how helpful the pain indicator was for making decisions about individualized pain management)[\n18\n]. An indicator could be important for accurately measuring pain but not useful because of the difficulties in practically implementing the indicator to assess pain in clinical practice.\nAn explanation of the purpose and description of the research was provided to participants with opportunities for clarification of questions prior to completion of the survey. Variable definitions were provided and respondents were asked to add any additional pain indicators they felt were important or useful to the list. Demographic information and level of experience with infants at risk for NI were also obtained from each of participating experts.\nAll study data were kept confidential by using only a code number on all completed information. Surveys were sent to each potential participant by electronic mail (e-mail) by a research administrative assistant, who was not familiar with the study and who could not link the participant's identity with any response. Any external reporting kept personal information confidential and would only be reported in aggregate form. Completion of the survey was voluntary and return of the completed survey implied consent to participate. This study was part of a larger program of research on pain in infants at risk for NI that was approved by the Research Ethics Boards at the universities and university-affiliated pediatric hospitals participating in the group of studies within this research program.\nThe delphi method\nThe Delphi method, developed by the Rand Corporation in the 1950s, is a research method for eliciting consensus opinions from experts using questionnaires in an iterative process known as rounds [\n19\n]. The number of rounds used in the Delphi process varies, although 2–3 rounds are frequently sufficient [\n20\n,\n21\n]. Questionnaires distributed to experts are both confidential and anonymous [\n22\n,\n23\n]. Responses from each round are collated and then the same experts are repeatedly requested to complete a revised questionnaire based on the results obtained from previous rounds. Although providing the results from previous rounds may introduce some response bias, the goal of Delphi polling in subsequent rounds is to challenge respondents to determine whether their responses were in agreement with the average responses of the participants. The Delphi is considered complete when there is convergence of opinion or when a point of diminishing returns is reached [\n22\n].\nThe Delphi allows experts to offer their opinions independently and confidentially without the pressures that may occur during face-to-face meetings [\n22\n]. Using electronic means, questionnaires can be distributed broadly across a variety of geographical locations and health care disciplines at a lower cost than face-to-face meetings [\n22\n]. Participants have the opportunity to alter their opinions in successive rounds [\n22\n,\n24\n,\n25\n] based on the results of previous rounds to achieve consensus. Consensus of items in a survey or questionnaire is indicative of content validity. The Delphi is potentially subject to researcher bias as the researcher controls the extent of opinions requested from the experts and participants are not able to discuss concerns as there is no formal discussion amongst group members where opinions can be challenged or debated [\n24\n]. In addition, based on the literature on the Delphi technique, there are no set criteria as to what determines final consensus opinion [\n22\n]. Despite these limitations, the Delphi technique has been used successfully as an initial step in instrument development.\nDelphi rounds\nWe predicted, according to the literature and previous expertise with the Delphi method, that we would require 2 to 3 rounds to reach consensus on pain indicators in infants at risk for NI. After Round 1, the results were tabulated and then reported back to the group. In Round 1, participants were asked to rate the 39 items according to how important and useful each pain indicator was in accurately identifying pain following a tissue-damaging painful procedure in each of the 3 Cohorts of infants. A priori, we decided that a mean rating of 6 or greater on the 10 point scale for importance and usefulness would be maintained as an acceptable level of consensus. All indicators that had a mean rating of less than 6 were dropped from the item list, following Round 1. In Round 2, participants were asked to re-rate the reduced list of items that were based on their aggregated and ranked responses in Round 1. These first two rounds are analogous steps to instrument development where item generation and item reduction would establish the content validity of any future pain measure [\n26\n-\n29\n]. Participants from Round 1 also participated in Round 2.\nData management and statistical analysis\nAll returned surveys were provided with a code number and data were double entered into SPSS version 12 and checked for data entry errors. Descriptive statistics (i.e., means, standard deviations, range) were first conducted prior to the analysis of participant responses in Round 1. Kendall's Coefficient of Concordance was used to determine the agreement of ratings between the expert respondents in Rounds 1 and 2. Mean rankings were based on 39 pain indicators in Round 1 and 21 indicators in Round 2 (Table \n1\n). The sum of the ranks from the pain experts is computed for each of the pain indicators. Kendall's W ranges between 0 (no agreement) and 1 (complete agreement). Statistical significance was assessed using Friedman's non-parametric test. The six observer agreement categories by Landis and Koch [\n30\n] were used to describe the strength of agreement between pain experts. A kappa value of 0.00–0.10 is considered poor strength of agreement, 0.11–.20 slight agreement, 0.21–0.40 fair agreement, 0.41–0.60 moderate agreement, 0.61–0.80 substantial agreement and 0.81–1.00 is considered almost perfect agreement [\n30\n].\nTable 1\nPain Variables Used in Delphi Rounds 1 and 2\nRound 1\nRound 2\nPhysical Signs\n*Decrease in heart rate\nIncrease in heart rate\n*Decrease respiratory rate\n*Increase respiratory rate\n*Decrease blood pressure\nIncrease blood pressure\nDecrease in oxygen saturation\n*Increase in oxygen saturation\nFluctuations/variations in HR\n*Change in skin colour\n*Sweating\nPresence of Facial Actions\nFacial grimacing (overall)\nBrow bulge\nEye squeeze\nNaso-labial furrow\nOpen lips\n*Vertical stretch mouth\n*Horizontal stretch mouth\n*Pursed lips\nTaut tongue\n*Chin quiver\nVocal Behaviour/Cry\nDuration of the first cry\nDuration of total crying session\n*Total number of cry bouts\n*Harshness of cry\n*High pitched cry\n*Low pitched cry\n*Melody of cry-flat\n*Melody of cry-melodious\n*Jitters in cry\nActivity\nInconsolability\nAgitation\nRigidity of body\nChanges in:\nBody movements\n*Head movements\n*Hand movements\n*Arm movements\n*Foot movements\nLeg movements\n*items removed in Round 2\nPhysical Signs\nDecrease in oxygen saturation\nIncrease in heart rate\nIncrease in blood pressure\nFluctuations/variations in heart rate\nPresence of Facial Actions\nFacial grimacing (overall)\nBrow bulge\nEye squeeze\nNaso-labial furrow\nOpen lips\nTaut tongue\nVocal Behaviour/Cry\nDuration of first cry\nDuration of the total crying session\nActivity\nInconsolability\nAgitation\nRigidity of body\nChanges in:\nBody movements\nLeg movements\nVocal Behaviour/Cry\n**Tears\n**Finger splay\n**Fighting against ventilator\n**Lack of or delayed responsiveness\n** items added in Round 2\nResults\nThe demographic information on the participants is described in Table \n2\n. To cover for potential loss to follow-up of respondents through invalid e-mail addresses that were used to invite individuals to participate in the surveys, Round 1 surveys were emailed to 42 infant pain experts identified in July, 2004. Reminder emails were sent to individuals two weeks after the initial email. A total of 6/42 individuals returned an email message stating that they were declining from completing the survey as they felt they were not experts in pain in infants with NI. Twenty-two individuals did not respond to the survey invitation, therefore, we have no information on reasons for nonparticipation. The 28 non respondents consisted of 10 nurses, 8 physicians, 9 psychologists and 1 pharmacist. A total of 14 surveys were returned in Round 1, 5 weeks after the initial survey distribution.\nTable 2\nDemographic Characteristics of Delphi Respondents (N = 14)\nProfessional role\n9 Nurse Scientists\n4 Psychologists\n1 Physical Therapist\nYears of experience in current position\n13.4 (minimum 5 years; maximum 24 years)\nLocation of Participant\nCanada = 6\nUnited States = 5\nAustralia = 2\nSweden = 1\nNon professional contact with infants who have or at risk for NI\nNone = 2\nVery Little = 8\nModerate amount = 3\nGreat deal = 1\nProfessional contact with infants who have or at risk for NI\nNone = 4\nVery Little = 2\nModerate amount = 3\nGreat deal = 5\nAcademic or school-based learning about infants at risk for NI\nNone = 2\nVery Little = 3\nModerate amount = 3\nGreat deal = 6\nAccording to our a priori criteria for item reduction, the list of pain indicators in Round 1 was reduced from 39 to 21. Pain indicators with a mean score of 6 or greater out of 10 were retained and the survey was revised to reflect these changes for Round 2. The revised survey listed each indicator according to mean ratings from the highest to lowest rating within each category. Based on the feedback from experts, 21 new indicators identified in Round 1 were subsumed within an existing indicator or were added as new individual indicators to this survey.\nRound 2 surveys were emailed to the 14 respondents from Round 1, 2 weeks after the first Round was completed. A second reminder was sent to respondents and resulted in a return rate of 100% for Round 2.\nPain indicator ratings for infants at mild risk for NI\nThe mean rankings for infants at mild risk for NI regarding importance and usefulness of pain indicators are summarized in Table \n3\n. In Round 1, moderate concordance was found across raters (W = .509, p = .001) on the importance of pain indicators. Moderate concordance was also noted across raters (W = .431, p = .001) for usefulness of pain indicators. The top five pain indicators rated from the highest to lowest rankings for importance and usefulness were the same, although the fourth and fifth indicators differed slightly in their ultimate rankings.\nTable 3\nRound One and Two: Top 5 Mean Ranking of Pain Indicators Mild Risk Group\nRank\nImportant Indicators\nMean Rank\nImportant Indicators\nMean Rank\nRound 1\nRound 2\n1\nBrow bulge\n36.3\nBrow bulge\n17.5\n2\nFacial grimace\n35.7\nFacial grimace\n17.0\n3\nInconsolability\n34.3\nEye squeeze\n16.7\n4\nAgitation\n32.8\nInconsolability\n15.6\n5\nEye squeeze\n32.7\nAgitation\n13.3\nRank\nUseful Indicators\nMean Rank\nUseful Indicators\nMean Rank\nRound 1\nRound 2\n1\nBrow bulge\n35.5\nBrow bulge\n16.6\n2\nFacial grimace\n34.8\nEye squeeze\n16.0\n3\nInconsolability\n32.0\nFacial grimace\n15.9\n4\nEye squeeze\n31.8\nInconsolability\n14.3\n5\nAgitation\n31.2\nIncreased heart rate from baseline\n13.8\nIn Round 2, fair concordance was found across raters (W = .350, p = .001) for importance of pain indicators. Similarly, for mean rankings for usefulness of pain indicators, concordance was fair across raters (W = .270, p = .001). The top five importance pain indicators were the same as the important indicators that were identified in Round 1. The top five usefulness indicators rated in Round 2 were the same as the usefulness indicators identified in Round 1, with the exception of increased heart rate from baseline replacing agitation. Brow bulge, facial expression and eye squeeze were consistently the highest three indicators rated for both usefulness and importance.\nPain indicator ratings for infants at moderate risk for NI\nThe mean rankings for infants at moderate risk for NI regarding importance and usefulness of pain indicators are summarized in Table \n4\n. In Round 1, concordance across raters was moderate (W = .447, p = .001) for importance of indicators. The mean rankings for usefulness of pain indicators also showed moderate agreement across raters (W = .416, p = .001). The top five pain indicators rated from the highest to lowest rankings for importance and usefulness were the same.\nTable 4\nRound One and Two: Top 5 Mean Ranking of Pain Indicators Moderate Risk Group\nRank\nImportant Indicators\nMean Rank\nImportant Indicators\nMean Rank\nRound 1\nRound 2\n1\nBrow bulge\n35.4\nBrow bulge\n17.5\n2\nFacial grimace\n34.6\nFacial grimace\n17.1\n3\nInconsolability\n32.0\nEye squeeze\n16.0\n4\nEye squeeze\n31.7\nInconsolability\n15.5\n5\nAgitation\n30.4\nIncreased heart rate from baseline\n13.1\nRank\nUseful Indicators\nMean Rank\nUseful Indicators\nMean Rank\nRound 1\nRound 2\n1\nBrow bulge\n35.4\nBrow bulge\n16.4\n2\nFacial grimace\n34.6\nFacial grimace\n15.8\n3\nInconsolability\n32.7\nEye squeeze\n15.0\n4\nEye squeeze\n32.2\nIncreased heart rate from baseline\n14.6\n5\nAgitation\n30.5\nInconsolability\n14.1\nIn Round 2, mean rankings for importance of pain indicators demonstrated fair concordance across raters (W = .358, p = .001) as did mean rankings for usefulness of pain indicators (W = .268, p = .001). Four out of the five indicators rated for importance were the same as those rated in Round 1, with increased heart rate from baseline replacing agitation. Similarly, the five highest ranking usefulness indicators were the same as those identified in Round 1 with increased heart rate from baseline replacing agitation (as was the case with infants in the mild risk for NI Cohort). Brow bulge, facial expression and eye squeeze were again consistently rated the highest three indicators for both usefulness and importance.\nPain indicator ratings for infants at severe risk for NI\nThe mean rankings for infants at severe risk for NI regarding importance of pain indicators are summarized in Table \n5\n. In Round 1, moderate concordance was found across raters (W = .466, p = .001). Mean rankings for usefulness of pain indicators revealed fair concordance across raters (W = .378, p = .001). Four of the five pain indicators with the highest mean rankings for importance and usefulness were the same with the exception of eye squeeze, which was rated important and nasolabial furrow, which was identified as useful.\nTable 5\nRound One and Two: Top 5 Mean Ranking of Pain Indicators Severe Risk Group\nRank\nImportant Indicators\nMean Rank\nImportant Indicators\nMean Rank\nRound 1\nRound 2\n1\nBrow bulge\n33.8\nInconsolability\n17.0\n2\nFacial grimace\n32.6\nFacial grimace\n16.4\n3\nInconsolability\n31.6\nBrow bulge\n16.1\n4\nEye squeeze\n29.6\nEye squeeze\n14.1\n5\nAgitation\n29.5\nFluctuations in heart rate\n14.1\nRank\nUseful Indicators\nMean Rank\nUseful Indicators\nMean Rank\nRound 1\nRound 2\n1\nInconsolability\n33.1\nInconsolability\n15.6\n2\nBrow bulge\n31.8\nIncrease in heart rate from baseline\n15.5\n3\nFacial grimace\n30.7\nBrow bulge\n15.1\n4\nAgitation\n30.6\nFacial grimace\n14.7\n5\nNasolabial furrow\n29.5\nReduced oxygen saturation\n14.2\nIn Round 2, mean rankings regarding importance of pain indicators found fair concordance across raters (W = .347, p = .001). Fair concordance was also reported for usefulness of pain indicators (W = .214, p = .002). Four of the five important indicators were the same as those identified in Round 1, where fluctuations in heart rate in Round 2 replaced agitation in Round 1. Increased heart rate from baseline and reduced oxygen saturation in Round 2 replaced agitation and nasolabial furrow in Round 1 for useful pain indicators. Inconsolability was rated the highest important and useful pain indicator for the severe risk group.\nDiscussion\nThis Delphi study resulted in expert consensus and achievement of item generation and reduction in the process of measurement development. In both rounds of the Delphi, consensus was demonstrated among raters as to the most important and useful pain indicators in infants at varying levels of risk for NI. The rankings were relatively similar across groups with the highest ranking indicators that were identified as important and useful for infants in the most severe risk group being inconsolability, facial grimace, brow bulge, eye squeeze, reduced oxygen saturation, increased heart rate from baseline and fluctuations in heart rate. These indicators are similar to the collection of behavioural and physiologic indicators found in some of the most validated measures of infant pain. Facial grimace is included in the Douleur Aiguë du Noveau-né (DAN[\n31\n]) a multidimensional behavioural measure, and in two composite pain measures, the Modified Postoperative Comfort Score [\n32\n] and the Echelle Douleur Incofort Nouveau-Né (EDIN[\n33\n]). The Premature Infant Pain Profile (PIPP) includes brow bulge and eye squeeze, two individual facial actions along with changes in oxygen saturation and heart rate [\n3\n,\n29\n]. The Modified Postoperative Comfort Score and the EDIN both measure consolability in the infant. Breau et al, [\n17\n] reported that health professionals might regard pain as more physiologically based in infants with NI compared to infants with lower risk for NI whose pain responses encompass both physiologic and behavioural indicators. Given the similarity of the findings from this study and existing measures, the question as to whether a new measure is required or whether an existing measure could be revised or expanded needs to be carefully considered.\nStrength of agreement between pain experts appeared to be higher in Round 1 compared to Round 2, where most of the experts demonstrated fair agreement when rating pain indicators for infants at varying risks of NI. There is a notable decline in scores in all 3 cohorts between Round 1 and Round 2 for both importance and usefulness as well as the decrease in concordance. The decline in scores is largely attributable to the decrease in the number of indictors from Rounds 1 to 2. The decrease in agreement may reflect the rater's difficulty in making finer rather than broader decisions (e.g. with less items). Conversely, it may reflect the uncertainty that researchers, who have expert knowledge of the importance and usefulness of pain responses but who may not have clinical expertise in directly observing the infants, have in evaluating indicators. Given that the indicators were fairly similar across the mild, moderate, and severe risk groups, one measurement tool might suffice for all infants at risk for NI; however, this dilemma demands that we incorporate the perspectives of both clinical experts and the responses of infants themselves as the \"gold standard\" in future research to arrive at an ultimate solution to this issue.\nConclusion\nWe have used a consensus methodology, the Delphi technique, as the first step in a comprehensive approach to measurement development and/ or validation for assessing pain in infants at risk for NI. The multidisciplinary and international participants were representative of experts in infant pain measurement research. When selected, study participants appeared to have a broad expertise in pain in infants and/ or children with NI; however, in some participants this expertise was less extensive according to participant self-ratings. As the co-investigators on this study had expertise in assessing and managing infants at risk for NI, they were not able to participate in this Delphi consensus exercise. The small number of potential participants reflects the number of available experts in this area of infant pain research. A broader sample of health professionals including physicians and pharmacists might have strengthened the validity of our findings.\nSpecified inclusion criteria for experts and defining our method for analysis strengthened the Delphi approach. Using electronic methods to allow ease of completing the Delphi exercise (distribution of surveys and reminder emails for completion of surveys) was time- and cost-effective, and provided easy access to the international participants [\n34\n]. However, this methodology did not provide us with detailed reasons for nonparticipation. Furthermore, as this study was exploratory in nature and the sample size was small, the results could be influenced by the opinions of outliers. As part of a larger study on pain in infants at risk for NI, parents were concurrently interviewed to obtain their perspectives on how they assessed and managed their infant's pain. Future research will include triangulation of the data from this Delphi consensus exercise with opinions of health care providers and actual infant responses to painful procedures to further develop a reliable and valid pain measure for infants at risk for NI.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nAll authors contributed to the design of the study, reviewed and approved the final manuscript. JY, JB conducted the statistical analysis. Interpretation of results was primarily conducted by BS, PM, JB, JY, SG.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
74
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nThe association between processes, structures and outcomes of secondary prevention care among VA ischemic heart disease patients\n\n**Article Abstract:**\n\nBackground\nHyperlipidemia and hypertension are well-established risk factors for recurrent cardiovascular events among patients with ischemic heart disease (IHD). Despite national recommendations, concordance with guidelines for LDL cholesterol and blood pressure remains inadequate. The objectives of this study were to 1) determine concordance rates with LDL cholesterol and BP recommendations; and 2) identify patient factors, processes and structures of care associated with guideline concordance among VA IHD patients.\nMethods\nThis was a cross sectional study of veterans with IHD from 8 VA hospitals. Outcomes were concordance with LDL guideline recommendations (LDL<100 mg/dl), and BP recommendations (<140/90 mm Hg). Cumulative logit and hierarchical logistic regression analyses were performed to identify patient factors, processes, and structures of care independently associated with guideline concordance.\nResults\nOf 14,114 veterans with IHD, 55.7% had hypertension, 71.5% had hyperlipidemia, and 41.6% had both conditions. Guideline concordance for LDL and BP were 38.9% and 53.4%, respectively. However, only 21.9% of the patients achieved both LDL <100 mg/dl and BP <140/90 mm Hg. In multivariable analyses, patient factors including older age and the presence of vascular disease were associated with worse guideline concordance. In contrast, diabetes was associated with better guideline concordance. Several process of care variables, including higher number of outpatient visits, higher number of prescribed medications, and a recent cardiac hospitalization were associated with better guideline concordance. Among structures of care, having on-site cardiology was associated with a trend towards better guideline concordance.\nConclusion\nGuideline concordance with secondary prevention measures among IHD patients remains suboptimal. It is hoped that the findings of this study can serve as an impetus for quality improvement efforts to improve upon secondary prevention measures and reduce the morbidity and mortality of patients with known IHD.\n\n**Article Body:**\n\nBackground\nHyperlipidemia and hypertension are prevalent and often co-existing conditions among patients with ischemic heart disease (IHD) [\n1\n]. Prior studies have found significant gaps in the achievement of nationally recommended low-density lipoprotein (LDL) cholesterol and blood pressure (BP) levels [\n2\n-\n5\n]. A basic principle of prevention is that intensity of risk reduction therapy should be adjusted to a person's overall risk [\n6\n]. Within 6 years of an initial event, up to one-third of patients will have a recurrent myocardial infarction, and almost 50% of women will be disabled with congestive heart failure [\n7\n]. In addition, the risk of a future IHD event, according to the Framingham risk estimates, is based on multiple factors including blood pressure level, cholesterol level, smoking status, and age [\n8\n]. Therefore, given the high absolute risk of recurrent cardiovascular events among IHD patients, studies addressing secondary prevention care should encompass multiple risk factors (e.g., hyperlipidemia and hypertension). However, prior studies assessing guideline concordance with secondary prevention measures have focused mainly on either hyperlipidemia or hypertension alone within any one study.\nTo improve secondary prevention care, factors associated with guideline concordance or non-concordance need to be further elucidated. One approach is to use the processes, structures and outcomes of care model [\n9\n] developed by Donabedian. He linked the three elements by stating that \"good structure increases the likelihood of good process, and good process increases the likelihood of a good outcome.\" This model can be used to identify specific factors that are associated with guideline non-concordance and these factors can serve as focus areas for quality improvement interventions. Accordingly, our objectives were to assess guideline concordance for secondary prevention care based on LDL cholesterol and blood pressure control and to identify specific patient, processes of care and structures of care factors associated with guideline concordance.\nMethods\nStudy population\nAll active patients with IHD enrolled in primary care clinics in any one of eight Pacific Northwest Veterans Affairs (VA) hospital facilities in Veterans Integrated Service Network (VISN) 20 were included in the study. Patients with IHD were identified by any one or more of the following International Classification of Diseases-9th revision (ICD-9) diagnosis codes in the 24 months before the index date (October 1, 2000), based on a previously validated algorithm: 410.x, 411.x, 412, or 414.x [\n2\n,\n10\n]. We searched for these diagnosis codes in the active problem list file of the VA computerized medical record, the outpatient care (OPC) file, and the patient treatment file (PTF). The OPC file contains data on all outpatient visits, whereas the PTF file contains data on all inpatient encounters. These files are part of the Consumer Health Information & Performance Sets (CHIPS) Data Warehouse [\n11\n], which is a relational database mirroring the clinical information system residing at each VA Medical Center and outpatient facility in VISN 20.\nActive patients were defined as being alive on October 1, 2000 (index date), and having at least one primary care clinic visit documented in the OPC file per year in each of the two previous years. A primary care visit was defined using the OPC file as any visit to one or more of the following clinics: General Internal Medicine, Women's Clinic, Primary Care/Medicine, or Geriatrics.\nIndependent variables\nClinical characteristics were defined by ICD-9 codes within either the OPC and/or PTF files within the 15 months before the index date: percutaneous coronary intervention (PCI), coronary artery bypass graft (CABG) surgery, diabetes, hypertension, hyperlipidemia, chronic obstructive pulmonary disease, peripheral vascular disease, cerebrovascular disease, myocardial infarction, congestive heart failure, malignancy, smoking status, and renal disease. The distance to medical center was calculated using the longitude and latitude coordinates of a patient's home address, based on their zip code and the longitude and latitude coordinates [\n12\n] of the medical center based on the medical center zip code.\nRecent cardiac hospitalization for an acute coronary syndrome (ACS) or coronary revascularization procedure(s) (i.e., PCI and/or CABG) were defined as occurring within the 15 months before the index date. Hospital admission for ACS was defined by a primary discharge diagnosis based on ICD-9 codes 410.x or 411.x in the PTF file. The number of outpatient clinic visits was aggregated over the 15 months before the index date.\nPatients were defined as having a current medication prescription for the following classes of medications if they had a prescription written or renewed within the last 15 months before the index date: aspirin, beta-blockers, angiotensin-converting enzyme (ACE) inhibitors or angiotensin receptor blockers, calcium channel blockers, diuretics, and 3-hydroxy-3-methylglutaryl coenzyme-A reductase inhibitors (statins). Patients frequently obtain aspirin over-the-counter rather than at VA pharmacies because of the lower cost and therefore rates of aspirin use are likely to be higher compared to the pharmacy prescription data. The total number of medications was based on the sum of all active prescriptions for the patient within 6 months from the beginning of the study period.\nFacility level data were obtained from the VISN Support Service Center website [\n13\n], a health care information and technical support organization serving the needs of the networks. Data on volume of primary care patients and visits were obtained for each of the eight facilities included in the analysis. Clinic volume was defined by the number of visits to the primary care clinics at each of the 8 hospitals in the study for the month of December 2000. The number of visits ranged from 3,821 to 18,613. On-site cardiologist was defined as the presence of a cardiologist based at a hospital. Five of the eight hospitals in the study had an on-site cardiologist.\nDependent variables\nThe primary outcomes of interest were achievement of: 1) LDL <100 mg/dl; and 2) BP <140/90 mm Hg [\n6\n,\n14\n], consistent with national guidelines as treatment targets for patients with underlying IHD. The combined outcome was defined as achievement of both LDL <100 mg/dl and BP <140/90 mm Hg. Any lipid level measured within 15 months before the index date was included, and the most current LDL level was used in the analyses. A LDL measurement was available for 83.4% of the patients. The LDL outcome variable was categorized into 3-levels of guideline concordance with each lower category indicating better concordance compared to a higher category: 0) LDL measurement and LDL <100 mg/dl, 1) LDL measurement, but LDL≥100 mg/dl, and 2) no LDL measurement.\nThe majority of patients (94.9%) had at least one BP measurement within the six months prior to the index date. Among patients with two or more BP measurements, the BP readings were averaged to get a better reflection of the true blood pressure. The BP outcome variable was also categorized into 3-levels of guideline concordance with each lower category indicating better concordance compared to a higher category: 0) SBP<140 and DBP<90 mm Hg; 1) SBP≥140 or DBP≥90 mm Hg, and 2) no BP measurement.\nStatistical analysis\nThe main objectives of our study were to identify specific patient, processes of care and structures of care factors associated with guideline concordance. We hypothesized \na priori \nthat the following patient factors would be associated with worse guideline concordance: older age, longer distance from home to medical center, diabetes and vascular disease (i.e. peripheral and/or cerebrovascular disease). For processes of care, we hypothesized \na priori \nthat the following factors would be associated with worse guideline concordance: higher total number of medications, lower number of outpatient visits and recent hospitalization for a cardiac event. Hospitalizations and cardiac procedures were categorized as process variables because the primary outcomes of interest were achievement of LDL and BP goals. Finally, for structures of care, we hypothesized \na priori \nthat the following factors would be associated with worse guideline concordance: lower primary care clinic volume and facility does not have an on-site cardiologist.\nIn our multivariable regression analyses, the cumulative logit model was used because there were 3 categories in both outcome variables. This model reports the odds ratio, which estimates the probability that each subject is in a lower (i.e., better concordance) category compared to a higher (i.e., worse concordance) category of guideline concordance.\nSince we were interested in the association between specific factors and guideline concordance, our multivariable risks models were constructed specifically to test the independent association between each of the hypothesis variables and guideline concordance, adjusting for baseline patient characteristics. To test the association between specific patient factors and guideline concordance, a baseline patient level risk model was constructed consisting of patient demographic factors, cardiac and non-cardiac co-morbidities as listed in Table \n1\n. Backward selection was performed (p < 0.05 to stay in model) to identify a parsimonious group of patient level factors associated with guideline concordance for risk adjustment. Then, each candidate independent variable of interest for hypothesis testing was individually entered into this baseline risk model to determine its association with the outcome of interest. Odds ratio and 95% confidence intervals are reported for each of the significant variables in the risk models.\nTable 1\nBaseline characteristics of the study population (N = 14,114)\nPatient characteristics\nN (%)\nAge, mean years (STD)\n*#\n68.1 (10.5)\nMale gender\n13,802 (97.8%)\nWhite race\n12,040 (85.3%)\nMarried*\n8,246 (58.4%)\nDistance from home to medical center, mean miles (STD)\n71.6 (203)\nPrior myocardial infarction*\n1,557 (11.0%)\nPrior percutaneous coronary intervention\n*#\n1,278 (9.0%)\nPrior coronary artery bypass graft surgery\n*#\n2,971 (21.0%)\nCongestive heart failure\n#\n2,954 (20.9%)\nDiabetes*\n4,939 (35.0%)\nHypertension\n*#\n10,093 (71.5%)\nHyperlipidemia\n*#\n7,856 (55.7%)\nObese (BMI>30 kg/m\n2\n)\n#\n6,048 (42.8%)\nSmoker\n2,909 (20.6%)\nChronic obstructive pulmonary disease\n#\n4,201 (29.8%)\nCerebrovascular disease\n#\n1,542 (10.9%)\nPeripheral vascular disease\n#\n1,613 (11.4%)\nRenal disease\n845 (6.0%)\nMalignancy\n#\n1,711 (12.1%)\n*Significantly associated with LDL guideline concordance\n#\nSignificantly associated with BP guideline concordance\nRisk models for the process of care analysis were built in a similar fashion as described for patient factors. A baseline risk model consisting of all significant patient-level factors identified in the prior analyses and the primary facility where a patient received care was constructed for risk adjustment. Then each of the process of care hypothesis variables was individually entered into the risk model to test the independent association between the variable and the outcome of interest.\nThe structures of care analyses were performed at the facility level using a hierarchical logistic regression model with a random facility effect that accounts for the clustering of patients by facilities. Models were estimated using maximum likelihood with the SAS procedure NLMIXED [\n15\n]. Multivariable hierarchical regression models were built to test the hypothesis of interest, accounting for clustering of patients within sites.\nBased on the multivariable analyses, we identified several patient factors and processes of care variables that were associated with guideline concordance. To enhance clinical interpretability of the results, we evaluated the association between the number of factors present versus guideline concordance, using the chi-square test to assess for a trend in this association.\nAll analyses were performed using SAS (Version 8.02, SAS Institute) [\n14\n]. The study was approved by the Colorado Multiple Institutional Review Board.\nResults\nOverall, 14,114 patients were identified as having IHD (Table \n1\n). The majority of the IHD patients were male and the mean age was 68.1 ± 10.5 (mean ± STD). These patients had a number of co-morbid conditions with 71.5% having a diagnosis of hypertension, 55.7% having a diagnosis of hyperlipidemia, and 41.6% having both of these conditions. They had frequent outpatient visits (mean 8.7 ± 7.0 visits) over a 15-month period and were prescribed multiple medications (mean of 11.2 ± 6.0 medications) (Table \n2\n).\nTable 2\nProcesses of care for the study population\nProcesses of care\nN (%)\nRecent hospitalization\nAcute coronary syndrome hospitalization\n534 (3.8%)\nPercutaneous coronary intervention\n213 (1.5%)\nCoronary artery bypass graft surgery\n284 (2.0%)\nOutpatient visit history\nTotal number of visits, mean (STD)\n8.7 (7.0)\nTotal number of primary care visits, mean (STD)\n7.3 (6.2)\nTotal number of specialty care visits, mean (STD)\n1.6 (3.3)\nPrimary care clinic visit\n13,425 (95.1%)\nCardiology clinic visit\n3,862 (27.4%)\nMedication history\nTotal number of medications, mean (STD)\n11.2 (6.0)\nAspirin prescription\n7,051 (50.0%)\nACEi or ARB prescription\n8,024 (56.8%)\nβ-blocker prescription\n8,209 (58.2%)\nCCB prescription\n5,238 (37.1%)\nDiuretic prescription\n6,650 (47.1%)\nAny lipid-lowering agent prescription\n9,020 (63.9%)\nStatin prescription\n8,060 (57.1%)\nGuideline concordance for LDL cholesterol and BP were suboptimal (Figure \n1\n). Only 38.9% of the patients had a LDL<100 mg/dl and 16.6% of the patients did not have a current LDL measurement. For BP control, 53.4% of the patients had a BP<140/90 mm Hg and 5.1% of the patients did not have a current BP measurement. When guideline concordance was based on both achievement of LDL<100 mg/dl and BP<140/90 mm Hg, only 21.9% of the patients met these targets. A significant proportion of patients, 29.5%, met neither LDL nor BP goals.\nFigure 1\nGuideline concordance for LDL cholesterol and blood pressure. * Patients were grouped into exclusive categories for \"LDL and BP at goal' and 'LDL or BP at goal'. Therefore, patients at both LDL and BP goal were not placed in the numerator for the category 'LDL or BP at goal'.\nThe multivariable findings are presented in Table \n3\n. For the LDL outcome, older age (OR 0.94, per 10 years; 95% CI 0.91–0.97; p < 0.01) was associated with worse guideline concordance. In contrast, diabetes (OR 1.44; 95% CI 1.35–1.54; p < 0.01), total number of prescribed medications (OR 1.01, per 1 medication; 95% 1.00–1.01; p < 0.01), total number of outpatient visits (OR 1.02, per 1 visit; 95% CI 1.01–1.02; p < 0.01), and recent cardiac hospitalization (OR 1.28; 95% CI 1.11–1.49; p < 0.01) were associated with better guideline concordance.\nTable 3\nMultivariable analyses for the association between the hypothesis variables and guideline concordance\n*#\nHypothesis variables\nLDL concordance (95% CI; p-value)\nBP concordance (95% CI; p-value)\nPatient factors\nAge (per 10 year increment)\n0.94 (0.91–0.97; p < 0.01)\n0.86 (0.83–0.89; p < 0.01)\nDistance to medical center (per 25 mile increment)\n0.99 (0.99–1.00; p = 0.19)\n0.99 (0.99–1.00; p = 0.30)\nDiabetes\n1.44 (1.35–1.54; p < 0.01)\n1.01 (0.94–1.08; p = 0.89)\nVascular disease\n&\n0.99 (0.91–1.07; p = 0.76)\n0.91 (0.84–0.99; p = 0.03)\nProcesses of care\nTotal medications (per 1 medication increment)\n1.01 (1.00–1.01; p < 0.01)\n1.01 (1.00–1.01; p = 0.03)\nTotal Visits (per 1 visit increment)\n1.02 (1.01–1.02; p < 0.01)\n1.02 (1.01–1.02; p < 0.01)\nRecent cardiac hospitalization\n1.28 (1.11–1.49; p < 0.01)\n1.34 (1.14–1.57; p < 0.01)\nStructures of care\nClinic volume\n1.01 (1.00–1.02; p = 0.76)\n0.82 (0.68–0.99; p < 0.01)\nOn-site cardiologist\n1.14 (1.00–1.30; p = 0.04)\n1.10 (0.99–1.22; p = 0.10)\n*The cumulative logit model estimates the probability that each subject is in a lower (i.e., better) category compared to a higher (i.e., worse) category of guideline concordance. The reported odds ratio is the probability of being in a lower category (i.e., better concordance) compared to a higher category (i.e., worse concordance). The outcome categories for LDL were the following: 0) LDL measurement and LDL <100 mg/dl, 1) LDL measurement, but LDL≥100 mg/dl, and 2) no LDL measurement. The outcome categories for BP were the following: 0) SBP<140 and DBP<90 mm Hg; 1) SBP≥140 or DBP≥90 mm Hg, and 2) no BP measurement.\n#Candidate covariates included all Table 1 and 2 variables.\n&Presence of cerebrovascular and/or peripheral vascular disease\nFor the BP outcome, older age (OR 0.86, per 10 years 95% CI 0.83–0.89; p < 0.01) and the presence of vascular disease, cerebrovascular and/or peripheral vascular disease (OR 0.91; 95% CI 0.84–0.99; p = 0.03) were both associated with worse BP control. In contrast, total number of medications (OR 1.01, per 1 medication; 95% CI 1.00–1.01; p = 0.03), total number of outpatient visits (OR 1.02, per 1 visit; 95% CI 1.01–1.02; p < 0.01), and recent cardiac hospitalization (OR 1.34; 95% CI 1.14–1.57; p < 0.01) were associated with better BP concordance.\nFor the structures of care analysis, there was a trend for an association between on-site cardiology and better LDL (OR 1.14; 95% CI 1.00–1.30; p = 0.04) and BP (OR 1.10; 95% CI 0.99–1.12; p = 0.10) guideline concordance. In contrast, higher clinic volume was associated with worse BP concordance (OR 0.82; 95% CI 0.68–0.99; p < 0.01).\nFinally, there was a graded inverse relationship between the number of factors present (i.e., age≥65, presence of vascular disease, lack of diabetes, and lack of recent cardiac hospitalization) and guideline concordance. LDL concordance ranged from 55% for those without any of the identified factors to 36% for those with all 4 factors (Figure \n2\n). Similarly, BP concordance ranged from 72% for those without any factors to 50% for those with all 4 factors. Achievement of both LDL cholesterol and BP goals (data not shown) ranged from 47% when no factors were present to 31% when all 4 factors were present (p < 0.01 for trend for all).\nFigure 2\nGuideline concordance based on the number of factors present. Factors: age≥65, presence of vascular disease, lack of diabetes, lack of recent cardiac hospitalization. p < 0.01 for trend for BP and LDL cholesterol concordance.\nDiscussion\nThe objectives of this study were to assess guideline concordance for secondary prevention care based on LDL cholesterol and blood pressure control and to identify specific patient, processes of care and structures of care factors associated with guideline concordance. We found that achievement of guideline recommendations for LDL (<100 mg/dl), and BP (<140/90 mm Hg) were 38.9%, and 53.4%, respectively. When concordance was assessed more globally, based on both LDL and BP control, less than one-quarter of patients were at target.\nSeveral factors were associated with guideline concordance based on our multivariable analyses. Patient factors including older age and vascular disease were associated with worse guideline concordance, while diabetes was associated with better guideline concordance. Processes of care measures, including higher total number of medications, higher total number of outpatient visits, and recent cardiac hospitalization were associated with better guideline concordance. Finally, clinic volume and on-site cardiology were associated with guideline concordance; however, given the small number of facilities (n = 8), and the fact that many of the structural characteristics were highly correlated with each other, definitive conclusions cannot be made regarding the structures of care variables.\nIn contrast to prior studies, we focused exclusively on patients with known IHD and assessed guideline concordance for both hyperlipidemia and hypertension. Prior studies evaluating concordance with guideline recommendations for secondary prevention measures have mainly focused on either LDL cholesterol or blood pressure in any one study and not both of these co-morbidities together. In previous studies, rates of achieving LDL <100 mg/dl among those with a LDL measurement have ranged from 30–50% [\n2\n,\n3\n,\n16\n] with significant variability depending on the patient population and study setting. For hypertension control, studies have not exclusively focused on patients with known coronary disease, who comprised only up to 30% of the patients in any one of the studies. In these studies, blood pressure was controlled in only approximately 40% [\n4\n,\n5\n,\n17\n] of the population. Pedrinelli, et al. recently evaluated global risk in a cohort of hypertensive patients and noted low rates of achievement of both LDL cholesterol and BP targets. Among the highest risk patients, those defined as having a 10 year risk for a IHD event >20% or those with known IHD, BP averaged 170/110 mm Hg and the mean LDL cholesterol was 148 mg/dl [\n18\n]. Together, these studies highlight a need to apply a global approach to risk factor modification, especially among those with known IHD, who are at high risk for recurrent cardiovascular events.\nRates of guideline concordance for LDL cholesterol and BP noted in the current study are similar to, if not better than those reported in the literature, and are consistent with prior studies supporting the quality of VA care compared to non-VA settings. For example, Jha, et al. compared VA to Medicare fee-for-service for multiple outpatient chronic conditions and found that the VA outperformed Medicare fee-for-service on 12 of 13 indicators in the year 2000 [\n19\n]. For lipid screening among diabetics, the rate was significantly higher among veterans compared to the Medicare fee-for-service patients (89% vs. 60%). Asch, et al. also noted better performance on many of the quality indicators for outpatient care among VA patients compared to a national community sample [\n20\n]. The adjusted rates of adherence to hyperlipidemia and hypertension indicators were 64% and 78%, respectively for VA patients compared to 53% and 65%, respectively for the community sample patients. These studies, along with the findings of the current study, thereby support a higher level of quality of care among veterans in the outpatient setting, although significant room for improvement remains.\nOverall, achievement of secondary prevention measures, both within and outside of the VA, remains suboptimal. Among patients above LDL goal, 38% of the patients were not prescribed any lipid-lowering medications and among patients above BP targets, 9% of the patients were not prescribed any antihypertensive medications in our study. Conditions such as hyperlipidemia and hypertension are often asymptomatic and less likely to be emphasized during outpatient visits that are frequently centered on acute problems and conditions. In addition to intensifying medical therapy (i.e., starting new medications or increasing dosages of existing medications), current processes of care can be modified to improve control of these measures. For example, computerized reminders directed at care providers [\n21\n,\n22\n] as a component of a multi-faceted intervention can be implemented to identify high-risk patients (e.g., high-risk based on the factors identified in this study) requiring aggressive treatment. In addition, outpatient visits, following the Chronic Care Model paradigm [\n23\n], can be planned to specifically focus on secondary prevention measures. These planned visits would allow care providers the necessary time to titrate therapy for these conditions. Similarly, disease management programs targeting secondary prevention measures can be established to complement usual care. Initial studies of disease management programs for various cardiovascular conditions [\n24\n] have been promising. Prospective rigorously designed studies are needed to determine whether changes to current care processes can improve LDL cholesterol and BP control among IHD patients.\nFurthermore, interventions directly targeting patients can be implemented to improve self-management and increase patient adherence to recommended therapies. Telehealth technologies, such as interactive voice response, the Internet or Health Buddies [\n25\n,\n26\n] (i.e., an in-home technology device) can be incorporated into routine patient follow-up. These technologies can increase patient contact with the healthcare system, without adding to clinic visits. Interactive voice response (IVR) technology has been shown to increase patient adherence with medications, as well as improve some intermediate outcomes such as blood pressure and glycemic control [\n25\n]. These telehealth technologies should be examined prospectively in clinical trials to determine if the addition of these technologies to usual care improves guideline concordance.\nThere are several potential limitations to this study. This was a 15-month cross sectional study and we cannot rule out the chance that the outcome (poor LDL or BP control) affected processes of care due to measurement overlap. However, our main objective was to identify an association between these factors and not to establish temporal associations between the independent and dependent variables. Second, we arbitrarily defined a timeframe to assess for the presence of outcomes. Patients could have had a measurement just prior to or after the defined time periods. The defined time periods however, were longer than guideline recommendations for follow-up of LDL cholesterol and BP [\n6\n,\n14\n] even among patients who have achieved target goals. Third, although the database included complete laboratory, pharmacy records, and visit histories from all Pacific Northwest VA facilities, information from outside the VA system was not available. Nevertheless, patients in the study had an average of 9 clinic visits during the study period and were prescribed an average of 11 medications and it was likely that we captured a significant proportion of all health care utilization by these patients. Lastly, the guideline targets used for the study were applicable to both patients with and without known IHD. The BP targets were SBP<140 and DBP<90 mm Hg [\n14\n], which are the same for patients without known IHD. Therefore, the blood pressure goals established for this study should be achieved in all patients regardless of ischemic heart disease status.\nConclusion\nWe found that less than one-quarter of patients with known ischemic heart disease have achieved both LDL cholesterol and BP targets as recommended by national guidelines. Patients at the highest risk for guideline non-concordance can be identified based on four factors, including age≥65, presence of vascular disease, lack of diabetes and lack of recent cardiac hospitalization. Quality improvement efforts are urgently needed to improve upon these secondary prevention measures to reduce the morbidity and mortality of patients with known ischemic heart disease.\nList of abbreviations\nACS: Acute Coronary Syndrome\nBP: Blood pressure\nCABG: Coronary Artery Bypass Graft\nDBP: Diastolic blood pressure\nIHD: Ischemic heart disease\nICD-9: International Classification of Diseases-9th revision diagnosis\nLDL: Low density lipoprotein\nOPC: Outpatient Care File\nPTF: Patient Treatment File\nPCI: Percutaneous Coronary Intervention\nSBP: Systolic blood pressure\nVA: Department of Veteran Affairs\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nAll authors contributed to the conception, design, and interpretation of the data. PMH performed the statistical analysis and drafted the article. All authors were involved in the revision. All authors gave final approval of the version to be published.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
75
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nHydralazine target: From blood vessels to the epigenome\n\n**Article Abstract:**\n\nHydralazine was one of the first orally active antihypertensive drugs developed. Currently, it is used principally to treat pregnancy-associated hypertension. Hydralazine causes two types of side effects. The first type is an extension of the pharmacologic effect of the drug and includes headache, nausea, flushing, hypotension, palpitation, tachycardia, dizziness, and salt retention. The second type of side effects is caused by immunologic reactions, of which the drug-induced lupus-like syndrome is the most common, and provides clues to underscoring hydralazine's DNA demethylating property in connection with studies demonstrating the participation of DNA methylation disorders in immune diseases. Abnormalities in DNA methylation have long been associated with cancer. Despite the fact that malignant tumors show global DNA hypomethylation, regional hypermethylation as a means to silence tumor suppressor gene expression has attracted the greatest attention. Reversibility of methylation-induced gene silencing by pharmacologic means, which in turns leads to antitumor effects in experimental and clinical scenarios, has directed efforts toward developing clinically useful demethylating agents. Among these, the most widely used comprise the nucleosides 5-azacytidine and 2'deoxy-5-azacytidine; however, these agents, like current cytotoxic chemotherapy, causes myelosuppression among other side effects that could limit exploitation of their demethylating properties. Among non-nucleoside DNA demethylating drugs currently under development, the oral drug hydralazine possess the ability to reactivate tumor suppressor gene expression, which is silenced by promoter hypermethylation \nin vitro \nand \nin vivo\n. Decades of extensive hydralazine use for hypertensive disorders that demonstrated hydralazine's clinical safety and tolerability supported its testing in a phase I trial in patients with cancer, confirming its DNA demethylating activity. Hydralazine is currently being evaluated, along with histone deacetylase inhibitors either alone or as adjuncts to chemotherapy and radiation, for hematologic and solid tumors in phase II studies.\n\n**Article Body:**\n\nReview\nHydralazine as an antihypertensive\nHydralazine, a potent arterial vasodilator that reduces peripheral resistance directly by relaxing the smooth muscle cell layer in arterial vessels, has long been used for management of hypertensive disorders and heart failure [\n1\n,\n2\n]; nonetheless, its current use is limited nearly to hypertensive disorders during pregnancy [\n3\n,\n4\n]. Despite numerous studies with the drug, its mechanism of action has remained unknown but it is suggested that hydralazine may function by either modulating the effect of purine-like compounds released from sympathetic nerve endings, and/or by producing an altered Ca\n2+ \nbalance in vascular smooth muscle cells [\n5\n-\n7\n]. The majority of its effects are confined to the cardiovascular system. Decrease in blood pressure after hydralazine administration is associated with a selective decrease in vascular resistance in coronary, cerebral, and renal circulation, with a lesser effect in skin and muscle. Hydralazine lowers peripheral vascular resistance equally in supine and upright positions; it also lowers pulmonary vascular resistance and increases cardiac output causing mild pulmonary hypertension. [\n1\n,\n2\n].\nHydralazine is well absorbed through the gastrointestinal tract, but systemic bioavailability is low. Because the acetylated compound is inactive, the dose necessary to produce a systemic effect is higher in fast acetylators. N-acetylation of hydralazine occurs in bowel and/or liver. Hydralazine's half-life is 1 h and systemic clearance of the drug is approximately 50 mL/kg/min. Hydralazine rapidly combines with circulating α keto-acid to form hydrazones, and the major metabolite recovered from the plasma is hydralazine piruvic acid hydrazone. This metabolite possesses a longer half-life than hydralazine but does not appear to be very active. Systemic metabolism is dependent on hydroxylation followed by conjugation with glucoronic acid in liver, which is not dependent on acetylation rate; therefore, half-life does not differ to a great degree between slow and fast acetylators [\n8\n]. Hydralazine peak concentration in plasma and peak hypotensive effect of the drug occurs within 30–120 min of ingestion. Although its half-life in plasma is approximately 1 h, duration of the hypotensive effect can last as long as 12 h; there is no clear explanation for this discrepancy. The antihypertensive effect of hydralazine has no clear dose-response effects. The dose varies from 10 mg four times a day to 50 mg four times daily. After stabilization with multiple daily doses, a twice-daily dose regimen can be effective. Slow acetylators require a lower dose. For heart failure, recommended doses are higher (up to 800 mg daily or more); as a rule, 10–100 mg four times a day can be effective [\n9\n].\nTwo types of side effects occur after hydralazine use. The first type, an extension of hydralazine's pharmacologic effect, includes headache, nausea, flushing, hypotension, palpitation, tachycardia, dizziness, and angina pectoris; hydralazine can produce salt retention with congestive heart failure development. The second type of side effect is caused by immunologic reactions, of which the drug-induced lupus-like syndrome is the most common [\n8\n,\n9\n].\nCancer epigenetics\nEpigenetics can be defined as the study of mitotically and/or meiotically heritable changes in gene function that can not be explained by changes in DNA sequence. There are two epigenetic systems that affect animal development and fulfill the heritability criterion: DNA methylation, and the polycomb-trithorax group (Pc-G/trx) protein complexes; nevertheless, post-transductional histone modification possesses some attributes of an epigenetic process and as such are studied within this field [\n10\n]. Epigenetics is a well-established phenomenon that plays a major role in a diversity of biological processes such as embryonic development, cancer biology, and immune system response, among many others. The two most widely studied epigenetic changes are DNA methylation and histone acetylation; however, the picture is much more complicated than this, with new players coming into the scenario; these include, among others, the RNA interference phenomenon, proven to be implicated in transcriptional silencing through small duplex RNA molecules that recruit silencing complexes to the chromatin, and the BORIS (Brother of the Regulator of Imprinted Sites)/CTCF gene family, which is involved in epigenetic reprogramming events [\n11\n,\n12\n].\nDNA methylation\nDNA methylation is a covalent chemical modification that mainly occurs at the cytosine ring, resulting in the addition of a methyl\nCH3 \ngroup at the carbon 5 position. Because DNA is made up of four bases, 16 possible dinucleotide combinations can occur; hence, the CpG dinucleotide should have a frequency of 6%. Nonetheless, actual presence is only 5–10% of its predicted frequency. The human genome is not uniformly methylated and contains regions of unmethylated interspersed with methylated segment regions. In contrast to the remainder of the genome, smaller regions of DNA – denominated CpG islands, ranging from 0.5–5 kb, and occurring on average every 100 kb – possess distinctive properties. These regions are unmethylated, GC-rich (60–70%), have a ratio of CpG:GpC of at least 0.6, and thus show no suppression of dinucleotide CpG frequency. Approximately one half of all genes in humans have CpG islands, these present in both housekeeping genes and in genes with tissue-specific patterns of expression [\n13\n,\n14\n].\nAt least three functional DNA methyltransferases (DNMT) have been identified; the most abundant is DNMT1, or maintenance DNMT. This methyltransferase enzyme copies pre-existing methylation patterns onto the new DNA strand during DNA replication to ensure clonal transmission of lineage-specific DNA methylation patterns in a mammalian genome during replication. Thus, DNMT1 is targeted to replication foci, interacts with proliferating cell nuclear antigen, and favors methylating the hemimethylated form of CpG sites. It has been demonstrated that DNMT1 methylates hemimethylated DNA with high processivity and a fidelity of >95% on one strand of double-stranded DNA during a single processive run; nevertheless, DNMT1 methylates unmethylated DNA with much less processivity, suggesting that these inherent enzymatic properties of Dnmt1 play an essential role in the faithful and efficient maintenance of methylation patterns in the mammalian genome [\n15\n,\n16\n].\nOther known functional methyltransferases include DNMT3a and DNMT3b, which are responsible for \nde novo \nmethylation during embryogenesis; thus, these have been classified as \nde novo \nmethyltransferases [\n17\n]. These enzymes are mainly responsible for introducing cytosine methylation at previously unmethylated CpG sites by at least three possible means: first, DNMT3 enzymes themselves might recognize DNA or chromatin via specific domains; second, DNMT3a and DNMT3b might be recruited through protein-protein interactions with transcriptional repressors or other factors, and third, the RNA-mediated interference (RNAi) system might target \nde novo \nmethylation to specific DNA sequences [\n18\n].\nIn addition to DNMTs, the machinery of methylation includes demethylases, methylation centers that trigger DNA methylation, and methylation protection centers [\n19\n]. The effect of DNA methylation on gene transcription can be observed only within the context of chromatin remodeling players. DNA methylation can interfere directly with transcriptional factor binding, thus inhibiting replication [\n20\n], in addition to the ability of DNA methyltransferases DNMT1, DNMT3a, and DNMT3b to repress transcription in a methylation-independent manner [\n21\n]. Methyl-CpG-binding proteins, which can recognize methylated DNA, have been shown to associate with large protein complexes containing HDACs and chromatin-remodeling activities. It has also been suggested that DNA methylation could produce gene silencing by methyl-binding domain proteins that recruit histone methyltransferases, which methylate lysine 9 in histone H3 and subsequently repress gene transcription [\n22\n]. As a result, histones are deacetylated and gene transcription repressed.\nHistones and post-translational modifications\nHow double-strand DNA is packaged into the dynamic structure of chromatin is crucial for the transcriptional control process by regulating transcription factor accessibility to DNA regulatory sequences. Chromatin is constituted of nucleosomes, which are comprised of 146 base pairs of DNA wrapped around a core of two copies each of histones H2A, H2B, H3, and H4. The N-terminal tails of histones, which undergo post-translational modifications such as acetylation, methylation, ubiquitination, phosphorylation, and sumoylation, protrude from their originating nucleosome and may contact adjacent nucleosomes as well as chromatin-associated proteins. These interactions are responsible, at least in part, for regulating chromatin structure [\n23\n]. The most widely studied modification is acetylation, which plays diverse roles in nucleosome regulation. Lysine acetylation, for example, may decrease histone-DNA interaction and promote accessibility of DNA for transcription activation. Moreover, acetylation specifically can also regulate DNA replication, histone deposition, and DNA repair by mechanisms of recruiting proteins that have an acetyl-lysine binding module, the bromodomain, a 100-amino-acid conserved sequence found in many chromatin-associated proteins. Thus, bromodomains in histone acetyltransferases and nucleosome remodeling complexes orchestrate the succession of chromatin regulators at a target site [\n24\n,\n25\n]. Overall, lysine acetylation results in chromatin decompactation, greater access of DNA to transcription factors, and the presence of a transcriptionally active genomic locus. This post-translational modification depends on the net local balance between histone acetyl transferase (HAT) and histone deacetylase (HDAC) activities. In general, hyperacetylation is found in more decondensed euchromatin, whereas hypoacetylation is characteristic of more condensed heterochromatin [\n26\n,\n27\n].\nEpigenetic alterations and cancer\nAbnormalities in DNA methylation have long been associated with cancer. Both hypo- and hypermethylation play prominent roles in carcinogenesis, and their contribution exhibits poorly defined boundaries. It has been known for some time that both alterations co-exist in cancer cells: malignant tumors exhibit global hypomethylation and regional hypermethylation. Whether one must precede the other or whether both should begin at the same time remains to be elucidated. In terms of carcinogenesis, initial observations were conducted on hypomethylation [28 29]; later, discovery of regional hypermethylation as a means to silence tumor suppressor gene expression gained the most attention [\n30\n].\nSilencing of tumor suppressor genes\nObservations that tumor suppressor gene function can be disrupted not only through structural changes (mutation and deletion) but also by lack of promoter hypermethylation-associated expression positioned tumor suppressor gene epigenetic silencing as a well-established oncogenic process [\n31\n]. The first suppressor gene known to be hypermethylated and silenced was \nRb \n[\n32\n]. This finding was soon followed by multiple publications describing similar findings for a variety of tumor suppressor genes, among them \np16\n, \nMLH1\n, \nVHL\n, and \nE-cadherin \n[\n33\n]. Whether gene promoter hypermetylation is the cause or consequence of tumor suppressor gene silencing remains a matter of controversy; nevertheless, these views are not mutually exclusive. That DNA methylation is causal has been shown by the ability of diverse pharmacologic compounds and molecular techniques to reactivate gene expression upon inhibition of DNA methylation in cancer cells [\n34\n]. On the other hand, other findings suggest that hypermethylation-induced gene silencing could be associated with changes that determine gene expression, such as chromatin modification, so that methylation aids in maintaining the gene's silenced status. Strong support for the second view has derived from experiments showing that histone H3 lysine 9 methylation – that is, chromatin modification – occurred along with \np16 \nre-silencing in absence of DNA methylation in cells in which \np16 \nhad previously been activated by DNA methyltransferase knock-out [\n35\n], and by data demonstrating \np16 \nsilencing in mammary epithelial cells that had escaped senescence and demethylated the promoter [\n36\n].\nSilencing of genes involved in tumor-host interaction\nAlthough cancer cells are less immunogenic than pathogens, the immune system is clearly capable of recognizing and eliminating tumor cells. However, tumors frequently interfere with immune response development and function through several mechanisms such as loss of antigen processing and presentation, the Fas counterattacking system, escaping from death receptor signaling, engaging in inhibition-blocking activation, suppression of antitumor responses by regulatory T cells, and tumor-induced immune suppression [\n37\n]. Current research demonstrates that epigenetic defects are involved in at least some mechanisms that preclude mounting a successful host-antitumor response, including the HLA system, tumor-associated antigens, and accessory/co-stimulatory molecules.\nAmong tumor-associated antigens, testis-associated genes (CTA) are a sub-group of tumor antigens with restricted expression in testis and malignancies; CTA include the MAGE, NYESO, and SSX gene families and the GAGE/PAGE/XAGE superfamilies [\n38\n]. Distinct CTA can encode for different antigenic peptides that are presented to the immune system in association with various human leukocyte antigens (HLA), HLA class I or HLA class II allospecificities, eliciting both cytotoxic T lymphocytes (CTL) and humoral immune responses. De Smet et al., first showed a link between genomic DNA hypomethylation and \nMAGE-1 \ngene expression [\n39\n], and subsequent studies demonstrated direct correlation between demethylation of CpG at the promoter of several cancer testis antigen coding genes with their expression [\n40\n-\n43\n]. Surprisingly, 5-aza-2'-deoxycytidine demethylation treatment led to induction of \nMAGE-, GAGE-, PAGE-\n, and \nXAGE-\ntype genes in tumor cells but not in normal cells [\n44\n].\nPresentation of antigens within the context of HLA molecules is crucial both during T-cell priming and the effector phase of an adaptive immune response. Alterations in antigen processing and presentation are commonly observed in malignancies. In tumors, the antigen presentation pathway is commonly disrupted as a consequence of the mutations and/or deletions of one or several genes encoding components of the antigen-processing machinery, including proteasomal subunits and transporters peptides; thus, complete HLA loss is a common event in several murine and human tumors [\n45\n]. As for CTA, DNA methylation participates in regulation of the expression of the three classes of human leukocyte antigen class I antigens: HLA-A; HLA-B, and HLA-C, which are CpG-rich at their gene promoters. Nie et al. showed down-regulation of HLA class I antigens in esophageal carcinoma as a common mechanism for transcriptional inactivation caused primarily by DNA hypermethylation [\n46\n], as well as in melanoma, where 5-aza-2'-deoxycytidine significantly enhances the constitutive expression of HLA class I antigens, of HLA-A1 and -A2 alleles, and of the co-stimulatory molecule, intercellular adhesion molecule-1, and lymphocyte function-associated antigen-3 [\n47\n]. Further, it was shown that 5-aza-2'-deoxycytidine leads to re-expression of HLA class I antigens and restoration of antigen-specific CTL response in melanoma cells [\n48\n]; likewise, it has been shown that methylation-induced silencing of the class II transactivator (CIITA) leads to lack of HLA-DR induction in hematopoietic tumor cells and solid tumors such as gastric and colorectal carcinomas [\n49\n,\n50\n].\nCurrent epigenetic therapy agents\nReactivation of tumor suppressor genes silenced by an epigenetic mechanism such as gene promoter methylation is a very attractive molecular target for cancer therapy. There are several demethylating agents currently being evaluated in pre-clinical and clinical studies (Table \n1\n). The classical demethylating agents comprise the analogs of deoxycytidine, including 5-azacytidine, 5-aza-2-deoxycytidine, 1-β-D-arabinofuranosil-5-azacytosine, and dihydro-5-azacytidine. 5-azacytidine and its analog 5-aza-2-deoxycytidine are the most frequently studied and were developed over 30 years ago as classical cytotoxic agents, but were subsequently discovered to be effective DNA methylation inhibitors [\n51\n]. These were tested as such in several phase II studies against solid tumors, demonstrating very modest activity [\n52\n]. Contrariwise, their antileukemic activity was very promising, and both are being revived due to their demonstrated inhibitory activity upon DNA methylation and gene-reactivating function.\nTable 1\nAgents targeting DNA methylation and histone deacetylase in preclinical and clinical development\nDNA methylation inhibitors\ndeoxycytidine analogs:\n5-azacytidine, 5-aza-2-deoxycytidine, 1-β-D-arabinofuranosil 5-azacytosine, dihydro- 5-azacytidine\nnucleic acid-based:\nMG98 antisense oligonucleotide\ncytidine deaminase analogs:\nzebularine\nnon-nucleoside analogs:\n(-)-epigallocatechin-3-gallate, procaine, procainamide, hydralazine, RG108, psammaplins\nHistone deacetylase inhibitors\nSmall molecular weight carboxilates:\nsodium butyrate, valproic acid, sodium phenylbutyrate and pivaloyloxymethyl butyrate\nHydroxamic acids:\nSAHA, trichostatin A, SBHA\nBenzamides:\nCI-994, MS-275\nEpoxyketones:\ntrapoxin B, 2-amino-8-oxo-9,10-epoxydecanoic acid\nCyclic peptides:\napicidin, depsipeptide\nHybrid molecules:\nCHAP 31, CHAP50\nMiscellaneous:\nCyclostellettamines, Carbamazepine\nAdapted from reference 106.\nCurrently, 5-azacytidine is Federal Drug Administration (FDA)-approved for use against myelodysplastic syndrome, and 5-aza-2-deoxycytidine is also being tested in myelodysplastic syndrome and in a variety of solid tumors due to its DNA demethylating properties [\n53\n]. In particular, 5-aza-2-deoxycytidine when infused for 10 days proved to be well-tolerated and induced responses in 65% of 50 patients with acute myelogenous leukemia, myelodysplasia, chronic myelogenous leukemia, and acute lymphocytic leukemia [\n54\n]. Despite poor activity against solid tumors of these nucleoside analogs, it is remarkable that proof of the concept concerning the ability of DNA methylation compound inhibitors to demethylate and reactivate tumor suppresor gene expression has been shown in solid tumors [\n55\n]. Whether or not the reactivating effect can translate into a clinical response on its own or in combination with classical cytotoxic therapies remains to be demonstrated.\nAs a second category of demethylating agents, there is the antisense oligonucleotide MG98 against the 3' untranslated region of \nDNMT1 \nmRNA that codes for the enzyme DNA methyltransferase 1, which is responsible for DNA methylation maintenance [\n56\n]. This agent has shown an ability to inhibit \nDNMT1 \ngene expression without affecting other \nDNMTs \nand to cause demethylation with \np16 \nre-expression in bladder and colon cancer cell lines, as well as to produce tumor growth inhibition in nude mice bearing human lung and colon xenografts [\n57\n]. MG98 has been evaluated in a phase I trial in patients with advanced or refractory solid tumors and has demonstrated its tolerability, despite the fact that dose-limiting toxicities of transaminitis, thrombocytopenia, and fatigue prohibited higher doses. MG98's molecular efficacy was demonstrated by producing a \nDNMT \nmRNA level decrease in the peripheral blood cells in six of 10 patients [\n58\n].\nThe fact that deoxycytidine analogs, like current cytotoxic agents, are not only carcinogenic but also exhibit neutropenia as their dose-limiting toxicity even when used at doses required for demethylation [\n59\n] has renewed interest in finding effective and less toxic demethylating agents. Zebularine is a new oral cytidine analog originally synthesized as a cytidine deaminase inhibitor that has shown to cause demethylation and reactivation of a silenced and hypermethylated \np16 \ngene in human bladder tumor cells grown in nude mice. Zebularine was also shown to be minimally cytotoxic \nin vitro \nand \nin vivo \nand can be administered continuously at a lower dose to maintain demethylation for a prolonged period, possible only because of its low-toxicity profile; to date, there are no results of clinical trials with this agent [\n60\n]. Within this class of so-called \"non-toxic and orally administered agents\", there is the green tea major polyphenol (-)-epigallocatechin-3-gallate (EGCG) that demonstrated to be an effective \nDNMT \nactivity inhibitor at micromolar concentrations and that was able to demethylate and reactivate expression of several tumor suppressor genes such as \np16\n, \nRAR-β2\n, and \nMGMT \nin cancer cell lines [\n61\n].\nThere is another class of so-called \"old drugs\" that includes hydralazine. The demethylating activity upon gene promoters of tumor suppressor genes of these compounds was recently demonstrated. Procainamide, a non-nucleoside inhibitor of DNA methyltransferases approved for treatment of cardiac arrhythmias, can demethylate the \nGSTP1 \npromoter, a common somatic genome change in human prostate cancer, and reactivates expression of the gene \nin vitro \nand in nude mice [\n62\n]. A related drug, procaine, possesses the ability to demethylate and reactivate tumor suppressor gene expression, such as the \nRARβ2 \ngene, in a breast cancer cell line, an effect accompanied by growth-inhibitory actions [\n63\n].\nHydralazine as a demethylating agent\nClues to underscoring hydralazine's DNA demethylating property have derived from its ability to induce a lupus-like syndrome in connection with studies demonstrating DNA methylation disorder participation in systemic lupus erythrematosus (SLE).\nLupus-like syndrome induced by hydralazine\nMore than 80 drugs have been associated with drug-induced lupus erythrematosus [\n64\n]; at least 39 of these are currently in use [\n65\n]. Only two of these, procainamide and hydralazine, are considered as high risk for induction of the syndrome, with up to 8 and 20% frequency respectively, during 1 year of therapy at currently employed doses [\n64\n,\n65\n]. Hydralazine was introduced as an antihypertensive drug in 1952, and the first case of hydralazine-induced lupus was reported soon thereafter [\n66\n]. Prevalence of slow acetylators among patient populations at risk for developing lupus erythrematosus is obviously much greater than the disease prevalence. Only 1–3% of populations of which at least 50% are slow acetylators develop hydralazine-induced lupus. In a study of 26 patients with hydralazine-induced lupus, 25 were slow acetylators, with a 4:1 ratio of females to males; this discrepancy may be explained by the fact that additional genetic traits are important in predisposing individuals to lupus [\n67\n,\n68\n].\nClinical features and laboratory manifestations of drug-induced lupus are similar to those of lupus erythrematosus. Symptom onset can be slow or acute, although an interval of 1–2 months typically occurs before diagnosis is made. As with idiopathic lupus, the most commonly observed abnormality is the presence of anti-nuclear antibodies, and these autoantibodies usually react with chromatin; however, unlike in patients with lupus, anti-chromatin antibodies rarely react with native (double-stranded DNA. In summary, neither the clinical nor the serologic picture are specific for drug-induced or idiopatic lupus; hence, the key (albeit retrospective) diagnostic tool is the observation that drug-induced lupus symptoms usually resolve within days to weeks after discontinuing the offending drug without introduction of anti-inflammatory medications [\n64\n].\nMechanisms of hydralazine-induced lupus syndrome\nEarly studies suggested that interaction between hydralazine with thymidine and deoxycytidine was at least partly responsible for initiating the syndrome [\n69\n], and that an immune response to hydralazine may be important in human hydralazine-induced SLE [\n70\n].\nAdditional recent studies have strongly supported that SLE pathogenesis is strongly related with disorders in DNA methylation, beginning with an observation by Richardson et al. that CD8 T cells treated with 5-aza-cytidine – but not with hydroxyurea, a DNA synthesis inhibitor – re-expressed CD4, implying that DNA methylation may be one of the mechanisms involved in thymocyte maturation [\n71\n]. Subsequently, the authors showed that the 5-azacytidine-treated cloned, CD4 IL-2- dependent antigen-specific T cells lost the requirement for antigen and could be activated by autologous macrophages [\n72\n]. Autoreactivity correlated with over-expression at a transcriptional level of lymphocyte function-associated antigen-1 (LFA-1) [\n73\n], and T cells overexpressing this molecule become auto-reactive and caused a lupus-like disease in syngeneic mice [\n74\n] as it did in mice injected with syngeneic normal murine T cells treated with demethylating drugs [\n75\n,\n76\n]. Latter, it was shown that 5-azacytidine, procainamide, and hydralazine induce CD11a promoter demethylation and re-expression [\n77\n]. Further, it has been demonstrated that patients with rheumatoid arthritis and SLE had DNA hypomethylation of T cells [\n78\n], which correlates with decreased DNA methyltransferase enzyme activity and DNMT1 mRNA due to inhibited ERK pathway signaling [\n79\n]. In addition, lymphocytes from patients with lupus had at least over-expression and promoter demethylation of genes coding for CD11a [\n80\n] and CD70, a B cell co-stimulatory molecule [\n81\n]. In summary, these studies indicate that DNA hypomethylation and deregulated expression of molecules including LFA-1 and CD70 are fundamental for the pathogenesis of both drug-induced and idiopathic human lupus.\nHydralazine in demethylating and reactivating tumor suppressor genes\nThese observations, unrelated to the field of DNA methylation in cancer and demonstrating that hydralazine possesses DNA demethylating activity [\n82\n], led to testing the hypothesis that hydralazine, by virtue of its DNA methylation inhibitory activity, could restore tumor suppressor gene re-expression by relieving hypermethylation at the gene promoter. To that end, demethylation and re-expression of tumor suppressor genes, estrogen receptor, and \np16, RARβ\n, which are methylated in MDA-231, T24, and MCF-7 cell lines, respectively, were studied. Treatment of these cell lines with hydralazine at 10 μM for 5 days led to gene promoter demethylation at these genes, which correlated with gene re-expression at the level of RNA and protein levels (Figures \n1\n and \n2\n); in addition, it was shown that the reactivated gene product was functional. Hydralazine's gene-demethylating and -reactivating effects were also observed for the estrogen receptor gene in estrogen receptor-negative MDA231 cell-xenographed mice treated for 7 days with hydralazine by intraperitoneal (i.p.) route at doses equivalent to those observed in hypertensive patients [\n83\n] (Figure \n3\n).\nFigure 1\nMethylation analysis of the ER, RARβ, and p16 genes. \nA\n, G is undigested genomic DNA as positive control, H is HpaII, and M is MspI. The band in H of control lanes indicates lack of digestion with HpaII and, therefore, methylation of untreated MDA-231 cells. \nB \nand \nC \nshow the analysis by methylation-specific PCR of RARβ and p16 genes in MCF-7 and T24 cells. W is wild type, M is methylated primers, and U is unmethylated primers. D and E show a time course experiment of RARβ and p16 gene demethylation over 5 days on the MCF-7 and T24 cells, respectively. (Reproduced with permission from the AACR. Ref. 83. \nClin Cancer Res \n2003, \n9\n:1596–1603).\nFigure 2\nExpression of the mRNA and proteins of \nA\n, ER (MDA-231); \nB\n, RARβ (MCF-7); and \nC\n, p16 (T24) genes by RT-PCR and Western blot. The positive control (+ctr) for A is MCF-7, for B is MDA-231 exposed to 5-aza-CdR/atRA, and for C is HeLa cells. (Reproduced with permission from the AACR. Ref. 83. \nClin Cancer Res \n2003, \n9\n:1596–1603).\nFigure 3\nAnalysis of methylation and product expression of the ER gene in nude mice. \nA \nshows that the tumor of control mice (CTR lanes) was methylated as shown by the band in the Lane H indicating no digestion with HpaII. The band disappeared with the treatment with 5-aza-CdR and hydralazine, which indicates gene demethylation. In PROC (procainamide) lanes, the band is absent in MspI but is very weak in HpaII, indicating that was only partially demethylated; \nB \nand \nD \nare the product expression by RT-PCR and Western blot. In both cases, the intensity of bands in procainamide is weaker, correlating with a partial demethylation, (\nC \nand \nE \nare the loading controls, GAPDH and actine respectively). G is undigested genomic DNA. (Reproduced with permission from the AACR. Ref. 83. \nClin Cancer Res \n2003, \n9\n:1596–1603).\nWith the aim of explaining hydralazine's demethylating effects, we assessed the structural and electronic properties between hydralazine and methyltransferase by modeling the most stable conformation of hydralazine and the pocket at the active site of the enzyme. Results indicate the existence of a high-affinity interaction between hydralazine and the DNA methyltransferase. The residues Lys 162 and Arg 240 within the enzyme active site demonstrated four interacting points with hydralazine (Figure \n4\n) at distances between these residues and hydralazine nitrogen atoms not exceeding 4A°. These interactions are energetically stable, supporting that hydralazine may inhibit DNA methyltransferase [\n84\n]. These results from modeling have been confirmed by experiments demonstrating the ability of hydralazine at concentrations between 10 and 20 μM to inhibit DNA methylation in an \nin vitro \nDNA methyltransferase assay (Figure \n5\n). It remains debatable whether or not hydralazine directly inhibits DNA methyltransferase enzymatic activity. In fact, Richardson's group failed to demonstrate enzymatic inhibition \nin vitro \nwith hydralazine; instead, the authors reported that hydralazine decreased RNA methyltransferase 1 and 3a expression in a similar manner to PD98059, a mitogen-activated protein kinase kinase (MEK) inhibitor, this suggesting that hydralazine does not directly inhibit DNA methyltransferase enzymatic activity [\n85\n]. These discrepancies with regard to hydralazine's precise mechanism of action as DNA methylation inhibitor may stem from the different DNA methyltransferase assays used. Richardson's group employed a methyltransferase assay with a partially purified enzyme obtained from Jurkat T cell lysates assayed upon hemimethylated double-stranded oligonucleotides and \n3\nH-AdoMet [\n85\n], whereas our group utilized an assay based on lack of DNA restriction after the DNA substrate was treated with M. SssI methylase enzyme; this latter assay has been used recently to characterize the demethylation inhibitory activity of newer demethylating compounds [\n86\n]. Nevertheless, the issue concerning this direct inhibition by hydralazine on the enzyme needs to be further addressed. It is remarkable, however, that our group likewise Richardson's group, also have observed decreased expression of DNMT1 and DNMT3a, but no DNMT3b mRNA by RT-PCR in MCF-7 cells after treatment with hydralazine (Figure \n6\n).\nFigure 4\nDocking between the enzyme DNA methyltransferase and hydralazine showing the residues at the pocket (Lys 162 and Arg 165) that interact with the hydralazine molecule (Modified from ref. 84. \nLett Drug Design Discov \n2005, \n2\n:282–286).\nFigure 5\nIn \nin vitro \nmethyltransferase assay of hydralazine. There was no digestion with HpaII (lanes H, with 0 and 5 μM of hydralazine) indicating full methylation. Starting at 10 μM of hydralazine, bands in the lanes digested with HpaII (H) are visible, and at 20 μM the pattern of bands in HpaII (H) and MspI (M) digestions is similar indicating full demethylation. (MW: molecular weight). The substrate DNA for the \nin vitro \nmethylation assay was a 1112 bp fragment of the type I Human Herpes Simplex virus tymidine kinase gene which has a high GC content. The methylation reaction contained 1 μg of substrate DNA and 10 units of M.SssI methylase (0.5 μmol/L, New England Biolabs, Beverly, MA) in a final volume of 30 μL. Hydralazine was added to final concentrations of 0, 5, 10, 15, and 20 μmol/L starting two hours before adding the M.SssI enzyme for the methylation reaction. Reactions were done at 37°C for 2 hours. After completion, the reaction the DNA was purified using the rapid PCR Purification system (Ijamsville, MD). Then, equal volumes of extracted DNA for each sample were placed in two separated eppendorf tubes for restriction enzyme digestion (one tube with HpaII and the other with MspI) both from New England Biolabs. Each reaction contained 10 U of the enzyme, in a final reaction volume of 50 μL at 37° for 3 hours. After digestion, samples were reduced to dryness by speedvac concentration and redissolved in 10 μL of ddH20 and then loaded into a 2% Tris-borate EDTA agarose gels for electrophoresis.\nFigure 6\nExpression of DNMT1 and DNMT3a in MCF-7 cells. The expression of DNMT1 and DNMT3a mRNA is decreased in MCF-7 cells treated with hydralazine. The lower band intensity was confirmed by densitometric (right) analysis, (control is untreated cells). MCF-7 cells were growth arrested for 48 hours by serum deprivation, then treated for 24 hours with hydralazine at 10 μM and then RNA extracted for analysis. Reverse transcription was carried out as previously described [110] using random hexamers, superscript II reverse transcriptase (Life Technologies) and 2.5 μg of total RNA as recommended by the manufacturer in a total volume of 50 μL. One microliter of RT reaction was used for subsequent PCR amplification for each of the desired transcripts with dNTPs and Amplitaq (Applied Biosystems). Primer sequences used were as follows: DNMT1 sense 5-gat cga att cat gcc ggc gcg tac cgc ccc ag-3 and antisense 5-atg gtg gtt tgc ctg gtg c-3. DNMT3a sense 5-ggg gac gtc cgc agc gta cac-3 and antisense 5-cag ggt tgg act cga gaa atc g-3. Amplification conditions were: 94 C° for 5 min 1 cycle; 94 C° 30 sec, (58°C for DNMT1 and 65°C for DNMT3a) annealing temperature for 1 min, and 72 C° for 30 sec, 35 cycles.\nA recent study from the Jones group compared the DNA-methylating and gene-reactivating activity of 5-aza-2'-deoxycytidine against non-nucleoside inhibitors (-)-epigallocatechin-3-gallate, hydralazine, and procainamide. These authors found that 5-aza-2-deoxycytidine is far more effective both in its DNA methylation inhibitory activity and in its ability to reactivate methylation-silenced genes in cancer cells [\n87\n]; nonetheless, the authors failed to reproduce the findings obtained by the three independent researcher groups who reported the effect of these non-nucleosides upon DNA methylation. Contrariwise, in a recent report the ability of hydralazine to demethylate and reactivate estrogen receptor gene expression was confirmed [\n88\n].\nAntitumor efficacy in pre-clinical hydralazine and valproic acid models\nDue to the well-known synergistic effect of DNA methylation and histone deacetylase inhibitors on gene re-expression and antitumor effects, the combined effect of hydralazine and valproic acid has been investigated in pre-clinical models. Results demonstrate that treatment with these drugs in combination possesses a strong growth inhibitory effect in several cell lines tested. Nevertheless, hydralazine alone at the concentration tested had no or small growth-inhibitory properties. With the exception of 5-aza-2'-deoxycytidine, a classical cytotoxic agent with demethylating properties [\n53\n], the \nin vivo \nor \nin vitro \nantiproliferative effects of other DNA demethylating agents such as procainamide, zebularine, tea polyphenol (-)-epigallocatechin-3-gallate, and RG108 [\n86\n] are low or absent at DNA demethylating concentrations. Interestingly, MCF-7 and SW480 were more sensitive to the combination of compounds, although the difference was statistically significant only in SW480 cells [\n89\n] suggesting that the known synergistic effect on tumor suppressor gene re-activation by a DNA demethylating agent and a HDAC inhibitor [\n90\n] lead in some models to stronger antitumor effects [\n91\n,\n92\n].\nData on the synergy between a DNA methylation inhibitor and an HDAC inhibitor for gene re-expression led to exploration of the effect of hydralazine plus valproic acid on global gene expression. Microarray analysis utilizing the Amersham CodeLink system containing 55K genes probes demonstrated that 1,281 genes (651 up-regulated and 630 down-regulated) were differentially expressed at least three-fold differently from an untreated control. Among up-regulated genes, 153 were specifically induced by hydralazine and 178, by valproic acid; however, when cells were exposed for 4 days to hydralazine and then for 16 h to valproic acid the number increased to 352, demonstrating that these epigenomic active drugs have a synergistic effect upon gene expression [\n89\n]. Synergy between DNA methylation inhibitor 5-aza-2'-deoxycytidine and deacetylase inhibitor trichostatin A on gene re-expression at a global scale is already known; it has been shown that the percentage of up-regulated genes with 5-aza-2'-deoxycytidine was 1.9, 1.1 with trichostatin A, but 10.4% with the combination [\n93\n], indicating that reversal of two epigenetic factors (i.e., DNA demethylation and histone hyperacetylation) synergizes gene re-expression [\n94\n]. Among genes up-regulated by hydralazine and valproic acid are those coding for major histocompatibility complex, class I-related and major histocompatibility complex, class II, DR alpha. This class I-related antigen is a powerful NKG2D ligand for NK cell-mediated antitumor immunity induction, whereas the DR alpha chain is crucial for antigen presentation within the context of class II MHC [\n95\n,\n49\n,\n50\n].\nUpon any stimuli, cells must orchestrate a number of changes in gene expression, as well as in other dynamic processes such as protein phosphorylation, protein trafficking, and protein-protein interactions, to cope with cytotoxic stress [\n96\n]. Therefore, it is vital for cells to possess intact transcription regulation machinery. On this basis, it was hypothesized that malignant cells exposed to cytotoxic chemotherapeutic drugs would have a deranged response and that this would perhaps compromise survival if co-treated with drugs targeting two of the main gene-regulating processes: DNA methylation and histone acetylation. In fact, hydralazine and valproic acid increased the cytotoxicity of chemotherapy agents cisplatin, doxorubicin, and gemcitabine (Figure \n7\n) [\n89\n]; it is noteworthy, however, that sensitization was higher for cisplatin and doxorubicin, as could be expected because loosening the chromatin structure by histone acetylation increases the efficiency of anticancer drugs that target DNA [\n97\n]. The observed chemosensitization \nin vitro \nwas evaluated in a murine model of fibrosarcoma using nude mice xenografted with the sarcoma cell line HT1080. Remarkably, while tumors receiving only adriamycin re-grew 1 week after the adriamycin final dose, animals treated with hydralazine plus valproic acid showed no tumor re-growth [\n89\n]. These results suggest that the combination's antitumor efficacy was higher and that therefore no microscopic residual remained or alternatively, that the treatment disabled cell proliferative capacity. This in principle may be particularly relevant for patients with minimal residual disease after curative attempt by surgery, chemotherapy, and/or radiotherapy.\nFigure 7\nHeLa cells were treated for 24 hours with panel \na\n: cisplatin (cddp), panel \nb\n: adriamycin (adr) or panel \nc\n: gemcitabine (gem) at or close to IC\n50 \nplus hydralazine (h) and valproic acid (v). Afterwards medium was removed and fresh medium containing only hydralazine and valproic acid was added for additional 48 hours after which viability was measured. There was a significant higher cytotoxicity of the chemotherapeutic agent when used in combination with hydralazine plus valproic acid. Cisplatin alone at 12 μM caused a reduction in viability to 37% in HeLa cells which was essentially zero viability when cells were co-treated with hydralazine plus valproic acid (h-v-c). The increasing toxicity of the combination was also seen with adriamycin and gemcitabine. Viability was 42% and 45% in the chemotherapy drugs alone versus 27% and 37% respectively when hydralazine plus valproic acid were added to chemotherapy drugs (h-v-c). (Reproduced from ref. 89. \nCancer Cell Int \n2006,\n6\n:2).\nClinical studies of hydralazine and valproic acid in patients with cancer\nThese pre-clinical studies were the foundation for performing a phase I study to investigate whether hydralazine administered by oral route at doses commonly used for treatment of high blood pressure could demethylate and re-activate tumor suppressor gene expression in the tumors of patients with cervical cancer [\n98\n]. The study was performed in 16 newly diagnosed patients with cervical cancer with locally advanced disease receiving 50, 75, 100, or 150 mg a day for 10 days. The treatment was well-tolerated and methylation analysis of the biopsies taken prior to and after 10 days of hydralazine administration was performed in all patients. Overall, 70% (89 of 128) of pre-treatment samples analyzed (eight genes for each of the 16 pre-treatment biopsies) had at least one methylated gene, and all 16 patients had at least one methylated gene. Irrespective of the hydralazine dose administered, post-treatment biopsies showed a gene-variable demethylation rate varying from 15% (2/13 samples) for the \nMGMT \ngene to 67% of demethylation for the \np16 \ngene. Correlation between demethylation analysis and dose level revealed the following: at 50 mg a day, 40% of methylated genes suffered demethylation; at 75 mg, this was 52%; at 100 mg, the rate was 43%, and the rate was 32% for the 150-mg dose (Figure \n8\n).\nFigure 8\nA\n. Pre- (dark bars) and post-hydralazine treatment (light bars). The bars represent the number of patients that showed methylation for each studied gene from each of the 16 patients. \nB\n. Representative cases of genes (M methylated, U unmethylated; pre/post): M/M; M/U; U/U, M/U; MU/U; M/ U-M. \nC\n. Percentage of demethylation after treatment according to the dose. Percentage was calculated considering 100% methylation the total number of pre-treatment methylated genes in each cohort of 4 patients (Reproduced from ref. 74. \nBMC Cancer \n2005, \n5\n:44).\nRegarding expression of the analyzed genes, 90% (116 of 128) of tumor samples expressed the messenger in the pre- and post-treatment biopsies regardless of methylation status; hence, these were not informative. Notwithstanding this, nine of 12 informative cases had the gene re-expressed after treatment: one case at 50 mg; four cases at 75 mg; one case at 100 mg, and three cases at 150 mg (Figure \n9\n). Interestingly, at the doses tested there were no observed changes in the methylation status of imprinted and \"normally methylated\" genes in the DNA of peripheral blood cells. Additionally, hydralazine lowered global methylcytosine content by 1% in tumors, as evaluated by a capillary electrophoresis method [\n99\n].\nFigure 9\nRepresentative cases correlating methylation and re-expression before and after hydralazine treatment. \nA \nis a patient treated with 75 mg/day that demethylated and re-expressed the DAPK gene. \nB \ncorresponds to a patient receiving 150 mg/day who showed only the methylated band pre-treatment, but both bands after treatment, which correlated with re-expression of MGMT. \nC \nis a 50 mg/day patient which failed to demethylate the DAPK gene and therefore lacked expression. D represents the distribution of informative cases. From the 128 genes/cases, 116 were RT-PCR positive regardless of the methylation status, hence were not informative. In the remaining 12 cases, nine demethylated and re-expressed the gene. (Reproduced from ref. 74. \nBMC Cancer \n2005, \n5\n:44).\nIt is widely accepted that cancer development has been associated with DNA methylation deregulation and aberrant histone deacetylase (HDAC) activity, which cooperate for inducing aberrant gene silencing [\n100\n]. Therefore, a number of investigation groups are currently exploring the clinical antitumor activity of a DNA methylation inhibitor plus a histone deacetylase inhibitor [\n101\n].\nAmong histone deacetylase inhibitors, the discovery that valproic acid, which belongs to the short-chain fatty acids category and which showed to be an effective HDAC inhibitor [\n102\n,\n103\n], encouraged investigation of this agent as a potential cancer therapy agent. We recently demonstrated, within the context of a phase I study, that magnesium valproate when used at only slightly higher doses than those utilized as anticonvulsant, not only produces H3 and H4 histone hyperacetylation in PBMN cells, but also leads to hyperacetylation of H3 and H4 hyperacetylation and HDAC activity inhibition in primary tumors of patients with cervical cancer [\n104\n]. These data have led us to investigate the clinical efficacy of hydralazine and magnesium valproate in a series of on-going phase II studies.\nBreast cancer exhibits a number of epigenetic alterations that potentially can be reverted by epigenetic therapies [\n105\n]; hence, in the first study newly diagnosed patients with locally advanced breast carcinoma receive four courses of neoadjuvant chemotherapy with adriamycin and cyclophosphamide plus hydralazine and magnesium valproate on a daily basis beginning 7 days before the first chemotherapy cycle and continuing through the end of chemotherapy, with pathologic response rate as the end point. Likewise, epigenetic alterations in cervical cancer are common [\n106\n]; hence we are performing a phase II trial in previously untreated FIGO stage IIIB cervical cancer. Patients receive standard weekly cisplatin plus radiation along with the combination of hydralazine and magnesium valproate with the aim of increasing clinical complete response rate.\nOn the other hand, studies have shown that DNA methylation and histone deacetylase inhibitors are able to resensitize drug-resistant tumors to established treatments [\n107\n]; hence, we are testing whether the combination of these epigenetic agents added to chemotherapy induces responses in common solid tumors such as breast, lung, cervical, ovarian, head & neck, prostate, and testicular carcinomas. In this trial, patients with measurable disease who exhibit non-response or tumor progression after three courses of palliative chemotherapy initiate with hydralazine and magnesium valproate plus the same chemotherapy scheme. Finally, we are also testing the clinical activity of the combination alone in myelodysplasic syndrome and refractory acute leukemia, because these tumor types are responsive to a combination of DNA demethylating and histone deacetylase inhibitors [\n108\n,\n109\n]. In all these trials, several parameters, including global and gene specific DNA methylation and histone acetylation, are being evaluated to gain insight into the predictive tumor response value of these molecular markers.\nConclusion\nTargeting DNA methylation and histone deacetylase constitutes a promising antitumor treatment, which is also denominated epigenetic therapy. The fact that the most extensively studied nucleosides with known DNA methylation inhibitory activity, 5-azacytidine and 5-aza-2'-deoxycytidine, exhibit myelosuppression even when used at low doses has spurred the search for less toxic alternatives. Among non-nucleoside demethylating agents, hydralazine is a good candidate for clinical development mainly due to the fact that its extensive use for decades for cardiovascular conditions has demonstrated its tolerability and safety. Existing data show that this agent is able to demethylate and re-activate tumor suppressor gene expression in patients with cancer. Its good tolerability also permits its use in combination with an epilepsy treatment-approved histone deacetylase inhibitor. The antitumor efficacy and safety of this \"epigenetic therapy\" are currently being evaluated in phase II studies, along with chemotherapy and/or radiation for a variety of malignancies in different scenarios. If encouraging, results of these trials will dictate its further testing in randomized phase III trials.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nCA and MC participated in writing sections of the review, B S-P, and E P-C conducted the laboratory work, and A D-G conceived of the review and wrote the manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
76
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nRationale and design of The Delphi Trial – I(RCT)\n2\n: international randomized clinical trial of rheumatoid craniocervical treatment, an intervention-prognostic trial comparing 'early' surgery with conservative treatment [ISRCTN65076841]\n\n**Article Abstract:**\n\nBackground\nRheumatoid arthritis is a chronic inflammatory disease, which affects 1% of the population. Hands and feet are most commonly involved followed by the cervical spine. The spinal column consists of vertebrae stabilized by an intricate network of ligaments. Especially in the upper cervical spine, rheumatoid arthritis can cause degeneration of these ligaments, causing laxity, instability and subluxation of the vertebral bodies. Subsequent compression of the spinal cord and medulla oblongata can cause severe neurological deficits and even sudden death. Once neurological deficits occur, progression is inevitable although the rapidity of progression is highly variable. The first signs and symptoms are pain at the back of the head caused by compression of the major occipital nerve, followed by loss of strength of arms and legs. The severity of the subluxation can be observed with radiological investigations (MRI, CT) with a high sensitivity.\nThe authors have sent a Delphi Questionnaire about the current treatment strategies of craniocervical involvement by rheumatoid arthritis to an international forum of expert rheumatologists and surgeons. The timing of surgery in patients with radiographic instability without evidence of neurological deficit is an area of considerable controversy. If signs and symptoms of myelopathy are present there is little chance of recovery to normal levels after surgery.\nDesign\nIn this international multicenter randomized clinical trial, early surgical atlantoaxial fixation in patients with rheumatoid arthritis and radiological abnormalities without neurological deficits will be compared with prolonged conservative treatment. The main research question is whether early surgery can prevent radiological and neurological progression. A cost-effectivity analysis will be performed. 250 patients are needed to answer the research question.\nDiscussion\nEarly surgery could prevent serious neurological deficits, but may have peri-operative morbidity and loss of rotation of the head and neck. The objective of this study is to identify the best timing of surgery for patients at risk for the development of neurological signs and symptoms.\n\n**Article Body:**\n\nBackground\nRheumatoid Arthritis (RA) is a chronic, systemic, inflammatory disease with an unknown etiology characterized by an erosive synovitis. Genetic and environmental factors play an important role. Both humoral and cellular immune responses are present. In caucasians the prevalence of RA is 0.8–1% [\n1\n] and the incidence is 27 per 100.000 of the general population [\n2\n]. The upper cervical spine shows signs of damage in 17–86% of patients with RA and is the most commonly involved structure after hands and feet [\n3\n]. The huge difference in the prevalence of cervical spine pathology is the result of absence of standardized international accepted definitions of subluxations of the atlantoaxial segment and inconsistent results in the literature. The use of better anti-inflammatory drugs in the last decade resulted in delayed and maybe a lower incidence of cervical spine involvement.\nThe spinal column consists of vertebrae stabilized by an intricate network of ligaments. Especially in the cervical spine, rheumatoid arthritis can cause degeneration of these ligaments, causing laxity, instability and subluxation of the vertebral bodies. Subsequent compression of the spinal cord and medulla oblongata can cause severe neurological deficits and even sudden death. Cervical spine involvement typically begins early in the disease process, and its progression has been closely correlated with the extent of peripheral disease activity [\n4\n-\n6\n]. Several types of subluxations have been described [\n3\n]. The first signs and symptoms of atlantoaxial instability are the result of rheumatoid synovial proliferation. Because of erosions of the transverse, apical and alar ligaments an anterior atlantoaxial subluxation (AAS) develops. Damage to the transverse ligament alone will allow approximately 3 to 4 mm of subluxation; a greater anterior atlanto dental interval (AADI) implies damage to the alar-apical ligament complex, an incomplete odontoid peg or a resorbed dens [\n4\n]. The average duration of RA at the onset of AAS has been reported being 12.7 years (3–26 years) [\n7\n]. Many patients acquire AAS in the first 3 years of their disease, but neurological impairments develop after a mean period of 18 years (range 4–50 years) [\n8\n]. When the odontoid process erodes a posterior AAS can evolve. Vertical Translocation (VT) (Cranial settling, basilar invagination, or superior migration of the odontoid process) results from progressive destruction of the lateral mass joints (atlantoaxial and occipitoatlantal) and the lateral masses themselves, as a result of chronic craniocervical instability [\n9\n-\n11\n]. The odontoid process moves towards and beyond the borders of the foramen magnum. Secondarily periodontoid pannus is formed in reaction to the chronic instability [\n3\n,\n12\n]. VT is observed in 4–35% of patients [\n13\n]. Because of VT the AADI can decrease, which virtually is a paradoxal improvement [\n9\n,\n14\n,\n15\n]. VT appears after a mean of 16.5 years (4–33 years) after the onset of the RA inflammatory process and almost exclusively after the onset of AAS [\n8\n,\n16\n]. Involvement of the subaxial spine (SAS) is less common, occurs later in the course of the disease, and manifests as multilevel anterior dislocation (7–29%) [\n13\n].\nSigns and symptoms\nClinical signs and symptoms as a result of AAS vary from asymptomatic to total incapacitation. Occipital pain, both from joint destruction and occipital nerve entrapment, and signs and symptoms of myelopathy are the most common complaints. Symptoms caused by instability are neck pain, headache and occipital neuralgia. As a result of medullary compression paresthesias, numbness, weakness, jactitations and sphincter disturbances can develop.\nWhen VT is present with medullary compression the signs and symptoms can be dysarthia, dysphonia, dysphagia, diplopia, facial numbness (cranial nerve palsies), sleep apnea, and long tract signs. The long tract signs are difficult to assess, since the disability caused by progressive joint disease can obscure objective long tract signs such as hyperreflexia and spasticity. Severe compression of the medulla oblongata can result in vascular insufficiency leading to dizziness, vertigo and syncope. Vertebrobasilar ischemia is rare and occurs as a result of compression by the odontoid process [\n17\n,\n18\n]. VT can also give rise to cruciate paralysis and occasionally sudden death. The presence of symptoms is not correlated with the severity of radiological abnormalities.\nNatural history\nThe time interval between the existence of AAS and the development of neurological signs and symptoms varies widely [\n16\n,\n19\n-\n24\n]. A review by Bouchaud-Chabot [\n3\n] showed that at least 15% of the patients with radiological subluxation had no symptoms or signs. Progressive neurological deficits have been reported to be present in 15 to 36% of patients with RA [\n13\n]. If neurological deficits occur, spontaneous recovery can not be expected with conservative treatment and progression is inevitable and portends a poor prognosis [\n6\n,\n25\n-\n29\n]. About 50% of these patients die within 6 months and almost everyone dies within a few years after the first signs of myelopathy [\n2\n,\n25\n].\nTreatment\nGenerally accepted indications for atlantoaxial surgical fixation are severe C2 neuralgia and neurological deficits (Ranawat IIIA and IIIB) with signs and symptoms of myelopathy [\n13\n,\n14\n,\n16\n,\n30\n]. Surgical intervention is indicated to reduce and stabilize the craniocervical junction, preserve or restore neurological function and prevent further neurological deterioration [\n1\n,\n2\n,\n9\n,\n31\n-\n33\n]. However, there is no consensus or guideline when to operate on asymptomatic patients with radiological abnormalities. Some surgeons and rheumatologists prefer to operate in an early stage of the disease [\n34\n], others operate once neurological signs and symptoms have occurred [\n14\n]. Surgery in patients without neurological deficits is easier and less complex compared to patients with neurological impairments [\n9\n,\n32\n,\n34\n-\n36\n]. On the other hand loss of rotation occurs and there is a small risk of morbidity.\nAs a result of lack of evidence of the beneficial effect of surgery in an early stage of the disease, not all rheumatologists screen routinely for AAS as a result of the RA. Some rheumatologists screen patients with plain radiographs, others perform radiological investigations once patients present with complaints or neurological deficits.\nUntil the early 90's, the classical surgical approaches had a very high peri-operative morbidity and mortality rate. Since 1996, new surgical techniques with titanium instrumentation are used that are safer and make it possible to mobilize patients the first day after surgery [\n37\n-\n42\n]. In a study performed by Agarwal [\n7\n] no VT appeared after 'early' atlantoaxial fixation in patients with anterior AAS. Adjacent level involvement after occipitocervical fixation is approximately 7% in 3 years [\n43\n], this percentage is lower if only a C1C2 fixation has been performed.\nThe mortality rate of patients with myelopathy treated conservatively is very high. However, non ambulant quadriparetic patients who were operated on had a poor prognosis as well [\n2\n,\n9\n,\n27\n]. In a study performed by Casey and Crockard, the mortality rate of operated Ranawat IIIB patients was 58% within 3 years, compared to 20% of Ranawat IIIA patients [\n2\n]. The Class IIIB patients have unique management considerations in which surgery (despite high morbidity) often remains the best therapeutic option available. Improvement of even one grade in their Ranawat score from Class IIIB to Class IIIA brought about by surgery confers on them a huge benefit in terms of their quality of life and survival [\n9\n].\nThe Delphi Trial – I(RCT)\n2\nWhat is lacking from the literature is a prospective, rheumatoid population based study that gives information about the prevalence and progression of AAS, VT, or other important manifestations of RA involvement of the cervical spine. Because of the variable time interval between the existence of radiological atlantoaxial cervical spine involvement and the development of neurological deficits, it is not known when surgical fixation has to be performed. In the literature many authors suggest that a randomized clinical trial about the best timing of surgery in AAS as a result of RA has to be performed [\n1\n,\n2\n,\n9\n,\n11\n,\n34\n,\n43\n]. The objective of this study is to compare early surgery with prolonged conservative treatment for patients with rheumatoid arthritis and atlantoaxial cervical spine involvement without neurological impairments.\nDesign\nAn international multicenter randomized clinical trial will be performed. Centers in the Netherlands (table \n1\n), Belgium, Denmark, France, Germany, Italy, Latvia, Portugal, Spain, Sweden, Switzerland, United Kingdom, USA and Canada will participate (table \n2\n and figure \n1\n and \n2\n). The multicenter design is necessary to recruit all patients in the inclusion period of 2 years. Early surgery will be compared with prolonged conservative treatment. The selection and randomization procedure is depicted in figure \n3\n. The overall range for randomization of the AAS is an AADI between 5–12 mm. Participating centers/countries are allowed to randomize different intervals of subluxation. The intervals are predefined as 5–8 mm, 5–12 mm and 8–12 mm. Demographic and clinical data will be collected of each patient. The randomization of all patients will be performed centrally at the LUMC by the trial coordinator and datamanager by a concealed randomization list in random permuted blocks.\nAfter a follow up of 5 years the main research question will be answered, although the total follow-up will be 10 years. Patients excluded from the trial will be followed in a cohort group and treated according to the usual care by surgical fixation or conservative treatment. The LUMC will function as the research and data coordinating center, where the data will be collected, analyzed and publications prepared. Eligibility criteria will differ from site to site, according to local perceptions of equipoise. These efforts will increase the generalization of the results. The authors have full access to the data, direct the data-analysis and are responsible for decisions regarding publication. The principal investigator and the trial coordinator assume full responsibility for the integrity and interpretation of the data.\nMain research questions\nNull hypothesis; there is no difference in outcome between early surgical fixation and prolonged conservative treatment in patients with AAS with an AADI between 5 and 12 mm without neurological complaints. Because of the many uncertainties in the rheumatoid arthritis process the following research questions will be answered.\n1. Does early surgery in neurological intact patients with RA and radiological signs of AAS result in less progression of C1–C2 subluxation and VT with or without complaints and neurological disability compared to prolonged conservative treatment?\n2. Is early surgery more cost-effective than prolonged conservative treatment in this patient population?\nDuring the explorative analyses the next questions will be answered.\n3. Is it possible to define subgroups, which benefit most from one of the allocated treatment strategies?\nPatients\nAll patients with RA and atlantoaxial cervical spine involvement on conventional X-rays, CT or MRI of the cervical spine without neurological impairments will be asked to participate in the trial at one of the participating RA specialized hospitals. If patients with RA, aged 18–70 years old, have an AAS in the randomization range without neurological impairments (Ranawat I and II) without severe comorbidity, MRI incompatibility or previous cervical surgery, early surgical fixation will be compared with prolonged conservative treatment. The in- and exclusion criteria of the delphi trial are listed in table \n3\n. Patients with neurological deficits as a result of cervical spine involvement will be followed in a cohort group.\nSample size/power calculation\nThe sample size is calculated on the basis of the outcome difference during the follow-up period of at least 5 years. Hypothetically, 8% of included patients will worsen in the 5 year follow up period resulting in an event (Kaplan Meier) (16,21). In the early surgery group the event rate is expected to be 2% or less [\n44\n]. 2% is chosen because it has to be a save alternative to 'wait and see'. A two-sided log rank test with an overall sample size of 250 patients, achieves 90% power at a 0.05 significance level to detect a difference in groups 1 and 2 after 5 years of follow up. Patients enter the study during an accrual period of 2 years. 50% of the enrolment is complete when 50% of the accrual time has past. A follow-up period of 5 years with a 20% loss from group 1 and a 20% loss from group 2 is calculated.\nInterventions\nSurgical treatment\nDifferent surgical opportunities and techniques for cervical fixation exist. The choice of technique depends on the severity of the cervical spine involvement and the surgeon's preference. Surgery will be performed according to local standards and to the discretion of the surgeons, but a standardized minimal surgical technique is required. All approved cervical spine fixation systems are allowed in this trial. If AAS is present a C1–C2 screw fixation according to Magerl or Harms with or without wiring techniques, or a Hook C1–C2 fixation will be performed. When VT has occured, the cranium will be fixated to the upper cervical spine with fixation to the C1–C2 screws. For each patient, the surgeons will register which technique they have used.\nConservative treatment\nConservative treatment consists of antirheumatoid drugs (i.e, NSAID, DMARD, biologicals). The choice of drugs is to the discretion of the rheumatologist. Occurrence of progressive neurological deficits, progressive radiological abnormalities, and intolerable pain represent a failure of conservative management and are an indication for surgical fixation.\nCohort study\nMany patients with rheumatoid arthritis do have cervical spine involvement but only a small proportion of these patients will be eligible for randomization. All patients with RA and AAS excluded for the randomization group will be offered to be followed in a separate cohort study design. The inclusion and exclusion criteria are only important for the group of patients that will be randomized and not for patients in the cohort group. Criteria for the cohort group are shown in table \n4\n. Patients with an AADI less than 5 mm will be treated conservatively until the AADI enlarges. Patients with an AADI larger than 12 mm will be offered surgery. A follow up with X-rays and MRI scans of the cervical spine will be performed at predefined time intervals. The neurological and radiological outcome and quality of life will be analyzed.\nPrimary and secondary outcome parameters\nThe primary outcome \nis the occurrence of an event. Events are defined as 1) neurological deficit, 2) radiological progression, 3) surgery, 4) resurgery, 5) death. (see table \n5\n).\n1). Neurological deficit is defined as a worsening in the Ranawat scale to IIIA or IIIB, or a deterioration of the MDI score >3 points. The Ranawat classification is a neurological classification and useful in evaluating patients, planning treatment and evaluating results. Class I patients have no neurological deficit, Class II patients have subjective weakness with hyperreflexia and dysesthesia. Class IIIA patients have objective weakness and long tract signs. Class IIIB patients are wheelchair bound or bedridden. The Ranawat classification fails to differentiate reliably between classes II and IIIA, the area of most clinical interest to the operating surgeon [\n45\n]. Casey and Crockard developed and validated the MDI according to the Stanford HAQ. The MDI consists of 10 functional questions. The more severe a patient has been disabled the higher the score [\n45\n].\n2). Radiological progression is defined as an enlarged AADI of more than 12 mm, development of VT with impingement of the spinal cord or medulla oblongata, or signs of myelopathy. The Redlund Johnell method will be used to measure the severity of VT, which is the distance of the base of C2 to the palato-occipital line of McGregor (less than 34 mm in men and 29 mm in women) [\n11\n].\n3). Incidence of surgery in the conservative treatment group. One of the goals of the conservative treatment is to avoid surgery for intolerable pain for example. The surgical rate is therefore an indication of the success or failure of the conservative treatment policy.\n4). The incidence of resurgery at the cervical spine in the early surgery group will be an indication of the failure rate for surgery.\n5). Death: all causes.\nSecondary outcome parameters\n1) 'Perceived recovery/deterioration.' This is a seven-point Likert scale measuring the perceived recovery or progression, varying from 'completely recovered' to 'worse than ever'.\n2). The American Spinal Injury Association (ASIA) and International Medical Society of Paraplegia have developed a standard form for capturing clinical information when evaluating a patient who has had a spinal cord injury. The ASIA score is a motor and sensory quantifying score of both arms and legs [\n46\n]. The ASIA score will be used once neurological deficits have occurred.\n3). The Disease Activity Score (DAS-28) is a classification used by many rheumatologists and is a measure of the overall disease activity of RA. In Europe the DAS is the recognized standard in research and clinical practice. For a good comparison of the severity and disability due to the RA inflammatory process between all patients in the two treatment groups of the different countries the DAS-28 will be used. The following parameters are included in the calculation: Number of joints tender to touch (TEN), Number of swollen joints (SW), Erythrocyte sedimentation rate (ESR), patient assessment of disease activity [\n47\n].\n4). VAS pain will be measured of pain in the neck and occiput before randomization and during the follow up. Pain will be assessed on a horizontal 100 mm scale varying from 0 mm, 'no pain', to 100 mm, 'the worst pain ever' [\n48\n].\n5) EuroQol classification system and VAS rating personal health [\n49\n]. A cost-utility analysis will be performed using QALY's based on the EuroQol questionnaire, which has been validated in many studies and is easy to fill out. Patients describe their general health status using the EuroQol classification system, consisting of 5 questions on mobility, self care, usual activities, pain/discomfort, and anxiety/depression. Patients also rate their personal health using a visual analogue scale (VAS) ranging from worst imaginable health to best imaginable health.\n6) Short-Form 36 (SF-36). Quality of life will also be assessed using the RAND-36 questionnaire [\n50\n]. This is a generic health status questionnaire, which can easily be filled out at home. The questionnaire consists of 36 items on physical and social functioning.\n7) Imaging findings. The results of the differences between the baseline X-ray, MRI and CT scan and those investigations during the follow up after randomization are important secondary outcome measures. The difference in AADI, PADI, Redlund-Johnell (VT), signs of myelopathy or compression, subaxial involvement, amount of pannus tissue and signs of fusion will be registered. Failures of surgery can be recognized by screw breakage, progression of AAS or VT.\nDatabase\nAll data collected of patients participating in this trial are registered in a database under the ProMISe data management system of the Department of Medical Statistics of the LUMC. Database access is secure and limited to the trial coordinator, the trial data manager and the principal statistician. At patient enrollment into the trial, a unique study identification number is issued. The database will not contain any information directly identifying the study subject. However, to avoid errors during data collection in the follow-up of the patient, the patient's initials (first character of first name and first character of last name) will be entered as well as the gender and date of birth of the patient. The local hospital number of the patient is also part of the registration. The investigator in each participating hospital will maintain a list in which the correspondence between the true identity of the subject and its study number is documented. Follow-up data sent from each participating hospital to the central data management will only contain the study ID of the subject but not any data directly revealing the identity of the subject. It is the responsibility of each local hospital research coordinator to ensure the integrity of the correspondence between the Study ID and the true identity of the patient. The data manager will enter follow up data and verify that the date of birth of the follow up data forms is identical to the date of birth on the entry form. Discrepancies are to be solved by the local coordinator. This system ensures that only a local physician can infer the identity of any participating subject.\nFollow up\nFollow up with clinical assessments and outcome measures will be assessed at baseline and after 3, 6, 12, 18 and 24 months. After two years the patient will be controlled once a year till eventually 10 years after randomization. During the follow up parameters will be registered to evaluate the quality of life, illness restrictions and neurological impairments. Direct and indirect medical costs will be calculated in each group.\nEvery control moment an X-ray of the cervical spine will be made (neutral/flexion/deflexion) except three months postoperatively. Prior to randomization and six months postoperatively a CT scan will be made to evaluate fusion and surgical stabilization. At fixed intervals and on clinical indication a MRI scan of the cervical spine will be performed. The clinical, neurological and radiological parameters will be registered on the follow up CRF. Data collection will take place per treatment center and will be gathered and analyzed at the LUMC in Leiden by the trial coordinator together with the statistical department and the epidemiological department of the VUMC in Amsterdam.\nStatistical analysis\nThe researchers will be aware of allocation to early surgery or conservative treatment at the time of the statistical analyses. There will be an intermediate analysis after 2 years of follow up. The intermediate outcome measures are progression of AAS and VT with or without (pain) complaints and neurological disability (measured with the MDI and Ranawat). The main analyses will be performed after 5 years and 10 years of follow up. At these intervals the primary outcome parameter is the occurrence of an event as described in table \n5\n. Baseline comparability will be investigated by descriptive statistics to examine if randomization was successful. Differences in success rates between both groups are calculated, together with 95 percent confidence intervals. In addition to an analysis of the difference in outcome between the two groups analyses of the difference in time to progression will be carried out. Continuous outcomes are evaluated as change scores (differences between baseline measurement and each follow-up measurement). Multivariable analyses are performed to adjust for the eventual differences between the groups at baseline in prognostic indicators. All the analyses are performed according to the intention-to-treat principle. An additional per protocol analysis will be performed comparing patients in the conservative group who received surgery with patients in the same group who had not and with patients in the surgery group. To compare the actual treatment sec instead of strategies an explorative analysis will be performed in subgroups of all patients who actually received surgery and who did not receive surgery in both groups. All patients withdrawn from the study are included in the analysis until the time of withdrawal.\nTo answer the third research question, explorative analyses are conducted to investigate whether the treatment effect varies in specific subgroups of patients. Using logistic regression for success rate and linear regression for severity of the disability, each prognostic indicator is checked for interaction with treatment.\nEconomic evaluation\nThe result of this study is based on both the short-term and long-term success of surgical intervention and prolonged conservative treatment. The economic evaluation will be performed from a societal perspective. Both health care costs and costs of production losses will be included. Health care costs will include costs of general practice care, medical specialist care, physiotherapy, hospitalisation, medication and other costs directly associated with diagnosis, treatment and rehabilitation.\nThere are many variable parameters influencing the total costs of the surgical fixation (surgery time, extend of surgical fixation, systems used), which makes it very difficult to calculate the real costs of the surgical procedure. Therefore, real costs of surgery will not be estimated but based on standard prices in the participating hospitals. The costs of hospital admission in the surgical group will be calculated by the days spent on the Intensive Care Unit and the surgical department. Side-effects and complications related to the treatment are recorded by the patients, the treating surgeon or rheumatologist. The costs of complications will be reflected in additional intervention, prolonged duration of ICU stay and total admission time. The costs for re-surgery in the early surgery group and surgery in the conservative group will also be estimated.\nIn the study MRI and CT scans will be performed in both treatment groups. The costs of these imaging techniques will be included. The costs of the CT scan will only be calculated for patients undergoing surgery, because in the normal situation, CT would only be performed if a surgical indication exists. CT scans that are only used for research purposes will not be included.\nPatients will register other health care needs in a diary (including physiotherapy, visits to GP's and specialists, nursing care and medication). Each diary covers a period of 3 months. The costs of health care will be assessed using standard prices. Patient/family costs and costs of production losses will also be collected in the cost diaries.\nCost-effectiveness and cost-utility analysis\nThe aim of the economic evaluation will be to determine and compare the total costs for patients receiving surgery or conservative care, and to relate these costs to the effects of the interventions. The economic evaluation will be conducted from societal perspective and will be carried out according to the intention-to-treat principle. Bootstrapping will be used for pair-wise comparison of the mean differences in total costs between the intervention groups. Confidence intervals will be obtained by bias corrected and accelerated (Bca) bootstrapping using 2000 replications.\nCost-effectiveness ratios will be calculated by dividing the difference in mean costs of the two interventions by the difference in mean effects of the two interventions. Ratios will include the primary clinical effect measures of the trial. Cost-utility ratios will also be calculated. Ratios will be graphically presented on cost-effectiveness and cost-utility planes. Acceptability curves will also be presented.\nDiscussion\nEthical considerations\nIs it fair to perform a surgical cervical fixation on patients with rheumatoid arthritis with atlantoaxial pathology without neurological complaints? From the literature it is not known which treatment is preferable. Advantages of early surgery are probable preservation of neurological functions with a higher degree of general functioning. The surgical fixation will be less extensive and easier to perform compared to surgery in a later stage, because of the more pronounced destruction of the joints and bones. If neurological deficits are present before surgical fixation, there is little chance of (full) neurological recovery. The large variability in the progression of AAS, eventually resulting in neurological deficits, makes it hard to determine the right timing for surgical fixation. It can take years before patients get neurological complaints or deficits. Another disadvantage is that with surgery in an earlier phase of AAS more patients have to be operated on. After surgical fixation, patients are more restricted in their head and neck movements. In turn, it must be noted that limited neck range of motion already exists in 90% of patients with RA. The overall conclusion is that it is fair to practice surgical fixation before the onset of neurological signs and symptoms in patients with significant AAS.\nList of abbreviation\nAAS: Atlanto Axial Subluxation\nASIA: American Spinal Injury Association\nAADI: Anterior Atlanto Dental Interval\nCT: Computer Tomography\nDAS: Disease Activity Score\nDMARD: Disease Modifying Anti Rheumatoid Drugs\nMDI: Myelopathy Disability Index\nMRI: Magnetic Resonance Imaging\nPADI: Posterior Atlanto Dental Interval\nRA: Rheumatoid Arthritis\nSF-36: Short Form 36\nSAS: Subaxial Subluxation\nVAS: Visual Analogue Scale\nVT: Vertical Translocation\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nJW and WP developed the study design, and are the writers of the manuscript, MB carried out the power calculation, and assisted in developing the study design, MT performed the cost-effectivity analysis and economic evaluation, RB and JH handed statistical advice, gave advice for the power calculation, RT commented on the final manuscript. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
77
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nPrevalence of self-reported hypercholesterolaemia and its relation to dietary habits, in Greek adults; a national nutrition & health survey\n\n**Article Abstract:**\n\nBackground\nThe strong causal role of hypercholesterolaemia on the progression of atherosclerosis and subsequently on the development of cardiovascular disease is well described. Main aim of this study was to evaluate the prevalence of self-reported hypercholesterolaemia and its relation to nutritional habits, in a representative nationwide sample of adult Greek population.\nMethods\nCross sectional survey. Based on a multistage sampling, 5003 adults (18 – 74 yr) were enrolled (men: 48.8%, women: 51.2%). All participants were interviewed by trained personnel who used a standard questionnaire. The questionnaire included demographic and socioeconomic characteristics, medical history, lifestyle habits and nutritional assessment.\nResults\nThe prevalence of self-reported hypercholesterolaemia was 16.4% in men and 21.8% in women (P < 0.001). Hypercholesterolaemic status was positively associated with the prevalence of hypertension, diabetes mellitus, renal failure, obesity and physical inactivity, and inversely with the prevalence of smoking. The analysis of reported food consumption patterns showed that consumption of fish, fruits and juices, cereals, and low fat milk and yogurt was significantly higher among hypercholesterolaemic participants while the opposite was observed for food items as red meat, pork, egg, full fat dairy products and desserts.\nConclusion\nHypercholesterolaemia seems to affect a large part of Greek population. It is hopeful that hypercholesterolaemics may have started adopting some more healthy nutritional behaviour compared to normocholesterolaemic ones.\n\n**Article Body:**\n\nBackground\nCardiovascular disease is the leading cause of death worldwide affecting millions of people in both developed and developing countries. In particular, in most European countries cardiovascular disease contributes about 40% to all cause mortality [\n1\n]. Accumulating evidence coming up from numerous studies [\n2\n-\n6\n], have revealed the strong causal role of hypercholesterolaemia on the progression of atherosclerosis and subsequently on the development of cardiovascular disease. According to the World Health Organization (WHO) it is estimated that high cholesterol causes around a third of all cardiovascular disease worldwide, and that 105 million people in the USA have cholesterol levels that are a cardiovascular risk [\n7\n].\nIt should be noted that the strength of the relationship between hypercholesterolaemia and atherosclerosis might be influenced by several lifestyle related factors, like smoking, physical activity and psychosocial conditions [\n2\n]. It is also known that well balanced dietary patterns, like the Mediterranean diet, are strongly related with blood lipids levels, as well as with the prevalence and the management of dyslipidemia [\n8\n-\n12\n]. Furthermore, it is encouraging that, primary and secondary prevention trials [\n13\n-\n15\n] have provided strong evidence that lowering serum cholesterol levels can be translated into a reduction in mortality rates from cardiovascular disease.\nThe limited current data regarding the prevalence of hypercholesterolaemia in Greece, in combination with the considerable variability of hypercholesterolaemia between countries, as well as within countries, and between different areas and population groups [\n16\n], motivated us to conduct a cross-sectional study in a nationwide sample of Greek adults. The study was also undertaken with aim to evaluate the association between nutritional habits and the prevalence of hypercholesterolaemia.\nMethods\nStudy sample\nIn the present study, which was carried out in Greece in autumn of 2004, 5003 adults (18 – 74 years) participated. In order to be the study's sample as more representative as possible, the selection of the participants (men: 48.8%, women: 51.2%) was random, multistage, nationwide (including 66.6% urban and 33.4% rural areas) and it was based on the age-gender distribution of Greek population provided by the National Statistical Service according to the census of 2000 (Table \n1\n). Furthermore, the sampling anticipated enrolling only one participant per household. All participants were interviewed with telephone by trained personnel (cardiologists, dieticians and nurses) who used a standard questionnaire.\nTable 1\nAge - gender distribution of the study's population and the Greek population.\nStudy's Population\nGreek Population\nAge (years)\nMen\nWomen\nMen\nWomen\n18–24\n11.2 %\n10.0 %\n13.7 %\n12.4 %\n25–34\n22.5 %\n21.0 %\n21.2 %\n19.9 %\n35–44\n20.0 %\n19.7 %\n19.4 %\n19.3 %\n45–54\n17.8 %\n17.7 %\n16.9 %\n16.9 %\n55–64\n14.6 %\n15.8 %\n14.7 %\n15.8 %\n65–74\n13.8 %\n15.8 %\n14.1 %\n15.7 %\nInvestigated measurements\nThe questionnaire addressed especially: a) individual demographic and socioeconomic characteristics (age, gender, schooling, occupation, residence); b) information relevant to health status assessment (hypercholesterolaemia, hypertension, diabetes mellitus and renal failure); c) food consumption pattern; d) lifestyle habits, such as smoking status and level of physical activity; and e) characteristics related to body composition (recalled weight and height).\nRegarding the assessment of hypercholesterolaemic status, the subjects were considered as hypercholesterolaemic if they were reporting that they had been previously diagnosed by a registered physician (type of answer: yes/no). In case of positive answer, they were asked to report the most recent measurement of total cholesterol in serum, and to provide data relevant to the selected way of treatment (drug treatment or dietary treatment or drug and dietary treatment or no treatment). Respective information (prior diagnosis, intensity of problem and selected way of treatment) concerning hypertension, diabetes mellitus and renal failure were retrieved too. Family history of all the aforementioned health problems was also recorded (type of answer: yes /no / don't know for father, mother, brother and sister).\nRelatively to the nutritional component of the questionnaire, the participants were asked to report their average weekly consumption (in servings) of a list of food items of all different food groups. The educational level of the participants (as a proxy of social status) was measured by the years of schooling (Group I: < 9 years, Group II: up to high school or technical colleges (10 – 14 years) and Group III: university). Current smokers were defined as those who smoked at least one cigarette per day; never smokers those who have never tried a cigarette in their life and former smokers were defined as those who had stopped smoking for at least one year. Physically active were considered all the participants who reported either that they participated in an exercise program (such as gym, sports, jogging etc.) during their leisure time at least once a week, or that their occupation presupposes certain level of physical fatigue. The rest of the subjects were defined as physically inactive. Finally, we used data of self reported weight and height to calculate body mass index (BMI). Participants were classified as obese if BMI was ≥ 30 kg/m\n2\n.\nStatistical analysis\nContinuous variables are presented as mean values ± standard deviation, while qualitative variables are presented as absolute and relative frequencies. Associations between categorical variables were tested by the use of contingency tables and the calculation of Pearson's chi-squared test. All comparisons among paired groups of sample in relation to normally distributed continuous variables were performed using the student t-test. Every reported \nP\n-value is based on two-sided tests and compared to a significance level of 5%. SPSS version 11.5 (Statistical Package for Social Sciences, SPSS Inc, U.S.A.) software was used for all the statistical calculations.\nResults\nThe characteristics (demographic characteristics, lifestyle habits and information from the medical history) of the study's participants in relation to gender are presented in Table \n2\n. The mean age of men was slightly smaller than that of the women (43.7 ± 16.1 and 44.7 ± 16.0 years, respectively). Additionally, men were more educated and physically active, as well as more frequently current and former smokers.\nTable 2\nCharacteristics of the study's participants (% by gender)\nMen (n = 2439)\nWomen (n = 2564)\nP\nAge (years)\n43.7 ± 16.1\n44.7 ± 16.0\n0.025*\nEducation status \na\n< 0.001*\n Group I\n710 (29.1 %)\n997 (38.9 %)\n \nGroup II\n763 (31.3 %)\n787 (30.7 %)\n \nGroup III\n966 (39.6 %)\n779 (30.4 %)\nPhysical status\n< 0.001*\n \nPhysically inactive\n1664 (67.8 %)\n2110 (82.3 %)\n \nPhysically active\n784 (32.2 %)\n454 (17.7 %)\nSmoking habits\n< 0.001*\n Never smoker\n700 (28.7 %)\n1381 (53.9 %)\n \nCurrent smoker\n1176 (48.2 %)\n901 (35.1 %)\n \nFormer smoker\n563 (23.1 %)\n282 (11.0 %)\nBMI (Kg/m\n2\n) \nb\n26.3 ± 5.7\n25.0 ± 5.3\n< 0.001*\nObesity (BMI ≥ 30 Kg/m\n2\n)\n322 (13.2 %)\n345 (13.5 %)\n0.703\nHypertension\n325 (13.3 %)\n455 (17.7 %)\n< 0.001*\nHypercholesterolaemia\n400 (16.4 %)\n560 (21.8 %)\n< 0.001*\nDiabetes mellitus\n152 (6.2 %)\n146 (5.7 %)\n0.422\nRenal failure\n23 (0.5 %)\n39 (0.8 %)\n0.065\na \nThe educational level of the participants was measured by the years of schooling (\nGroup I\n: < 9 years, \nGroup II\n: up to high school or technical colleges (10 – 14 years) and \nGroup III\n: university\nb \nBMI\n: Body mass index.\nP < 0.05 Statistical significant difference between men and women\nAnalysis of data relevant to the medical history showed statistically significant difference among men and women in relation to prevalence of hypercholesterolaemia and hypertension, but not to prevalence of obesity, diabetes mellitus and renal failure. In particular, 400 men (16.4%) and 560 women (21.8%) reported that they had hypercholesterolaemia, while 325 men (13.3%) and 455 women (17.7%) reported that they were hypertensive. Hypercholesterolaemic status was inversely associated with the prevalence of smoking and positively with the prevalence of the rest cardiovascular risk factors investigated (i.e. hypertension, diabetes mellitus, obesity, physical inactivity) in the overall sample. The prevalence's values of the aforementioned cardiovascular risk factors among normocholesterolaemic and hypercholesterolaemic subjects are presented in Table \n3\n (all \nP\ns < 0.001).\nTable 3\nPrevalence of cardiovascular risk factors in relation to hypercholesterolaemic status (in percentages)\nNormal (n = 4043)\nHypercholesterolaemic subjects (n = 960)\nP\nHypertension\n11.1 %\n34.7 %\n< 0.001\nDiabetes Mellitus\n4.2 %\n13.3 %\n< 0.001\nObesity\n11.8 %\n19.6 %\n< 0.001\nSmoking\n43.2 %\n34.3 %\n< 0.001\nPhysical inactivity\n73.2 %\n84.1 %\n< 0.001\nThe distribution of hypercholesterolaemic study's participants by age group, which is presented in Table \n4\n, shows that the significant difference mentioned before between men and women in relation to hypercholesterolaemic status (women > men) is attributed to the large differences observed in older age groups (55 – 74 yr).\nTable 4\nDistribution of hypercholesterolaemic study's participants by age group\nMen\nWomen\nP\nTotal\nAge\nn\nn\nn\n18–24\n333\n2 (0.6 %)\n317\n7 (2.2 %)\n0.08\n650\n9 (1.4 %)\n25–34\n518\n24 (4.6 %)\n510\n25 (4.9%)\n0.84\n1028\n49 (4.8 %)\n35–44\n474\n66 (13.9 %)\n496\n48 (9.7%)\n0.04\n970\n114 (11.8 %)\n45–54\n412\n101 (24.5 %)\n433\n106 (24.5%)\n0.99\n845\n207 (24.5 %)\n55–64\n358\n110 (30.7 %)\n405\n177 (43.7%)\n< 0.001\n763\n287 (37.6 %)\n65–74\n344\n97 (28.2 %)\n403\n197 (48.9%)\n< 0.001\n747\n294 (39.4 %)\nTotal\n2439\n400 (16.4 %)\n2564\n560 (21.8%)\n< 0.001\n5003\n960 (19.2 %)\nDifference was found between hypercholesterolaemic men and women relatively to the selected treatment of hypercholesterolaemia (P = 0.031). Table \n5\n present the respective distribution. Meanwhile, analysis of participants' family history of hypercholesterolaemia showed a positive association (P < 0.001) only between brothers (independently of gender) and not between parents and descendants. Specifically, only 2.1% of the normocholesterolaemic participants reported that they have a hypercolesterolaemic brother or a sister in contrast with 9.48% of hypercholesterolaemic participants who reported that they have a brother or a sister with the same health problem.\nTable 5\nSelected treatment of hypercholesterolaemia by study's participants (by gender, P = 0.031)\nMen \n(n = 400)\nWomen \n(n = 560)\nTotal \n(n = 960)\nDrug treatment only\n10.8 %\n12.3 %\n11.7 %\nDietary treatment only\n48.5 %\n51.4 %\n50.2 %\nCombined drug and dietary treatment\n16.8 %\n19.8 %\n18.5 %\nNo treatment\n24.0 %\n16.4 %\n19.6 %\nSeveral associations were also detected between nutritional habits and hypercholesterolaemic status. The average weekly consumption (expressed in servings) of the investigated food groups by normocholesterolaemic and hypercholesterolaemic subjects is presented in Table \n6\n. With the exception of some food groups or items i.e. chicken (P = 0.562), vegetables (P = 0.272) and legumes (P = 0.431), hypercholesterolaemic participants differ significantly when compared to normocholesterolaemics in relation to the consumption of the food groups examined. Specifically, statistic analysis of reported food consumption patterns showed that hypercholesterolaemics consume more frequently items from the groups of fish (P < 0.001), bread and cereals (P = 0.031), fruits and juices (P < 0.001) and low fat milk and yogurt (P < 0.001), while normocholesterolaemic participants have greater consumption of red meat (P < 0.001), pork (P < 0.001), egg (P < 0.001), pasta and rice (P < 0.001), potatoes (P < 0.001), full fat milk and yogurt (P < 0.001), yellow cheese (P < 0.001), white cheese (P < 0.001) and desserts or ice creams (P < 0.001).\nTable 6\nFood items consumed (in servings/week) in relation to hypercholesterolaemic status\nNormocholesterolaemic\nHypercholesterolaemic\nP\nRed meat\n1.64 ± 1.28\n1.44 ± 1.12\n< 0.001*\nPork\n1.27 ± 1.15\n0.95 ± 0.99\n< 0.001*\nPoultry\n1.42 ± 1.11\n1.44 ± 0.96\n0.562\nFish\n1.31 ± 1.11\n1.55 ± 1.15\n< 0.001*\nEgg\n1.29 ± 1.63\n0.69 ± 1.16\n< 0.001*\nBread & Cereals\n11.94 ± 8.76\n12.61 ± 8.27\n0.031*\nPasta & Rice\n2.08 ± 1.50\n1.69 ± 1.25\n< 0.001*\nPotatoes\n2.25 ± 1.74\n1.79 ± 1.43\n< 0.001*\nVegetables\n7.15 ± 3.81\n7.30 ± 3.79\n0.272\nFruits & Juices\n7.45 ± 6.15\n8.48 ± 6.92\n< 0.001*\nMilk & products Full Fat\n3.77 ± 5.00\n2.09 ± 3.88\n< 0.001*\nMilk & products Low Fat\n2.27 ± 4.14\n3.57 ± 4.83\n< 0.001*\nCheese Yellow\n2.26 ± 2.52\n1.69 ± 2.24\n< 0.001*\nCheese White\n5.07 ± 3.29\n4.47 ± 3.19\n< 0.001*\nLegumes\n1.21 ± 0.94\n1.24 ± 0.90\n0.431\nDessert or Ice Cream\n2.12 ± 2.68\n1.59 ± 2.43\n< 0.001*\nP < statistical significant difference between normo- and hypercholesterolaemic participants\nDiscussion\nThis cross – sectional study of about 5000 individuals from Greece investigated the prevalence of self-reported hypercholesterolemia and its relation to the nutritional habits of the participants. The main finding of this work was that about 1 out of 5 participants (overall population: 19.2%, men: 16.4%, women: 21.8%) reported of having high serum levels of total cholesterol. Meanwhile, the published epidemiological data regarding the current prevalence of hypercholesterolaemia in the Greek population are limited. In particular, the ATTICA study [\n17\n] is the only known, well organized and large – scale health survey that provided relevant data from an urban population. According to the aforementioned study, which was conducted to a sample from the province in which the capital of the country is located, the prevalence of clinical confirmed hypercholesterolaemia was 46.0% for men and 40.0% for women.\nIt is obvious that the respective figures of ATTICA study are around twofold of our estimations. Furthermore, our finding that hypercholesterolaemia is more prevalent in women than in men is also in contrast with the results of ATTICA study. The observed differences between the results of ATTICA study and our work can be possibly ascribed to the selected way of identifying hypercholesterolaemic participants in our study. Due to the fact that the participants self – reported whether they are hypercholesterolaemic (without confirmation via clinical examination), it is possible the prevalence's values to be underestimated as it is generally accepted that there is a large group of hypercholesterolaemic individuals unaware of their condition. Specifically, several studies [\n18\n-\n22\n] have reported that around half of those with hypercholesterolaemia are aware of their elevated cholesterol levels (the proportion varies from one-third to two-thirds across populations). Furthermore, according to the results from the WHO MONICA Project [\n16\n] (a multinational survey), the prevalence of awareness of hypercholesterolaemia was substantially higher in most populations among women. However, the fact that the prevalence of hypercholesterolaemia increases with age, which is a frequent finding of similar surveys, was also observed in the present work (Table \n4\n).\nThe significant positive associations observed between the prevalence of hypercholesterolaemia and hypertension, diabetes mellitus, obesity and physical inactiity (Table \n3\n) confirm the frequent finding from other studies [\n23\n-\n25\n], that hypercholesterolaemics usually, apart from high total cholesterol in serum, have to confront additional health problems, the coexistence of which enhances the total cardiovascular risk. However, the inverse association observed between the hypercholesterolamic status and the smoking habit is a \"pleasant\" finding since it possibly shows a trend among hypercholesterolaemic participants of avoiding this unhealthy habit in order to delay the progression of atherosclerosis. Therefore the above findings emphasize in the need for implementation of effective policies in Greece for the detection and control of hypercholesterolaemia.\nIn the present study, the expected higher prevalence of obesity (Table \n3\n) in the subgroup of hypercholesterolaemic participants was confirmed, as well as the greater values of BMI in the same subgroup (hypercholesterolaemics: 27.21 ± 6.47 kg/m\n2\n, normocholesterolaemics: 25.21 ± 5.25 kg/m\n2\n, p < 0.001). This finding shows that although hypercholesterolaemic participants are aware of their hypercholesterolaemic status, they have not managed yet to approach an ideal body weight. However, analysis of the reported food consumption patterns suggests that they might have started adopting some more healthy nutritional behaviour compared to normocholesterolaemic ones. Specifically, as it was mentioned in the results section, consumption of fish, fruits and juices, cereals, and low fat milk and yogurt was found to be higher among hypercholesterolaemic subjects while the opposite was observed for food items as red meat, pork, egg, full fat dairy products and desserts (Table \n6\n). This finding possibly reveals a first level of compliance of the Greek hypercholesterolaemic subpopulation to the respective dietary guidelines. The considerable differences observed among the two subpopulations in relation to the consumption of eggs and full fat dairy products (about twofold) support this hypothesis, since avoidance of the over-consumption of the specific food items, due to their high content of saturated fat, is a very common guideline to people with hypercholesterolaemia. Furthermore, the majority of the hypercholesterolaemic participants (65.3% of men and 71.2% of women) reported (Table \n5\n) implementation of dietary treatment (combined or not with drug treatment), which possibly explains the observed trend towards a more healthy food consumption pattern. However, the reported food consumptions are quite different from the recommended ones, according to the beneficial dietary pattern of Mediterranean Diet [\n10\n,\n26\n,\n27\n] which among others highlights the importance of adequate consumption of vegetables and legumes.\nLimitations\nThis study as a cross-sectional one cannot establish causal relations but only generate hypothesis that could be evaluated by future prospective randomized trials. Additionally, the applied method of self – reporting hypercholesterolaemia neither is able to provide data relevant to the level of hypercholesterolaemia's awareness (thus the evaluated prevalence of hypercholesterolaemia may be underestimated), nor can be as accurate as the biochemical tests. However, Natarajan et al. [\n28\n], who investigated the validity of self-reported hypercholesterolaemia in the U.S. adult population, suggested that this method may be used for surveillance of hypercholesterolaemia trends in the absence of measured cholesterol levels, but caution should be given when interpreting the results due to low sensitivity of the method. Another methodological limitation of the present study is that analysis of semi-quantitative food frequency questionnaires cannot provide accurate data in terms of specific nutrients, so conclusions should be expressed only in relation to food groups or items tested.\nConclusion\nAccording to the presented data, hypercholesterolaemia affects a large part of the Greek population. Possibly the adoption of \"westernized\" dietary patterns by Greeks during last decades, played a strong role for this phenomenon. Since, effective treatment of hypercholesterolaemia is an important element of strategies to prevent cardiovascular disease, we suggest that periodic cholesterol measurement is considered essential and must be followed by active and effective interventions.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
78
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nComplete atrioventricular canal\n\n**Article Abstract:**\n\nComplete atrioventricular canal (CAVC), also referred to as complete atrioventricular septal defect, is characterised by an ostium primum atrial septal defect, a common atrioventricular valve and a variable deficiency of the ventricular septum inflow. CAVC is an uncommon congenital heart disease, accounting for about 3% of cardiac malformations. Atrioventricular canal occurs in two out of every 10,000 live births. Both sexes are equally affected and a striking association with Down syndrome was found. Depending on the morphology of the superior leaflet of the common atrioventricular valve, 3 types of CAVC have been delineated (type A, B and C, according to Rastelli's classification). CAVC results in a significant interatrial and interventricular systemic-to-pulmonary shunt, thus inducing right ventricular pressure and volume overload and pulmonary hypertension. It becomes symptomatic in infancy due to congestive heart failure and failure to thrive. Diagnosis of CAVC might be suspected from electrocardiographic and chest X-ray findings. Echocardiography confirms it and gives anatomical details. Over time, pulmonary hypertension becomes irreversible, thus precluding the surgical therapy. This is the reason why cardiac catheterisation is not mandatory in infants (less than 6 months) but is indicated in older patients if irreversible pulmonary hypertension is suspected. Medical treatment (digitalis, diuretics, vasodilators) plays a role only as a bridge toward surgery, usually performed between the 3rd and 6th month of life.\n\n**Article Body:**\n\nDisease name and synonyms\nComplete atrioventricular canal (CAVC); Common atrioventricular canal; Complete atrioventricular septal defect.\nEuropean paediatric cardiac code\nReference of Complete atrioventricular canal is 06.06.09.\nDefinition\nCAVC is a complex cardiac malformation characterised by a variable deficiency of the atrioventricular area (crux cordis) in the developing heart. The malformation involves the atrial, ventricular and atrioventricular septa and both atrioventricular valves.\nDiagnosis criteria\nDiagnosis of CAVC might be clinically suspected in patients presenting in the first few months of life with congestive heart failure, cardiomegaly on chest X-ray and left axis deviation, bi-atrial enlargement and bi-ventricular pressure and volume overload on electrocardiogram (ECG). Echocardiography is the key tool for the diagnosis and anatomic classification of this malformation. It shows the ostium primum atrial septal defect, with the underlying common atrioventricular valve, and the defect of the ventricular septal inflow (Figure \n1\n).\nFigure 1\nEchocardiography of Complete atrioventricular canal.\nThe anatomic subgroups (Rastelli's type A, B and C) can be classified on the basis of the chordal insertions and morphology of the superior bridging leaflet of the common atrioventricular valve (Table \n1\n). Similarly, a thorough echocardiographic examination shows the degree of dysfunction of the common atrioventricular valve, as well as the presence of associated cardiac malformations. To date, cardiac catheterisation is not considered as mandatory for the diagnosis, but can be indicated in patients older than 6 months with suspected irreversible pulmonary hypertension. Cardiac catheterisation allows accurate quantification of the left-to-right shunt as well as assessment of the degree of pulmonary hypertension and the reversibility of the pulmonary artery resistances by hyperoxia and/or pharmacological tests. On left ventricular angiography, the appearance of the \"gooseneck deformity\" of the left ventricular outflow tract is peculiar of atrioventricular canal malformations.\nTable 1\nAnatomic classification of CAVC [4]\nType A\nthe superior bridging leaflet is almost completely adherent to the left ventricle and is firmly attached on the ventricular septum by multiple chordal insertions\nType B\nthe superior bridging leaflet is attached over the ventricular septum by an anomalous papillary muscle of the right ventricle\nType C\nthe superior bridging leaflet is not attached to the ventricular septum (free-floating leaflet)\nDifferential diagnosis\nDifferential diagnosis of CAVC involves mainly the unrestrictive ventricular septal defect, associated or not to mitral valve insufficiency. The clinical picture of congestive heart failure, the bi-atrial and bi-ventricular overload on ECG, and cardiomegaly and pulmonary congestion on chest X-ray are common to the ventricular septal defect. However, on ECG the left axis deviation of QRS at -30°, usually combined with a various degree of right bundle branch block, appears to be suggestive of CAVC. Eventually, the echocardiographic examination is the cornerstone for diagnosis and is of help for that of any further associated cardiac malformation.\nEpidemiology\nCAVC accounts for about 3% of all cardiac malformations. Atrioventricular canal occurs in two out of every 10,000 live births. Both sexes are equally affected, with a slightly higher frequency in female (female/male ratio 1.3/1) and a striking association with Down syndrome was found [\n1\n,\n2\n].\nPathology\nThe complete form of AVC shows an ostium primum atrial septal defect, a common atrioventricular valve and a variable deficiency of the interventricular septum inlet [\n2\n,\n3\n]. This anatomic arrangement gives a scooped out appearance to the ventricular inlet and a long and narrow morphology to the left ventricular outlet. The key finding for the anatomic classification in type A, B or C of this malformation is the morphology of the common atrioventricular valve [\n4\n]. It is basically built-up of five leaflets (superior, inferior, mural in the right and left ventricle and antero-superior), embryologically derived from the original endocardial cushions. The size of the antero-superior leaflet is reciprocal with the extent of bridging of the superior leaflet. In type A, the superior bridging leaflet is almost completely adherent to the left ventricle and is firmly attached on the ventricular septum by multiple chordal insertions. In type B, the superior bridging leaflet is larger and overhangs the ventricular septum more than in type A, attached over it by an anomalous papillary muscle of the right ventricle. In type C, the superior bridging leaflet is larger and is not attached to the ventricular septum (free-floating leaflet), thus provoking an unrestricted interventricular communication. Type A CAVC is most frequently associated with left-sided obstructions. Type B is the least common form of atrioventricular canal. Type C is often associated with other complex cardiac malformations such as tetralogy of Fallot. Other cardiac malformations are the left ventricular inflow and outflow obstructions, mainly due to anomaly of the left component of the common atrioventricular valve, and to ventricular imbalance, with right ventricular dominance. These additional left-sided anomalies are more frequent in children without Down syndrome [\n5\n-\n7\n].\nA \"partial variant\" of AVC exists (also known as ostium primum atrial septal defect). Nevertheless, some authors observed how \"complete\" and \"partial\" are inappropriate adjectives to describe these variants [\n8\n-\n11\n]. Indeed, despite the septal deficiency, the essence of the atrioventricular canal malformations (or atrioventricular septal defects) is the common atrioventricular junction [\n8\n-\n11\n]. Within this common junction, there may be a common atrioventricular valvar orifice (so called \"complete\" defects), or separate right and left valvar orifices for the right and left ventricles (so called \"partial\" defects).\nThe space between the left ventricular components of the superior and inferior bridging leaflets is traditionally called \"cleft\". Morphological studies suggested that this gap functions as a commissure, even though it is not supported by a papillary muscle [\n12\n]. In Rastelli's type A malformation, the space in the common anterior leaflet is also called \"cleft\". Again, it potentially functions as a commissure, being supported by the medial papillary muscle of the right ventricle [\n12\n].\nClinical description\nSymptoms occur in infancy as a result of high pulmonary blood flow associated with pulmonary hypertension, and often complicated by insufficiency of the common atrioventricular valve. Failure to thrive, as well as congestive heart failure and frequent pulmonary infections, are invariably seen. Thus, patients with CAVC often have feeding problems and are virtually symptomatic in the first few months of life. Signs of congestive heart failure consist in feeding difficulties, excessive sweating, tachycardia, tachypnea, subcostal and intercostal retractions, mild wheezing, hepatic enlargement and poor peripheral blood perfusion [\n13\n]. If a significant regurgitation of the common atrioventricular valve is present, a systolic cardiac murmur and gallop rhythm are frequently heard. Over time, irreversible pulmonary hypertension develops, improving the signs of congestive heart failure but worsening tolerance to effort. When pulmonary artery resistances becomes higher than systemic artery resistances, the intracardiac shunt reverses and cyanosis develops, further decreasing the exercise capacity.\nNatural history\nHalf of children with untreated CAVC die in the first year of life [\n1\n,\n13\n,\n14\n]. The main cause of death in infancy is either heart failure or pneumonia. In surviving patients with unrepaired complete atrioventricular canal, irreversible pulmonary vascular disease becomes increasingly common, and affects virtually all patients older than 2 years of age [\n15\n]. Long-term prognosis in patients with irreversible pulmonary hypertension is poor.\nTreatment\nMedical treatment\nMedical therapy aims to improve the signs and symptoms of congestive heart failure. Thus, it should be just considered as a bridge toward surgery. Pharmacological therapy is based on digitalis, diuretics and vasodilators. Oral therapy with digoxin starts with a loading dose of 20–40 \nμ\ng/kg (depending on the patient's age, from premature to child) in 3 doses over 24 h, continuing with a maintenance dose of 8–10 \nμ\ng/kg/day in 2 doses. Diuretic therapy is mainly based on furosemide, at the dose of 1–6 mg/kg/day, and spironolactone, at the dose of 2–3.5 mg/kg/day. Vasodilator therapy consists chiefly in the angiotensin converting enzyme inhibitors, captopril (0.5–3 mg/kg/day, tid) or enalapril (0.1–0.4 mg/kg/day, bid). Increasing interest is raising regarding the utilisation and potential benefits of beta-blockers (mainly, propanolol, metoprolol and carvedilol) in infants and children heart failure due to congenital heart defects with left to right shunt, although long-term results are needed. Finally, the new generation of pulmonary vasodilators dramatically improved the post-operative course and the overall prognosis of the patients [\n16\n].\nSurgical treatment\nSurgical treatment is preferably scheduled before 6–12 months of life. Generally, the great majority of surgeons perform the repair between the 3rd (to reduce the incidence of pulmonary hypertension crisis) and the 6th month of life. Surgical palliation with pulmonary artery banding is now seldom indicated in high-risk infants (very low weight and/or in critical conditions). It reduces the pulmonary artery flow and pressure, so controlling the congestive heart failure, promoting the patient's growth and preventing the development of pulmonary vascular disease, but is contra-indicated in patients with severe atrioventricular valve regurgitation. However, more frequently complete intracardiac repair is indicated. It consists in closure of the intracardiac communications with a single or separate atrial and ventricular patches, in construction of two separate and competent atrioventricular valves using the available tissue from the common atrioventricular valve leaflet, and in repair of associated cardiac anomalies [\n13\n,\n17\n,\n18\n]. An alternative technique, using a direct suture closure of the ventricular component, accompanied by pericardial patch closure of the atrial component, was first suggested by Wilcox \net al\n. [\n19\n]. Depending on the specific anatomic findings (\ni.e\n., in absence of severe \"scooping\" of the ventricular septum), the lesion can be adequately repaired in most instances by sewing down the bridging leaflets to the crest of the ventricular septum.\nRisk factors for surgical repair include the patient's age, the severity of pre-operative common valve incompetence, the presence of associated cardiac malformations and the degree of the functional class [\n20\n][\n21\n][\n22\n][\n23\n]. The prognosis is directly related to the repair of the left A-V valve [\n20\n]. To date, the overall mortality for primary repair of CAVC is below 5–10%. Long-term survival is good and in 80%–95% of cases there is no need for reoperation [\n18\n,\n21\n]. Of note, the closure of the cleft results in longer times before a reoperation is necessary [\n24\n].\nAetiology\nFormation of atrioventricular canal results from complex interactions of components of the extracellular matrix. Septation of the atrioventricular junction is brought about by downgrowth of the primary atrial septum, fusion of the endocardial cushions and forward expansion of the vestibular spine between atrial septum and cushions [\n3\n]. Thus, atrioventricular canal can result from arrest or interruption of the normal endocardial cushion development [\n25\n,\n26\n]. Experimental studies showed that environmental teratogens [\n27\n] or endogenous metabolic abnormalities [\n28\n] might result in abnormal development of the atrioventricular area, which may be due to altered apoptosis of these forming cells [\n29\n]. Trancription factors (TBX2, Foxp1 among the others) and signal pathways (ErbB receptor activation) involved during embryogenesis in the heart development process have been strongly suggested to have a role in atrioventricular septation [\n30\n-\n32\n].\nEpidemiological studies [\n2\n,\n33\n] showed that complete atrioventricular canal tends to be associated with chromosomal abnormalities, mainly Down syndrome [\n10\n], del [8p] syndrome [\n34\n], trisomy 9, trisomy 18 [\n6\n,\n35\n]. Furthermore, CAVC with Down syndrome has been less frequently associated with left cardiac anomalies than the isolated form [\n5\n,\n7\n]. In this latter subset of patients, the analysis of potential risk factors revealed an association with maternal diabetes and antitussive drugs [\n36\n]. However, in patients with Down syndrome and complete AVC, no strong association other than maternal age has been found. In the asplenia syndrome, the CAVC is virtually always present, while it occurs in about 25% of patients with polisplenia [\n37\n]. An association between nonchromosomal defects and atrioventricular malformations have also been reported [\n5\n,\n6\n].\nGenetic counselling and antenatal diagnosis\nIn the presence of a single affected family member, the risk of siblings of inheriting the defect is about 2%, with a higher percentage for the offspring of an affected parent. Concordance for atrioventricular malformations among siblings is higher than for other types of congenital heart defects [\n38\n].\nDue to the strict association with Down syndrome and other chromosomal anomalies, genetic antenatal counselling after the foetal echocardiographic diagnosis of CAVC is mandatory. At present, prenatal diagnosis of CAVC has been associated with a 58% risk of aneuploidy, mainly trisomy 21 [\n39\n]. Again, due to the strong association between chromosomal abnormalities and CAVC, when this malformation seems isolated at antenatal echocardiography, the risk of trisomy 21 is significantly higher than when other associated cardiac lesions are diagnosed.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
79
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nCan We Identify Sources of Fine Particles Responsible for Exercise-Induced Ischemia on Days with Elevated Air Pollution? The ULTRA Study\n\n**Article Abstract:**\n\nEpidemiologic studies have shown that ambient particulate matter (PM) has adverse effects on cardiovascular health. Effective mitigation of the health effects requires identification of the most harmful PM sources. The objective of our study was to evaluate relative effects of fine PM [aerodynamic diameter ≤ 2.5 μm (PM\n2.5\n)] from different sources on exercise-induced ischemia. We collected daily outdoor PM\n2.5\n samples between autumn 1998 and spring 1999 in Helsinki, Finland. The mass of PM\n2.5\n was apportioned between five sources. Forty-five elderly nonsmoking persons with stable coronary heart disease visited a clinic biweekly for submaximal exercise testing, during which the occurrence of ST segment depressions was recorded. Levels of PM\n2.5\n originating from local traffic and long-range transport were associated with ST segment depressions > 0.1 mV, with odds ratios at 2-day lag of 1.53 [95% confidence interval (CI), 1.19–1.97] and 1.11 (95% CI, 1.02–1.20) per 1 μg/m\n3\n, respectively. In multipollutant models, where we used indicator elements for sources instead of source-specific PM\n2.5\n, only absorbance (elemental carbon), an indicator of local traffic and other combustion, was associated with ST segment depressions. Our results suggest that the PM fraction originating from combustion processes, notably traffic, exacerbates ischemic heart diseases associated with PM mass.\n\n**Article Body:**\n\nFor a long time, it was assumed that ambient particulate matter (PM) damages primarily the lungs (\nDockery and Pope 1994\n; \nPope 1989\n). Epidemiologic evidence accumulated during the last decade shows that daily PM levels are also associated with daily changes in mortality and hospitalizations due to cardiovascular diseases (\nKatsouyanni et al. 2001\n; \nSamet et al. 2000\n; \nSchwartz 1999\n; \nZanobetti et al. 2000\n). Cohort studies suggest that cumulative effects of air pollution on cardiovascular health are even more important than acute effects (\nPope et al. 2002\n, \n2004\n). Although the relative risks associated with exposure to PM are small compared with some other cardiovascular risk factors, the attributable health effects may be enormous because of the ubiquitous nature of exposure. As an example, 6% of annual deaths has been assigned to PM air pollution in three European countries (\nKünzli et al. 2000\n). Consequently, the World Health Organization (WHO) in the 1990s included air pollution on the list of 10 major risks for death and disability (\nWHO 1996\n).\nIn general, air quality has markedly improved in developed countries during the last few decades. Unfortunately, no lower threshold has been observed for the effects of PM (\nDaniels et al. 2000\n), and further efforts to decrease the PM levels are increasingly costly. Cost-effective mitigation of health effects requires regulation of primarily those PM sources that are responsible for the effects. However, the constituents and characteristics of PM responsible for the observed cardiovascular effects are unknown. Toxicologic studies suggest the importance of transition metals (\nGoldsmith et al. 1998\n; \nPagan et al. 2003\n), organic carbon compounds (\nBonvallot et al. 2001\n; \nUrch et al. 2004\n), endotoxins (\nLong et al. 2001\n; \nOsornio-Vargas et al. 2003\n), and the smallest PM fraction, ultrafine particles (UF; < 0.1 μm in diameter) (\nBrown et al. 2003\n; \nLi et al. 2003\n). The few epidemiologic studies that have compared the relative effects of different sources on cardiovascular health suggest that combustion particles are more important than crustal particles (\nLaden et al. 2000\n; \nMar et al. 2000\n; \nTsai et al. 2000\n).\nThe occurrence of ST segment depressions during stress tests indicates myocardial ischemia [\nAmerican College of Cardiology/American Heart Association (ACC/AHA) 1997\n]. We have previously shown in a panel of coronary heart disease patients that increases in the daily levels of UF and fine PM [aerodynamic diameter ≤ 2.5 μm (PM\n2.5\n)] are associated with increased risk of ST segment depressions in Helsinki, Finland (\nPekkanen et al. 2002\n). Our results provided an explanation for the associations observed in epidemiologic studies between ambient PM and hospitalizations and death due to ischemic heart diseases. We recently apportioned PM\n2.5\n measurements of the earlier study between five major sources (\nVallius et al. 2003\n). Using these data, we now evaluate the relative, short-term effects of PM\n2.5\n from different sources on myocardial ischemia.\nMaterials and Methods\nStudy population and protocol.\nThe ULTRA (Exposure and Risk Assessment for Fine and Ultrafine Particles in Ambient Air) study was conducted in Amsterdam, the Netherlands, Erfurt, Germany, and Helsinki, Finland, between autumn 1998 and spring 1999. In each city, we followed panels of elderly subjects with stable coronary heart disease for 6 months with biweekly clinic visits and daily symptom and medication diaries. At the same time, levels of PM and gaseous air pollutants were monitored at fixed outdoor monitoring sites. We conducted all methods according to standard operating procedures (\nPekkanen et al. 2000\n).\nThe main inclusion criteria for the study were a self-report on a doctor-diagnosed coronary artery disease and being a nonsmoker and at least 50 years of age. The study subjects were characterized by a questionnaire and recording of a 12-lead standard resting electrocardiogram. For each subject, the clinic visit was scheduled for the same weekday and time of day. At every visit, ambulatory electrocardiogram was recorded during a standardized protocol, which included 6-min submaximal exercise with a bicycle ergometer (\nPekkanen et al. 2002\n).\nEthical committees in each country had approved the study protocol. All subjects gave a written informed consent before the study.\nRecording of ST segment depressions.\nWe have described elsewhere the methodology used for the recording of ST segment depressions in detail (\nPekkanen et al. 2002\n). Briefly, the ambulatory electrocardiograms were recorded with Oxford MR-63 tape recorders (Oxford Instruments, Abington, UK), and the recordings were analyzed with the Oxford Medilog Excel II system (V7.5, Oxford Instruments) in one core laboratory. ST depressions were measured at 63 msec after J-point. Only ST depressions having their start time during the exercise test were considered.\nWe used two end points in the present analyses: ST depressions > 0.1 mV regardless of the direction of the ST slope (\nRijneke et al. 1980\n), and ST depressions > 0.1 mV with horizontal or downward slope (i.e., stricter criteria) (\nACC/AHA 1997\n). The present analyses are limited to Helsinki, because there were only seven ST segment depressions > 0.1 mV in Amsterdam and five in Erfurt (\nPekkanen et al. 2002\n). This was mainly due to the low heart rates achieved during the exercise tests. The low heart rates were mostly attributable to the fact that the study was done in the community setting and the fieldworkers were very cautious in performing the exercise tests among coronary patients.\nExposure monitoring.\nIn Helsinki, all study subjects lived within a 5-km radius of the fixed outdoor PM\n2.5\n monitoring site. We collected daily noon-to-noon PM\n2.5\n filter samples with single-stage Harvard impactors, 1 November 1998 to 30 April 1999. PM\n2.5\n concentrations were determined gravimetrically. After weighing, blackness of filters was measured and transformed into absorption coefficients [i.e., absorbance (ABS)]. ABS is correlated with elemental carbon content of urban PM (\nCyrys et al. 2003\n; \nJanssen et al. 2001\n). We have reported the laboratory methods and quality-control results elsewhere (\nBrunekreef et al. 2005\n; \nJanssen et al. 2001\n).\nAll PM\n2.5\n filter samples were analyzed for elemental composition with energy-dispersive X-ray fluorescence spectrometry. Automated Tracor Spectrace 5000 system (Tracor X-ray, Austin, TX, U.S.) was used for analyses in the Department of Chemistry, University of Antwerp (Belgium). The accuracy varied between 1 and 28% depending on the element and its concentration on the filter. Eighteen elements were analyzed. Details of the elemental analyses have been reported earlier (\nBrunekreef et al. 2005\n; \nJanssen et al. 2005\n).\nNumber counts of UF were measured with an electrical aerosol spectrometer developed in the Institute of Environmental Physics of the University of Tartu, Estonia (\nTammet et al. 2002\n). The Helsinki Metropolitan Area Council (Helsinki, Finland) provided the data on daily average temperature, and the Finnish Meteorological Institute (Helsinki, Finland) provided the data on relative humidity.\nData analysis.\nWe used principal component analysis and multivariate linear regression to apportion PM\n2.5\n mass between different sources. We identified source categories by examining the loadings of elements and other variables on the varimax (orthogonal) rotated principal components. We obtained estimates of daily source-specific PM\n2.5\n concentrations by regressing the measured PM\n2.5\n concentrations on absolute principal component scores (\nThurston and Spengler 1985\n). Besides components of PM\n2.5\n (elemental concentrations and ABS), daily data on UF and accumulation mode PM (diameter 0.1–1.0 μm), nitrogen dioxide, and sulfur dioxide were used to identify sources. We excluded 4 days from the elemental data because of outliers, leaving 164 days for analyses. Five main source categories were identified: local traffic (with contribution from other local combustion), long-range–transported air pollution, crustal source, oil combustion, and salt source. The source apportionment methodology and results have been previously published (\nVallius et al. 2003\n).\nAir pollution concentrations of 0- to 3-day lags were evaluated. Lag 0 concentration was defined as the 24-hr average from noon the previous day to noon of the day of the clinic visit; lag 1 concentration as the average concentration of the previous 24 hr, and so on. A basic confounder model was built for ST segment depressions > 0.1 mV without including PM, and the same model was used for the horizontal- or downward-sloping ST segment depressions > 0.1 mV. Loess functions were used to explore shapes and lags (0–3) of the covariates in S-Plus 2000 software (MathSoft Inc., Seattle, Washington, USA) (\nHastie and Tibshirani 1990\n). Criteria for building the basic model were Akaike’s Information Criterion (\nAkaike 1974\n) and covariate-response plots. The protocol of statistical analyses is available at the ULTRA study web-site (\nhttp://www.ktl.fi/ultra\n). Because of the recently raised questions on the usability of generalized additive models in S-Plus for air pollution research (\nDominici et al. 2002\n), we conducted final analyses in the statistical package R (R \nProject 2006\n) using logistic regression (R-GAM function) with penalized splines (\nEilers and Marx 1996\n; \nWood 2001\n). The basic model included a dummy for each subject; linear terms for time trend, temperature (lag 3), and relative humidity (lag 3); and a penalized spline (df = 3) for change in heart rate during the exercise test.\nAs a sensitivity analysis, we evaluated the effect of extreme concentrations on results. For each PM\n2.5\n source, we calculated an outlier concentration corresponding to three times the interquartile range of each lag and excluded all observations higher than the lowest of these outlier concentrations from all the lags.\nVarimax rotation used in principal component analysis forces the daily source-specific PM\n2.5\n concentrations to be noncorrelating (\nThurston and Spengler 1985\n), which does not always reflect reality. To allow correlation, we also constructed multipollutant models where indicator elements for sources were used instead of source-specific mass. For every source, the element with the highest correlation with source-specific mass was chosen as the indicator.\nFinally, we evaluated whether potentially toxic elements, not among the indicator elements, would be associated with ST segment depressions. Various two-pollutant models were also constructed using individual elements and UF, but gaseous pollutants were not included in the models. Gaseous pollutants measured at a fixed outdoor monitoring site have been observed to reflect better exposures to PM\n2.5\n than to gases themselves (\nSarnat et al. 2005\n). Thus, interpretation of the models would have been difficult.\nResults\nThere were 417 exercise tests performed during 511 visits among 47 subjects. Of the 417 exercise tests, we excluded 67 because of substandard quality of the recording and eight because of missing data on covariates, leaving 342 exercise tests for analyses. There were altogether 45 study subjects in the final analyses; 24 of them were male. Mean (± SD) age of the subjects was 68.2 ± 6.5 years. Twenty-three of the subjects had had coronary bypass surgery or percutaneous transluminal coronary angioplasty, 27 had history of myocardial infarction, and 31 used beta-blockers. Details of the study panel have been published previously (\nPekkanen et al. 2002\n).\nDuring the study, 164 valid outdoor samples were collected. Thirteen elements [potassium (K), vanadium (V), manganese (Mn), copper (Cu), zinc (Zn), lead (Pb), aluminum (Al), silicon (Si), sulfur (S), chlorine (Cl), calcium (Ca), iron (Fe), nickel (Ni)] were detectable in > 50% of samples, and the rest were excluded from analyses. In addition, Pb and Al were left out of the present analyses because of low precision and reliability (\nJanssen et al. 2005\n). However, these elements were used in source apportionment, because even less precisely detected elements can improve the apportionment of PM between sources (\nVallius et al. 2003\n).\nDescriptive statistics for components of PM\n2.5\n and UF are presented in \nTable 1\n. Sulfur was the most abundant element. Half of mass was apportioned to sulfur-rich long-range–transported PM\n2.5\n.\nMany of the elements were highly correlated (\nTable 2\n). PM\n2.5\n was highly correlated with K, S, Zn, and ABS but not with UF. The highest correlation coefficients between elements and source-specific PM\n2.5\n were found between Si and crustal PM\n2.5\n, S and long-range–transported PM\n2.5\n, Ni, and V and PM\n2.5\n from oil combustion, Cl and PM\n2.5\n from salt source (salt source also characterized by high Pb concentrations), and ABS and traffic-originating PM\n2.5\n.\nMedian (minimum) daily temperature and relative humidity during the study period were −0.44°C (−23.3) and 87.6% (51.1), respectively. Temperature was negatively correlated with PM\n2.5\n from local traffic (\nr\n = −0.33) and oil combustion (\nr\n = −0.35), and relative humidity with PM\n2.5\n from oil combustion (\nr\n = −0.36) and crustal source (\nr\n = −0.55).\nAssociations between levels of source-specific PM\n2.5\n and the occurrence of ST segment depressions are presented in \nTable 3\n. PM\n2.5\n originating from local traffic as well as long-range–transported PM\n2.5\n were associated with ST segment depressions > 0.1 mV. In addition, when the stricter criterion for ST segment depressions was used, a suggestive association of PM\n2.5\n originating from oil combustion emerged. The highest observed odds ratios (ORs) were for PM\n2.5\n from crustal source and from salt source at lag 3, but the associations were not consistent or statistically significant.\nExclusion of extreme concentrations (at maximum 13 measurements per lag) from source-specific PM\n2.5\n changed the results only for oil combustion. The OR at lag 2 fell below 1, and for the strict criteria for ST segment depression, the association got weaker.\nIn a multipollutant model that included indicator elements for all sources, only ABS, a marker for local traffic, was associated with ST segment depressions (\nTable 4\n). The confidence intervals (CIs) were rather wide, and wider than in single-pollutants models (data not shown), obviously because of inclusion of several correlating variables in the same model.\nIn the single-pollutant models most of the individual elements—Cu, Fe, K, Mn, Ni, S, and Zn—were significantly (\np\n < 0.05) associated with ST segment depressions > 0.1 mV at lag 2 (data not shown), possibly due to high intercorrelations. However, when potentially toxic elements (Cu, Fe, Zn, V) were included in two-pollutant models together with ABS, none of them was associated with ST segment depressions. In all two-pollutant models, statistically significant association between ABS and ST segment depressions > 0.1 mV remained at lag 2, and ORs for ABS varied only slightly: from 3.93 to 5.03 (data not shown).\nInterquartile range of long-range–transported PM\n2.5\n was much higher than interquartile ranges of other source-specific masses (\nTable 1\n). We therefore also calculated ORs at lag 2 per interquartile range of source-specific PM\n2.5\n for ST segment depressions > 0.1 mV (\nFigure 1\n). For comparison, ORs for the association of (total) PM\n2.5\n, UF, and ABS are also presented.\nFinally, we tested whether the association of UF with ST segment depressions > 0.1 mV is robust to adjustment for ABS. The effect of ABS remained, but UF was no more significantly associated with ST segment depressions at lag 2. OR (95% CI) for ABS was 3.44 (1.25–9.50), and for UF, 1.38 (0.53–3.61).\nDiscussion\nExposure to air pollution, especially PM, has been linked to exacerbations of ischemic and arrhythmic cardiac diseases and congestive heart failure (\nKwon et al. 2001\n; \nLe Tertre et al. 2002\n; \nPeters et al. 2000\n; \nZanobetti et al. 2000\n) and triggering of the onset of myocardial infarction (\nPeters et al. 2001\n, \n2004\n). Promotion of atherosclerosis is likely to be involved in the chronic pathways of air pollution effect (\nBrook et al. 2004\n). The plausibility of a causal association is increased by the established association between passive smoking and heart disease (\nBarnoya and Glantz 2004\n). Our research team has previously published evidence on the association between PM\n2.5\n and myocardial ischemia, as indicated by the occurrence of exercise-induced ST segment depressions among patients with coronary heart disease (\nPekkanen et al. 2002\n). The observed association provided a plausible biologic link between levels of PM air pollution and adverse cardiac outcomes (\nVerrier et al. 2002\n). The same data were used in the present study.\nAmbient PM is a very heterogeneous mixture of organic and inorganic components from multiple sources, and it is unlikely that all components have similar effects on the cardiovascular system. Our present results suggest that the composition of PM\n2.5\n originating from local traffic is the most toxic, because the OR per microgram was high and the association was statistically significant. However, the effect of long-range–transported PM\n2.5\n was comparable with the effect of traffic-originating PM\n2.5\n when the estimate was calculated per measured interquartile range of the pollutant. This is caused by greater daily variability in the levels of long-range–transported PM\n2.5\n and implies that by reducing high-concentration days of either of the sources, equal benefits are attainable. Associations between other sources and ST segment depressions were less consistent and not statistically significant, although high ORs were observed. PM\n2.5\n originating from local traffic correlated highly with UF (\nr\n = 0.79), whereas long-range–transported PM\n2.5\n correlated highly with PM\n2.5\n (\nr\n = 0.82). Considering this, present results are in line with our previous study (\nPekkanen et al. 2002\n), where we found levels of UF and PM\n2.5\n to be independently associated with ST segment depressions.\nThere are few earlier studies that have compared health effects of PM\n2.5\n from different sources, and all of them are mortality studies in the United States. The studies suggest effects of PM\n2.5\n from a variety of combustion sources, and fewer effects of soil-originating PM\n2.5\n. In a time-series study of six eastern U.S. cities (\nLaden et al. 2000\n), only PM\n2.5\n from traffic was weakly associated with increased daily mortality from ischemic heart disease, whereas both traffic and coal combustion were associated with increased total mortality. There was also a suggestion of a positive effect of oil-combustion–originating PM\n2.5\n on total mortality in the cities where the source was identified. In Phoenix (\nMar et al. 2000\n), cardiovascular mortality was associated with PM\n2.5\n from traffic, biomass combustion, and regional pollution (indicated by sulfate). Total mortality was associated positively, although inconsistently, with regional sulfate. At three sites in New Jersey (\nTsai et al. 2000\n), both total and cardiorespiratory mortality were associated with several sources of inhalable PM (aerodynamic diameter < 15 μm) including, depending on site, traffic and oil combustion, industry, and sulfate aerosol.\nThe source-apportionment method as used in our study yields noncorrelating source-specific PM\n2.5\n concentrations. In an alternative approach, we constructed multipollutant models where indicators of sources were used instead of source-specific masses, and thus sources were allowed to correlate. In these models, only ABS (measure of elemental carbon), the chosen indicator for local traffic, was associated with ST segment depressions, whereas the effect of long-range PM\n2.5\n, as represented by sulfur, disappeared. ABS correlated in our study both with local traffic and long-range–transported PM\n2.5\n (\nr\n = 0.74 and \nr\n = 0.46, respectively). Thus, results suggest that the effect of long-range PM\n2.5\n is more related with carbon products than with secondary sulfate. ABS is associated with a variety of combustion processes, but ambient concentrations are mostly affected by diesel particles (\nGray and Cass 1998\n).\nIt has been suggested that transition metals and/or organic carbon compounds adsorbed onto the elemental carbon core formed in incomplete combustion are responsible for the cellular changes associated with PM (\nChin et al. 1998\n; \nObot et al. 2002\n). Capability to induce oxidative stress in lungs is common to transition metals and organic carbon compounds (\nKelly 2003\n). In the present study, most of the elements were associated with ST segment depressions, probably due to high intercorrelations. We did not find evidence for an effect of any of the potentially toxic transition metals when adjusting for ABS.\nRecently, some toxicologic studies have suggested that the effects of UF on human health would be due to organic chemicals (\nLi et al. 2003\n; \nXia et al. 2004\n). On the other hand, the composition of UF might not be decisive, but even inert PM in the UF size range seems to be capable of inducing oxidative stress because of great number, large surface area, and high penetration (\nBrown et al. 2003\n; \nDonaldson et al. 2001\n). When we adjusted UF for ABS, the association of UF with ST depressions weakened. Two-pollutant models of correlating variables should be interpreted with caution, but the results suggest that carbon content of PM may be more important than size. Consequently, the apparently independent effects of PM\n2.5\n and UF that we observed previously could be explained by considering the two pollutants as indicators of two combustion sources with different temporal variation—long-range transport and local traffic.\nWe have previously shown in this same study population that outdoor concentrations of ABS correlate longitudinally (the relevant measure in time-series studies) highly with personal exposure, even better than PM\n2.5\n (\nJanssen et al. 2000\n). There is a general lack of such information for UF, and it is possible that central outdoor measurements reflect worse day-today changes in exposure to UF than to ABS (\nPekkanen and Kulmala 2004\n). This could weaken the association of UF with ST segment depressions in the two-pollutant model. However, most of the study participants lived very close (within 2 km) to the central monitoring site, which is likely to improve not only spatial but also longitudinal correlation.\nPM can increase cardiovascular disease risk through several pathways, which have different lags. It is hypothesized that the local inflammation in lungs caused by PM starts a cascade of events that leads to systemic inflammation as indicated by increased levels of inflammatory mediators in blood (\nBrook et al. 2004\n). The systemic inflammation in turn might transfer the myocardium and myocardial circulation into a state that is vulnerable to various triggers of acute coronary syndrome (\nMuller et al. 1994\n). In our study, the effect of ABS on ST segment depressions was delayed, with strongest association observed at a 2-day lag, which is in agreement with systemic inflammation. There is evidence that PM can also trigger acute events. PM\n2.5\n has been observed to increase risk of myocardial infarction both several hours and several days after exposure (\nPeters et al. 2001\n). In a recent study, an association was found between exposure to traffic and the onset of myocardial infarction within 1 hr afterward (\nPeters et al. 2004\n). Chronic exposure to traffic-related air pollution has also been associated with adverse effects on health (\nFinkelstein et al. 2004\n; \nGauderman et al. 2004\n; \nHoek et al. 2002\n).\nLow numbers posed two major limitations in our study. Low number of study subjects calls for caution when comparing the magnitudes of odd ratios. Modest number of elements available for analyses leaves room for speculations about unidentified harmful constituents. Above all, we were not able to analyze organic compounds. Newer, more sophisticated methods of source apportionment could also be used in the future. However, different source-apportionment methods usually produce similar main sources, although, for example, traffic is a more difficult source because of lack of unique elemental tracers (\nThurston et al. 2005\n). We used UF and gaseous pollutants in the source apportionment, which clearly improved the results (\nVallius et al. 2003\n). No method totally bypasses the fact that meteorology drives the concentrations of pollutants from all sources into the same direction. In our case, local traffic partly included emissions from other, nonspecified local combustion processes due to common meteorology. In any case, any source-specific PM\n2.5\n in our study should be considered merely as a marker of a harmful factor in PM; causal factors are still to be identified.\nAn unavoidable limitation in the study was the exclusion of summer time, because the elderly in Helsinki tend to spend most of the summer at summer cottages in the countryside. It is difficult to say whether the effect estimates would have been higher or lower during summer than during the cooler seasons. Exposure to ambient PM is probably higher during summer because of more frequent opening of windows at home and more frequent engagement in outdoor activities. On the other hand, cold temperatures are associated with increased rate of ischemic events (Barnet et al. 2005), and there is some evidence that the effects of air pollution on ischemic heart diseases are higher during the cool season (\nWong et al. 2002\n).\nAirborne PM has conventionally been measured and regulated based primarily on mass. Effective reduction of health effects associated with mass of PM requires identification of the most harmful PM sources. Our results suggest that the fraction of PM originating from combustion processes, notably traffic, may be responsible for the observed effect of PM air pollution on ischemic heart diseases.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
80
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nA role for CETP TaqIB polymorphism in determining susceptibility to atrial fibrillation: a nested case control study\n\n**Article Abstract:**\n\nBackground\nStudies investigating the genetic and environmental characteristics of atrial fibrillation (AF) may provide new insights in the complex development of AF. We aimed to investigate the association between several environmental factors and loci of candidate genes, which might be related to the presence of AF.\nMethods\nA nested case-control study within the PREVEND cohort was conducted. Standard 12 lead electrocardiograms were recorded and AF was defined according to Minnesota codes. For every case, an age and gender matched control was selected from the same population (n = 194). In addition to logistic regression analyses, the multifactor-dimensionality reduction (MDR) method and interaction entropy graphs were used for the evaluation of gene-gene and gene-environment interactions. Polymorphisms in genes from the Renin-angiotensin, Bradykinin and CETP systems were included.\nResults\nSubjects with AF had a higher prevalence of electrocardiographic left ventricular hypertrophy, ischemic heart disease, hypertension, renal dysfunction, elevated levels of C-reactive protein (CRP) and increased urinary albumin excretion as compared to controls. The polymorphisms of the Renin-angiotensin system and Bradykinin gene did not show a significant association with AF (p > 0.05). The TaqIB polymorphism of the CETP gene was significantly associated with the presence of AF (p < 0.05). Using the MDR method, the best genotype-phenotype models included the combination of micro- or macroalbuminuria and CETP TaqIB polymorphism, CRP >3 mg/L and CETP TaqIB polymorphism, renal dysfunction and the CETP TaqIB polymorphism, and ischemic heart disease and CETP TaqIB polymorphism (1000 fold permutation testing, P < 0.05). Interaction entropy graph showed that the combination of albuminuria and CETP TaqIB polymorphism removed the most entropy.\nConclusion\nCETP TaqIB polymorphism is significantly associated with the presence of AF in the context of micro- or macroalbuminuria, elevated C-reactive protein, renal dysfunction, and ischemic heart disease.\n\n**Article Body:**\n\nBackground\nAtrial fibrillation (AF) is the most common sustained arrhythmia in clinical practice and is associated with an increase in total and cardiovascular mortality, as well as cardiovascular morbidity, including stroke and heart failure. [\n1\n]. It is therefore important to detect and treat AF at an early stage to prevent refractory AF and cardiovascular events in the future. Currently, our knowledge on the early pathophysiological changes in the atria is limited due to lacking understanding of molecular mechanisms. Studies in genetics of AF may provide some new insights in the etiology of AF. The familial form of AF is uncommon and AF is more often related to structural abnormalities. Therefore, analysis of AF as monogenic disease in family members with AF as primary electrical disease will tell us more about the etiology of AF, but cohort studies comparing cases to age and gender matched controls may explain the development of AF and identify genetic factors that predispose subjects to AF in combination with structural abnormalities [\n2\n]. Recently, activation of the renin-angiotensin system (RAS) and higher inflammatory state has been associated with AF in the future. [\n3\n,\n4\n]. Activation of RAS may cause the development of structural abnormalities partly by degrading bradykinin, which normally has a cardioprotective effect by diminishing the development of fibrosis. [\n5\n]. It was already known from studies in experimental AF that inhibition of the RAS prevents adverse atrial remodeling. [\n6\n]. Furthermore, genetic variations in the renin angiotensin system genes and inflammatory genes are associated with AF indicating the complexity of the development of AF [\n7\n,\n8\n]. Genetic variations in the cholesteryl ester transfer protein (CETP) gene are also interesting candidates to play an important role in cardiovascular disease. CETP enables the transfer of cholesteryl esters from high density lipoprotein (HDL) towards lipoproteins of lower density, thereby lowering HDL cholesterol. [\n9\n]. A high CETP concentration may be a determinant of increased cardiovascular risk in subjects with high triglycerides [\n10\n]. Variations in the CETP gene could be involved in the development of cardiovascular disease by increasing CETP activity and thereby reducing the cholesterol content of HDL relative to low density lipoprotein (LDL). Furthermore, a decreased CETP activity might prevent oxidation of LDL and decrease inflammation of the vascular wall through its effect on HDL [\n11\n]. Accumulating evidence suggests that CETP polymorphisms may be linked to coronary artery disease, as well as hypertension, which are both strongly linked to the incidence of AF. [\n12\n,\n13\n].\nIt is increasingly clear that the relationship between the genome and susceptibility to cardiovascular disease is complex [\n14\n]. As such, genetic analysis methods are needed that embrace, rather than ignore, this complexity [\n15\n]. In this case-control study, we investigate the association between several environmental factors and loci of candidate genes, which might be related to the presence of AF. In addition to the traditional univariate analyses, we explored the effects of gene-gene and gene-environment interactions on AF using the multifactor dimensionality reduction (MDR) method and creating an interaction entropy graph [\n16\n].\nMethods\nSubjects\nThe population analyzed in this study was obtained from the PREVEND study. [\n17\n]. The PREVEND (Prevention of Renal and Vascular Endstage Disease) study was designed to investigate the natural course of microalbuminuria and its relation with renal and cardiovascular disease in the general population. [\n17\n]. All inhabitants of the city of Groningen (Netherlands) between age 28–75 were asked to send in a morning urine sample and to fill in a short questionnaire on demographics and cardiovascular medical history. A total of 40,856 subjects responded. Subjects who were pregnant or using insulin were excluded. All subjects with a urinary albumin concentration ≥ 10 mg l\n-1 \n(n = 7,768) and a randomly selected sample of subjects with a urinary albumin concentration <10 mg l\n-1 \n(n = 3,395) were invited to perform two visits at an outpatient clinic. The screening program was completed by 8,592 subjects. From these, we selected all patients with AF on the electrocardiogram (n = 97). For every case, an age and gender matched control was selected from the PREVEND cohort. All participants gave written informed consent. The PREVEND study was approved by the local medical ethics committee and conducted in accordance with the guidelines of the declaration of Helsinki.\nElectrocardiography\nStandard 12-lead electrocardiograms were recorded using the computer program MEANS (Modular ECG Analysis System) [\n18\n], and AF was defined according to Minnesota codes 8.3.1 and 8.3.3. Infarct patterns, suggestive of myocardial infarction, were defined by Minnesota codes 1.1 and 1.2. Major ischemia was defined by Minnesota codes 4.1, 4.2, 5.1, or 5.2. The presence of left ventricular hypertrophy (LVH) was identified using the Cornell voltage-duration product, which was calculated as follows: RaVL ± SV\n3 \n(with 6 mm added in women) × QRS duration. A threshold of 2440 mm·msec was used to identify LVH.\nLaboratory measurements\nThe urinary albumin excretion rate was measured as the mean of two 24-h urine collections, and microalbuminuria was defined as an albumin excretion rate between 30 and 300 mg per 24 h and macroalbuminuria > 300 mg per 24 h. Urinary albumin concentrations were determined by nephelometry with a threshold of 2.3 mg l\n-1 \nand intra- and inter-assay coefficients of variation of less than 2.2% and 2.6%, respectively (Dade Behring Diagnostic, Marburg, Germany). High-sensitive C-reactive protein (CRP) was also determined by nephelometry with a threshold of 0.175 mg l\n-1 \nand intra- and inter-assay coefficients of less than 4.4% and 5.7%, respectively (BNII N, Dade Behring). CRP levels below the detection level were scored as 0.18 mg l\n-1\n. Plasma glucose, serum cholesterol, serum and urinary creatinine were determined by Kodak Ektachem dry chemistry (Eastman Kodak, Rochester, NY, USA). HDL-cholesterol was measured with a homogeneous method (direct HDL, no. 7D67, AEROSET System; Abbott Laboratories). Serum triglycerides were measured enzymatically. [\n9\n]. LDL-cholesterol is estimated from quantitative measurements of total and HDL-cholesterol and triglycerides using the empirical relationship of Friedewald et al. [\n19\n]. Urinary leukocyte and erythrocyte measurements were done by Nephur-test+leuco sticks (Boehringer Mannheim, Mannheim, Germany).\nGenotyping of the RAS, Bradykinin and CETP gene polymorphisms\nThe AGT A-6G (rs5051) single nucleotide polymorphisms was analyzed using PCR primers and dual labeled TaqMan (non-MGB) probes as described earlier. [\n20\n]. The AT1R A-1166C (rs5186), the BDKRB2 C-58T (rs1799722) and C-181T (rs1046248), and the CETP Taq1B (rs708272) and I-405V (rs5882) polymorphisms were analyzed using TaqMan-MGB probes and PCR primers, designed through the Assay-by-Design service (Applied Biosystems). The ACE I/D and the BDKRB2 exon 1 insertion/deletion polymorphisms were also analyzed by PCR amplification, one of the primers having a fluoresent label, and subsequent determination of the lengths of the PCR products on a capillary sequencer. Primers were picked with the aid of online Primer3 software [\n21\n]. After PCR cycling, samples of the above assays were pooled and separated on a MegaBACE 1000 sequencer. Fragments were analyzed with Genetic Profiler 2.0 software (Amersham Biosciences).\nDefinition of risk factors\nHypertension was defined as a systolic blood pressure ≥ 140 mm Hg or a diastolic blood pressure ≥ 90 mm Hg or the use of antihypertensive medication. Hypercholesterolemia was defined as a total serum cholesterol level of ≥ 6.5 mmol/l or the use of lipid-lowering therapy. Diabetes was defined as a fasting plasma glucose level >7.0 mmol/l or a non-fasting plasma glucose level >11.1 mmol/l or the use of antidiabetic medication. Obesity was defined as a body mass index ≥ 30 kg/m\n2\n. Smoking was categorized as no smoking or current smoking (current or stopped <1 year ago). Creatinine clearance (CrCl) was calculated as the mean of two 24-h urine creatinine excretions divided by plasma creatinine. Creatinine clearance was adjusted for body surface area, BSA = 0.007184 × weight\n0.425 \n× length\n0.725\n, by dividing CrCl by BSA. Moderate renal dysfunction was defined as CrCl <60 mL/min/1.73 m\n2 \nor the presence of microalbuminuria. Presence of ischemic heart disease was defined as prior myocardial infarction with hospitalization reported by questionnaire and/or an infarct and/or major ischemia patterns on the electrocardiogram.\nStatistical analysis\nContinuous data are reported as mean (standard deviation) or median (interquartile range) if the data was skewed. Categorical data are presented as per group percentages. Differences between subgroups were evaluated by Student's \nt\n-test for the normally distributed continuous variables, or by the Mann-Whitney test if data was skewed. Differences in genotype frequencies and other categorical data between cases and controls were compared with the χ\n2 \ntest or Fisher's exact test. Consistency of genotype frequencies with the Hardy-Weinberg equilibrium (HWE) was tested using a chi-squared goodness-of-fit test on a contingency table of observed versus expected genotype frequencies in cases and controls. The expected genotype frequencies were calculated using allele frequencies estimated from the control sample of the entire PREVEND cohort. When departure of HWE was detected in the control group, the Armitage test for trend in proportions was used which does not assume HWE [\n22\n]. Genotype-phenotype associations were examined with dominant, and recessive models using logistic regression. Odds ratios for the presence of AF on the electrocardiogram and their 95% Confidence intervals were calculated. All \np\n-values are two-tailed. A p-value of <0.05 was considered statistically significant. All abovementioned calculations were performed with SPSS version 12.0.1 software (SPSS, Chicago, IL).\nFor the evaluation of gene-gene and gene-environment interactions, we used the MDR method [\n23\n-\n26\n]. This method includes a combined cross-validation/permutation-testing procedure that minimizes false-positive results that might otherwise result from multiple examinations of the data [\n27\n]. Cross-validation divides the data into a training set and a testing set. With 10-fold cross-validation, the data are divided into 10 equal parts, and the model is developed on 9/10 of the data (training set) and then tested on 1/10 of the remaining data (testing set). This is repeated for each possible 9/10 and 1/10 of the data, and the resulting 10 testing accuracies are averaged. In addition to the testing accuracy, we also report the cross-validation consistency (CVC) that is a measure of how many times out of 10 divisions of the data that MDR found the same best model. Models that are true-positives are likely to generalize to independent datasets and will have estimated testing accuracies of greater than 0.5. Permutation testing was performed to assess the probability of obtaining a testing accuracy as large or larger than observed in the original data given the null hypothesis of no association is true. This is carried out by randomizing the case-control labels 1000 times and repeating the MDR analysis on each randomized dataset. This process yields an empirical distribution of testing accuracies under the null hypothesis that is in turn used to calculate a p-value. We report here the significant two-factor models. The MDR analysis was carried out using version 0.5.1 of the open-source MDR software package that is freely available. [\n28\n].\nThe following cardiovascular risk factors predisposing to AF were included in the MDR analysis: hypertension, hypercholesterolemia, obesity, diabetes, current smoking, family history for cardiovascular disease, HDL-cholesterol < 1 mmol/l, alcohol intake > = 1 drink per day, CRP > 3 mg/L, presence of micro- or macroalbuminuria, renal dysfunction, electrocardiographic left ventricular hypertrophy and ischemic heart disease.\nThe following genotypes were included in the MDR analysis: ACE gene insertion/deletion (I/D) polymorphism, the -6GA polymorphism of the Angiotensin (AGT) gene, the A1166C polymorphism of the angiotensin II type 1 receptor gene (AT1R), Bradykinin B2 receptor gene -81CT, -58CT, 9bp insertion/deletion polymorphisms, and the CETP TaqIB, I405V polymorphisms.\nAn interaction graph using entropy (measurement of randomness) estimates as described by Jakulin and Bratko. [\n29\n] and Moore et al [\n16\n] will be created to confirm, visualize and interpret the results obtained by logistic regression analysis and MDR. Interaction graphs are compromised of a node for each attribute with pairwise connections between them. The percentage of entropy removed by each attribute is visualized for each node and the percentage of entropy removed for each pairwise product of attributes is visualized for each connection. Thus, the independent main effects of each factor can be compared to the interaction effect and whether interactions are additive or non-additive can be quickly determined. Positive entropy values indicate synergistic interaction and negative entropy values indicate redundancy. The interaction graphs are created using Orange machine learning software package, which is written in Python and provided for free as open-source [\n30\n].\nResults\nThe clinical characteristics of cases and controls are shown in Table \n1\n. Subjects with AF had a higher prevalence of electrocardiographic LVH, ischemic heart disease, hypertension, renal dysfunction, and higher levels of CRP and urinary albumin excretion as compared to age and gender matched controls.\nTable 1\nBaseline characteristics of the nested case-control study divided by control group of subjects without atrial fibrillation (AF) and cases with AF. Data shown as percentages for categorical variables and mean ± standard deviation for continuous variables. HDL-cholesterol, Triglycerides, Creatinine, C-reactive protein, and urinary albumin excretion are expressed as median [interquartile range].\nAF Controls (n = 97)\nAF Cases (n = 97)\nP-value\nAge, years\n59 ± 1\n60 ± 1\nMatched\nMale\n56.7%\n56.7%\nMatched\nCaucasian\n91.8%\n92.8%\n0.79\nBody Mass Index\n27.1 ± 0.4\n27.8 ± 0.4\n0.24\nCurrent smoking\n28.9%\n30.2%\n0.84\nIschemic heart disease\n15.8 %\n38.0 %\n0.001\nLeft ventricular hypertrophy\n3.1%\n11.5%\n0.03\nSystolic blood pressure\n135 ± 2\n137 ± 2\n0.47\nDiastolic blood pressure\n76 ± 1\n79 ± 1\n0.03\nHypertension\n42.7%\n60.6%\n0.01\nDiabetes Mellitus\n5.2%\n6.2%\n0.77\nHDL-cholesterol, mmol/l\n1.24 [1.01–1.56]\n1.18 [0.93–1.47]\n0.29\nTotal cholesterol, mmol/l\n5.9 ± 0.10\n5.7 ± 0.11\n0.14\nLDL cholesterol, mmol/l\n4.0 ± 1.0\n3.8 ± 1.0\n0.15\nTriglycerides, mmol/l\n1.2 [0.9–1.9]\n1.3 [0.9–1.7]\n0.49\nCreatinine (μmol/L)\n84 [75–95]\n86 [78–105]\n0.07\nCreatinine clearance (mL/min/1.73 m\n2\n)\n90.9 ± 25.7\n81.2 ± 23.4\n0.01\nModerate renal dysfunction\n14.0%\n40.2%\n<0.01\nC-reactive protein (mg/L)\n1.55 [0.66–2.81]\n2.28 [1.18–4.81]\n<0.01\nUrinary albumin excretion\n11.95 [7.07–21.44]\n17.75 [8.92–45.35]\n<0.01\nAlcohol intake > = 1 drink per day\n24.7 %\n23.7 %\n0.87\nExcept for the CETP I405V genotype (p = 0.03), all polymorphisms examined in this study were in HWE both in the cases as in the controls. The frequencies of the genotypes are listed in Table \n2\n. In the same table, the results of the association study using the dominant and recessive models are given. The polymorphisms of the RAS and Bradykinin gene did no show a significant association with AF in this case-control study. The two genetic variations in the CETP gene were associated with AF. The I405V genotype was associated with AF in the recessive model (p = 0.015)and TaqIB in the dominant model (p = 0.005). The Armitage test (not assuming HWE) for trend was used to replicate the associations found using logistic regression. Using the Armitage test, CETP I405V was not significantly associated with AF (p for trend = 0.34). CETP TaqIB polymorphism remained significant associated with AF (p for trend = 0.03). After adjustment for other significant risk factors predisposing to AF (presence of electrocardiographic LVH, ischemic heart disease, hypertension, renal dysfunction, elevated CRP, and micro- or macroalbuminuria), the association between CETP TaqIB polymorphism and AF remained significant (Odds ratio [95% confidence intervals] for AF: 0.35 [0.16–0.76], p = 0.008).\nTable 2\nDistribution of genotypes in controls without atrial fibrillation (AF) and subjects with AF.\nLocus\nAF Controls (n = 97)\nAF Cases (n = 97)\nP value (Chi-square) OR (95%CI)*\nACE gene I/D\n0.44\nII\n22.7%\n31.1%\n0.65 (0.33–1.27)\nID\n50.0%\n43.3%\n0.92 (0.47–1.78)\nDD\n27.3%\n25.6%\nAGT gene G-6A\n0.96\nAA\n16.1%\n17.6%\n1.07 (0.59–1.97)\nAG\n46.0%\n46.2%\n1.11 (0.51–2.44)\nGG\n37.9%\n36.3%\nAT1R gene A1166C\n0.28\nCC\n8.0%\n11.6%\n0.73 (0.41–1.32)\nAC\n46.0%\n34.7%\n1.50 (0.55–4.05)\nAA\n46.0%\n53.7%\nBradykinin 2 C58T CC\n34.1%\n36.8%\n0.92 0.89 (0.48–1.63)\nTT\n18.2%\n16.8%\n0.91 (0.43–1.96)\nCT\n47.7%\n46.3%\nBradykinin 2 C181T\n0.54\nCC\n72.7%\n76.3%\n0.83 (0.42–1.62)\nTT\n1.1%\nn.a. (empty cells)\nCT\n26.1%\n23.7%\nBradykinin 2 exon1\n0.35\n-9/-9\n38.2%\n29.3%\n1.08 (0.60–1.94)\n-9/+9\n43.8%\n45.7%\n1.49 (0.80–2.77)\n+9/+9\n18.0%\n25.0%\n1.52 (0.74–3.12)\nCETP I405V\n0.02\nAA\n44.3%\n46.8%\n0.90 (0.50–1.62)\nAG\n52.3%\n38.3%\n4.96 (1.37–17.90)\nGG\n3.4%\n14.9%\nCETP TaqIB\n0.02\nB1B1\n24.1%\n44.1%\n0.40 (0.21–0.77)\nB1B2\n62.1%\n43.0%\n0.93 (0.39–2.19)\nB2B2\n13.8%\n12.9%\n* Odds ratios (95% Confidence Intervals) for the presence of AF on the electrocardiogram were obtained by logistic regression; the top OR is for autosomal dominant model and the bottom for autosomal recessive model.\nTable \n3\n and Figure \n1\n shows the best interaction models to explain AF in this study as determined by MDR analysis. The overall best interaction model included the combination of micro- or macroalbuminuria and CETP TaqIB polymorphism. Other significant models were the combination of CRP >3 mg/L and the CETP TaqIB polymorphism, the combination of renal dysfunction and the CETP TaqIB polymorphism, and the combination of ischemic heart disease and CETP TaqIB polymorphism (P < 0.05). Similar significant interactions were found for the CETP I405V polymorphism (data not shown because of deviation HWE).\nTable 3\nSummary of Multi-Factor Dimensionality (MDR) results\nModel\nTraining Accuracy\nTesting Accuracy\nP-value*\nCVC†\nCETP TaqIB – Micro or Macroalbuminuria\n0.6761\n0.6283\n0.04\n8/10\nCETP TaqIB – C-reactive protein>3 mg/L\n0.6650\n0.6661\n0.002\nNA\nCETP TaqIB – Renal dysfunction\n0.6701\n0.6728\n0.002\nNA\nCETP TaqIB – Ischemic heart disease\n0.6650\n0.6578\n0.006\nNA\n* 1000 fold permutation test\n† \nCross-validation Consistency\nFigure 1\nDistribution of high-risk (dark shading) and low-risk (light shading) combinations associated with atrial fibrillation in the four significant gene-environment models using Multifactor Dimensionality Reduction (MDR) analysis. \nThe percentage of patients with atrial fibrillation (left bar in boxes) and matched control subjects (right bar in boxes) is shown for each combination. Boxes were labeled as high-risk (dark-shaded) if the ratio of the percentage of cases to controls met or exceeded the threshold of 1.0.\nAfter identifying the high-risk combinations of factors using MDR, we applied interaction entropy algorithms to visualize the observed interactions and to determine whether they are additive or non-additive (Figure \n2\n). Entropy analysis showed a small synergistic interaction between the presence of albuminuria and CETP TaqIB polymorphism on AF. Next to the independent effects of both factors, the combination removes an additional 2.52% of the total entropy. The other three significant interactions found by MDR are mostly additive as illustrated by the interaction graph.\nFigure 2\nInteraction entropy graph. \nThe interaction models illustrated in the interaction graph describe the percent of the entropy in case-control status (i.e. presence of atrial fibrillation) that is explained by each factor or two way interaction. Each gene or environmental factor is shown in a box with the percent of entropy below the label. Two way interactions between factors are depicted as an arrow accompanied by a percent of entropy explained by that interaction. Redundancy is depicted as a line between factors accompanied by a negative percent of entropy. LVH: Left ventricular hypertrophy. IHD: Ischemic heart disease. CRP: C-reactive protein.\nDiscussion\nThis study showed for the first time an association between the CETP TaqIB polymorphism and AF. Using the MDR method, we established that the CETP TaqIB polymorphism in association with other risk factors of AF, i.e. albuminuria, elevated CRP, renal dysfunction, and presence of ischemic heart disease could predict AF even more strongly. Other genetic polymorphisms of genes encoding bradykinin and elements of the RAS did not correlate with the presence of AF.\nThe underlying biological mechanism explaining the association between AF and the CETP TaqIB polymorphism remains unclear in this study. A logical explanation would be that the widely acknowledged association between CETP gene variations (resulting in lower plasma CETP) and higher HDL cholesterol levels. [\n12\n] may prevent the initiation of (preclinical) atherosclerosis and subsequently the development of AF. This mechanism is very likely considering the modulating effect of ischemic heart disease on the association between CETP TaqIB polymorphism and AF in the present study.\nData corroborating this have recently been published. Some studies have linked CETP polymorphisms to cardiovascular disease, hypertension, and even longevity. [\n13\n,\n31\n]. Since new-onset AF in about 40% of the cases is linked to either coronary artery disease, hypertension, or both. [\n32\n], genetic variants impacting the CETP mass may provide a pathophysiologically rational correlate of AF. However, ancillary mechanisms such as inflammation, oxidative stress and use of alcohol cannot be excluded as the link between CETP and the predisposition to AF. Decreased CETP activity in the subjects who have the B2B2 genotype of the CETP TaqIB polymorphism might prevent oxidation of LDL and decrease inflammation of the vascular wall through its effect on HDL [\n11\n]. In this study, subjects with AF had lower levels of HDL cholesterol, but this difference did not reach statistical significance due to the small population.\nIt has recently been recognized that oxidative stress and inflammation may facilitate the development of AF [\n33\n]. The fact that the combination of an elevated CRP and CETP TaqIB polymorphism was more powerful in predicting AF than either one alone indicate a potential role of inflammation as underlying mechanism. Another common pathway might be the presence of insulin resistance, which has been suggested to contribute to the development of AF [\n34\n]. Variations in the CETP gene might influence the different components of insulin resistance [\n35\n].\nThe significant interaction between CETP TaqIB polymorphism and renal dysfunction and especially the presence of albuminuria in predicting AF, pleads for (at least in part) accessory pathway involving the renin-angiotensin system. One common denominator could be the altered expression of liver X receptor, which in turn might modulate CETP expression as well as renin expression, although this is highly speculative. [\n36\n,\n37\n].\nThe MDR method indicated four significant two-way interaction models, but did not specify whether there is a synergistic relationship. Therefore, we created an interaction entropy graph to visualize and interpret the observed interactions. This graph showed that the interaction between albuminuria and CETP TaqIB was (partly) synergistic in the presence of significant main effects. If the interaction between albuminuria and CETP TaqIB was purely additive, the total amount of entropy removed would be 13.0%, but instead the total amount of entropy removed by the combination of CETP TaqIB and albuminuria was 15.5%, indicating a synergistic interaction. On the other hand, an additive interaction was observed between the CETP TaqIB polymorphism and elevated C-reactive protein, presence of renal dysfunction or ischemic heart disease. It is therefore more likely that the found interactions between the CETP TaqIB polymorphism and elevated C-reactive protein, presence of renal dysfunction or ischemic heart disease are not biological meaningful.\nThe relation between polymorphisms of the renin-angiotensin system and AF found by Tsai et al [\n7\n]. could not be replicated in our case-control study. Possibly, our study was underpowered. It is important to note the difference in ethnicity between the two samples (Caucasian vs. Taiwanese). It is possible that the RAS genes influence susceptibility to AF differently in the context of different genetic backgrounds. Moreover, studies of genetic polymorphisms of the RAS have been generating conflicting results, possibly due to small sample size, inadequate study populations, and unconditional statistics. A contributory role of genetic variants of the ACE, angiotensin, and AT1R genes in AF is in our opinion still open to debate.\nA limitation of our study is the relatively small sample size. The CETP I405V polymorphism deviated from HWE in the control group which could arise due to the small sample of the population and the results of this CETP polymorphism needs to be interpreted with caution. On the other hand, the MDR method, which has been validated in studies with small samples, confirmed the association between CETP TaqIB polymorphism and AF detected by traditional logistic regression analyses. Furthermore, the Armitage test for trend in proportions which does not assume HWE, showed a significant trend between the CETP TaqIB polymorphism and AF. However, the CETP TaqIB polymorphism is not likely to be functional and is probably a marker for one or several functional variants located within the CETP gene or its vicinity. Thus, the results found in this study need to be confirmed in another population preferable with a larger size. Until then, these data are rather hypothesis generating than definite.\nAdditional studies need also to be done to establish the underlying mechanisms explaining the association between CETP TaqIB polymorphisms and AF and to understand the interactions among CETP TaqIB polymorphism and presence of micro- or macroalbuminuria, elevated CRP, renal dysfunction, and ischemic heart disease. Clinical trials investigating pharmacological inhibitors of CETP might consider to include AF as exploratory outcome.\nAlso, in this population based cohort, no clinical information such as echocardiographic features could be obtained due to the epidemiological nature of the study. In addition, the type of AF (paroxysmal or persistent) could not be determined, because one standard 12 lead electrocardiogram was made during two minutes.\nConclusion\nIn summary, we observed an association between AF and TaqIB polymorphism of the CETP gene. Using the MDR method, we showed that the combination of CETP TaqIB polymorphism and the presence of albuminuria, an elevated CRP, renal dysfunction or ischemic heart disease are the best models for predicting AF in this nested case-control study. Further studies are warranted to further elucidate this association and to investigate whether a true biological link exits between CETP and AF or that both are associated with a common factor such as e.g. atherosclerosis, hypertension, inflammation, oxidative stress or alcohol intake.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nFA was involved in the design of the study, performed the statistical analyses and drafted the first and final version of the manuscript. JM was involved in the MDR analyses, creating the interaction entropy graph, and revising the manuscript critically for important intellectual content. MvdB was involved in the design of the study and revising the manuscript critically for important intellectual content. ER was involved in revising the manuscript critically for important intellectual content. RdB was involved in revising the manuscript critically for important intellectual content. RD critically revised the manuscript for important intellectual content. GN critically revised the manuscript for important intellectual content. WvG participated in the design of the study and revising the manuscript critically for important intellectual content.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
81
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nKnowledge of modifiable risk factors of heart disease among patients with acute myocardial infarction in Karachi, Pakistan: a cross sectional study\n\n**Article Abstract:**\n\nBackground\nKnowledge is an important pre-requisite for implementing both primary as well as secondary preventive strategies for cardiovascular disease (CVD). There are no estimates of the level of knowledge of risk factor of heart disease in patients with CVD. We estimated the level of knowledge of modifiable risk factors and determined the factors associated with good level of knowledge among patients presenting with their first acute myocardial infarction (AMI) in a tertiary care hospital in Karachi, Pakistan.\nMethods\nA hospital based cross-sectional study was conducted at the National Institute of Cardiovascular Disease, a major tertiary care hospital in Karachi Pakistan. Patients admitted with their first AMI were eligible to participate. Standard questionnaire was used to interview 720 subjects. Knowledge of four modifiable risk factors of heart disease: fatty food consumption, smoking, obesity and exercise were assessed. The participants knowing three out of four risk factors were regarded as having a good level of knowledge. A multiple logistic regression model was constructed to identify the determinants of good level of knowledge.\nResults\nThe mean age (SD) was 54 (11.66) years. A mere 42% of our study population had a good level of knowledge. In multiple logistic regression analysis, independent predictors of \"good\" level of knowledge were (odds ratio [95% confidence interval]) more than ten years of schooling were 2.5 [1.30, 4.80] (verses no schooling at all) and nuclear family system (verses extended family system) 2.54 [1.65, 3.89]. In addition, Sindhi ethnicity OR [3.03], higher level of exercise OR [2.76] and non user of tobacco OR [2.53] were also predictors of good level of knowledge.\nConclusion\nOur findings highlight the lack of good level of knowledge of modifiable risk factors for heart disease among subjects admitted with AMI in Pakistan. There is urgent need for aggressive and targeted educational strategies in the Pakistani population.\n\n**Article Body:**\n\nBackground\nProgressive urbanization, and adoption of a \"western\" lifestyle contributed to the rising burden of cardiovascular disease (CVD) in the developing world [\n1\n-\n3\n]. Developing nations continue to be ill-equipped to handle this burden and this coupled with poor literacy rates and lack of awareness of disease symptoms result in worse disease outcomes [\n4\n]. This is reflected in the rising rates of hospital admissions and mortality from CVD at an early age [\n5\n-\n7\n], which in turn inflate the disability adjusted life year (DALYs) [\n5\n,\n8\n]. Furthermore, People of South Asian descent have one of the highest risks of CVD in the world. Thus it is likely that escalation of the global CVD epidemic will be most marked in Pakistan and India.\nPrevention of CVD is the most effective way of combating the CVD epidemic in the resource poor nations. Knowledge of modifiable risk factors (smoking, lack of exercise, obesity and consumption of fatty foods) for heart diseases has been identified as a prerequisite for change in behavior and is often targeted by prevention programs [\n9\n,\n10\n]. Although knowledge alone is insufficient, it is assumed to be a key component of behavioral change decision making [\n11\n], and provides cues for action [\n12\n]. Estimating the level of knowledge of the population at large as well as those suffering from CVD can help to guide public health programs especially those directed towards reducing modifiable risk factors for CVD. Earlier studies have revealed that education programs for the elderly were effective in improving health promotion knowledge and behaviors [\n13\n,\n14\n].\nThe level of knowledge of risk factors for CVD varies among different populations. In the US whites have higher level of knowledge about risk factors of CVD than others, often disadvantaged groups, such as African Americans [\n11\n]. Similarly, in the UK, South Asian families were less likely to take regular exercise, and had a lower awareness of cholesterol or dietary content (fiber, sugar, salt) compared to the native white population[\n15\n,\n16\n]. The level of education is one of the predictors of knowledge of healthy life styles. In South Asia the family is often the source of knowledge and awareness of a healthy life style. The traditional extended family household may not be as updated in current knowledge as a nuclear family household because of a more orthodox attitude to health beliefs.\nA study on the risk factors for heart disease has shown that tobacco use, ghee (clarified butter) intake, raised fasting glucose, high cholesterol, paternal history of CVD, low income, and low levels of education are associated with premature myocardial infarction in Pakistan [\n17\n]. A more recent study reported very poor knowledge amongst a general population surrogate in Karachi [\n18\n]. There are no estimates of the level of knowledge in patients with CVD. The purpose of this study was to examine the level of knowledge and to determine the factors associated with a good level of knowledge of modifiable risk factors of CVD in a sample of individuals who were hospitalized with their first acute myocardial infarction (AMI). This was a part of a larger study which focused on delay in seeking early medical care after AMI onset.\nMethods\nA hospital based cross-sectional study was conducted at the National Institute of Cardio-Vascular Disease (NICVD) at Karachi from July 2003 to February 2004. Although NICVD is a tertiary care government hospital, it is the initial point-of-care for the majority of patients (across the socioeconomic spectrum) with heart disease in Karachi. All subjects admitted to NICVD during the study period with their first episode of AMI and who fulfilled the AMI criteria were eligible to participate in the study. AMI was defined using the European Society of Cardiology and American College of Cardiology's criteria [\n19\n,\n20\n]. The presence of at least two of the following three factors was considered as diagnostic for AMI:\n1. Typical chest pain lasting for at least 20 minutes\n2. Electrocardiogram showing ST elevation of at least 2 mm in two or more contiguous leads with subsequent evolution of the ECG\n3. Diagnostic cardiac marker (doubling of creatine kinase with at least 10% MB fraction) or elevated or positive troponin I (T).\nThe admission records of the Emergency Room of the NICVD were reviewed daily to identify patients admitted to the hospital with a first AMI. Those who survived for first 24 hours post admission were eligible for screening. A trained research medical officer approached each of these patients to determine eligibility. Patients who gave informed consent were invited to participate in the study. Patients with mentally unstable conditions, those with life threatening conditions and patients who were already in the hospital at the time of onset of symptoms of AMI were excluded from our study.\nA structured questionnaire was used to collect data. Components of the questionnaire were taken from published studies [\n9\n,\n10\n,\n21\n,\n22\n]. The questionnaire was initially developed in English and then translated into Urdu, the national language of Pakistan. To ensure accuracy of the English to Urdu translation, the questionnaire was back translated from Urdu into English. The majority of the questions were close ended.\nThis analysis focused on identifying the level of knowledge about the modifiable risk factors for CVD [\n9\n]. Four aspects of knowledge of the modifiable risk factors for heart disease were assessed: a) fatty food consumption b) smoking c) obesity and d) lack of exercise [\n23\n]. Subjects were asked about the association of each risk factor, as well as direction of association, with heart disease [see \nadditional file 1\n]. For each risk factor, if the subject correctly identified the association and the direction of the association of the risk factor with heart disease s/he would get a score of one otherwise zero for that component. Subjects scoring a total greater than or equal to three, out of a possible total of four were regarded as having a good level of knowledge of CVD risk factors. The questionnaire also incorporated additional questions designed to cross check validity of subject responses. Multiple logistic regression models were constructed for the primary outcome of having a good level of knowledge of CVD risk factors. We also analyzed each of these four modifiable risk factors separately, which enabled us to identify specific knowledge gaps in our population.\nThe independent variables of this study were age, gender, ethnicity (defined according to mother tongue) [\n24\n], marital status, level of education (years formal education was defined as person who had ever attended school), type of family system (nuclear family system was defined as a household consisting of two parents and their legal children; extended family system was defined as a household where multiple generations of family were living together), income, occupation, history of hypertension (self reported and subjects who were taking antihypertensive medication were defined as hypertensive), history of diabetes (self reported and subjects who were taking anti diabetic medication were defined as diabetic) and general health behavior including tobacco use, physical activity, number of visits to any health care facility in the previous year and knowledge of symptoms of a myocardial infarction (self reported).\nDescriptive analyses were performed to assess the distribution of our data. Univariate logistic regression was run to determine the relationship of each independent variable with the outcome variables. All variables with a p-value < 0. 25 in the univariate analysis were included in multiple logistic regression model, and retained if they were significantly associated with the primary outcome in the final model (p < 0.05) [\n25\n]. Age and hypertension were included at all stages of the logistic regression analysis, because of their known importance. Confounding variables (change in the beta coefficient greater than 10%) were also retained in the model. [\n26\n]. Odds Ratios and 95% CI were reported to interpret our final model.\nThe study was approved by the Ethical Review Committee of the Aga Khan University and permission from the NICVD obtained. After explaining the purpose of the study to the participants, the informed consent form was read out clearly and verbal or written consent was requested. The questionnaire was administered by a trained research medical officer who read it out to the study subjects in Urdu. Questionnaire was read out to them by a trained research medical officer in Urdu. The participants had the right to refuse to answer any specific question or withdraw from the study at any time.\nResults\nWe interviewed 720 subjects. The response rate was 100%. Seventy eight percent of the subjects were male. The mean age (SD) was 54 (11.6) years (Table \n1\n). Only 16% had completed more than 10 years of education. Around one third of married subjects were related to each other before marriage. Two thirds of the subjects lived in an extended family system. Around half of the subjects reported that they had never smoked. Only 42% of the subjects had a good level of knowledge of the risk factors of heart disease. Almost all subjects 693 (96%) were able to identify at least one risk factor. However, only 143 (20%) participants correctly identified the relationship of all four modifiable risk factors with heart disease (Table \n2\n).\nTable 1\nCharacteristics of the subjects with acute myocardial infarction in Karachi, Pakistan (n = 720)\nCharacteristics\nn (%)\nDemographic and socio-economic Characteristics\nAge\n Mean (SD)\n54.1 (11.6)\nSex\n Male\n562 (78.1)\nEthnicity\n Muhajir\n524 (72.8)\n Sindhi\n61 (8.5)\n Punjabi\n44 (6.1)\n Pushto\n28 (3.9)\n Balochi\n16 (2.2)\n Others \n§\n47 (6.5)\nMarital status\n Single\n28 (3.9)\n Married\n645 (89.6)\n Separated\n01 (0.1)\n Widowed\n46 (6.4)\nLiteracy Status\nCan read & write a paragraph (3 line)\n Yes\n471 (65.4)\nReceived formal (school) education\n None (defined as Illiterate)\n25 (3.5)\n ≤ 5 years\n130 (18.0)\n 6–10 years\n197 (27.4)\n > 10 year\n119 (16.5)\nParents related prior to marriage\n Yes\n246 (34.2)\nType of relationship\n First cousins\n+\n217 (30.1)\n Second cousins *\n29 (4.0)\nFamily history of CVD (first degree relative)\n Yes\n265 (36.8)\nTypes of family system\n Nuclear\n246 (34.2)\n Extended\n474 (65.8)\nIncome (PKRS)\n Median (IQR⊥)\n4500 (4000)\n ≤ 3000\n185 (25.7)\n 3001–5000\n241 (33.5)\n 5001–8000\n151 (21.0)\n > 8000\n101 (14.0)\n Did not reveal\n42 (5.8)\nGeneral health behaviors\nTobacco use\n Never used\n360 (50.0)\n Current user\n141 (19.6)\n Ex-user\n219 (30.4)\nExercise \n€\n Yes\n31 (4.3)\nNumber of visits for any health facility in past one year\n ≤ 4\n302 (41.9)\n 5 – 6\n249 (34.6)\n ≥ 7\n169 (23.5)\nClinical Characteristics\nHypertension\n Yes\n312 (43.3)\nDiabetes\n Yes\n197 (27.4)\n§= include Rajistani, Bengali, Gujrati, Marhwi, Katchi, Sirayki or Hindi\n+ = first cousins are the people, who have the same grandparents. (Children of aunts and uncles)\n* = Second cousins are the people who do not have the same grandparents.\n⊥ = IQR (Inter quartile range)\n€ = Exercise (that lasted for at least 20 minutes with hard breathing and sweating)\nTable 2\nKnowledge of modifiable risk factors for CVD in patients admitted with acute myocardial infarction in Karachi, Pakistan (n = 720)\nCharacteristics\nn (%)\nKnowledge of modifiable risk factors\n Don't know any risk factor\n27 (3.8)\n Only one risk factor\n89 (12.4)\n A total of two risk factors\n302 (41.9)\n Good level of knowledge*\n302 (41.9)\nKnowledge of symptoms of heart attack\n Don't Know\n586 (81.4)\n List 1 symptom\n93 (12.9)\n List at least 2 symptoms\n41 (5.7)\n*defined as identifying three out of four modifiable risk factors (smoking, lack of exercise, obesity and consumption of fatty foods\nOut of 720 study subjects, 665 (92%) had good level of knowledge about the association of fatty food consumption with heart disease, 597 (83%) were able to correctly identify the association of smoking with heart disease, 302 (42%) were knowledgeable about the association of obesity with heart disease, and only 178 (25%) knew about the protective effect of exercise (figure \n1\n).\nFigure 1\nPercentage of knowledge of modifiable risk factor of heart disease among 720 subjects with acute myocardial infarction.\nTable \n3\n shows the crude, and adjusted odds ratios and 95% CI of our patient's knowledge of modifiable risk factor for heart disease. We found that subjects of Sindhi ethnicity, who had more year's formal of education, a higher level of exercise, a higher knowledge of symptoms of AMI and who lived in a nuclear family system, or did not use tobacco were more likely to have a good level of knowledge of modifiable risk factors of heart disease. These variables were adjusted for age, gender, profession, socioeconomic status, and history of hypertension because these were potential confounders.\nTable 3\nCrude and adjusted OR of knowledge of modifiable risk factors for heart diseases among subjects with first heart attack in a tertiary care hospital Karachi Pakistan. (n = 720)\nVariable\nCrude OR\n95% CI\naOR*\n95% CI\nAge\n Older > 45 yrs\n1.00\nnot significant\n Younger ≤45\n1.41\n(0.95, 2.09)\nSex\n Female\n1.00\nnot significant\n Male\n2.81\n(1.59, 4.96)\nEthnicity\n Muhajir (Urdu)\n1.00\n1.00\n Sindhi\n2.12\n(1.81, 3.82)\n3.03\n(1.54, 5.95)\n Punjabi\n2.19\n(1.12, 4.30)\n1.90\n(0.86, 4.19)\n Pushtoo\n0.57\n(0.17, 1.91)\n1.09\n(0.29, 4.11)\n Others\n1.47\n(0.79, 2.73)\n1.33\n(0.64, 2.77)\nYears of school education\n Illiterate\n1.00\n1.00\n < 5 years\n0.85\n(0.45,1.58)\n0.66\n(0.33, 1.31)\n 6–10 years\n1.73\n(1.08, 2.79)\n1.17\n(0.67, 2.03)\n > 10 years\n3.24\n(2.14, 5.85)\n2.50\n(1.30, 4.83)\nExercise\n No\n1.00\n1.00\n Yes\n4.12\n(1.98, 8.53)\n2.76\n(1.21, 6.28)\nType of family\n Extended\n1.00\n1.00\n Nuclear\n3.14\n(2.16, 4.58)\n2.54\n(1.65, 3.89)\nTobacco use\n Current user\n1.00\n1.00\n Ex user\n0.46\n(0.10, 2.26)\n0.45\n(0.08, 2.42)\n Never used\n2.28\n(1.11, 4.69)\n2.53\n(1.15, 5.56)\nIncome\n > 8000\n1.00\n 5001–8000\n0.69\n(0.40, 1.21)\nnot significant\n 3001–5000\n0.39\n(0.23, 0.66)\n ≤ 3000\n0.35\n(0.20, 0.63)\n Didn't reveal\n0.41\n(0.17, 1.03)\nHypertension\n No\n1.00\nnot significant\n Yes\n0.81\n(0.56, 1.17)\n*Adjusted for confounding variable age, sex, profession, socioeconomic status (income) and history of hypertension\nDiscussion\nTo the best of our knowledge, this is the first study of knowledge of risk factors for heart disease and its determinants in this high risk population of Pakistan. Knowledge of modifiable risk factors for heart disease, i.e. fatty food consumption, smoking, obesity, and exercise, was assessed among patients diagnosed with their first acute myocardial infarction at a tertiary care hospital. We found that subjects of Sindhi ethnicity, who had more year's formal of education, a higher level of exercise, who lived in a nuclear family system or who did not use tobacco were more likely to have a good level of knowledge of modifiable heart disease risk factors.\nThe present study also demonstrates that 96% of participants were able to recognize at least one risk factor for heart disease, but only 20% of the participants were fully aware of all four key modifiable risk factors of heart disease. Most of participants identified the association of fatty food consumption and smoking with heart disease (i.e. 92% and 83%). However, only minority could identify obesity or lack of exercise as risk factors for heart disease. These findings are similar to those of a recent study looking at cardiovascular knowledge in patient attendants as a surrogate for the general Pakistani population [\n18\n]. This pattern of knowledge may be due to relatively more aggressive state-funded advertising campaigns as well as educational programs discouraging the use of saturated fats and tobacco and a relative dearth of the same for obesity and exercise.\nThere was a strong, positive and independent association between the level of education and a good level of knowledge of modifiable risk factors of heart disease. This is consistent with previous studies [\n9\n-\n11\n,\n18\n,\n21\n,\n27\n-\n30\n]. Individuals who are better able to read are more able to understand health messages that are conveyed through print media and/or visual media. This finding identifies the need for targeting illiterate (and poorly educated) individuals in Pakistan with educational programs that are tailored to their level of understanding.\nA significant majority of study participants (66%) were noted to be living in an extended family system. Interestingly, subjects who lived in an extended family system had less knowledge of risk factors for heart disease than those living in a nuclear families. One would have thought that those living in an extended family would have been more likely to be exposed to close relatives with heart disease, and thus to the medical advice that was offered, but the data do not support this. There are several possible explanations of this observation. First, the frequent and close contact of an extended family system may lead to exposure and reinforcement of traditional and potentially unhealthy health practices and beliefs [\n31\n]. Second, extended family living is frequently a necessity owing to the economic constrains of living independently. Thus persons living in extended families are more likely to be poor and less educated – a likely explanation of their lower level of knowledge. Third, people living in an extended family system may be more susceptible to depression and anxiety. [\n32\n] which may contribute towards less knowledge. To the best of our knowledge, the association between type of family system and level of knowledge of risk factors for heart disease has not been previously reported.\nIn this study, current and ex tobacco users were less knowledgeable about risk factors for heart disease than those who never used tobacco. This finding was consistent with other studies conducted in the US and Scotland [\n11\n,\n22\n]. One explanation is that tobacco users are not aware of the adverse consequences of their habit. On the other hand, it may be that tobacco users are simply less prepared to admit the health implications of what we commonly perceive as an unhealthy practice, at least in regard to their own health [\n22\n].\nEarlier studies have shown a clear distinction in various health beliefs and health-seeking behavior among different ethnic groups [\n33\n,\n34\n]. In this study, Sindhi subjects showed higher levels of knowledge of the modifiable risk factors for heart disease than Urdu speaking people. However in the analysis of each modifiable risk factors separately, Sindhi participants had less knowledge of the relationship of fatty food consumption with heart disease compared to Urdu speaking. These ethnic differences in the knowledge base are not surprising since the various ethnic groups in Pakistan have significantly different cultural practices and beliefs [\n33\n]. However, these associations within these ethnic groups need to be further explored in future studies.\nThe American Heart Association has recently focused on physical inactivity as a major modifiable risk factor for heart disease [\n35\n]. In this study, 75% of the study subjects could not identify the relationship of exercise with heart disease. A study conducted in the US also reported that only 15% of the subjects recognized lack of exercise as a cause of heart disease [\n36\n]. In our study very few people (4%) exercised on a regular basis which is consistent with previous finding [\n37\n]. Our study showed that people who exercised regularly were more knowledgeable about the relationship of modifiable risk factors for heart disease, which is also consistent with Ford's study [\n11\n]. This finding highlights a potential area of emphasis for future educational programs.\nA very worrying finding was that 81% of the study participants were not aware of any symptoms of heart attack and only 6% could identify two or more symptoms. This may increase the delay in seeking early medical care among AMI subjects, which would lead to a worse outcome. Therefore, we should also educate our population about the symptoms of heart attack along with risk factors of heart attack.\nOur study has few limitations. First, Level of knowledge was assessed using a structured questionnaire. Subjects may have responded positively to all risk factors introduced, knowing that the study was about heart disease and risk factors, so we may have overestimated the total level of risk factor knowledge in this population. However, this cannot account for the striking difference in knowledge between certain groups, eg those classified by education or ethnic subgroup. Secondly, reliance of ability to recall risk factors for CVD introduces recall bias and may underestimate knowledge. Third, our questionnaire has not been validated; however, components of our questionnaire have been validated in other studies [\n9\n,\n10\n,\n21\n,\n22\n]. The content validity of questionnaire items was examined by the clinical experts and peer review. Fourth, the choice of a cumulative score of 3 as \"good\" knowledge is somewhat arbitrary; however we feel that this cut-off provides reasonable discrimination between those who are knowledgeable and those who are not. Finally, due to the cross sectional study design, one cannot determine the level knowledge status \nprior \nto the index event. It is likely that individual patients may have acquired some knowledge during their hospital stay as a direct consequence of being questioned about them during their admission. However, as our study subjects were recruited on the day following the AMI, we feel that a relatively limited degree of knowledge would have been accrued in the hospital and the knowledge assessed largely reflects their pre-event status.\nConclusion\nOur findings highlight a striking lack of knowledge of modifiable risk factors among individuals with a first heart attack. Only 42% of our subjects had a good level of knowledge about heart disease, and a mere of 20% were able to correctly identify all four risk factors of heart diseases in the Pakistani population. The results of this study have also helped to identify segments of the population who need to be targeted for educational interventions. These include tobacco users, people who have not completed high school education, people with a sedentary lifestyle, and those living in an extended family system and those of Urdu-speaking ethnic origin. The findings of our study suggest that aggressive and targeted education about the relationship of obesity and exercise with CVD in particular is needed.\nOur study calls for efforts such as targeted public health education to increase the level of knowledge of risk factors of heart disease. Education can be provided to the public through the media (including both electronic and print) and workshops. These programmes must be sensitive to the attitudes, perceptions and capabilities of targeted individuals. Physicians must also ensure they impart education to their patients, as patients usually rely on doctors for first hand information. Further epidemiological studies, especially longitudinal studies and population based, are needed in Pakistan to assess the level of knowledge regarding modifiable behavioral risk factors for heart disease.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nMS did the study under the supervision of TJ and performed the statistical analysis, and drafted the manuscript. JH supervised the statistical analysis. FH, IR&; AF provided the clinical knowledge of AMI. TJ, JH and NC contributed to review, and to the revision of the report. All authors read and approved the final manuscript\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\nSupplementary Material\nAdditional File 1\nKnowledge about the modifiable risk factors of heart disease. Its one of the part of our questionnaire in which we asked questions about the knowledge of modifiable risk factors of heart disease from our study patricians.\nClick here for file\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
82
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nPost-stenotic aortic dilatation\n\n**Article Abstract:**\n\nAortic stenosis is the most common valvular heart disease affecting up to 4% of the elderly population. It can be associated with dilatation of the ascending aorta and subsequent dissection. Post-stenotic dilatation is seen in patients with AS and/or aortic regurgitation, patients with a haemodynamically normal bicuspid aortic valve and following aortic valve replacement. Controversy exists as to whether to replace the aortic root and ascending aorta at the time of aortic valve replacement, an operation that potentially carries a higher morbidity and mortality.\nThe aetiology of post-stenotic aortic dilatation remains controversial. It may be due to haemodynamic factors caused by a stenotic valve, involving high velocity and turbulent flow downstream of the stenosis, or due to intrinsic pathology of the aortic wall. This may involve an abnormality in the process of extracellular matrix remodelling in the aortic wall including inadequate synthesis, degradation and transport of extracellular matrix proteins.\nThis article reviews the aetiology, pathology and management of patients with post-stenotic aortic dilatation.\n\n**Article Body:**\n\nMethods\nAn English literature search using Pubmed-Medline database between 1960 and today was carried out. Key words used included aortic valve, aortic stenosis, aortic dilatation, bicuspid aortic valve, surgery and matrix metalloproteinase.\nDefinition\nAortic stenosis (AS) is the most common valvular heart disease affecting up to 4% of the elderly population [\n1\n,\n2\n]. Post-stenotic aortic dilatation is defined as dilatation of the vessel wall distal to the area of a partial stenosis. It refers to dilatation of the ascending aorta, >4.0 cm, distal to a stenotic/malformed aortic valve (AV). This dilatation is usually progressive > 0.3 cm/year.\nAortic dilatation is thought to be a precursor to aortic dissection and rupture, both of which are potentially fatal.\nAetiology\nPost-stenotic aortic dilatation has been shown to occur in patients with AS/aortic regurgitation (AR), haemodynamically normal bicuspid aortic valve (BAV) and following aortic valve replacement (AVR). It does not appear to be related to the degree of AS [\n3\n], although this study was conducted on patients with a valve area < 2.0 cm\n2\n, and appears to be independent of whether the patient has had valve replacement [\n4\n]. This suggests a possible genetic basis for the dilatation as well as the mechanical stresses placed on the vessel wall downstream of a stenotic lesion.\nBAV is an independent risk factor for both AS and progressive aortic dilatation [\n5\n].\nAortic stenosis (AS)\nAortic stenosis is the most common valvular heart disease and the third most common heart disease, after hypertension and coronary artery disease, in Europe and North America. In the elderly the prevalence of aortic stenosis has been reported to be up to 4%. Aortic sclerosis, the precursor of aortic stenosis, has been found in approximately a third of patients over the age of 65 years [\n1\n,\n2\n]. In most patients the underlying cause is calcific AS [\n6\n]. This is a chronic progressive disease that begins with thickening and calcification of the valve cusps without haemodynamic significance and ends in heavily calcified, stiff cusps that cause severe valve stenosis. Recent studies have shown that this is not only a degenerative process due to mechanical stress, but also an active process, involving inflammation and lipid infiltration, similar to that seen in atherosclerosis. Epidemiological studies have confirmed that AS and atherosclerosis share several common risk factors: male sex, older age, hypertension, diabetes, smoking and elevated levels of low-density lipoprotein (LDL) cholesterol and lipoprotein(a) [\n1\n,\n7\n]. These observations have led to the proposal of pharmacological strategies, already used in atherosclerosis, e.g. angiotensin-converting enzyme inhibitors and hydroxymethylglutaryl-coenzyme A reductase inhibitors (statins), which may slow the progression of AS. However, the SALTIRE study [\n8\n] has shown results contrary to this. This was a double-blind, placebo-control trial (n = 155) in which patients were treated with 80 mg of atorvastatin or matched placebo. They were assessed at follow up (median 25 months) for AS and AV calcification by echocardiography and serum LDL cholesterol. They concluded that intensive lipid-lowering therapy did not halt the progression of calcific aortic stenosis or induce its regression but that large, long-term, randomised trials were needed.\nBicuspid aortic valve (BAV)\nBAV is a common congenital abnormality found in adults. It occurs in approximately 1–2% of the population [\n9\n,\n10\n]. This compares to 0.8% of all other forms of congenital cardiac disease combined. The frequency of BAV is higher in males (male: female ratio, 2:1). Approximately a third of BAV patients develop serious complications. Therefore, it causes more morbidity and mortality than the combined effects of all other cardiac conditions [\n9\n,\n11\n]. BAV is associated with premature valve stenosis, regurgitation, infective endocarditis, ascending aortic aneurysms and dissection. Nearly all patients with a BAV will require valve surgery during their lifetime and it has been suggested that an underlying congenitally malformed valve is more common than a tricuspid aortic valve (TAV) as the underlying cause for isolated AVR for AS in adults [\n12\n].\nPathogenesis of BAV\nEmbryology\nBAV is the result of abnormal aortic cusp formation in valvulogenesis. There is fusion of adjacent cusps to form a single aberrant cusp, which is larger than the one remaining normal-sized cusp but smaller than 2 normal cusps combined. It is therefore likely that BAV is the result of a complex developmental process and not simply the fusion of 2 normal cusps. The larger leaflet has a false commisure that, on histological examination, shows no valve tissue. It is thought that congenital AV malformations maybe a phenotypic continuum of unicuspid (severe form), bicuspid (moderate form), tricuspid (normal) and the rare quadricuspid forms [\n13\n,\n14\n].\nBAV is associated with coarctation of the aorta, patent ductus arteriosus and left main stem stenosis which supports a genetic cause for the disease [\n15\n,\n16\n]. There is also a high incidence of familial clustering of BAV, compatible with autosomal dominant inheritance with reduced penetrance [\n17\n].\nFlow related theory\nThis theory sites abnormal blood flow through the AV during valvulogenesis resulting in abnormal cusp separation and the formation of a BAV. There is, however, no concrete evidence to support this theory.\nSupport for intrinsic aortic disease leading to post-stenotic dilatation\nPatients with BAV have a larger ascending aortic diameter compared to age and sex-matched control subjects, irrespective of altered haemodynamics [\n18\n]. The left ventricular outflow tract, aortic cusps, arterial media of the ascending aorta and aortic arch are all linked embryologically as they all originate from the neural crest [\n19\n]. Disorders of the neural crest have also been implicated in the development of cervicocephalic arterial dissection. A familial cluster of aorto-cevicocephalic arterial dissection and BAV has been described strengthening the theory of an underlying neural crest defect in the development of BAV [\n20\n].\nEndothelium-derived nitric oxide (NO) plays a role in valvulogenesis as well as cell growth and apoptosis, post developmental vascular remodelling and angiogenesis. Mice deficient in endothelial NO synthase, which synthesizes endothelium-derived NO, were found to have a significantly high incidence of BAV [\n21\n]. This suggests that the genetic determinants of BAV are linked to the genetic determinants of arterial abnormalities.\nNO has also been implicated in regulating the expression of matrix metalloproteinase-9 in the aortic wall of rats. It may, therefore, be involved in the homeostasis between matrix metalloproteinases (MMPs) and tissue inhibitors of metalloproteinases (TIMPs); a deficiency of NO tending towards matrix degradation [\n22\n].\nGurvitz et al [\n23\n] studied 2 groups of patients, one with isolated BAV (n = 76) and the other normal tricuspid AV (TAV) (n = 41), under the age of 21 years old, diagnosed using transthoracic echocardiography. Patients were excluded if they had other cardiac anomalies, a diagnosis of Turner's or Marfan's syndrome, or a surgical or catheter-based aortic valve intervention. Aortic root dimensions at the annulus, sinus of Valsalva, sinotubular junction (STJ) and the proximal ascending aorta were assessed in the parasternal long-axis view in systole. The haemodynamic state of the AV was evaluated using colour flow and spectral Doppler. In normal subjects it was seen that aortic root dimensions correlated well with height and body surface area (BSA), better than with age. It was also seen that at every level of the aortic root, in patients with isolated BAV, independent of the functional state of the valve, the diameter was significantly greater than normal TAV, but within the normal range (Table \n1\n).\nTable 1\nMean z scores, in relation to height, in children with BAV compared to those with TAV.\nStudy\nN\nAo Ann\nAo Sinus\nSTJ\nAsc Ao\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nGurvitz \n23\n76\n41\n2.0\n0\n1.6\n0\n1.2\n0\n3.3\n0\np Value\n< 0.001\n< 0.001\n< 0.001\n< 0.001\nAo Ann = aortic annulus, Ao Sinus = aortic sinus, STJ = sinotubular junction, Asc Ao = ascending aorta.\nBAV = Bicuspid aortic valve, TAV = Tricuspid aortic valve\nMean circumferential stress in the dilated ascending aorta increases linearly with blood pressure and diameter. Distensibilty has been shown to be due mainly to the intrinsic elastic properties of the aorta itself. Different groups of patients studied, including patients with Marfan's syndrome and BAV with associated aneurysm, have different predicted distensibility. In patients with BAV, it was seen that valve function did not influence either the elastic properties or the distensibility of the aorta suggesting again that it is the intrinsic abnormalities within the wall of the aorta, and not abnormal flow patterns, which lead to aortic dilatation [\n24\n].\nAortic dilatation associated with haemodynamically normal AV\nNkomo et al [\n25\n] carried out a community-based study to determine whether the association between BAV and aortic dilatation could be demonstrated in patients with BAV, without significant stenosis or regurgitation. Patients were identified by echocardiography. They were excluded if there was evidence of AS, more than trivial AR, aortic coarctation, or mitral, pulmonic or tricuspid valve disease, cardiomyopathy, pericardial disease, Marfan's syndrome or a family history of Marfan's syndrome, or any other form of congenital heart disease. 44 patients were matched to an equal number of controls with normal TAV of the same age (mean 35 ± 13 years), sex (65% male) and BSA. Aortic dimensions were measured at the annulus, aortic sinus, proximal ascending aorta and aortic arch. It was found that the dimensions of the aortic root were consistently larger in patients with BAV. The largest difference was seen in the dimensions of the proximal ascending aorta. There was no significant difference between the BAV and control groups with respect to dimensions of the aortic arch. Other studies have confirmed these findings, of dilatation of the aortic root and ascending aorta in patients with BAV, and have also shown that there is no increased dilatation seen in the descending or abdominal aorta [\n26\n,\n27\n] (Table \n2\n).\nTable 2\nAortic dimensions (mm) in patients with haemodynamically normal AV.\nStudy\nN\nAo Ann\nAo Sinus\nAsc Ao\nAo Arch\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nNkomo \n25\n44\n44\n23.2\n21.6\n33.5\n30.3\n33.3\n27.9\n24.2\n25.3\np = 0.002\np = 0.0001\np = 0.0001\np = 0.16 (N/S)\nNistri \n26\n66\n70\n23.6\n22.7\n31.6\n28.7\n31.2\n26.9\nN/A\nN/A\np = N/S\np < 0.001\np < 0.001\nCecconi \n27*\n162\n162\n15.4\n14.4\n22\n19.5\n23.7\n18.6\n15.1\n14.4\np = N/S\np < 0.01\np < 0.001\np = N/S\n* Dimensions in mm/m\n2\nAo Ann = aortic annulus, Ao Sinus = aortic sinus, Asc Ao = ascending aorta, Ao Arch = aortic arch.\nBAV = Bicuspid aortic valve, TAV = Tricuspid aortic valve\nN/A = not applicable, N/S = not significant\nAortic dilatation associated with aortic stenosis\nCrawford and Roldan [\n3\n] carried out a study to determine the prevalence of dilated aortic root in patients with AS. They studied the echocardiograms of 118 patients with AS, with a valve area of <2.0 cm\n2\n. They were age-matched to patients with aortic sclerosis, but no stenosis, and to normal controls. The aortic root diameter at the annulus, coronary sinus and STJ levels were measured using transthoracic echocardiography. Dilated aortas were defined as 2 SDs above the mean values obtained in the normal group. This study concluded that aortic root dilatation is common in AS, but is not related to severity of the stenosis. They did not, however, make any comparison between BAV and TAV. As stated earlier, one of the limitations of this study is that only patients with a valve area < 2.0 cm\n2 \nwere included in the study.\nMorgan-Hughes et al [\n28\n] carried out a prospective study measuring the aortic root and ascending aortic diameters, using CT scan images, on patients (BAV, n = 10; TAV, n = 18) with severe AS prior to undergoing AVR. They concluded that patients with BAV and pure, severe AS have moderately dilated thoracic aorta compared to matched TAV (p < 0.005) (Table \n3\n).\nTable 3\nAortic dimensions (mm) in patients with AS\nStudy\nN\nAo Ann\nAo Sinus\nSTJ\nCrawford \n3\nNo AS\n108\n25\n36\n30\nMild AS\n47\n25\n36\n36*\nModerate AS\n29\n24\n36\n36*\nSevere AS\n42\n24\n36\n35*\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nMorgan-Hughes \n28\n10\n18\nN/A\nN/A\n41.1\n33.8\n39.1\n31.1\np Value\n< 0.005\n< 0.005\n*p < 0.001 compared to normal/sclerotic AV.\nAo Ann = aortic annulus, Ao Sinus = aortic sinus, STJ = sinotubular junction.\nBAV = Bicuspid aortic valve, TAV = Tricuspid aortic valve\nN/A = not applicable.\nKeane et al [\n29\n] carried out a retrospective study to compare aortic size in BAV and controls with matched valvular lesions (AS, AR or mixed lesions). They measured the diameter of the left ventricular outflow tract (LVOT), sinus of Valsalva, STJ and proximal ascending aorta using transthoracic echocardiograms. 118 consecutive patients with BAV were compared to controls with TAV. Paired analysis demonstrated significant aortic dilatation at all levels measured in BAV patients, with all degrees of AS and/or AR, compared to controls (Table \n4\n). These differences were seen despite the significantly older age of the control group compared to the BAV group (mean 55.3 years (TAV) and 43.9 years (BAV)). This study also confirms the result mentioned above, that the degree of dilatation is not related to the severity of AS. It suggests that post-stenotic dilatation is a feature of BAV but not of congenitally normal valves. It supports the theory that this is due, in part, to an underlying pathology within the aortic wall.\nTable 4\nAortic dimensions (mm) of matched patients with AS/AR/Mixed valve disease.\nStudy\nN\nAo Sinus\nSTJ\nProximal Aorta\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nBAV\nTAV\nKeane \n29\n77\n77\n37.4\n35.1\n35.4\n33.4\n36.1\n34.0\np Value\n< 0.01\n< 0.001\n< 0.001\nAo Sinus = aortic sinus, STJ = sinotubular junction.\nBAV = Bicuspid aortic valve, TAV = Tricuspid aortic valve\nAortic dilatation occurring post AVR\nPatients that undergo AVR often have some degree of ascending aortic dilatation. At present, replacing the aortic root at the time of AVR is controversial as the risk of aortic dilatation following AVR is uncertain. Some studies have been carried out to determine the natural history of ascending aortic dilatation following AVR.\nYasuda et al [\n4\n] carried out a retrospective analysis of patients (BAV n = 13, TAV n = 14), using echocardiography, before and after AVR and 18 BAV patients without AVR. Diameters were measured at the sinus of Valsalva, STJ and the proximal ascending aorta. The annual dilatation rate was calculated by dividing changes of diameter during the follow-up period by the BSA and the observational interval. Aortic dilatation in BAV patients was seen to be significantly faster than that of TAV at the proximal aorta only (0.18 compared to -0.08 mm/m\n2\n/year). There was no significant difference in the dilatation rates of BAV patients with and without AVR (0.03 and 0.02 mm/m\n2\n/year respectively). This study showed that AVR could not prevent progressive aortic dilatation in BAV. However, TAV patients did not show further aortic dilatation after AVR. It therefore seems that haemodynamic factors are not responsible for the ongoing dilatation in BAV.\nGenetic/structural abnormality\nAssociations have been found between post-stenotic dilation and genetic and structural abnormalities within the AV and ascending aorta, as set out below. However, there is a lack of randomised trial data to establish whether these associations are in fact causal.\nFibrillin-1\nFibrillin-1 is a major protein component of extracellular matrix fibrils, called microfibrils. The FBN1 gene, found on chromosome 15, encodes for this large glycoprotein. Vascular tissues with deficient fibrillin-1 microfibrils release metalloproteinases. These enzymes weaken the vessel wall by degrading the elastic matrix components and leading to matrix disruption and consequent dilatation of the vessel.\nMarfan's syndrome results from mutations in the FBN1 gene. The most common cardiovascular complication of this condition is progressive aortic root enlargement, initially occurring at the sinus of Valsalva, and ascending aortic aneurysms. The aneurysms develop as a consequence of disruption of the medial and adventitial elastin and collagen in association with focci of cystic medial necrosis of the medial smooth muscle. There is also seen to be increased expression of MMPs (especially 2 and 9) within the aneurysmal aorta and, to a lesser extent, the AV [\n30\n].\nFedak et al [\n31\n] carried out a study to assess the vascular matrix remodelling in patients with BAV and its implication for aortic dilatation. Samples of aorta and pulmonary artery were obtained from patients undergoing surgery with BAV (n = 21) and TAV (n = 16). The amount of fibrillin-1, elastin and collagen was determined using quantitative immunohistochemical analysis, using fluorescence microscopy, for fibrillin-1, and hydroxyproline determination. Fibrillin-1 content was significantly reduced, in both the aorta and pulmonary artery, of BAV patients compared to that seen in TAV suggesting a systemic deficiency of this. It was independent of valve function and patient age. However, the amount of matrix components, elastin and collagen, were unchanged. This decrease in the amount of fibrillin-1 in the vasculature of patients with BAV may trigger MMP production leading to matrix disruption and vascular dilatation.\nRecent studies have demonstrated that there is a difference in the expression of matrix proteins between the convexity and concavity of the dilated aorta in patients with BAV [\n32\n]. These results are consistent with the wall-stress asymmetry that has also been reported by Robicsek and colleagues [\n33\n]. They studied three explanted haemodynamically normal congenitally BAV, where they used a simulator to produce a computerised digital model. They showed excessive folding and creasing persistent throughout the cardiac cycle, extended area of leaflet contact, significant morphologic stenosis and asymmetrical flow patterns and turbulence. Furthermore, Richards et al [\n34\n] studied the influence of structural geometry on the severity of BAV and stenosis using transthoracic, transoesophageal echocardiography and computer simulations. They demonstrated that for the same anatomic orifice area, functional severity is greater in BAV than in degenerative TAV patients with AS.\nMatrix metalloproteinases (MMPs)\nThe MMPs are a family of proteases that play an important role in the homeostasis of connective tissue. They are synthesized by a variety of cell types including endothelial and smooth muscle cells, fibroblasts and macrophages. They are classified into classic MMPs and novel MMPs. The classic MMPs are secreted as proenzymes and include 3 subgroups: (1) the interstitial collagenases (MMP-1, MMP-8 and MMP-13), which degrade fibrillar collagen; (2) the gelatinases (MMP-2 and MMP-9), which act on type IV collagen and partially degrade fibrillar collagens as well as elastin; and (3) stromelysins (MMP-3, MMP-7 and MMP-10), which have a broad substrate specificity. A metalloelastase (MMP-12), which degrades elastin, is also included in this group. The novel MMPs are secreted in active form or are associated with the cell surface. The activity of the MMPs is regulated by their interaction with 4 types of tissue inhibitors of metalloproteinases (TIMPs). The balance between MMPs and TIMPs regulates the degradation of extracellular matrix in normal and pathological states [\n35\n-\n37\n]. TIMP-1 is the most common in the aorta. It is a 25-kd polypeptide capable of inhibiting most MMPs and is produced by fibroblasts or smooth muscle cells.\nDegradation of ECM, especially elastin, within the aortic wall is a hallmark of abdominal aortic aneurysms (AAA). Studies have identified increased expression of MMP-1, MMP-2, MMP-9, TIMP-1, TIMP-2 and MMP/TIMP ratios as an important factor in the aetiology of AAA formation. However, the predominant MMP expressed in AAA is MMP-9, produced by macrophages [\n38\n].\nElastin and collagen degradation in thoracic aortic aneurysms is mediated by MMPs, particularly the gelatinases, MMP-2 and MMP-9.\nLe Maire et al [\n39\n] studied MMP expression in ascending aortic aneurysms associated with BAV and TAV. Samples of ascending aorta were obtained from 29 patients (BAV n = 14, TAV n = 15). Histological and immunohistochemical analysis was carried out on the specimens. They showed that ascending aortic aneurysms exhibited increased MMP expression when compared to controls (non-aneurysmal aortic tissue). The pattern of MMP expression, however, differed between aneurysms associated with BAV and those with TAV. Another study, carried out by Boyum et al [\n40\n], showed that there was an increase in the level of MMP-2 and MMP-9 in thoracic aortic aneurysms associated with BAV compared to TAV. They did not, however, find any significant difference in the expression of TIMP-1 or TIMP-2.\nMost studies have looked at the increased expression of MMPs within aneurysmal tissue. Ikonomidis et al [\n41\n] studied the effects of deletion of the TIMP-1 gene on the progression of murine thoracic aortic aneurysms (TAA). They used adult wild-type and TIMP-1 knockout mice. They showed that deletion of the TIMP-1 gene resulted in an increase in size and continued progression of TAA formation compared with wild-type mice. They concluded that this was, at least in part, due to the alteration of the balance between gelatinase activity and its endogenous inhibition. These results suggest that therapeutic strategies that can shift the MMP/TIMP stoichiometric balance away from net proteolysis may be used to inhibit the incidence and progression of TAA.\nIn diseased or degenerated congenitally deformed valves, increased local MMP activity could alter their elastic and collagen component leading to structural and functional failure.\nHistological and immunohistochemical analysis of the AV in patients with nonrheumatic TAV and AS revealed an inflammatory infiltrate within the AV leaflets and an increase in expression of MMP-1, MMP-2 and MMP-3 in AV of patients with severe AS. It was also found that MMP-9 was only present in the leaflets of patients with AS [\n42\n,\n43\n].\nKoullias et al [\n44\n] carried out a study to semiquanitatively analyse the expression of MMPs (1, 2 and 9) and TIMPs (1 and 2) in AV tissue. The study group consisted of 26 patients, undergoing surgery for AS, AR, ascending aortic aneurysm or type A dissection (BAV n = 10, TAV n = 16, controls n = 4). They showed that MMP-9 expression was significantly higher in BAV compared to normal and diseased TAV. This increased proteolytic presence in BAV may lead to the observed decrease in elastin and collagen content and their resultant functional failure. Others have reported similar results [\n45\n].\nIn summary, these findings suggest that an increase in MMP expression in the aorta of BAV patients may explain the predilection to aneurysm formation. Therefore, by modifying the MMP activity, it maybe possible to reduce or prevent the progression of thoracic aortic aneurysms (TAA). There may also be a role for altering the expression of MMPs to help reduce the progression of BAV disease.\nHistological abnormalities\nCongenital BAV is associated with cystic medial necrosis, that is, necrosis of the medial smooth muscle cells and accumulation of proteoglycan, of the aorta. De Sa et al [\n46\n] examined the histological changes in the ascending aorta and pulmonary trunk in patients with BAV. They studied 31 patients (BAV, n = 20 and TAV, n = 11) undergoing AVR. Samples of ascending aorta and pulmonary trunk were collected at the time of surgery. The degenerative changes (medionecrosis, fibrosis, cystic medial necrosis (mucoid material accumulation), changes in smooth muscle cell orientation and elastic fragmentation) in the ascending aorta and pulmonary trunk of patients with BAV disease were significantly more severe than in TAV patients. This severity was mainly related to degree of cystic medial necrosis, smooth muscle cell changes and elastic fragmentation. These findings may explain aortic root and ascending aortic dilatation in patients with BAV disease and pulmonary autograft dilation in certain patients following the Ross procedure.\nAscending aortic dilatation post AVR\nReplacement of the ascending aorta at the time of AVR is controversial because the risk of progressive dilatation following AVR is uncertain (Table \n5\n). Andrus et al [\n47\n] set out to determine the natural history of ascending aorta dilatation following AVR. They studied 185 patients undergoing AVR. They measured the ascending aortic diameter, 2 cm above the sinotubular ridge, using transthoracic echocardiography before surgery and during the follow-up period. Progressive aortic dilatation was defined as an increase in diameter of >0.3 cm from the preoperative measurement. This was observed in only 15% of the study population. No patients with baseline aortic dilatation (3.5–5.3 cm) dilated > 5.5 cm during the follow-up period (n = 107, mean 33.6 months). They found no clinical or valvular characteristics that predicted progressive aortic dilatation. Their conclusion was therefore against routine replacement of the ascending aorta at the time of AVR.\nTable 5\nAscending aorta dilatation rate following AVR\nStudy\nN\nF/U (mo)\nExpansion Rate (cm/year)\nAndrus \n47\n185\n30.0\n-0.03*\n107\n33.6\n-0.01*\nBAV\nTAV\nBAV\nTAV\n21\n164\n30.0\n+0.14 **\n-0.05\nMatsuyama \n48\n35\n97.2\n+0.058*\nYasuda \n4\nBAV\nTAV\nBAV\nTAV\n13\n14\n116.4\n+0.018***\n-0.008\ncm/(m\n2\n/yr)\ncm/(m\n2\n/yr)\n*p = N/S, **p = 0.06, ***p = 0.03\nBAV = Bicuspid aortic valve, TAV = Tricuspid aortic valve\nF/U (mo) = follow-up (months)\nAnother clinical study, by Matsuyama et al [\n48\n], looked at the incidence of aortic complications in 35 patients following AVR, with a preoperative dilated ascending aorta = 4.0 cm, assessed by computed tomography or operative findings. The baseline aortic diameter in the study population ranged from 4.0–5.5 cm. The mean follow -up period was 8.1 ± 3.5 years (range: 2.3–13 years). Aortic events occurred in 5 patients (1 aortic dissection, 2 aortic rupture and 2 reoperations). These complications occurred in patients with baseline aortic diameters 4.7–5.0 cm. The authors concluded that the clinical course of patients with dilated ascending aorta is unpredictable and may occur even in patients with a baseline aortic diameter < 5.0 cm. They concluded that preventative aortic surgery at the time of AVR should be considered, to prevent aortic rupture and dissection, in patients with ascending aorta of 4.0–5.0 cm.\nAs mentioned earlier, Yasuda et al [\n4\n] showed that AVR in patients with BAV did not prevent progressive dilatation of the ascending aorta.\nSurgical implications\nAt present there is controversy over the best management for mild to moderate aortic dilatation associated with AV disease, especially BAV. This is partly due to the lack of concrete evidence for progressive dilatation following AVR and partly due to the increased risk associated with aortic root replacement (ARR).\nA retrospective study carried out by Shapira et al [\n49\n] over a 10 year period (1987–1997) showed that advances in non-invasive diagnosis and improved perioperative management has lead to a decrease in morbidity and mortality of patients undergoing surgery on the proximal aorta with the operative mortality of thoracic aortic aneurysm repair reduced from between 9–17% to 2.6%.\nShould the ascending aorta be replaced in patients with BAV?\nAVR is the treatment of choice for patients with symptomatic AV disease. Current recommendations for the surgical replacement of ascending aortic aneurysms are diameter >5.5 cm or = 5.0 cm in patients with Marfan's syndrome [\n50\n]. Borger et al [\n51\n] studied 201 patients with BAV (mean age 56 ± 15 years) who underwent AVR. Patients were excluded if they had concomitant ascending aorta replacement. All BAV with ascending aorta > 5.0 cm had ascending aortic replacement and were therefore excluded. During the follow-up period of 10.3 years, 22 patients had long-term complications related to the ascending aorta including replacement of ascending aorta for aneurysm (n = 18), dissection (n = 1) and sudden cardiac death (n = 3). 44 patients had reoperations, mainly for AV prosthesis failure. The 15-year freedom from ascending aorta-related complications was 86%, 81% and 43% in patients with an aortic diameter of <4.0 cm, 4.0–4.4 cm and 4.5–4.9 cm respectively. The authors therefore concluded that patients undergoing AVR for BAV disease should have their ascending aorta replaced if the preoperative diameter is >4.5 cm.\nUbranski et al [\n52\n] carried out a case-matched study that showed that replacement of the ascending aorta and AV can be performed with similar operative risk, valve-related mortality and late cardiac mortality as isolated AVR. They analysed 100 patients with AV disease and aneurysm (diameter >4.5 cm) of the aorta who underwent AVR and ascending aorta replacement (± complete root) and a matched group of patients undergoing just an AVR. There was no significant difference in the early mortality. 5-year survival seen in the ARR group was 60.7% compared to 86.3% in the AVR group (p = 0.13). At a mean follow-up period of 37 ± 17 months the freedom from cardiac deaths was almost identical in both groups. Similarly, Sundt and colleagues [\n53\n] in a retrospective analysis comparing ARR with separate valve and ascending aorta replacement reported no significant difference in early mortality, but showed better survival for the complete root replacement at 5.6 years follow-up (p = 0.04).\nAnother surgical approach suggested for the management of BAV, associated with a dilated ascending aorta < 5.5 cm, is to carry out AVR with wrapping of the ascending aorta. This method has a low morbidity and mortality rate and was seen to decrease the risk of further dilatation, aneurysm formation and dissection [\n54\n,\n55\n]. More recently this procedure has been carried out using an external support made to fit the patient's aorta. This was done using digital information from magnetic resonance images to make a replica of the patient's aorta and then computer-aided design to produce the tailored graft [\n56\n].\nSuitability of the Ross procedure in BAV\nThe Ross and Ross-Konno procedure allows the replacement of a stenotic or regurgitant AV in children and young adults with congenital AV disease. Dilatation of the pulmonary autograft root is a common complication following the Ross procedure. The pulmonary and aortic roots share a common embryological origin and it has been proposed that the dilatation of the pulmonary autograft may occur as a result of an intrinsic abnormality within the wall, as seen in the aorta of patients with congenital AV disease [\n57\n]. This theory is supported by the findings of de Sa et al [\n46\n], that the degenerative changes in the ascending aorta and pulmonary trunk of patients with BAV were more severe than those with TAV. However, this result has been contradicted by Schmid et al [\n58\n], who failed to show an association between morphological abnormalities in the dilated aorta and pulmonary artery, in patients with either BAV or TAV. They did, however, confirm the finding of more severe degenerative changes in the aorta associated with BAV. Risk factors for late dilatation of the pulmonary autograft include younger patients, preoperative aortic aneurysm, BAV and those having ARR without support of the annulus and STJ [\n57\n,\n59\n]. Inclusion techniques have also been described whereby the pulmonary aoutograft is encased in a Dacron tube to prevent dilatation [\n60\n].\nHraska et al [\n61\n] analysed the mid-term results of 66 children who had undergone the Ross procedure. The mortality rate approached zero in both simple and complex left heart lesions, including infants and neonates. Their main concern was dilatation of the neo-aortic root leading to progression of AR, especially in patients with BAV. Bogers and colleagues analysed 123 patients, 81 with BAV who underwent the Ross procedure at a median follow-up of 5.3 years. Freedom from allograft and autograft intervention was similar in both groups [\n62\n].\nOther therapeutic modalities\nB-blockers\nB-blockers decrease the sheer stress of the vessel wall distal to a stenotic lesion. B-blockers are used as long-term therapy in Marfan's syndrome to reduce the rate of pressure change in the aortic root. This is achieved by using their negative inotropic and chronotropic effects to reduce the impulse of the left ventricular ejection and decrease the heart rate. This has been shown to decrease the rate of aortic dilatation and reduce the development of aortic complications [\n63\n]. However, no studies have been carried out in BAV patients.\nIn animal models of AR β-blockers have been shown to reduce the ventricular dilatation and improve remodeling.\nAngiotensin-converting enzyme (ACE) inhibitors and statins\nAortic stenosis and atherosclerosis share several common risk factors: male sex, older age, hypertension, diabetes, smoking and elevated levels of low-density lipoprotein (LDL) cholesterol and lipoprotein(a) [\n1\n,\n7\n]. These observations have led to the proposal of pharmacological strategies, already used in atherosclerosis, e.g. ACE inhibitors and hydroxymethylglutaryl-coenzyme A reductase inhibitors (statins), which may slow the progression of AS.\nACE has been shown to play an important role in development of atherosclerosis, presumably via its proinflammatory effects. ACE has been found to be present in aortic sclerotic and stenotic valves, but is not found in normal aortic valves, where it may participate in lesion development, as is evidenced by the presence of its enzymatic product, angiotensin II. The observed association between ACE and LDL in both lesions and plasma suggests that LDL may deliver ACE to the lesions [\n64\n]. It has previously been shown that ACE inhibitors slow calcium accumulation in aortic valves but a recent study found that ACE inhibitors did not slow the haemodynamic progression rate of AS [\n65\n].\nStatins are used in the prevention and treatment of atherosclerosis by reducing the levels of LDL cholesterol and lipoprotein(a). Statins have also been shown to slow aortic valve calcium accumulation and a recent study has found that they significantly reduce the haemodynamic progression of both mild-moderate and severe aortic stenosis. This rate of haemodynamic progression was unrelated to cholesterol levels and it is therefore thought that the effects of statins at the valvular level maybe due to their pleiotropic or anti-inflammatory properties rather than by their cholesterol-lowering effects [\n66\n]. However, as stated previously, the SALTIRE study group [\n8\n] found that treatment with atorvastatin did not halt the progression of calcific aortic stenosis or induce its regression. The anti-inflammatory effects, independent of their lipid-lowering effects, of statins have also been implicated as the mechanism by which they have been shown to suppress the development of experimental abdominal aortic aneurysms (AAA) in normal and hypercholesterolaemic mice. AAAs are associated with atherosclerosis, chronic inflammation and matrix metalloproteinase (MMP)-mediated connective tissue destruction. Statins were shown to preserve the medial elastin and smooth muscle cells and to alter the aortic wall expression of MMPs and their inhibitors [\n66\n].\nCalcium antagonists\nThese have been used in Marfan's syndrome to reduce the rate of dilatation of the aortic root [\n67\n]. No studies have yet been carried out in BAV patients but they may have a role in decreasing the rate of post-stenotic dilatation.\nN-terminal B-type natriuretic peptide\nB-type natriuretic peptide (BNP) and N-terminal BNP (NtBNP) are neurohormones synthesized and secreted mainly by the ventricular myocardium. An increase in synthesis of NtBNP is associated with wall stress. Natriuretic peptides have been reported to be independent predictors of outcome in congestive heart failure, primary pulmonary hypertension, acute myocardial infarction and pulmonary embolism. Plasma levels of natriuretic peptides are known to be related to disease severity and symptomatic status in AS [\n68\n,\n69\n] and now preoperative NtBNP has been shown to predict postoperative outcome with regard to survival, symptomatic status and left ventricular function in severe AS [\n70\n]. As yet, this has not been measured in aortic disease.\nSynthetic MMP inhibitors (MMPIs)\nThe MMPs are involved in many physiological functions and, therefore, general inhibition may not be feasible and specific inhibition may be required. The activity of MMPs is kept under tight control at the level of transcription, activation of latent proenzymes and inhibition of proteolytic activity. Modulation of MMP regulation can occur at various biochemical sites. Therapeutic manipulation of the extracellular matrix has been used in other disease processes, including arthritis and malignancy. Possible mechanisms of MMP inhibition include: increasing the levels of the naturally occurring inhibitors (TIMPs), by either exogenous administration of recombinant TIMPs or by increasing their local production; administration of synthetic inhibitors; and decreasing the production of MMPs.\nSynthetic inhibitors of MMPs have been investigated in other disease processes, including the use of minocycline in rheumatoid arthritis, and several are currently under investigation for the use in cardiovascular disease [\n35\n].\nConclusion\nPost-stenotic aortic dilatation is most commonly seen in patients with a BAV. The degree of this dilatation, however, may not be related to the degree of AS and does not appear to be influenced by the occurrence of AVR. It is likely that the dilatation of the ascending aorta is due, mainly, to intrinsic pathology within the aortic wall rather than the haemodynamic effects of a dysfunctional AV.\nThere is controversy as to whether the ascending aorta should be replaced at the time of initial AV surgery, if the diameter of the aorta is < 5.5 cm. Most of the evidence suggests that the aorta will continue to dilate at an unknown rate. With improvements of surgical technique and perioperative management resulting in decreased morbidity and mortality following ARR, replacement of the ascending aorta should probably be considered for diameters of 4.5 – 5.5 cm. Other therapeutic strategies being investigated that may reduce the rate of dilation are β-blockers, statins and the new synthetic MMP inhibitors.\nCompeting interests\nThe author(s) declare that they have no competing interests.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
83
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nTwo-year follow up study of stress-related disorders among immigrants to Israel from the Chernobyl area.\n\n**Article Abstract:**\n\nWe report on findings from a 2-year follow-up study of immigrants originating from exposed areas around the site of the 1986 Chernobyl accident matched with comparison subjects emigrating from other republics in the Confederation of Independent States. In the initial study of 708 immigrants, the samples were matched by age, gender, and year of immigration. We assessed two exposure groups--high and low--by estimating levels of ground cesium contamination from the International Atomic Energy Agency maps. We reinterviewed 520 immigrants from the first wave of data collection (a reinterview rate of 73%), 87 from high-exposure areas, 217 from low-exposure areas, and 216 comparison subjects. This study examined the prevalence of symptoms of posttraumatic stress disorders (PTSD), depression, somatization, anxiety, and physical effects (high blood pressure, acute symptoms, and chronic illness). The results obtained in the first wave conducted 8 years after the accident showed that psychological symptoms were significantly higher in exposed respondents than in the comparison group. During the second wave (10 years after the accident) we observed a decline in the prevalence of PTSD and related distress except for somatization, which remained at the same level. An association between exposure and high blood pressure was observed in the first wave of data, but was not still significant in the second wave of data collection. The proportion of those who reported three or more chronic health problems was 48.3% among the high-exposure group, 49.3% in the low-exposure group, and 30.6% in the comparison group (p = 0.0003). The most commonly reported problems were heart disease. problems with vision or hearing, migraine headaches, problems with the lymphatic system, and arthritis. Based on the results, it was concluded that the Chernobyl accident was a powerful stressor, having a strong impact on both mental and physical health. Since all respondents were engaged in the process of acculturation and accommodation to a new country after emigration, it is encouraging that this study shows that levels of psychological distress are waning as the new immigrants are absorbed into Israeli society. However, there still remains some independent effect on health associated with the experience of the Chernobyl accident.\n\n**Article Body:**\n\n\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
84
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nAn adult cystic fibrosis patient presenting with persistent dyspnea: case report\n\n**Article Abstract:**\n\nBackground\nPersistent dyspnea is a common finding in the cystic fibrosis patient that typically leads to further work up of an alternative pulmonary etiology. Adult cystic fibrosis patients; however, are growing in numbers and they are living into the ages in which coronary artery disease becomes prevalent. Coronary disease should be included in the consideration of diagnostic possibilities.\nCase presentation\nA 52-year-old white male with cystic fibrosis was evaluated for exertional dyspnea associated with vague chest discomfort. Diagnostic testing revealed normal white blood cell, hemoglobin and platelet count, basic metabolic panel, fasting lipid profile, HbA1c, with chest radiograph confirming chronic cystic findings unchanged from prior radiographs and an electrocardiogram that revealed sinus rhythm with left anterior fascicular block. Stress thallium testing demonstrated a reversible anteroseptal perfusion defect with a 55% left ventricular ejection fraction. Heart catheterization found a 99% occlusion of the left anterior descending artery extending into the two diagonal branches, with 100% obstruction of the left anterior descending artery at the trifurcation and 70% lesion affecting the first posterior lateral branch of the circumflex artery.\nConclusion\nThis case report represents the first description in the medical literature of a cystic fibrosis patient diagnosed with symptomatic coronary artery disease. Applying a standard clinical practice guide proved useful toward evaluating a differential diagnosis for a cystic fibrosis patient presenting with dyspnea and chest discomfort.\n\n**Article Body:**\n\nBackground\nCystic Fibrosis (CF) is the most common lethal inherited disease in the Caucasian population. It was once considered a childhood disease; however, with advances in health care there is a growing population of adults with CF [\n1\n]. A life expectancy that was only 8 years of age in 1974 had advanced to the age of 21 years in 1994, and today is estimated as high as 40 years of age [\n2\n]. There are patients on the Cystic Fibrosis Foundation Patient Registry in 2003 that are in their eighth decade of life [\n1\n].\nWith new found longevity comes a new spectrum of disease prevalence associated with aging. Cystic Fibrosis Related Diabetes (43% prevalence) is now the number two chronic illness in the adult CF patient following chronic lung disease and surpassing liver disease (24% prevalence) in patients greater than 30 years of age [\n3\n]. Cardiovascular disease has been essentially isolated to cor pulmonale as a consequence of end stage obstructive pulmonary disease. Hypertension has not been considered a serious problem in this patient population [\n4\n]; however, a 20% prevalence has been observed at our CF adult center. Symptomatic coronary artery disease, one of the most prevalent of diseases in the adult patient population, has never been reported in the CF population from a PubMed literature search to date. Guides for care of health concerns in adult patients with CF were published in a January 2004 Consensus Report to help transition CF health care from pediatrician to internists or other adult care providers [\n3\n]. Many aspects of cardiovascular discussions such as hypertension and forms of heart disease separate from cor pulmonale are missing from this consensus report. The following discussion illustrates the need to continually update and add new information that will lead to optimizing the care of adult CF patients.\nCase presentation\nA 52-year-old white male with CF presented with persistent exertional dyspnea and cough with scant sputum production. Physical examination demonstrated oxygen saturation of 91%, with normal temperature and vital signs. His weight had fallen from 79.2 to 77.1 kg over 3 months. Cardiovascular exam was entirely normal. Lungs demonstrated coarse breath sounds bilaterally with scattered rales throughout the lung fields. The abdomen was normal, extremities demonstrated significant clubbing and there was no peripheral edema. Forced expiratory volume at 1 second (FEV\n1\n) had decreased from 50% to 36%. The chest radiograph resembled baseline findings with no obvious infiltrate or pneumothroax. He received a month-long course of azithromycin, aztreonam and inhaled tobramycin for suspected pulmonary exacerbation of acute super-infection in the setting of underlying chronic CF lung disease.\nOne month later, follow-up revealed no improvement in dyspnea and no change in the scant sputum production, despite full adherence to the antibiotic regimen and airway clearance techniques. Exertional discomfort located along the sternum and left anterior chest associated with dyspnea without radiation or pressure sensation was further described but was not associated with palpitations, diaphoresis or nausea. This discomfort improved with rest and was not associated with meals. He did report the need to sleep upright in a recliner, but denied paroxysmal nocturnal dyspnea.\nCF was diagnosed in this patient by sweat chloride at age 35 after an episode of hemoptysis, with subsequent genetic analysis identifying a ΔF508, 2789+5G>A mutation. He also has gastroesophageal reflux, Barrett's esophagus, azoospermia, and pancreatic insufficiency. He had sinus surgery at age 47. Medications include albuterol, ipratropium, fluticasone, dornase alpha, salmeterol, omeprazole, pancreatin and multivitamin. The patient's father had a myocardial infarction at age 37, his mother had coronary artery bypass surgery at 52 years of age, and a brother underwent coronary bypass at age 61. The patient has never smoked and alcohol intake was minimal.\nDiagnostic testing demonstrated normal white blood cell, hemoglobin and platelet count. Electrolytes, albumin, protein and glucose were normal with a 5.1% HbA1c. Total cholesterol was 139 mg/dl, LDL 80 mg/dl, HDL 30 mg/dl and triglycerides at 76 mg/dl. Chronic findings with cystic changes were evident on chest radiograph, but with no obvious consolidation. Electrocardiogram revealed sinus rhythm with a left anterior fascicular block and normal ST findings.\nStress thallium testing was subsequently arranged within a week of the follow up visit, with results positive for moderate anteroseptal area of reversible perfusion with a left ventricular ejection fraction of 55%. Subsequent heart catheterization revealed 99% occlusion of the left anterior descending artery with extension into the two diagonal branches, 100% obstruction of the left anterior descending artery at the trifurcation and 70% lesion affecting the first posterior lateral branch of the circumflex artery. The patient was evaluated for possible coronary artery bypass graft; however, because of his current pulmonary status, angioplasty was elected with successful stenting of the left anterior descending artery. On follow up one year out from stent placement, the patient remained asymptomatic with exercise tolerance and pulmonary function returning to baseline.\nConclusion\nThis is the first report of a cystic fibrosis patient diagnosed with symptomatic coronary artery disease (CAD) and acknowledges that adult cystic fibrosis patients have indeed survived into the years were coronary artery disease becomes prevalent. Therefore, the likelihood of coronary disease should be included in the diagnostic consideration of persistent dyspnea associated with chest discomfort by applying the same standards used in grading a differential with an anginal presentation in non-CF patients [\n5\n].\nThe patient presented in this case had a Framingham score estimate that predicted a 10-year cardiovascular risk at 4% [\n6\n]. However, because of the presence of subtle chest discomfort associated with dyspnea, medical decision making includes an active alternative diagnosis of atypical angina based on two of three positive criteria of exertional symptoms with symptom relief upon resting [\n5\n]. Persistent dyspnea may be an occasional finding for a cystic fibrosis patient, and one that typically leads to further work up of a pulmonary etiology; however, cardiovascular disease was additionally considered in this patient.\nThe typical differential diagnosis of persistent dyspnea in an adult cystic fibrosis patient would include pneumothorax (5% prevalence) [\n7\n], atypical mycobacterial pneumonia (15% prevalence) [\n8\n], allergic bronchopulmonary aspergillosis (30% prevalence) [\n9\n], and cor pulmonale (3% prevalence in association with severe CF pulmonary disease) [\n10\n]. Without a history for hemoptysis, atypical mycobacterium and allergic bronchopulmonary aspergillosis would be less likely. Physical exam and chest radiograph did not support either pneumothorax or congestive heart failure. Symptoms could also be explained by this patient's progression of gastroesophageal reflux and/or Barrett's esophagus.\nAtypical angina would be the most prevalent differential diagnosis, at 60%, for our patient's clinical presentation of chest pain in the non-CF male patient at this age [\n5\n]. The risk of CAD is not typically considered as an active alternative diagnosis for the CF patient; yet with aging, even CF patients will be at risk for CAD. This risk may even be greater given higher prevalence of known risk factors such as diabetes mellitus in the CF versus non-CF patient [\n11\n].\nTwo cases of asymptomatic coronary artery disease have been reported in association with CF with some advanced detail. One case came to diagnosis at autopsy, characterized as generalized atherosclerosis in a 41-year-old female CF patient [homozygous G542X] with diabetes mellitus that died from respiratory failure [\n12\n]. Further review of this case revealed a 200 mg/dl averaged cholesterol level, progressive hypertension with biopsy proven nephrosclerosis by 31-years of age, and a diabetic course complicated by gastrointestinal pseudoparesis, retinopathy and neuropathy. In this case, coronary artery disease was an incidental finding on autopsy as she was asymptomatic for myocardial ischemia during her lifetime.\nA second case was described in which segmental hypokinesis with grade 2 systolic function was found as an incidental finding on Doppler echocardiography from a prevalence study looking at pulmonary hypertension that included an adult cystic fibrosis patient population [\n10\n]. This study identified a 40-year-old diabetic male, diagnosed with asymptomatic coronary artery disease after performing a thallium perfusion scan. Further testing by cardiac catheterization was not reported in this study.\nWhat about other coronary risk factors? Cholesterol and hypertension were not identified risk factors present in our patient. The autopsy case report had several risk factors present, most notably, diabetes and hypertension, but with only a borderline elevated cholesterol level. What is the expected lipid level in a CF patient? The largest lipid study conducted on a CF population reported 134 ± 84 mg/dl triacylglycerol and 138 ± 84 mg/dl total cholesterol values [\n14\n]. Only 4% of patients had cholesterol levels >200 mg/dl in this study, with a maximum total cholesterol identified at 240 mg/dl. Serum cholesterol levels can be highly variable in CF patients. Patients with pancreatic insufficiency have low to normal cholesterol levels even with a high fat diet and enzyme supplementation as seen in this case [\n15\n]; however, CF patients with pancreatic sufficiency are likely at the same risk as the general population for complications for hyperlipidemia [\n16\n]. Another study of aortic atherosclerosis in CF patients found that they have less fatty streaking of the aorta than their weight matched counterparts [\n17\n]. Clearly there are other factors that may lead to atherosclerosis than lipid levels; however, applying a clinical practice guide published by the American College of Physicians [\n5\n] proved helpful toward diagnosing CAD in this CF patient presenting with dyspnea associated with a chest discomfort.\nAbbreviations\nCF – cystic fibrosis; FEV\n1 \n– forced expiratory volume at 1 second; LDL – low density lipoprotein; HDL – high density lipoprotein; CAD – coronary artery disease;\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nGMO contributed to the literature review cited in the discussion and editing of the original manuscript. CLF providing medical care for the patient described in this case presentation, and wrote the original manuscript detailing the clinical findings encountered from the clinical assessment. All authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
85
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nComparison of exercise, dobutamine-atropine and dipyridamole-atropine stress echocardiography in detecting coronary artery disease\n\n**Article Abstract:**\n\nBackground\nDipyridamole and dobutamine stress echocardiography testing are most widely utilized, but their sensitivity remained suboptimal in comparison to routine exercise stress echocardiography. The aim of our study is to compare, head-to-head, exercise, dobutamine and dipyridamole stress echocardiography tests, performed with state-of-the-art protocols in a large scale prospective group of patients.\nMethods\nDipyridamole-atropine (Dipatro: 0.84 mg/kg over 10 min i.v. dipyridamole with addition of up to 1 mg of atropine), dobutamine-atropine (Dobatro: up to 40 mcg/kg/min i.v. dobutamine with addition of up to 1 mg of atropine) and exercise (Ex, Bruce) were performed in 166 pts. Of them, 117 pts without resting wall motion abnormalities were enrolled in study (91 male; mean age 54 ± 10 years; previous non-transmural myocardial infarction in 32 pts, angina pectoris in 69 pts and atypical chest pain in 16 pts). Tests were performed in random sequence, in 3 different days, within 5 day period under identical therapy. All patients underwent coronary angiography.\nResults\nSignificant coronary artery disease (CAD; ≥50% diameter stenosis) was present in 69 pts (57 pts 1-vessel CAD, 12 multivessel CAD) and absent in 48 pts. Sensitivity (Sn) was 96%, 93% and 90%, whereas specificity (Sp) was 92%, 92% and 87% for Dobatro, Dipatro and Ex, respectively (p = ns). Concomitant beta blocker therapy did not influence peak rate-pressure product and Sn of Dobatro and Dipatro (p = ns).\nConclusion\nWhen state-of-the-art protocols are used, dipyridamole and dobutamine stress echocardiography have comparable and high diagnostic accuracy, similar to maximal post-exercise treadmill stress echocardiography.\n\n**Article Body:**\n\nBackground\nExercise stress echocardiography is more sensitive and specific for detecting inducible ischemia than exercise electrocardiography testing alone [\n1\n-\n4\n]. Dipyridamole and dobutamine stress echocardiography testing are most widely utilized, but their sensitivity remained suboptimal in comparison to routine exercise stress echocardiography [\n5\n,\n6\n]. This diagnostic challenge provoked development of stress protocols including addition of atropine [\n7\n-\n12\n]. The objective of this study was to assess in head-to-head fashion diagnostic value of dipyridamole-atropine, dobutamine-atropine and exercise stress echocardiography in the same group of patients presented for evaluation of coronary artery disease.\nMethods\nStudy population\nBetween January and July 2004, 166 consecutive patients referred for coronary angiography were evaluated. Of them, only 117 (91 male, 26 female; mean age 54 ± 10 years) patients without resting wall motion abnormalities were enrolled in the study. Exclusion criteria were: presence of left ventricular wall motion abnormality at baseline, heart failure, left bundle branch block, unstable angina, congenital or valvular heart disease, severe hypertension (systolic ≥180 mmHg and diastolic pressure ≥110 mmHg), serious arrhythmias and chronic obstructive pulmonary disease.\nInformed consent was obtained from all patients. They underwent exercise, and pharmacological stress echocardiography. Previous non-transmural myocardial infarction was present in 32 patients, 69 had angina pectoris and 16 patients experienced atypical chest pain.\nThe study was approved by the Institutional Review Board of the Institute of Cardiovascular Diseases in Belgrade.\nConcomitant beta blockers were used in 34% (40/117), calcium antagonists in 37% (44/117) and nitrates in 45% (53/117) of patients. Teophylline, caffeine-containing products, and dipyridamole preparations were not allowed for at least 12 hours before testing.\nPatients performed stress testing in 3 different days in random sequence within 5 day period, at least 14 days after uncomplicated myocardial infarction.\nStress protocols\nExercise echocardiography \n(\nEx\n) was performed according to maximal Bruce treadmill protocol.\nDobutamine-atropine (Dobatro)\nDobutamine was infused in 3-minutes dose increments, starting from 5 to 40 mcg/kg/min. In echocardiography negative patients, atropine was added (in 4 divided doses up to a maximum of 1 mg of atropine) to the continuing 40 mcg/kg/min dobutamine infusion [\n11\n].\nDipyridamole-atropine (Dipatro)\nDipyridamole was infused at a dose of 0.56 mg/kg over 4 min, followed with 4 min of no dose and then, if the test was still negative, 0.28 mg/kg in 2 min. In dipyridamole echocardiography negative patients, 3 min after the end of infusion, atropine was given in 4 divided doses up to a maximum of 1 mg of atropine [\n12\n].\nThe test was considered positive in the presence of obvious left ventricular regional wall motion abnormality. The other reasons for test interruption were: peak atropine dose (for pharmacological tests), achievement of maximal age predicted heart rate, significant ST segment depression or elevation, severe chest pain, exercise-limiting dyspnea, fatigue and/or claudication, symptomatic hypotension (decrease in systolic blood pressure >20 mmHg) or hypertension (>220/120 mmHg), severe arrhythmias or intolerable side effects of administered drugs. Intravenous aminophylline (250 mg) was given after cessation of Dipatro test, and beta blockers (metoprolol 5 mg) or nitroglycerin if required.\nA 12-lead electrocardiogram monitoring was performed continuously and recorded at baseline, at the end of each stage and during recovery period accompanied with blood pressure recordings. Rate pressure product was calculated by multiplying systolic blood pressure and heart rate.\nEchocardiographic analysis\nTwo-dimensional echocardiography was performed with the patient in the left lateral decubitus position. Standard apical and parasternal views were recorded, facilitating the analysis from the off line digitized videotapes (Image View, ATL). We used 16-segment left ventricular model [\n13\n]. Segmental wall motion was evaluated using standard method: normal – 1, hypokinetic – 2, akinetic – 3, or dyskinetic – 4 [\n13\n]. Wall motion score index was derived for rest and peak stress tests. Video tapes were analyzed independently by two experienced observers unaware of patients' data or other tests results with overall agreement of 92%. By subgroup analysis, the interobserver agreement was 93%, 94% and 90% for Dobatro, Dipatro, and Ex. In case of discrepancy decision was made by consensus.\nCoronary angiography and quantitative angiographic analysis\nAll patients underwent selective coronary angiography according to Judkin's technique, within one week of stress echocardiography tests. Angiograms were analyzed using quantitative coronary angiography (MEDIS CMS, Leiden, The Netherlands) by observers unaware of the patient's data. Significant coronary artery stenosis was considered as ≥50% diameter stenosis present in at least one major epicardial coronary vessel.\nStatistical analysis\nThe data are expressed as mean ± SD. Comparison of continuous variables was performed using ANOVA As, Newman-Keuls procedure and \nt \ntest where appropriate, whereas dichotomous variables were compared using chi-square (McNemar-s test for paired proportions). A coefficient of correlation (r) was used to compare peak wall motion score index of different tests. Confidence intervals were calculated according to standard formulas (95%CI) as well as sensitivity, specificity and diagnostic accuracy.\nCalculation of sensitivity, specificity and diagnostic accuracy were performed according to standard formulas. A p value less than 0.05 was considered statistically significant.\nResults\nAngiographic characteristics\nCoronary artery disease was present in 69 patients: one-vessel coronary artery disease was present in 57 patients, 12 patients had multi-vessel coronary artery disease. The distribution of lesions were: left anterior descending – 50 patients, circumflex artery – 15 patients, and right coronary artery – 16 patients.\nFeasibility, safety and hemodynamic changes\nFeasibility was 95% and 97% for Dobatro and Dipatro (p = ns), respectively. Limiting side effects occurred in 6 and in 4 patients during Dobatro and Dipatro, including non-sustained ventricular tachycardia and short run of supraventricular tachycardia in the absence of myocardial ischemia. They disappeared after cessation of the test or after administration of specific antidote.\nLimiting side effects occurred in 17 patients (14%) during Ex in the absence of diagnostic end point and consisted of serious ventricular and supraventricular rhythm disturbances, severe chest pain, hypertensive response and fatigue. Thus, feasibility of Ex was 85%. There was no significant difference in feasibility of all three tests (p = ns for all intergroup differences). There were no late complications in the ensuing hours after finishing the tests.\nHemodynamic changes during stress echocardiography tests are presented in Table \n1\n.\nTable 1\nPeak hemodynamic data during dobutamine, dobutamine-atropine, dipyridamole, dipyridamole-atropine and exercise stress tests.\nDob\nDobatro\nDip\nDipatro\nEx\nHeart rate, beat/min\n110 ± 27\n138 ± 25*\n91 ± 15\n125 ± 25*\n148 ± 22**\nSystolic blood pressure, mmHg\n155 ± 20\n160 ± 30*\n138 ± 22\n158 ± 20*\n182 ± 24**\nDiastolic blood pressure, mmHg\n98 ± 15\n103 ± 10\n90 ± 9\n97 ± 12\n109 ± 14**\nPRR, mmHg × beat/min/100\n170 ± 64\n221 ± 60*\n126 ± 32\n198 ± 59*\n348 ± 61**\nValues are given as mean ± SD. Dob indicates dobutamine; Dobatro, dobutamine-atropine; Dip, dipyridamole; and Dipatro, dipyridamole-atropine; RPP, rate-pressure product. Asterisk indicates significant difference for Dobatro vs. Dob, and Dipatro vs. Dip (p < 0.0001). Two asterisks indicate significant difference between Ex and other tests (p < 0.0001 for all).\nDiagnostic value of stress echocardiography\nAtropine was added to dobutamine in 69% (81/117) of patients and to dipyridamole in 68% (80/117) of patients. Stress-induced wall motion abnormalities appeared in 70, 68 and 68 patients during Dobatro, Dipatro and Ex, respectively. The sensitivity was 96%, 93% and 90% for Dobatro, Dipatro and Ex in detection of myocardial ischemia (p = ns for Ex vs. Dobatro vs. Dipatro) (Figure \n1\n). Specificity was 92% both for Dobatro and Dipatro, and 87% for Ex (p = ns for all intergroup differences). Diagnostic accuracy was: 94% for Dobatro, 92% for Dipatro and 90% for Ex, respectively (p = ns for Ex vs. Dobatro vs. Dipatro).\nFigure 1\nSensitivity, specificity and diagnostic accuracy of stress echocardiography tests\n. Bar graph showing sensitivity (Sn), specificity (Sp) and diagnostic accuracy (Acc) of dobutamine-atropine (Dobatro), dipyridamole-atropine (Dipatro) and exercise (Ex) stress echocardiography tests. There was no statistically significant difference between three tests. Asterisk indicates significant difference between stress tests (p < 0.01).\nDobatro, Dipatro and Ex provoked significant change from the rest to peak stress WMSI (1.32 ± 0.18, 1.31 ± 0.17 and 1.28 ± 0.18, for Dobatro, Dipatro, and Ex; p = ns for all), with significant correlation (p < 0.0001) of peak WMSI between all tests.\nSingle vs. multivessel CAD: The sensitivity of stress in detection of one-vessel coronary artery disease was 95% for Dobatro and 95% for Dipatro and 93% for Ex (p = ns for Ex vs. Dobatro, and Ex vs. Dipatro). The sensitivity for detection of multivessel coronary artery disease was 100% for Dobatro and Dipatro and 92% for Ex (p = ns).\nThe impact of concomitant beta – blocker therapy on stress echocardiographic results\nForty (34%) patients received concomitant beta blocker therapy (34 with coronary artery disease). There was significant difference between patients with (BB+) and without beta-blocker therapy (BB-) in the peak heart rate for Dob, Dip, and Ex (p < 0.001), whereas addition of atropine excluded significant influence of beta-blocker therapy on peak heart rate. Rate-pressure product at baseline and peak stress tests in patients with (BB+) and without (BB-) concomitant beta-blocker therapy are presented in Table \n2\n.\nTable 2\nRate-pressure product at baseline and peak stress tests in patients with (BB+) and without (BB-) concomitant beta-blocker therapy\nRPP (mmHgxbpm/100)\nbaseline\nDob\nDobatro\nDip\nDipatro\nEx\nBB+ group\n110 ± 25\n167 ± 27\n213 ± 58\n135 ± 10\n199 ± 37\n233 ± 22\nBB- group\n123 ± 40*\n205 ± 20\n230 ± 53\n145 ± 12*\n210 ± 40\n389 ± 77*\nRPP indicates rate-pressure product; Dob indicates dobutamine; Dobatro, dobutamine-atropine; Dip, dipyridamole; Dipatro, dipyridamole-atropine; Values are given as mean ± SD. Asterisk indicates significant difference between stress tests (p < 0.001).\nAtropine was added to dobutamine in 75% of patients in BB+ (34/40) and in 61% in BB- group (47/77), and to dipyridamole in 85% of patients in BB+ (34/40) and 60% (46/77) in BB- group. Addition of atropine resulted in similar sensitivity (Dobatro: BB+ 86% vs. BB- 89%, p = ns; Dipatro: BB+ 88% vs. BB- 92%, p = ns). However, sensitivity of Ex was significantly affected by beta-blocker therapy (BB+ 80% vs. BB- 92%, p < 0.01) (Figure \n2\n).\nFigure 2\nSensitivity of stress echocardiography tests in patients with and without concomitant beta-blocker therapy\n. Sensitivity of dobutamine-atropine (Dobatro), dipyridamole-atropine (Dipatro) and exercise (Ex) in patients with and without concomitant beta-blocker therapy. There was no significant difference in sensitivity for Dobatro and Dipatro between patients with (BB+) and without (BB-) concomitant beta-blocker therapy, whereas sensitivity of Ex was significantly higher in patients without concomitant beta-blocker therapy. Asterisk indicates significant difference between stress tests (p < 0.01).\nDiscussion\nThis study represents for the first time direct comparative evaluation of dobutamine-atropine and dipyridamole-atropine – with exercise stress echocardiography performed in the same group of patients. Dipyridamole-atropine and dobutamine-atropine stress echocardiography have comparable and high diagnostic accuracy, similar to maximal post-exercise treadmill stress echocardiography. In addition, dipyridamole-atropine and dobutamine-atropine stress echocardiography testing overcomes the effects of concomitant beta-blocker therapy reaching high and comparable diagnostic value.\nOur results are comparable with previous findings showing that atropine coadminitsration significantly improved sensitivity in dobutamine and dipyridamole negative patients [\n11\n,\n12\n]. In addition, Pingitore et al. have shown, in comparative study with dobutamine-atropine and dipyridamole-atropine, that both tests have comparative sensitivity of 84% and 82%, respectively, without significant difference between them [\n14\n].\nIt has been shown that beta-blocker therapy can significantly influence results of stress echocardiography tests if routine doses are employed. Beta-blockers are known to protect from exercise induced ischemia [\n15\n]. They also affect the results of dipyridamole stress echocardiography, despite the fact that hemodynamic profile is at least affected by dipyridamole [\n16\n]. In our study, addition of atropine induced significant increase in heart rate, systolic blood pressure and rate pressure product as well as increase of diagnostic accuracy in comparison to dobutamine and dipyridamole alone regardless of beta blocker therapy. In comparison to exercise stress echocardiography testing, atropine coadministration resulted in similar sensitivity and specificity of dobutamine-atropine and dipyridamole-atropine stress echocardiography in both groups of patients. Thus, atropine factor in pharmacological stress echocardiography testing can overcome the effects of beta-blocker therapy, as it has been shown in previous studies [\n17\n,\n18\n].\nPathophysiological mechanisms\nWe used three tests with different mechanisms of provoking myocardial ischemia through a) an increase in oxygen demand, exceeding the fixed supply – dobutamine and exercise; and b) flow maldistribution, due to inappropriate coronary artery vasodilatation. Atropine superimposes a marked chronotropic stress to dipyridamole and dobutamine increasing oxygen demand, decreasing, at the same time, myocardial oxygen supply by shortening the diastole whose duration is important for perfusion in the presence of maximal vasodilatation [\n19\n] and increasing the ischemic potential of stress echocardiography [\n11\n,\n12\n].\nComparison with previous studies\nSeveral meta-analytic comparisons of echocardiographic stressors have been performed in the past [\n20\n-\n23\n]. They unanimously reached the conclusion that dipyridamole is more specific than dobutamine and exercise, and exercise and dobutamine are more sensitive than dipyridamole for noninvasive detection of coronary artery disease affecting the recent cardiology guidelines [\n4\n] and standard textbook knowledge [\n24\n], which suggests to use dipyridamole stress in combination with perfusion scintigraphy and consider only dobutamine stress as a suitable pharmacological stress to be combined with echocardiography. However, this conclusion conflicts the results of present study. The reason of this apparent discrepancy is the fact that with the vasodilator stress echocardiography, one needs the high dose protocol with atropine to optimize the diagnostic sensitivity. The same result can be obtained, without atropine, by using the high dose over a shorter infusion time of dipyridamole: the so called accelerated protocol [\n25\n]. As a matter of fact, the 1998. Guidelines of the American Society of Echocardiography clearly recommended high dose + atropine, as the standard protocol to achieve optimal accuracy with dipyridamole stress echocardiography [\n13\n]. Accordingly, if we consider only the literature with state-of-the-art dipyridamole protocols (with accelerated infusion or with atropine coadministration), the conclusions of the guidelines and recent textbook recommendations clash against available evidence. Two previous reports [\n26\n,\n27\n] comparing accelerated dipyridamole versus dobutamine stress echocardiography tests, and 2 additional reports [\n14\n,\n28\n] comparing dipyridamole-atropine stress echocardiography versus dobutamine stress echocardiography, have reached consistent conclusion of each individual study – cumulative analysis has shown that dipyridamole had a better specificity and the same sensitivity in comparison with high dose dobutamine stress echo. These results of the published literature, as well as the results of the present study, represent a weight of evidence which may influence current guidelines and recent cardiology textbooks statements. When state of the art protocols are used, either dobutamine or dipyridamole provide excellent and comparable diagnostic sensitivity and overall accuracy.\nStudy limitations\nThe study group was derived from patients referred for coronary angiography and angioplasty, so large majority of patients had the one-vessel coronary artery disease. The use of a qualitative assessment of wall motion during stress echocardiography is a limitation of this technique, although qualitative assessment of regional wall motion by trained observers remains the only clinically applied method in stress echocardiography.\nConclusion\nWhen state-of-the-art protocols are used, dipyridamole and dobutamine stress echocardiography have comparable and high diagnostic accuracy, similar to maximal post-exercise treadmill stress echocardiography. In addition, dipyridamole-atropine and dobutamine-atropine stress echocardiography testing overcome the effects of concomitant beta-blocker therapy reaching high and comparable diagnostic value.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nWe would like to report specific contribution of each author of the manuscript: IN made the concept, performed stress echocardiography tests and participated in the echocardiographic analysis. MO participated in the design of the study and interpretation of data. BB performed quantitative coronary angiography and help to draft the manuscript. ADD carried out the stress echocardiography testing. JS performed stress echocardiography tests and participated in its interpretation. MN performed coronary angiography. SS performed coronary angiography and quantitative coronary angiography analysis. GS participated in the interpretation of data. JS helped in quantitative coronary angiographic analysis. ZP carried out the selection of patients. VG participated in the statistic analysis. PM participated in the design of study and helped to draft the manuscript.\nAll authors read and approved the final manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** definitely relevant"
}
] |
definitely relevant
|
86
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nValidation of Heart Failure Events in the Antihypertensive and Lipid Lowering Treatment to Prevent Heart Attack Trial (ALLHAT) Participants Assigned to Doxazosin and Chlorthalidone\n\n**Article Abstract:**\n\nBackground\nThe Antihypertensive and Lipid Lowering Treatment to Prevent Heart Attack Trial (ALLHAT) is a randomized, double-blind, active-controlled trial designed to compare the rate of coronary heart disease events in high-risk hypertensive participants initially randomized to a diuretic (chlorthalidone) versus each of three alternative antihypertensive drugs: alpha-adrenergic blocker (doxazosin), ACE-inhibitor (lisinopril), and calcium-channel blocker (amlodipine). Combined cardiovascular disease risk was significantly increased in the doxazosin arm compared to the chlorthalidone arm (RR 1.25; 95% CI, 1.17–1.33; \nP \n< .001), with a doubling of heart failure (fatal, hospitalized, or non-hospitalized but treated) (RR 2.04; 95% CI, 1.79–2.32; \nP \n< .001). Questions about heart failure diagnostic criteria led to steps to validate these events further.\nMethods and Results\nBaseline characteristics (age, race, sex, blood pressure) did not differ significantly between treatment groups (\nP \n< .05) for participants with heart failure events. Post-event pharmacologic management was similar in both groups and generally conformed to accepted heart failure therapy. Central review of a small sample of cases showed high adherence to ALLHAT heart failure criteria. Of 105 participants with quantitative ejection fraction measurements provided, (67% by echocardiogram, 31% by catheterization), 29/46 (63%) from the chlorthalidone group and 41/59 (70%) from the doxazosin group were at or below 40%. Two-year heart failure case-fatalities (22% and 19% in the doxazosin and chlorthalidone groups, respectively) were as expected and did not differ significantly (RR 0.96; 95% CI, 0.67–1.38; \nP \n= 0.83).\nConclusion\nResults of the validation process supported findings of increased heart failure in the ALLHAT doxazosin treatment arm compared to the chlorthalidone treatment arm.\n\n**Article Body:**\n\nThe Antihypertensive and Lipid Lowering Treatment to Prevent Heart Attack Trial (ALLHAT) is a randomized, two-component clinical trial sponsored by the National Heart, Lung, and Blood Institute (NHLBI). A double-blind, active-controlled hypertension component is designed to compare the rate of fatal coronary heart disease (CHD) or nonfatal myocardial infarction (MI) (the primary endpoint) in high-risk hypertensive participants, aged 55 years or older, between those randomized to treatment initiated with a diuretic (chlorthalidone) and treatment initiated with each of three alternative antihypertensive drugs: a calcium-channel blocker (amlodipine), an angiotensin-converting enzyme (ACE)-inhibitor (lisinopril), or an alpha-adrenergic blocker (doxazosin). An open-label lipid-lowering component is designed to determine if lowering LDL cholesterol with pravastatin compared to \"usual care\" reduces all-cause mortality in a subset of moderately hypercholesterolemic patients. Randomization to the hypertension component began in February, 1994, and continued through January, 1998, with 42,418 participants recruited at 623 clinical centers in the United States, Canada, Puerto Rico and the US Virgin Islands. Randomization of 10,355 participants into the lipid trial ended May 31, 1998. Follow-up on all participants continued through March, 2002 [\n1\n].\nFollowing independent reviews by the Data and Safety Monitoring Board (DSMB) on January 6, 2000, and by an Ad Hoc Committee on January 21, 2000, the Director of the National Heart, Lung, and Blood Institute accepted a recommendation to discontinue the doxazosin treatment arm of the antihypertensive trial. This recommendation was based on the low probability of doxazosin showing benefit over chlorthalidone for the primary endpoint, as well as the significantly increased occurrence of the secondary endpoint, combined cardiovascular disease (CVD) (encompassing CHD deaths, nonfatal MI, stroke, coronary revascularization procedures [coronary artery bypass graft or CABG, percutaneous transluminal coronary angioplasty or PTCA/stent], angina [hospitalized or treated as an outpatient], heart failure [HF/treated in the hospital or as an outpatient], and peripheral arterial disease [in-hospital or outpatient revascularization]) in the doxazosin arm (RR 1.25; 95% CI, 1.17–1.33; \nP \n< .001), with a doubling of risk of HF (fatal, hospitalized and treated but nonhospitalized) (RR 2.04; 95% CI, 1.79–2.32; \nP \n< .001). When only fatal and hospitalized HF were analyzed, the large difference remained (RR 1.83; 95% CI, 1.58–2.13;\nP \n< .001). The findings and operational aspects of stopping the doxazosin arm of the study have been previously described [\n2\n-\n4\n].\nThe observed increase in HF in the doxazosin group as compared to the chlorthalidone group led to several additional analyses aimed toward validation of the diagnoses, with a focus on hospitalized and fatal HF. The purposes of these analyses were: 1) to evaluate the reality of HF cases, i.e. whether diagnosis, management, and clinical course were what might be expected, and 2) to compare these features between the two treatment groups.\nMethods\nStudy Design\nThe rationale and design of ALLHAT are described in detail elsewhere [\n1\n]. Briefly, those eligible for randomization had systolic blood pressure (SBP) of at least 140 mm Hg and/or diastolic blood pressure of at least 90 mm Hg, or took medication for hypertension, and had at least one other risk factor for CHD events. Risk factors included previous MI or stroke, left ventricular hypertrophy by electrocardiogram or echocardiogram, history of type 2 diabetes, current cigarette smoking, and low high-density lipoprotein (HDL) level.\nThe primary endpoint of the blood pressure (BP) trial is the composite of nonfatal MI and fatal CHD. The four protocol-defined secondary clinical outcomes are all-cause mortality, combined CHD (including CHD death, nonfatal MI, coronary revascularization procedures and hospitalized angina), stroke, and combined CVD (including CHD death, nonfatal MI, stroke, coronary revascularization procedures, angina treated in the hospital or as an outpatient, lower extremity peripheral arterial disease treated in the hospital or with outpatient revascularization, and HF, fatal or treated in the hospital or as an outpatient).\nThe validation of HF diagnosis entailed answering several questions:\n1. Did HF cases meet ALLHAT diagnostic criteria?\n2. Were baseline characteristics and medical management for HF cases as expected and similar across the drug groups?\n3. Were prevalence and severity of systolic dysfunction as expected and similar across drug groups?\n4. Were case-fatality rates as expected and similar across drug groups?\nUnless otherwise specified, all data for these analyses were collected as of December, 1999.\nHeart Failure Diagnosis\nAt each follow-up clinic visit the occurrence of study clinical events was assessed, and, if identified by the clinical investigator, reported on an endpoint form. For each event involving hospitalization, a hospital discharge summary or expiration summary was to be submitted, and for each death a death certificate was required. Endpoint forms and supporting documentation were reviewed at the ALLHAT Clinical Trials Center (CTC) for accuracy and appropriateness. When a discrepancy or ambiguity was found, the CTC sent a written query to the Principal Investigator, who retained the final word concerning the diagnosis or cause of death. A random 10% sample of strokes, nonfatal MIs and CHD deaths was selected for blinded quality control evaluation by the ALLHAT Endpoints Subcommittee; for these cases additional documentation was requested.\nNo such routine Endpoints Subcommittee quality control was initially planned for reported HF. However, the Subcommittee was subsequently called upon to evaluate a random sample of reported fatal and hospitalized nonfatal HF events. As this occurred prior to the termination of the doxazosin arm, neither the chair nor the members of the Subcommittee was informed of the major reason for this review, namely, the trend toward a higher HF event rate in the doxazosin group compared to the chlorthalidone group. The Subcommittee was told that the review was undertaken at the request of the DSMB to address the reliability and validity of reported HF events. This evaluation consisted of fifty events, evenly distributed across the four treatment groups, reported as fatal or hospitalized nonfatal HF and with protocol-required documentation (discharge summary for hospitalized events, death certificates for deaths). Additional material was not requested, since this would have posed an undue burden on the clinical site staff and would have risked raising questions about emerging differences among treatment groups.\nThe ALLHAT definition of HF, used previously in the Systolic Hypertension in the Elderly Program (SHEP) [\n5\n], includes \"patients with clear-cut signs or symptoms of left or right ventricular dysfunction that cannot be attributed to other causes...\" The diagnosis of HF must include at least one of four stated symptoms [paroxysmal nocturnal dyspnea, dyspnea at rest, New York Heart Classification functional class III (for definition see Additional Information, Item 1), or orthopnea], and one of seven stated signs (rales, 2+ or greater ankle edema, tachycardia of 120 beats/minute or more after five minutes at rest, cardiomegaly by chest x-ray, chest x-ray characteristic of HF, S\n3 \ngallop, or jugular venous distention). Since lower extremity edema or exertional dyspnea may be due to non-cardiac causes, the presence of either of these alone, without other indications of heart failure, is not sufficient for a diagnosis of HF. Study guidelines caution against a hasty HF diagnosis in patients with severe pulmonary disease, including chronic obstructive pulmonary disease (COPD), pneumonia, or other severe, documented lung disease.\nBaseline Characteristics and Medical Management\nBaseline characteristics of chlorthalidone and doxazosin participants were compared. These analyses were stratified by HF outcome: 1) fatal and hospitalized HF; 2) treated, non-hospitalized HF; and, 3) no HF.\nPost-HF event medical management may provide additional evidence of the physicians' confidence in the HF diagnosis. The post-event use of open-label diuretics, ACE-inhibitors, and beta-blockers, i.e., accepted treatments for HF [\n6\n-\n9\n], was compared between doxazosin and chlorthalidone groups, as was the proportion in each group of those who remained on assigned blinded medication after the event. (For study guidelines regarding the use and reporting of open-label medicines of the same class as the blinded drugs, see Additional Information, Items 2 and 3.)\nEjection Fraction Review\nA CTC physician plus non-medical staff reviewed in a blinded fashion 361 hospitalized HF events (representing 278 participants) for ejection fraction data: looking for whether an ejection fraction was measured, the method utilized, and the measurement. Results, tabulated by randomization groups, reflected data that had been collected up to July, 1999, the time of the review.\nCase-Fatality Rates and Causes of Death\nAs a measure of the diagnostic validity and severity of HF and comparability between drug groups, time-from-event-to-death analyses of participants with hospitalized or treated HF were compared between the two groups. Causes of death of such participants were also compared in the doxazosin and chlorthalidone groups.\nStatistical Analyses\nData were analyzed according to participants' randomization assignments and HF outcome status, regardless of subsequent medication adherence. The Kaplan-Meier method was utilized in calculating cumulative event rates. Descriptive statistics by treatment groups were presented for baseline characteristics, HF ascertainment, ejection fractions and use of HF medications. Comparability of baseline characteristics of the treatment and HF outcome groups was ascertained by the χ\n2 \ntest for categorical variables and standard normal (z) test for continuous variables.\nResults\nHeart Failure Diagnostic Criteria\nThe blinded review by the Endpoints Subcommittee of 50 fatal or hospitalized HF events from the 4 drug groups determined 11 (22%) to have incomplete data for a definitive review. Of the remaining 39, 33 (85%) were confirmed to have HF by one or both reviewers. For both the chlorthalidone and doxazosin groups, the diagnosis of HF was confirmed in 90% (18/20).\nBaseline Characteristics\nBaseline characteristics for the doxazosin and chlorthalidone treatment groups, stratified for HF status, are described in Table \n1\n.\nTable 1\nBaseline Characteristics of Participants With and Without Heart Failure\nHospitalized and Fatal HF\nTreated, Nonhospitalized HF\nWithout HF*\nC\nD\nC\nD\nC\nD\nNo. of subjects\n327\n346\n93\n145\n14493\n8347\nAge, years, mean (SD)\n70.7 (8.3)\n71.0 (8.6)\n70.3 (8.2)\n69.9 (7.2)\n66.8 (7.6)\n66.6 (7.6)\nRace\n White, non-Hispanic, %\n61.2\n55.8\n63.4\n64.8\n47.3\n46.3\n Black, non-Hispanic, %\n30.6\n35.3\n32.3\n30.3\n32.0\n32.9\n Hispanic, %\n4.6\n5.5\n2.2\n2.8\n15.6\n16.1\n Other, %\n3.7\n3.1\n2.2\n2.1\n5.1\n4.8\nWomen, %\n42.8\n39.6\n33.3\n44.1\n47.0\n46.5\nEducation, years, mean (SD)\n10.5 (3.9)\n10.7 (3.4)\n11.3 (3.6)\n12.1 (3.2)\n11.0 (4.0)\n11.0 (4.0)\nCigarette smoking, current, %\n19.0\n19.4\n11.8\n17.9\n22.1\n21.9\nAntihypertensive treatment\n Treated > 2 months, %\n86.9\n86.8\n95.7\n95.2\n86.9\n86.7\n Treated < 2 months, %\n3.3\n3.3\n1.1\n0.0\n3.3\n3.3\n Untreated, %\n9.8\n10.0\n3.2\n4.8\n9.9\n10.0\nBlood pressure, mm Hg, mean (SD)\n147.8/81.1 (17.6/10.9)\n150.1/81.8 (16.5/11.0)\n147.1/82.2 (16.0/10.5)\n145.9/82.0 (15.8/10.6)\n146.2/84.1 (15.6/10.0)\n146.1/84.1 (15.7/10)\nPulse pressure, mm Hg, mean (SD)\n66.7 (16.5)\n68.3 (15.3)\n64.9 (13.0)\n63.9 (15.3)\n62.1 (14.1)\n62.1 (14.2)\nEligibility risk factors\n†\n LVH\n By electrocardiogram, %\n20.5\n22.3\n18.3\n21.4\n16.1\n16.1\n By echocardiogram, %\n6.3\n4.7\n4.4\n1.4\n4.6\n4.6\n Old MI or stroke, %\n36.1\n34.7\n41.9\n33.1\n23.1\n22.3\n CABG/Angioplasty, %\n22.6\n18.5\n25.8\n26.2\n12.9\n12.6\n ASCVD, %\n33.3\n29.2\n31.2\n31.0\n23.4\n24.6\n‡\n Type 2 diabetes, %\n46.8\n48.3\n43.0\n40.7\n35.9\n34.7\n HDL<35 mg/dl, %\n12.8\n13.6\n14.0\n13.8\n11.9\n11.7\n ST-T wave changes, %\n12.8\n10.6\n10.9\n12.9\n10.4\n10.2\nHF= Heart Failure C = Chlorthalidone treatment group D = Doxazosin treatment group mm Hg = millimeters mercury LVH = Left ventricular hypertrophy MI = Myocardial infarction CABG = Coronary artery bypass graft ASCVD = Atherosclerotic cardiovascular disease HDL = High-density lipoprotein *Only participants with at least one follow-up visit are included. 355 chlorthalidone and 229 doxazosin participants are excluded due to lack of at least one follow-up visit. \n†\nFor trial eligibility, participants had to have at least 1 other risk factor in addition to hypertension. The indicated risk factors are not mutually exclusive or exhaustive and do not represent prevalence. \n‡\nP \n= .0484\nBaseline characteristics of doxazosin and chlorthalidone participants with subsequent hospitalized or fatal HF were compared. Doxazosin participants with hospitalized or fatal HF had a higher baseline SBP than the chlorthalidone participants (150.1 vs. 147.8 mm Hg at the randomization visit). More doxazosin participants had LVH by ECG (22.3% vs. 20.5% of chlorthalidone participants); slightly more chlorthalidone than doxazosin participants had LVH by echocardiogram. Several eligibility risk factors, including previous MIs or strokes, coronary revascularization procedures, other atherosclerotic cardiovascular disease (ASCVD), and ST-T wave changes, were reported more often in chlorthalidone than in doxazosin participants, though the differences were not significant. Chlorthalidone and doxazosin participants with hospitalized or fatal HF had similar pre-trial antihypertensive treatment durations. None of these differences was significant at \nP \n< .05.\nParticipants with HF events displayed higher rates of most cardiovascular risk factors compared to those without HF events. Approximately 35–36% of chlorthalidone and doxazosin participants with fatal or hospitalized HF had reported prior MI or stroke as baseline eligibility risk factors, compared to 22–23% of those without HF (\nP \n< .001). Participants with hospitalized/fatal HF had significantly higher rates of pre-randomization coronary artery bypass grafts (CABGs) and coronary angioplasties (19–23% of those with HF vs. 13% of those without; \nP \n< .001) and other atherosclerotic cardiovascular disease (ASCVD) (29–33% of those with HF vs. 23–25% of those without; \nP \n< .001). Diabetes as a baseline risk factor occurred more frequently in those with HF: 47–48% in those with HF, 35–36% in those without (\nP \n< .001). Left ventricular hypertrophy (LVH) by ECG was a risk factor in 21–22% of those who later developed HF, compared with 16% of those in each group who did not develop HF (\nP \n< .001).\nBaseline pulse pressure (PP) showed some variation between participants who did and did not develop HF. For participants with subsequent hospitalization or death from HF, PP was 67 and 68 mm Hg for the chlorthalidone and doxazosin groups, respectively. Treated, non-hospitalized participants showed a lower mean baseline PP of 65 (chlorthalidone group) and 64 mm Hg (doxazosin group), and an even lower mean PP in those without HF (62 mm Hg in each group).\nMedical Management\nTable \n2\n presents post-event pharmacologic treatment of participants with HF and antihypertensive treatment of participants without HF. Following hospitalization for HF, 36% (83/232) of chlorthalidone participants and 45% (126/281) of doxazosin participants remained on their blinded medications. Percentages of participants on open-label diuretics and ACE-inhibitors were similar following the event: 58% (135/232) of chlorthalidone participants and 64% (180/281) of doxazosin participants were prescribed open-label diuretics; 39% (90/232) of chlorthalidone participants and 41% (114/281) of doxazosin participants were prescribed open-label ACE-inhibitors. Beta-blockers were prescribed for 14% of each group following the event, which was actually somewhat less than for participants who did not develop HF. Three-quarters of hospitalized HF participants in each group (169/232 in chlorthalidone group, 210/281 in doxazosin group) received at least one of the three medications (diuretic, ACE-inhibitor, or beta-blocker) post-hospitalization.\nTable 2\nPost-Event Pharmacologic Treatment of Participants With and Without Heart Failure\nHospitalized Heart Failure*\nTreated, Nonhospitalized Heart Failure*\nWithout Heart Failure\n†\nC\nD\nC\nD\nC\nD\nNo. of participants\n232\n281\n93\n145\n14493\n8347\nPost-event medication\n Blinded medication, (%)\n83 (35.8)\n126 (44.8)\n54 (58.1)\n93 (64.1)\n11247 (77.6)\n6096 (73.0)\n Open-label diuretic (%)\n135 (58.2)\n180 (64.0)\n57 (61.3)\n98 (67.6)\n1279 (8.8)\n1153 (13.8)\n Open-label ACE-inhibitor (%)\n90 (38.8)\n114 (40.5)\n31 (33.3)\n44 (30.3)\n1154 (8.0)\n826 (9.9)\n Open-label beta-blocker (%)\n33 (14.2)\n38 (13.5)\n18 (19.4)\n32 (22.1)\n3149 (21.7)\n2016 (24.0)\n Open-label diuretic, ACE-inhibitor or beta-blocker (%)\n169 (72.8)\n210 (74.8)\n72 (77.4)\n119 (82.1)\n4829 (33.3)\n3347 (40.1)\nC = Chlorthalidone treatment group D = Doxazosin treatment group ACE = Angiotensin converting enzyme *Represents data as of first clinic visit after event. \n† \nRepresents data as of most recent clinic visit. All participants represented have at least one follow-up visit. 355 chlorthalidone and 229 doxazosin participants are excluded due to lack of at least one follow-up visit.\nAmong participants treated but not hospitalized for HF, 58% (54/93) of the chlorthalidone group and 64% (93/145) of the doxazosin group remained on their blinded medication. Over 60% of participants in each group were prescribed open-label diuretics and over 30% received ACE-inhibitors. Open-label beta-blocker use post-event occurred in 19% (18/93) of the chlorthalidone group and 22% (32/145) of the doxazosin group, approximately the same frequency as in participants without HF. In both treatment groups, a diuretic, ACE-inhibitor or beta-blocker was prescribed for over 75% of these participants (72/93 in chlorthalidone group, 119/145 in doxazosin group).\nEjection Fraction Review\nTable \n3\n displays the ejection fraction data. About half (178/361) of reviewed discharge summaries mentioned ejection fractions measured during hospitalization, two-thirds (116/169) of which had quantitative measurements reported in the discharge summaries (data not given). Considering only the earliest ejection fraction information ascertained for each HF participant, 63% (29/46) of the chlorthalidone and 70% (41/59) of the doxazosin participants had ejection fractions at or below 40%. Just under half (27/59) of the ejection fractions reported in the doxazosin group were at or below 30%, compared with one third (15/46) in the chlorthalidone group. Two-thirds of ejection fractions were obtained by echocardiograms, though catheterizations accounted for a larger percentage of results in the doxazosin group than in the chlorthalidone group (36% vs. 24%).\nTable 3\nEjection Fraction Data for Participants Hospitalized with Heart Failure*\nChlorthalidone Treatment Group\nDoxazosin Treatment Group\nTotal\nParticipants with hospitalized heart failure\n245\n296\n541\nHospitalized heart failure participants reviewed\n134\n144\n278\nTotal reviewed heart failure participants with quantitative ejection fractions\n†\n46\n59\n105\n By cardiac catheterization (%)\n11 (23.9)\n21 (35.6)\n32 (30.5)\n By echocardiogram (%)\n33 (71.7)\n37 (62.7)\n70 (66.7)\n Method not given (%)\n2 (4.3)\n1 (1.7)\n3 (2.9)\nEjection fraction (%)\n‡\n1–30%\n15 (32.6)\n27 (45.8)\n42 (40.0)\n31–40%\n14 (30.4)\n14 (23.7)\n28 (26.7)\n41–50%\n9 (19.6)\n7 (11.9)\n16 (15.2)\n51–60%\n3 (6.5)\n10 (16.9)\n13 (12.4)\n>60%\n5 (10.9)\n1 (1.7)\n6 (5.7)\n*Evaluation of documentation for ejection fractions was completed in July, 1999, 6 months prior to the decision to discontinue the doxazosin arm of ALLHAT. Total numbers of events and participants with heart failure in Table \n3\n are based on data at the time of review. \n†\nEvent documentation which referred to ejection fraction measurements but which did not provide numeric values was excluded from this tally. \n‡\nEjection fraction for a participant is based upon the earliest post-randomization heart failure hospitalization with quantitative ejection fraction information provided.\nCauses of Death and 2-Year Case-Fatality\nCauses of death of participants with previous HF hospitalization were distributed similarly in the two groups, with slight variations. HF accounted for 21.2% (11/52) of the deaths among chlorthalidone participants and 17.1% (12/70) of the deaths among doxazosin participants. Over half of the deaths in each group (29/52 in the chlorthalidone group; 43/70 in the doxazosin group) were due to cardiovascular events. Fifteen percent (8/52) of deaths in the chlorthalidone group were attributed to cancer, compared to 9% (6/70) in the doxazosin group (Table \n4\n).\nTable 4\nCauses of Death of Participants with Prior Heart Failure Hospitalization\nChlorthalidone Treatment Group\nDoxazosin Treatment Group\nNo. of participants with hospitalization for heart failure prior to death*\n280\n317\n No. of deaths (%)\n52 (18.6)\n70 (22.1)\n Cause of death (%)\n Myocardial infarction\n7 (13.5)\n5 (7.1)\n Definite CHD\n5 (9.6)\n9 (12.9)\n Possible CHD\n1 (1.9)\n7 (10.0)\n Stroke\n1 (1.9)\n3 (4.3)\n Heart failure\n11 (21.2)\n12 (17.1)\n Other CVD\n4 (7.7)\n7 (10.0)\n \nTotal cardiovascular deaths (%)\n29 (55.8)\n43 (61.4)\n Cancer\n8 (15.4)\n6 (8.6)\n Kidney disease\n1 (1.9)\n1 (1.4)\n Accident/suicide/homicide\n0 (0)\n1 (1.4)\n Other non-CVD\n8 (15.4)\n11 (15.7)\n Unknown\n6 (11.5)\n8 (11.4)\nCHD = Coronary heart disease CVD = Cardiovascular disease *Excludes participants for whom death is the first reported heart failure event\nCase-fatality for participants with hospitalized HF events showed no significant differences (RR 0.96, 95% CI, 0.67–1.38, \nP \n= 0.83) between the two treatment groups (Figure \n1\n). Among participants in the doxazosin treatment group who had been previously hospitalized for HF, 22.1% (70/317) subsequently died, compared to 18.6% (52/280) of those in the chlorthalidone group (Table \n4\n). As previously reported, all-cause mortality did not significantly differ in the two treatment groups (RR 1.03, 95% CI 0.90–1.15, \nP \n= 0.56) [\n2\n].\nFigure 1\nKaplan-Meier estimates for cumulative mortality for hospitalized heart failure cases in the chlorthalidone and doxazosin groups (RR 0.96, 95% CI, 0.67–1.38; \nP \n= 0.84)\nDiscussion\nThe finding of significantly increased HF events in the doxazosin group compared with the chlorthalidone group created a dilemma for ALLHAT. Since the trial was not designed to focus on HF, a component of a secondary endpoint, the validity of reported HF events became an issue. In this paper, we have described several analyses to address this concern.\nAs previously reported, lost-to-follow-up and event documentation were similar in the two treatment groups [\n2\n]. Steps employed to validate the HF outcome in these treatment groups confirmed the consistency of HF event reporting. Participants in the two drug groups had similar baseline characteristics when stratified by HF status. The differences in eligibility risk factors between those participants with HF and those without is not surprising: larger percentages of those with HF had a history of MI, stroke, CABG, angioplasty, other atherosclerotic cardiovascular disease (ASCVD), diabetes, low HDL levels and ECG abnormalities. Nonetheless, these eligibility factors were not substantially different between chlorthalidone and doxazosin participants with HF.\nPost-diagnosis pharmacologic management of patients is one measure of the strength of physicians' confidence in the HF diagnoses. Open-label diuretics, ACE-inhibitors and beta-blockers, all recognized treatments for HF, were prescribed similarly for the chlorthalidone and doxazosin groups, suggesting similar assessment of these events in the two treatment groups.\nALLHAT criteria for HF were equivalently met in the two groups. While the sample (n = 50) of hospitalized or fatal HF reports reviewed by the ALLHAT Endpoints Subcommittee was limited in number and in adequacy of corroborating documentation, the review nonetheless showed adherence to study criteria for the majority (85%) of the event reports. The sometimes-discrepant results between reviewers pertained more often to incomplete data than to rejection of a HF diagnosis.\nClinical use of more objective measures, including noninvasive and/or invasive tools for the measurement of left ventricular function, offers a means of establishing and quantifying systolic failure in cases clinically suggestive of HF [\n7\n,\n10\n]. Among the ejection fractions reported in the ALLHAT events that were reviewed, the majority fell at or below 40%, indicating some degree of systolic dysfunction. However, HF is a clinical diagnosis that does not necessarily exclude those with intact left ventricular systolic function [\n11\n]. Hypertension is a major risk factor for diastolic HF; as many as 25% of asymptomatic hypertensives with left ventricular hypertrophy have diastolic dysfunction. Additionally, 90% of patients with coronary artery disease may have some degree of diastolic dysfunction [\n12\n].\nThe two-fold increased relative risk of HF in the doxazosin group compared to the chlorthalidone group changed little when confined to hospitalized and fatal events. Further, HF patients in both the doxazosin and chlorthalidone treatment groups showed a rather high 20% case-fatality rate over two years, as expected in HF patients [\n11\n,\n13\n,\n14\n], further supporting the validity of the diagnoses in the two groups. Among participants hospitalized for HF who subsequently died, over half of the deaths in each drug group were attributed to cardiovascular causes.\nTreatment group differences in mortality attributed to HF may take time to be recognized. Patients with HF are at risk for other competing causes of death. Accordingly, it may be too early to determine if a higher rate of HF in the doxazosin group translates into a higher overall mortality rate. A 20% 2-year case-fatality rate with a 4% difference in HF incidence rate translates into a 0.8% potential difference in total mortality without any competing causes of death. With competing causes, the difference would be smaller and difficult to detect even in a trial of ALLHAT's size.\nThe diagnosis of HF is generally made on the basis of signs and symptoms that may overlap with those of other cardiovascular and pulmonary pathologies. Moreover, the clinical picture may be further complicated for patients taking doxazosin, side effects of which (edema, dyspnea, and tachycardia) [\n15\n] may be misinterpreted as manifestations of HF.\nThe capture of events in a \"large and simple trial\" such as ALLHAT has potential limitations. Built into a structure composed largely of community-based physicians is the assumption that their characterization of clinical events reflects diagnostic standards of the medical community, and, as such, meets study criteria. However, with its large number of endpoints, resources available to ALLHAT precluded more than modest confirmatory event documentation. Resources were allocated for additional documentation for quality control validation only for a sample of the primary endpoint (MIs and fatal CHD) and for strokes. While all reported events are reviewed at the CTC, the sometimes incomplete supporting details in documentation may not allow for validation of all events according to ALLHAT criteria. Some discharge summaries and death certificates may lack sufficient descriptive information needed to confirm the clinical diagnoses. Clinic staff are unable to provide corroborating documentation for 2% of ALLHAT event reports.\nEfforts to authenticate the HF events in the doxazosin and chlorthalidone treatment groups represented a desirable step in the examination of the increased rate of HR in the doxazosin group. All methods employed provided confirmatory evidence that both the HF diagnosis and the difference in HF rates noted between the doxazosin and chlorthalidone groups were valid. Results of this exploratory investigation support the event ascertainment methods developed for ALLHAT, specifically for HF events. This validation exercise further illustrates the ability of large, simple trials to answer important public health questions requiring large sample sizes and to grapple with unexpected results in a responsible and meaningful manner.\nCompeting Interests\nThe authors of this paper disclose their affiliations with Aventis (A), Abbott (AB), AstraZeneca (AZ), Bayer (B), Biovail (BV), Bristol-Myers Squibb (BMS), Forest (F), Glaxo-SmithKline/SmithKline Beecham (GSK/SKB), King Pharmaceuticals/Monarch (KM), Merck (M), Novartis (N), Nu-Pharm (NP), Pharmacia/Upjohn (PHU), Pfizer, Inc. (P), Sankyo (SY), Searle (SE), Solvay (SV), Takeda (T). These relate to personal or institutional-affiliated receipt of income in the areas of research grants, consultant fees, or other compensation: BRD (AB,BMS,F,M,P,PHU,GSK/SKB), WCC (AZ,BMS,F,M,P,PHU,SY,SE,SV,T), JTW (A,B,BMS,F,KM, M,N,P), FHHL (AZ,B,BMS,M,NP,P,PHU), LJH (PHU); the other authors report no competing interests.\nAdditional Information\n1) New York Heart Classification functional class III: \"Patients with cardiac disease resulting in marked limitation of physical activity. They are comfortable at rest. Less than ordinary physical activity causes fatigue, palpitation, dyspnea, or anginal pain.\" 1994 Revisions to Classification of Functional Capacity and Objective Assessment of Patients with Diseases of the Heart: AHA Medical/Scientific Statement.\n2) The ALLHAT Manual of Operations provides for prescription of open-label medicines of the same class as the blinded medications, when a compelling indication exists, such that the total dose of the added open-label drug should not exceed 1/2 of the maximum dose as recommended in the Sixth Report of the Joint National Committee on Detection, Evaluation and Treatment of High Blood Pressure (JNC VI). If a compelling reason requires a higher dose, it is permitted.\n3) The ALLHAT follow-up form allows for reporting of open-label ACE-inhibitors and diuretics; among beta-blockers, only atenolol is reported. The use of other beta-blockers cannot be ascertained from the data.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
87
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nSummary of the American College for Advancement in Medicine November 2005 Conference on Scientific Integrative Medicine: Advancing Health Horizons\n\n**Article Abstract:**\n\n\n\n**Article Body:**\n\nThe American College for Advancement in Medicine's (ACAM) 64th International Educational Symposium on Complementary, Alternative and Integrative Medicine (CAIM) was held on November 9–13, 2005 at the Anaheim Hilton Hotel in Anaheim, California. ACAM's Fall 2005 conference, ‘Scientific Integrative Medicine: Advancing Health Horizons’, offered a total of 70.5 AMA CME credits and brought together an international cadre of approximately 600 physicians, scientists and medical students/residents (from nine countries) for a fascinating educational program on the scientific and clinical evidence supporting the practice of a wide range of CAIM therapies.\nConference keynote presentations addressed a diverse breadth of common medical conditions and provided scientific substantiation for many of the most effective treatments used by physicians who have successfully incorporated CAIM into their practice of medicine. Presenters highlighted strategies for successfully using CAIM to address conditions such as hypothyroidism, hypertension, endothelial dysfunction, degenerative disc disease, osteoporosis, infectious diseases (bacterial and viral) and the autistic spectrum disorders. Keynote lectures also focused upon the effects of nutrient–gene interactions and the vast spectrum of potential therapeutic interventions using nutrients to address and to compensate for common single nucleotide polymorphisms (SNPs). Presenters also emphasized the importance of epigenetic gene modification and they elucidated the mechanisms by which food, nutrients and environmental toxins, such as heavy metals, can modify gene expressions.\nIn a featured lunchtime awards ceremony, actress and author Suzanne Somers became the first recipient of ACAM's Legacy Award for her dedication to making the public more aware of the use of bio-identical hormones in the treatment of the peri- and post-menopausal symptoms. Her best selling book, \nThe Sexy Years\n, featured interviews with many forward-thinking clinicians and noted integrative physicians who have helped bring bio-identical hormone replacement therapy into the forefront of the American public. During her moving presentation, Ms Somers emphasized the importance of physicians educating their patients with regard to treatment options that use bio-identical hormone replacement therapy. She commended medical organizations such as ACAM for their open-minded approach and for the training they impart to thousands of physicians and medical students. Ms Somers also highlighted her own innovative approaches and experience in her battle against breast cancer. The awards ceremony received rave reviews and Ms Somers received a standing ovation after her presentation. Dr Allan Magaziner, ACAM's outgoing president, proudly presented Ms Somers with ACAM's first Citizen's Legacy Award. ACAM's Citizens Legacy Award was established to recognize the outstanding contributions of non-physicians toward bringing greater public awareness to CAIM practices and to advancing CAIM therapies.\nACAM's incoming president, Kenneth Bock, MD, observed that the fall conference provided ‘solid and scientifically based information supporting the field of integrative medicine and that the therapies, discussed by the presenters, were readily applicable to most physicians' practice of medicine’. Dr Bock assumed his leadership role as ACAM's president following the conference. During the conference, he emphasized ACAM's intention of ‘building bridges with other CAIM organizations, as well as with more academic and conventional medical organizations.’\nA complete list of the keynote conference presentations can be found following this article.\nACAM's Fall 2005 meeting also offered four in-depth 2-day pre-conference workshops along with a 1-day workshop on Scientific Writing. Two-day workshop themes included Prolotherapy, Hyperbaric Medicine, Nutrition and Metabolism, and Chelation and Heavy Metal Toxicity.\nACAM's Prolotherapy Workshop was Chaired by Jeffrey J. Patterson, DO, Professor of Family Medicine at the University of Wisconsin School of Medicine. He was assisted by Carl Osborn, DO and Jean Paul Ouellette, MD. Prolotherapy involves the injection of an irritant solution into the area where ligaments have either been weakened or damaged through injury or strain. The injection stimulates an inflammatory response that results in a tightening of aberrant ligamental laxity and produces biomechanical stabilization of the hyper-mobile region. The Prolotherapy Workshop consisted of lectures describing the general history of prolotherapy and the specific techniques employed in the practice of prolotherapy. Demonstrations of joint examinations and prolotherapy injections were accomplished with the use of patient models and video. This workshop allowed both the physician new to prolotherapy and the experienced prolotherapist to advance their skills and knowledge. Each of the two days of the workshop concluded with a panel discussion that reviewed case histories, prolotherapy ‘pearls’, and common complications encountered in the practice of prolotherapy. Dr Patterson commented, ‘It was exciting to work with ACAM on this workshop. We found the people in the organization to be stimulating and eager to explore prolotherapy as a treatment for chronic [musculoskeletal] pain.’\nDileep S. Sachan, DVM, PhD, Professor in the Department of Nutrition at the University of Tennessee and a board member for the American College of Nutrition, chaired ACAM's Nutrition and Metabolism Review Workshop. The workshop reviewed the fundamentals of physiology and biochemistry as applied to the metabolism of various macro- and micronutrients, including those involved with a number of inborn errors of metabolism. Aspects of drug metabolism, nutrient–drug interactions and food allergy were also discussed. The pathophysiologies of acute and chronic disease conditions were reviewed and nutritional interventions in these conditions were addressed. The workshop's teaching faculty reviewed some of the nutritional requirements inherent in conditions such as metabolic syndrome, lipid dystrophies and disorders of the gastrointestinal tract, and the hepatobiliary, renal and cardiovascular systems. They also reviewed nutritional requirements through the life cycle as well as nutritional status assessment and methods of feeding.\nACAM's Hyperbaric Oxygen Therapy (HBOT) Workshop was moderated by Joseph Rich, MD MPH, Director of the Center for Environmental and Integrative Medicine in Knoxville, Tennessee. HBOT is the periodic treatment of the entire body with 100% oxygen at greater than normal atmospheric pressures. The workshop convened a distinguished international group of physicians and scientists who addressed the medical uses of HBOT in a diverse range of disorders, including autism, cerebral palsy, stroke/brain injury, non-healing wounds, osteomyelitis and Lyme disease. Dr Rich commented, ‘Hyperbaric oxygen therapy is an underutilized safe and effective therapy that has a surprisingly broad spectrum of application for a wide number of medical disorders. I urge progressive minded physicians to become more familiar with HBOT and not to hesitate in employing it in many acute and chronic diseases.’ The HBOT Workshop allowed attendees to gain a broad understanding of the principles and practical applications of HBOT in medicine.\nEdwin Cooper, PhD, Distinguished Professor, Department of Neuroimmunology, at the David Geffen School of Medicine at University of California, Los Angeles, chaired ACAM's Writer's Workshop. The workshop helped participants interested in developing their scientific writing skills to develop a foundational perspective in the art and science of writing for the peer-reviewed scientific literature. Several participants brought their work for review and received constructive advice on optimizing their presentations for submission to medical journals.\nOverall, conference attendees were very impressed with the scientific and clinical evidence, which was presented in support of CAIM therapies. Dr Bock commented ‘as the incoming president of ACAM, it is a thrill for me to be a part of such a positive event, and I greatly look forward to our next meeting in Dallas, Infection and Chronic Illness: Integrative Approaches to Lyme Disease, Stealth Infections and Inflammation, which looks to be incredibly thought provoking and very practical for any practitioners involved in the treatment of chronic illness.\nAnyone who missed the opportunity to attend ACAM's scientific conference ‘Scientific Integrative Medicine: Advancing Health Horizons’ or the pre-conference workshops on ‘Scientific Writing’, ‘Prolotherapy’, ‘Hyperbaric Medicine’, ‘Nutrition and Metabolism’, and/or ‘Chelation and Heavy Metal Toxicity’ can order DVDs/CDs from \n or through telephone (800-532-3688 or 949-583-7666).\nThe American College for Advancement in Medicine (ACAM) is a not-for-profit professional medical organization for physicians interested in learning about evidence-based CAIM therapies. ACAM's goals are to improve skills, knowledge and diagnostic procedures as they relate to complementary and alternative medicine; to support research and to develop awareness of alternative methods of medical treatment. ACAM is dedicated to educating physicians and other health care professionals on the latest findings and emerging procedures in CAIM, botanical medicine, environmental medicine and in the use of effective evidence-based nutritional therapeutics. As the voice of CAIM, ACAM strives to increase awareness and recognition of complementary, alternative and integrative medical therapies, and play an active role in shaping the future of the CAIM movement.\nACAM represents nearly 1000 physicians in 30 countries and is the largest and oldest organization of its kind in the world dedicated to providing its members with educational excellence in integrative medicine. ACAM's leading edge educational programming facilitates the incorporation of clinically relevant biomedical therapies by fast-tracking scientific advancements in nutritional medicine, nutraceuticals and ethnopharmacology into the practice of cutting edge CAIM medicine.\nACAM was the first major medical organization to educate its members about such now well-accepted concepts as insulin resistance/metabolic syndrome, the detrimental effects of homocysteine, the protective effects of antioxidants, the clinical uses of essential fatty acids, cancer chemoprotection therapies with diet and herbs, testing for cardiosensitive C-reactive protein, the benefits of natural thyroid replacement and nutritional medicine as applied to psychiatry.\nACAM's next scientific conference ‘Infection and Chronic Illness: Integrative Approaches to Lyme Disease, Stealth Infections and Inflammation’ (approved for 17 AMA ACCME hours) will be held at the Intercontinental Hotel in Dallas Texas, from May 3–7, 2006. Pre-conference workshop topics include 2-day trainings (approved for 15 AMA ACCME's) in ‘Metal Toxicology’, ‘Oriental Medicine’ and ‘Hyperbaric Oxygen Therapy’. ACAM will introduce two exciting new 1-day workshops in Dallas, IV Therapies In Clinical Practice', and ‘Integrating CAIM into Clinical Practice’, which are both approved for 7.5 AMA ACCME credits.\nFor further information, please see \n or contact ACAM at +1-800-532-3688 (in the USA) or +1-949-583-7666 (outside the USA).\nSummary of Presentations\nDavid Brownstein, MD\nDr Brownstein is a Clinical Assistant Professor of Family Medicine at Wayne State University and author of seven books.\nThe Clinical Use of Iodine\nDr Brownstein reviewed the history of iodine including aspects about its discovery, the recommended daily allowances, and its widespread deficiency in the modern diet. He highlighted studies suggesting maternal imbalance of iodine may be related to impaired psychoneurological development in their children. He also noted that areas with the highest incidence of goiter have higher rates of sudden infant death syndrome. Dr Brownstein went on to discuss the physiology of iodine and conditions successfully treated with iodine therapy. He highlighted attention deficit disorder, fibrocystic breast disease, thyroid disorders, ovarian cysts, peyronie's disease, infections, keloids and others. Dr Brownstein emphasized that the breast is the second major storage compartment for iodine just behind the thyroid and that diseased breast tissue, such as that found in fibrocystic disease, will likely require more iodine because of greater tissue depletion.\nMark Houston MD\nDr Houston is a Clinical Professor of Medicine at Vanderbilt University School of Medicine and Chief of the Nutrition Division at Saint Thomas Medical Group, Saint Thomas Hospital in Nashville, Tennessee.\nThe Natural Treatment of Hypertension\nDr Houston reviewed the role of vascular biology in the pathogenesis of hypertension. He discussed the environmental and genetic interactions with micronutrients and their role in modulating vascular inflammation in a manner that may result in potentially less hypertension and end organ damage. Dr Houston reviewed the wealth of scientific evidence that confirms that oxidative stress, inflammation and immunologic dysfunction initiate and propagate hypertension and cardiovascular disease. He also summarized the mechanism of action for the role of numerous nutrients, including amino acids, minerals bioflavonoids and fatty acids, in reversing hypertension.\nKonrad Kail, ND\nDr Kail the co-founder of the Southwest College of Naturopathic Medicine and Health Sciences and a recent advisor to the National Center for Complementary and Alternative Medicine at the NIH.\nManaging Subclinical Hypothyroid\nDr Kail reviewed the risks associated with the syndrome of Subclinical Hypothyroidism introducing a new management paradigm that optimizes thyroid function based on resting Metabolic Rate and Brachioradialis Reflexometry. He reviewed factors affecting thyroid function including lead, mercury, PCBs, fungicides and medications and highlighted nutrients that help restore its function. Additionally, he made the case for potentially significant declines in health based on untreated subclinical hypothyroidism, including increased cardiovascular, neurological and endocrinological complications.\nThomas Levy, MD, JD\nDr Levy was formerly an Assistant Professor of Medicine at Tulane Medical School and is currently a Fellow of the American College of Cardiology, and the author of four books.\nVitamin C: Past, Present and Future Applications\nDr Levy reviewed the strong role of Vitamin C in the prevention of infection, treatment of scurvy and neutralization of toxins. He made the very important point that all infections and toxins will induce a localized and/or systemic Vitamin C deficiency, which in its extreme form, may induce injury to lipids. He reviewed the documented record of success of Vitamin C in treating encephalitis, mononucleosis, diphtheria, viral pneumonia, tetanus, mushroom poisoning, snakebites and even barbiturate overdose. He reviewed vitamin C's role in dental disease and the unparalleled track record of safety of this key nutrient.\nJoseph C. Maroon, MD\nDr Maroon, the Vice Chairman of the Department of Neurological Surgery at the University of Pittsburgh School of Medicine and the team neurosurgeon for the Pittsburgh Steelers.\nOmega 3 EFA for Spine Pain\nDr Maroon reviewed the role of Omega 3 essential fatty acids in the treatment of inflammation and highlighted the results of his study using Omega 3 fatty acids in the treatment of 250 non-surgical neck or back pain patients. At the end of the study, 60% of the participants stated their overall pain was improved and 60% stated specifically that their joint pain had improved. Overall, 80% stated they were satisfied with their improvement and 88% stated they would continue to take fish oils. Dr Maroon reviewed other botanical therapies for inflammation including Green Tea, Turmeric, White Willow Bark, Ginger and Boswellia. He also addressed the dosages of Omega 3 oils necessary to control pain and he contrasted the negligible side effects of Omega 3 oils with the well-documented adverse drug reactions from over the counter and prescription non-steroidal anti-inflammatory medications.\nAmy Yasko, ND, PhD\nAmy Yasko, ND, PhD, received her doctorate from Colgate University in Microbiology, Immunology and Infectious Disease and studied Naturopathy at Clayton College of Natural Health.\nNutrigenomics, Methylation and RNA-Based Nutrients\nDr Yasko discussed the laboratory studies that allow for testing for genetic susceptibility to disease and she extensively discussed the science of nutrigenomics. ‘Nutrigenomics’ is defined as the integration of concepts in molecular biology and genomics in order to study the ability of foods and nutritional supplements to interact with genes and to influence our health and lower the genetic risk component for multi-factorial disease. Dr Yasko described the methionine/folate pathway as a central pathway that is especially amenable to nutrigenomic screening. Defects in methylation can make one more susceptible to diabetes, cardiovascular disease, thyroid dysfunction, neurological inflammation, neurotransmitter imbalances, atherosclerosis, cancer and autism. Dr Yasko also described how defects in methylation can make one more susceptible to the toxic effects of heavy metals, especially arsenic and mercury. Dr Yasko described how heavy metals can decrease the brain neurotransmitters, such as serotonin and dopamine, if there are defects with BH4 and BH2 genes. By identifying the precise areas of genetic fragility, it is possible to target appropriate nutritional supplements. Dr Yasko discussed the potential uses of specific RNA-based supplementation.\nJohn Longhurst, MD, PhD\nJohn Longhurst, MD, PhD, earned both his Medical Degree and his PhD in Cardiovascular-Pulmonary Physiology from the University of California at Davis. He is now Associate Dean at UC Irvine and currently oversees the Susan Samueli Center for Complementary and Alternative Medicine.\nThe Role of Acupuncture in Modern Healthcare, Mechanistic Focus on the Cardiovascular System\nAcupuncture is a 3000-year-old treatment and is known to be useful in a number of chronic conditions such as pain, depression, recurrent nausea and vomiting among other conditions. Only recently has acupuncture been implicated in the treatment of cardiovascular diseases. Dr Longhurst described acupuncture's usefulness in the treatment of hypertension and chronic chest pain associated with myocardial ischemia. He presented his laboratory's research on the cardiovascular influence of electroacupuncture (EA). His laboratory has shown that EA at the Jianshi-Neiguan acupuncture points stimulates the underlying median nerve to provide sensory information through afferent nerve fibers to the central nervous system, particularly to specific nuclei in the hypothalamus and midbrain that are concerned with the regulation of the sympathetic nervous system. Dr Longhurst described how manual acupuncture and EA can also cause similar sympathetic response to the cardiovascular system and reduce blood pressure and ameliorate cardiac dysfunction in an experimental model of demand induced myocardial ischemia. It appears that one of the ways that acupuncture has clinically significant effects is through a number of opioid and opiod-like modulatory neuropeptides that reduce the activity of neurons in the brain.\nLeo Galland, MD\nLeo Galland, MD author of ‘Super Immunity for Kids’ and ‘Power Healing’.\nInteractions in Clinical Practice: Drug-Supplement, Drug-Nutrient\nDr Galland explained that over half of all prescription medication have the ability to deplete specific nutrients. Dietary supplements can interact with medication affecting absorption and toxicity of many drugs. Coenzyme Q10, folic acid, magnesium, zinc, vitamins B2 and B6 are the nutrients most commonly depleted. Mechanisms by which drugs influence nutrients include the impairing of absorption or bioactivation and through increasing excretion. Examples of clinically significant nutrient depletions include statin and Adriamycin depletion of Coenzyme Q10, Cisplatin depletion of magnesium, Thiazides and 5-ASA derivatives depletion of folate, and loop diuretics depletion of a wide range of nutrients, including potassium, magnesium, calcium, certain B-vitamins and Vitamin C. Dr Galland described some beneficial drug–nutrient interactions such as the protective effects on acetaminophen toxicity from the use of \nn\n-acetyl-cysteine, \nl\n-methionine, SAMe, milk thistle and schisandra. Protective supplements for aspirin and NSAID gastropathy (in human trials) include Vitamin C, SAMe, deglycyrrhizinated licorice and colostrum.\nStephen Sinatra, MD\nStephen Sinatra, MD is a Board Certified Cardiologist and fellow of the American College of Cardiology and the American College of Nutrition.\nMetabolic Cardiology: A New Paradigm for The Prevention and Treatment of Heart Disease\nDr Sinatra's presentation introduced the concept of ‘metabolic cardiology’ and highlighted the use of metabolic therapies in heart disease. Metabolic therapy involves the administration of a substance, that is normally found in the body, to enhance a metabolic reaction within the cell. Dr Sinatra extensively discussed the biology of Coenzyme Q 10, a lipid soluble antioxidant that plays vital roles in cellular ATP processes and thereby influences both systolic and diastolic function. Dr Sinatra suggested that mitochondrial dysfunction may result in symptoms of heart disease through some association with Coenzyme Q 10 levels. As studies indicate that women cannot make as much Coenzyme Q 10 as men and that women with mitral valve prolapse and hypertension have more diastolic dysfunction, since diastole requires more cellular energy than systole and is more dependent on ATP, Dr Sinatra hypothesized that women maybe more susceptible to diastolic dysfunction due to lower Coenzyme Q10 and resultant lower ATP. Dr Sinatra also discussed nutraceuticals that support cardiac metabolism, such as D-Ribose and \nl\n-Carnitine. D-Ribose is a naturally occurring pentose sugar that rebuilds the energy stores in the cell. In the myocardium, the rate-limiting step in the salvage and synthesis of ATP is the availability of D-Ribose. These three compounds, Coenzyme Q10, \nl\n-Carnitine and D- Ribose formed the triad of Sinatra's Metabolic Cardiology.\nRandolph M Howes, PhD, MD\nRandolph M Howes, PhD, MD completed residency in general surgery and plastic surgery while doing basic research in oxygen-free radicals at Johns Hopkins University. He invented the triple lumen catheter and, in 2004, published the first selective world review on oxygen metabolism in his book: UTOPIA (Unified Theory of Oxygen Participation in Aerobiosis).\nPro-oxidant Protection and Oxidative Self-Healing\nDr Howes discussed his research in free radical biology and stated that his belief the free radical theory is unfounded and that electronically modified oxygen derivatives (EMOD) are of low toxicity and are essential for energy production, pathogen protection, secondary messenger signaling and as tumoricidal agents. His unified theory states that EMOD deficiency levels allow for the manifestation of diseases, including neoplasia, and is integral in the aging phenomena. Dr Howes described how antioxidants become pro-oxidants. He summarized his presentation by discussing how antioxidants have failed to control aging and disease and he stated that the scientific literature is increasingly showing that antioxidants can harm biological systems.\nMichael Uzick, ND\nDr Uzick received his doctorate of Naturopathic Medicine from Bastyr University in Seattle Washington. He practices in Tucson Arizona and lectures on alternative therapies for cancer, hepatitis C and environmental toxicities.\nNatural Strontium: A Highly-Effective Treatment for Osteoporosis\nDr Uzick reviewed the fundamentals of osteoporosis and introduced evidence that strontium can be a safe and an effective adjunctive osteoporosis therapy. He pointed out that conventional drug therapies using bisphosphonates are associated with esophageal complications, inflammatory conditions and osteonecrosis of the jaw. Natural treatments that include calcium and other minerals, vitamin D and vitamin K are both safe and effective. Strontium is a non-toxic natural mineral that was first reported in 1959 by the Mayo Clinic to be useful for improving pain in severe osteoporosis. More recently, several studies have documented the benefits of strontium for both improving Dual Energy X-ray Absorptiometry (DEXA) scores and in dramatically reducing fracture rates. When supplementing with strontium and calculating bone mineral density (BMD), DEXA scores must be adjusted to produce a ‘strontium-adjusted BMD’ due to strontium's blockage of X-rays. At 2 g of strontium per day, studies have shown as much as a 49% decreases in fracture risk by one year, a 14% increase in lumbar BMD and 12% decrease in C-telopeptide. Bone biopsies from hundreds of animals and humans, who have consumed strontium, show normal mineralization and no cellular toxicity. Side effects were no greater than placebo in most studies.\nJack Challem\nJack Challem is author of \nFeed Your Genes Right, The Inflammation Syndrome,\n and \nSyndrome X\n. He writes and publishes \nThe Nutrition Reporter ™\n newsletter. He has also published original scientific articles in several journals, where he has focused on the role of free radicals and antioxidants in primate evolution.\nFeed Your Genes Right: A Conceptual Framework for Nutrient–Gene Interactions\nMr Challem described the biology of nutritional cofactors, which affect gene structure and function, as well as the role of genetic variations, which induce unique nutrient needs. Using vitamin B-1 as an example, he pointed out that deficiency in lab rats turns off 1000 genes and turns on 664 other genes. Similar effects are likely for most nutritional deficiencies. Mr Challem pointed out that the vast majority of people in our population have many nutrient deficiencies. Mr Challem made a case that the future of genetics research lies in the field of ‘Epigenetics’, which is the science devoted to the modifiers of gene function and expression, rather than just looking at effects of gene structure. He described how methylation often silences genes while acetylation usually expresses them. Mr Challem discussed how epigenetics can even be used to explain multi-generational observations, since the effects of nutrition and exercise have been observed to affect the health of future generations.\nLaura Power, PhD\nDr Power is a nutritional biochemist, with a Masters degree in Nutritional Sciences from the University of Maryland and a Doctorate in Holistic Clinical Nutrition from International University. Her area of expertise is in the fields of immunology, allergy and epidemiology.\nThe 5 Biotypes Diets\nDr Power presented her 20 years of unique research correlating blood types and ancestry to food allergies. Her research identifies five diets based on ABO blood types (A1, A2, B, O and AB), plus three subtypes based on being Rh-negative and one's gender. These blood types were correlated statistically to four kinds of food allergies—IgE, IgG, Lectins and T-cell mediated. She summarizes these results in her Diet Compass™, a diagram that denotes the evolutionary origin of the different dietary strategies.\nEfrain Olszewer, MD\nDr Olszewer is the Director and Professor of the Brazilian Foundation of Advanced Health Sciences, which teaches postgraduate courses in medicine. He is the author of 38 books and dozens of research articles.\nEDTA, Calcium, Sodium and Suppositories as a Therapeutic Approach for Chronic Degenerative Vascular Diseases\nDr Olszewer discussed the administration of EDTA for vascular disease and the effectiveness of different forms of EDTA and different routes of administration. He began by stating that, many years ago, his group in Brazil switched from the ‘standard bottle’ of using 3 g of EDTA to the ‘1/2-bottle’ of using 1.5 g of EDTA, because they found it just as effective in prior studies. He presented data from a study of 12 patients with stable angina where he compared the effectiveness of IV Mg-NaEDTA with rapid IV CaEDTA and NaEDTA rectal suppository. The IV treatments were administered once weekly and the suppositories were five days per week. The total weekly dose of EDTA was 1.5 g in each arm, administered over 90 min for the MgNaEDTA, administered over 15 minutes for the CaEDTA, and administered over a period of five days for each of the 300 mg EDTA suppositories. The study went for 12–15 months, and IV patients received a total of 25 infusions. The outcomes measured were chest pain on a stress test. Positive results were observed in 87% of the MgNaEDTA patients, 69% of the CaEDTA patients and 53% for those who used suppositories. After 20 weeks, non-responders were moved from the CAEDTA and suppository arms to the MgNaEDTA arm, where they also reached an 87.5% positive response rate.\nA second study looked at peripheral vascular disease in 24 patients, with positive improvements noted in 93% for the MgNaEDTA group, 33% for CaEDTA group and 17% for suppository group. Again, when non-responders were moved to the MgNaEDTA arm, they achieved a positive response rate of 83%.\nA third study looking a strokes at less than 6 months, with 14 patients showed a similar pattern in clinical improvement of 87.5% for MgNaEDTA, 66.6% for CaEDTA and 33.3% for suppositories. 12.\nThree patients were moved to the group receiving MgNaEDTA and all three improved. A fourth study, analyzing lead toxicity in the hair of 14 patients, showed positive responses in all patients in all three arms. There was a slight trend for patients in the CaEDTA arm to have rising creatinine levels, which decreased after changing them to the MgNaEDTA arm. Dr Olszewer's concluded that IV MgNaEDTA is the best approach for vascular disease, and the IV CaEDTA is not as effective, but it can be used for patients who will not sit still for the 90 min IVs. All three approaches are powerful tools for lead detoxification. The NaEDTA suppositories are effective only for lead intoxication, not for vascular disease.\nAlan Miller, ND\nDr Miller is a 1989 graduate of Bastyr University. He is the senior technical advisor for Thorne Research and is the senior editor of \nAlternative Medicine Review\n, the MEDLINE-indexed journal published by Thorne Research. He has authored over 20 scientific papers.\nl\n-Arginine and its Effects On Endothelial Function and Cardiovascular Health and Disease\nDr Miller reviewed endothelial function and pathophysiology and then discussed the roles of nitric oxide (NO) and \nl\n-arginine on blood vessel dilation. \nl\n-arginine is made primarily in the kidneys from \nl\n-ornithine and \nl\n-citrulline, with 3–5 g derived from dietary protein sources. Dr Miller noted that many studies have shown improved endothelial function after giving \nl\n-arginine. Nitric Oxide Synthase (NOS) activity is inhibited by ADMA (asymmetric dimethylarginine), which is increase in hyperlipidemia, hypertension, diabetes, CHF and renal failure. Supplemental \nl\n-arginine can reverse the detriments of ADMA by restoring endothelial NOS activity. \nl\n-arginine has been shown to improve the vascular dilation effect of statin drugs, improve exercise duration in CHF, reduce homocysteine, lower blood pressure and increase cardiac perfusion by 22%. Dr Miller noted that \nl\n-arginine works in complement with nutraceuticals such as B-vitamins, fish oil, red rice yeast extract and CoQ-10.\nThe authors wish to thank Michael Janson MD for his proofreading and editing of this article.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
88
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nLeft Septal Fascicular Block: Myth Or Reality?\n\n**Article Abstract:**\n\nAnatomic studies have shown that the left bundle branch divides into three fascicles in most humans. Changes in the 12 lead ECG (electrocardiogram) due to conduction abnormalities of the left anterior fascicle and left posterior fascicle are now part of the standard repertoire of electrocardiographic interpretation. There are no standard criteria for detecting conduction defects involving the third left fascicle, the septal or median fascicle, and the very existence of such defects is still a matter of controversy. The purposes of this article are to review the available evidence on this subject, suggest electrocardiographic criteria for its recognition, and present examples which illustrate that left septal fascicular block does indeed exist as a specific entity. Left septal fascicular block is a polymorphic conduction defect which may explain some previously inadequately understood electrocardiographic abnormalities.\n\n**Article Body:**\n\nIntroduction\nMore than thirty years ago Rosenbaum, Elizari, and Lazzari [\n1\n,\n2\n] presented their monograph defining left anterior and left posterior fascicular blocks, or what they termed \"the hemiblocks\". These divisional blocks involving part of the left bundle branch system have become well-recognized aspects of clinical electrocardiography [\n3\n-\n6\n] Anatomic studies, however, have suggested that the termination of the left bundle branch itself is more complex than just a bifurcation [\n7\n-\n14\n]. Studies of the conduction system going as far back Tawara's work in 1906 [\n7\n] have indicated that as the left bundle branch divides, it gives off fibers to the left endocardial surface of the interventricular septum, as well as to its better recognized anterior and posterior divisions [\n7\n-\n14\n]. In some cases these septal fibers are distributed broadly over the left septal surface like an interconnecting network [\n7\n,\n8\n,\n11\n]. But the elegant histologic reconstructions of the left conduction system by Demoulin and Kulbertus [\n12\n] in 1972 showed that, although there is considerable variability in its anatomy, in most cases the septal fibers can be identified as a distinct third division of the left bundle branch, as shown in \nFigure 1\n.\nIn 1970 Durrer and his coworkers [\n15\n] described the activation sequence of the ventricles using isolated, perfused human hearts. They found that earliest activation of the left ventricle occurred, 0 to 5 ms after the onset of the left ventricular cavity potential simultaneously in three endocardial regions: an anterior paraseptal area just below the mitral valve, a posterior paraseptal area about one third of the way from apex to base, and the central region of the left septal surface. Right ventricular activation began about 5 ms later near the insertion of its anterior papillary muscle. It was concluded from these studies that these three areas of simultaneous left ventricular activation corresponded roughly to the insertions of the three fascicles that were the terminations of the left bundle branch [\n12\n,\n15\n]. It was also pointed out that the activation waves resulting from the anterior and posterior areas of initial left ventricular activation progress in directions approximately opposite to each other, and hence the resulting potential fields they create tend to cancel each other [\n9\n,\n16\n]. This leaves activation of the interventricular septum starting from its left septal surface to dominate the QRS in its first 10 ms, despite a small, opposite, slightly delayed potential from activation of the right septal surface via the right bundle branch [\n3\n,\n15\n]. This produces initial QRS forces directed to the right and anteriorly, causing initial negative deflections in left-to-right oritented leads, q waves in leads I, V5-V6. These q waves have been termed \"septal q waves\" [\n17\n]. This model of ventricular activation incorporates a quadrafascicular picture of the ramifications of the His bundle: right bundle branch and three fascicles of the left bundle branch [\n15\n,\n18\n]. It is helpful to have this trifascicular pattern of the left bundle branch divisions in mind when trying to understand the changes that occur in direction of initial QRS forces with left anterior and left posterior fascicular blocks [\n2\n-\n5\n,\n9\n,\n16\n,\n19\n]. The term \"hemiblock\" is therefore no longer felt appropriate in describing these left intraventricular conduction abnormalities [\n12\n,\n20\n].\nThe QRS alterations in left anterior and left posterior fascicular blocks are well described not only in the monograph of Rosenbaum, Elizari, and Lazzari [\n2\n], but also in medical articles [\n19\n], and texts of electrocardiography and vectorcardiography [\n3\n-\n6\n,\n16\n]. There are reasons why such agreed upon criteria do not exist for block of the third division of the left bundle branch, left septal fascicular block (LSFB). The anatomy of this fascicle, where it exists as a distinct entity, varies more than that of the other two left fascicles [\n12\n]. These septal fibers usually have many interconnections [\n8\n,\n12\n]. This makes some persons less likely than others to suffer block of this division of the left bundle branch. Septal fibers of the left bundle branch may have the shortest refractory period of conduction fibers originating from this bundle branch [\n21\n,\n22\n]. Various criteria for LSFB have been proposed based on case reports, [\n11\n,\n23\n-\n29\n] on consequences of experimental incision of septal fibers in the dog, [\n30\n,\n31\n] on electrical-anatomical models, [\n9\n] and on computer-based projections of QRS morphology [\n32\n,\n33\n]. It may present with multiple morphologies, and is frequently combined with other conduction abnormalities which obscure its presence [\n9\n,\n23\n,\n34\n]. Popular textbooks of electrocardiography tend to ignore the possibility of its existence [\n5\n], to dismiss it as unproven [\n6\n], controversial [\n4\n], or to maintain it cannot be diagnosed [\n4\n,\n35\n]. When it is mentioned, the coverage is brief [\n3\n,\n6\n,\n36\n].\nOne major reason for the multiple morphologies with which LSFB may present is that septal activation is normally accomplished by a double envelopment starting from both left and right septal surfaces as contrasted to the single, endocardial to epicardial direction of activation of the free walls of the two ventricles [\n37\n-\n39\n]. Reference to a diagrammatic depiction of normal ventricular activation in \n2A\n illustrates this point. Activation of the right septal surface is initiated by septal branches of the right bundle branch, starting no more than 5 ms after first activation of the left septal surface [\n15\n,\n37\n]. The activation wave traverses the septum in either direction in about 40 ms, so that septal activation is nearly completed within 35 ms of the beginning of ventricular depolarization [\n15\n,\n37\n], except perhaps for parts of the basal septum, which has a relative dearth of Purkinje fibers leading into it [\n3\n,\n11\n,\n40\n]. By the time instantaneous QRS vectors are dominated by left ventricular free wall activation and have already rotated to the left at 40 ms, septal activation has been almost completed and will have little effect on the direction or magnitude of terminal QRS forces [\n37\n].\nThe amount of the septum normally activated via the right bundle branch varies between individuals [\n15\n]. Orientation of the septum also varies, facing to the right, anteriorly and inferiorly in horizontal hearts, and anteriorly, superiorly, and either to the left or right in vertical hearts [\n41\n]. As the direction of initial QRS forces is related to the orientation of the septum [\n42\n], the effect of LSFB on the ECG may vary with septal orientation.\nPossible Models of LSFB\nBased on this model of ventricular activation, \nFigure 2\n illustrates a range of possibilities with LSFB. In \nFigure 2A\n is represented the normal sequence of ventricular activation. In \nFigure 2B\n, the delay in left septal activation is only slight, such that the potentials arising from the activation wave proceeding from left-to-right are exactly balanced by those generated by the right-to-left activation wave. This would result in a leftward shift of initial QRS forces, with abolition septal q waves, but with little other change in QRS configuration or duration [\n9\n]. In \nFigure 2C\n the delay in left septal activation is greater, resulting in dominant right-to-left and front-to-back septal activation, yielding initial QRS forces directed to the left and posterior. If not counterbalanced by simultaneous anteriorly directed forces from right ventricular activation, this would result in q waves in right precordial leads, particularly V1 and V2, in addition to the absence of septal q waves from left oriented leads, and possibly to increase in magnitude of leftward and posteriorly oriented QRS forces (increased depth of S in right precordial leads) at 30 to 40 ms from the start of ventricular activation. In \nFigure 2D\n is depicted what might be expected when left septal activation is blocked in a situation where for some reason right-to-left septal activation is attenuated or delayed (e.g., with some degree of right bundle branch block). In this case septal activation is significantly delayed and has to be initiated from depolarization waves reaching it from left ventricular myocardium which has been previously activated by anterior and posterior fascicles of the left bundle branch. Initial QRS forces will likely be directed leftward, with disappearance of septal q waves. Left-to-right and posterior-to-anterior septal activation will occur later than left ventricular free wall activation, and will be relatively unopposed by any right-to-left septal activation. Depending on the degree of this delay, this may produce only a decrease in depth of right precordial S waves, or might actually result in an anterior shift in mid-to-late QRS forces with an increase in their anterior magnitude, somewhat analogous to the left-superior and right-inferior mid-to-late QRS shifts seen respectively with left anterior and left posterior fascicular blocks. Unfortunately, in some cases this would be masked by the coexisting right bundle branch block (RBBB). Such prominent anterior forces, otherwise unexplained by right ventricular hypertrophy or posterior infarction, have been claimed in anecdotal cases to be the result of just such a LSFB [\n11\n,\n12\n,\n23\n-\n27\n]. That some of these were shown to be associated with RBBB when the conduction defect worsened is consistent with this hypothetical model [\n25\n,\n26\n]. A transient anterior shift of QRS forces has been seen during myocardial ischemia produced by occlusion of the anterior descending artery during balloon angioplasty, possibly due to block of right septal activation [\n43\n]. Other studies have shown that otherwise unexplained prominent anterior forces can be a normal variant without unfavorable clinical implications [\n44\n].\nProposed Criteria for LSFB\nIn \nTable 1\n are listed proposed criteria for diagnosis of LSFB based on the above considerations. The major criterion is based on changes in the first part of the QRS: septal q waves are markedly diminished or lost by shift in initial QRS forces to the left, and in some cases also posteriorly due to loss or frank reversal of initial left-to-right septal activation [\n9\n,\n29\n,\n32\n,\n34\n,\n46\n]. This means loss of q waves from I, V5-6, and/or from inferior leads in cases with vertical heart orientation. Q waves may develop in V1-2 especially when anteriorly directed forces of right ventricular free wall activation fail to overbalance the posteriorly directed forces of \"right-to-left\" septal activation. With intact right bundle branch conduction, this may produce qrS complexes in V1-2, but QS complexes can occur, which mimic the chronic picture of anterior infarction. It must also be differentiated from complete or incomplete LBBB, ventricular pre-excitation, congenitally corrected transposition of the great vessels, effects of left or right ventricular hypertrophy, and orthotopic cardiac transplantation among other conditions. As right septal activation still starts via the right bundle branch no more than 5 ms after the start of left ventricular activation, a moderate delay in activation of its left septal surface would not be expected to increase the QRS duration importantly. Mean frontal plane QRS axis and ventricular activation times in aVL, aVF, and V5-6 should remain normal, as activation of the left ventricular free wall and apex via the left anterior and posterior fascicles is undisturbed. Absence of slurring or delay in R wave upstroke in leads overlying the left ventricle helps to differentiate this conduction defect from various degrees of incomplete LBBB [\n46\n]. Prominent anterior shift in mean QRS vector, manifested as prominent R waves with increased R:S ratio in V1-2, can occur when right septal activation is blocked or otherwise limited, resulting in relatively late, predominantly left-to-right and posterior-to-anterior septal activation. This is more likely to be seen when there is coexistent delay of conduction in the right bundle branch.\nIllustrative Examples Of Probable And Possible LSFB\nAbsent Septal Q Waves in Otherwise Normal ECGs: LSFB, Pure Septal Infarction, or a Normal Variant?\nAbsence of septal q waves in ECGs that are otherwise normal is the simplest way that LSFB might present. In prior work, comparison was made of 92 consecutive cases showing this pattern with age- and gender-matched \"controls\" with normal tracings including the presence of septal q waves [\n47\n]. No significant difference was found in incidence of overt cardiac disease. Moreover, this did not seem to be an acquired ECG pattern, as the age distribution in cases with normal ECGs except for absence of septal q waves was identical to that of a larger group with normal ECGs including presence of septal q waves. Thus the absence of septal q waves in ECG's that are otherwise completely normal in most instances probably represents a variant of normal found in about 7 percent of normal electrocardiograms. This is consistent with vectorcardiographic studies in normal populations [\n48\n-\n50\n]. However, the identical ECG pattern might result from myocardial infarction limited to the interventricular septum [\n51\n]. In this case, comparison with prior tracings and clinical correlation might be needed for certain differentiation.\nLSFB without Other Fascicular Conduction Defects\nHowever, such a pattern can result from an aberration in intraventricular conduction [\n52\n]. In \nFigure 3\n such an example is shown in a 20 year old woman suffering an adult respiratory distress syndrome following her second stem cell transplant for recurrent acute myelogenous leukemia. She had no signs or symptoms of cardiovascular disease. In this case premature atrial beats were conducted with slight aberrancy, the major result of which was disappearance of q wave from leads II, III, aVF, and V4-V6, leaving septal q waves absent. QRS duration and frontal plane mean QRS axis were unchanged. There was some increase in amplitude of anterior QRS forces at about 30 ms. The aberrant conduction was probably due to LSFB, with that fascicle in this case having the longest refractory period of the four fascicles. Aberrant beats remained otherwise within normal limits, without secondary ST or T changes. Twelve minutes after this ECG she developed atrial fibrillation with a ventricular rate of 195 per minute; at that time all beats showed the same aberrant conduction as was seen only on premature beats in the preceding ECG. If such an aberrant form of intraventricular conduction were to become permanent, without other abnormalities, and without prior tracings, there would be no way to separate the resulting ECG from a normal variant as described in the preceding paragraph, or from the result of a pure septal infarction [\n51\n-\n56\n].\nIn my experience, it was not hard to find examples of this type of transient LSFB [\n52\n]. It was seen most commonly in subjects with atrial fibrillation, particularly with rapid ventricular rates. Short R-R intervals would result in disappearance of septal q waves, as shown in the example of \nFigure 4\n. This was taken on a 69 year old woman who experienced paroxysmal atrial fibrillation without any prior cardiac history. Presence of prominent septal q waves in inferior leads and V5-V6 was seen in the second ECG taken 12 minutes later, after spontaneous conversion to sinus rhythm. An echocardiogram was normal except for presence of left atrial enlargement. Response of left ventricle to dobutamine stress was normal. Rate-related, transient loss of septal q waves in every beat was also encountered in some cases of supraventricular tachycardia or atrial flutter with 2:1 atrioventricular block [\n52\n]. \nFigure 5\n shows an ECG during supraventricular tachycardia in a 27 year old woman complaining of recurrent palpitations. In every other beat, septal q waves are absent along with slight increase in anteriorly directed forces. This is a rate-related 2:1 LSFB, a form of electrical alternans. Following conversion to sinus rhythm, all beats had septal q waves. She had no clinical or echocardiographic evidence of structural heart disease. Subsequent electrophysiological study showed this to be an atrioventricular nodal re-entrant tachycardia of the usual variety. Attacks were abolished with radiofrequency catheter AV nodal modification.\nIn other cases the change in initial QRS direction in aberrantly conducted beats can vary with degree of prematurity of the ectopic atrial beats. \nFigure 6\n is an electrocardiogram from an 75 year old man with severe disease of his peripheral, carotid and coronary arteries. His echocardiogram showed a left ventricle with inferior and posterobasal hypokinesis, and an ejection fraction of 45%. Some aberrantly conducted beats lacked septal q waves. In others septal q waves were markedly attenuated. With the most premature ectopic atrial beat which occurred while right precordial leads were being recorded, an initial q appeared in leads V1-V3, suggesting posterior shift of initial QRS forces, which was probably due to a greater degree of LSFB.\nThe example shown in \nFigure 7\n was from a 90 year old woman with a past history of hypertension, paroxysmal atrial fibrillation, and Parkinsonism,. Her echocardiogram showed left atrial enlargement, but left ventricular size and wall motion were normal despite the presence of electrocardiographic voltage criteria for left ventricular hypertrophy (LVH). Atrial premature beats cause two distinct forms of aberrant QRS complexes. The first type was not associated with discernable change in direction of initial QRS forces, but was associated with development of marked left and superior axis deviation and new broad terminal S in I and slurred terminal R in aVR consistent with left anterior fascicular block (LAFB) combined with RBBB. The second type, in which the ectopic atrial beat occurred slightly earlier, was associated with loss of septal q waves from aVL, V5 and V6, loss of r waves in V1-V3, but no major change in frontal plane mean QRS axis or QRS duration. There was increase in depth of S waves in V1-V4, and in height of R waves in V5 and V6. It would be natural to claim that the latter type of aberration in \nFigure 7\n was due to incomplete LBBB, but such is not likely in that the neither ventricular activation time nor total QRS duration was changed, nor was there slurring of R wave upstroke in V5 or V6 in aberrantly conducted beats. This is more likely another example of LSFB. The resulting QRS configuration mimics an anterior infarct, and augments the voltage signs of LVH. Diminution in amplitude or complete loss of septal q waves in the systolic overload pattern of LVH [\n57\n] has been ascribed to augmented left ventricular free wall forces that are not counterbalanced by left-to-right septal forces [\n58\n]. It is more likely that the loss of septal q waves in this situation is the result of a conduction defect, LSFB [\n5\n,\n29\n]. This type of aberrancy has been produced with programmed premature electrical stimulation of the right atrium in subjects with known LVH [\n29\n], and has been reported after spontaneous early premature atrial beats [\n28\n]. This manifestation of LSFB may be a major cause of QS complexes that can occur in V1-V2 in some cases of severe LVH [\n3\n,\n29\n,\n59\n,\n60\n]. It could also contribute to the low specificity of QS complexes in V1-V2 and of absent septal q waves for diagnosing septal or anterior infarction [\n51\n,\n59\n-\n63\n].\nThe series of ECGs shown in \nFigure 8\n probably also demonstrate this type of LSFB complicating aortic balloon valvuloplasty in a 17 year old boy with severe congenital aortic stenosis. Two preoperative tracings showed LVH with tiny q waves in leads I and V6, and initial r waves in V1-V2. Following the valvuloplasty procedure on 2/6/01, he lost his initial r waves in V1-V2, and q waves were no longer seen in I and V6 (although q waves persisted in inferior leads). QRS duration and ventricular activation time in V5 and V6 did not change. Postoperative troponin I levels peaked at 0.54 ng/ml (normal ≤ 0.1) with normal total creatine kinase (CK) and CK-MB values, so anterior or septal infarction was unlikely to have been the cause of the ECG change. No ST-T changes evolved. The fourth tracing in the series, taken 3 weeks later, showed return of initial r wave in aVL and V2, but QS remained in V1, and clear septal q waves had not returned to V6.\nCombination of Left Septal Fascicular Block with Other Left Fascicular Blocks\nThe presence of four fascicles (three left and one right) rather than the traditional three, adds complexity to the possible combinations of fascicular blocks [\n9\n] In \nTable 2\n are listed the resulting 15 possibilities for mono- and poly-fascicular blocks. This listing would be even more complex if fascicular blocks were further subdivided into incomplete and complete varieties.\nFigure 9\n shows three sequential ECGs taken on a patient during a bout of spontaneous angina. This 60 year old woman had mixed angina with a 50 percent diameter stenosis of her proximal anterior descending coronary artery, and an 80 percent ostial right coronary arterial stenosis. Her baseline ECG showed LAFB. On the day of the tracings in \nFigure 9\n an episode of spontaneous angina occurred in her cardiologist's office. The three ECGs shown were recorded with the patient supine on an examining table, without moving the electrodes between tracings. As her angina was waxing, her ECG showed LAFB without q waves in lead I, with QS deflections in V1-V2, and ST segment depression that was downslanting in I, nearly horizontal in V6, and upsloping in V4-V5. After recovery from the attack, shown in the third tracing, a q wave in lead I, and initial r waves in V1-V2 had reappeared, and ST depression had disappeared, leaving her ECG exactly as it had been on contemporary but prior tracings. In retrospect, the transient ECG changes had also been associated with decrease in S wave amplitude in V2-V3. The initial ECG of this series looks like LAFB complicated by anterior infarction with lateral subendocardial ischemia. But the transient nature of the QS in right precordial leads and loss of q in lead I could be due to transient LSFB, a conclusion suggested by others describing similar cases [\n64\n,\n65\n]. One could also argue convincingly in this setting that the QRS changes were due to left septal \"parietal\" block, given the presence of myocardial ischemia at the time [\n33\n], or to severe ischemia causing septal muscle to be transiently electrically inert [\n28\n,\n66\n-\n68\n]. If the changes seen were due to LSFB, this case would illustrate that superimposed on a chronic LAFB, a transient LSFB can be associated with a leftward and sometimes also posterior rotation of initial QRS forces, as would be predicted from the hypothetical model described above. This raises the possibility that a leftward orientation of initial QRS forces in LAFB, deemed inconsistent with a diagnosis of LAFB by Rosenbaum et al. [\n69\n], but seen in a large fraction of cases of this conduction abnormality [\n70\n-\n73\n], could in some cases be due to LAFB combined with involvement of left septal fibers, as suggested by others [\n32\n,\n71\n], particularly when q waves are present in right precordial leads. By reference to \nFigure 1\n, it is easily seen how a discrete lesion in the region of the left anterior fascicle could produce such a conduction defect, when the bulk of septal fibers of the left bundle branch originate as a branch of the left anterior fascicle.\nFigure 10\n illustrates a case with a chronic pattern consistent with LAFB combined with LSFB in an 83 year old man with severe aortic stenosis, concentric left ventricular hypertrophy, but normal coronary arteries and left ventricular wall motion. Initial QRS forces were directed to the left, inferiorly and possibly posteriorly. QS deflections in V1-V2 mimicked anterior infarction, although there was no clinical or echocardiographic evidence of prior myocardial infarction.\nI have yet to find examples that could convincingly be called left posterior fascicular block (LPFB) combined with LSFB, although such probably exist. Part of the problem is that septal q waves in left facing leads most commonly diminish or disappear when isolated LPFB develops, due to superior and usually leftward shift of initial QRS forces [\n2\n,\n9\n,\n16\n]. This means the addition of LSFB to existing LPFB might not cause any recognizable change in QRS configuration. One can speculate, however, that when LPFB is present, in the absence of intervening infarction, the diminution or disappearance of q waves from inferior leads and of r waves from right precordial leads might indicate the addition of LSFB.\nLSFB Combined with RBBB with or without Other Left Fascicular Blocks\nThe presence of RBBB is a special case in the detection of coexisting LSFB. RBBB alone may cause slight decrease in amplitude of initial r waves in V1-2, but does not change the direction of initial QRS forces [\n5\n,\n29\n,\n46\n,\n74\n-\n76\n]. Hence, septal q waves are preserved when RBBB occurs [\n46\n,\n74\n,\n76\n]. In the special case of RBBB combined with LSFB, both right ventricular and interventricular septal activation are dependent on delayed left-to-right and back-to-front septal activation via depolarization waves originating from myocardium activated originally through the left anterior and posterior fascicles. Assuming a block of the proximal right bundle branch, there will be no early right-to-left component to septal activation, which must thus occur asynchronously later than the start of depolarization of the free wall of the left ventricle, and is a necessary prelude to depolarization of the right ventricular free wall. Direction of initial QRS forces will depend on the orientation of net potentials generated by the start of left ventricular activation via the left anterior and left posterior fascicles. This might well vary from person to person, but will not be modified by early forces from right ventricular free wall activation. It probably would be directed to the left [\n9\n], but conceivably could point either anteriorly or posteriorly, superiorly or inferiorly. Thus septal q waves would likely be absent from left facing leads, which is not an expected effect of uncomplicated RBBB [\n46\n,\n74\n-\n76\n]. But the presence or absence of initial r waves in right precordial leads would be hard to predict. Their absence when RBBB exists would add weight to a presumptive diagnosis of coexistent LSFB, but their presence would not necessarily rule it out.\nThe direction of forces in the middle of the QRS in this setting would be deviated anteriorly by delayed and relatively unopposed left-to-right and back-to-front activation of the interventricular septum. But this would be hard to separate from the anterior and rightward terminal QRS forces due to delayed activation of the right ventricular free wall. Hence, RBBB combined with LSFB might look just like RBBB except for atypical alterations in the direction of initial QRS forces.\nFigure 11\n shows ECGs from a 96 year old woman with asthma, hypertrophic cardiomyopathy, and moderate aortic stenosis. Diastolic thicknesses of interventricular septum and posterior left ventricular free wall in 1999 were 13 mm and 12 mm respectively. Systolic anterior motion of the mitral valve was seen intermittently and was associated with a moderate systolic pressure gradient in the aortic outflow tract. Left ventricular wall motion and ejection fraction were normal. She never had hypertension or a clinical myocardial infarction. The two tracings shown are examples of the numerous ECGs she had at two periods of her life. The first one dated in 1995 is typical of her ECGs prior to 1998. It showed high voltage of left ventricular hypertrophy and a typical RBBB. Initial QRS forces were directed to the right, anteriorly and slightly superiorly, resulting in clear septal q waves in left facing leads, and initial r waves in V1 and V2. All ECGs after 1998 were like the second one shown in figure 11 dated in 1999. Initial QRS forces were directed to the left, probably slightly posteriorly, but still slightly superiorly. Septal q waves had disappeared from left facing leads, and in right precordial leads initial r waves had been replaced by q waves. S waves in the mid-precordial leads were deeper. There were no significant changes in her echocardiograms between these two tracings. The change in direction of initial QRS forces responsible for these ECG changes is almost certainly due to the superimposition of LSFB on the RBBB [\n9\n].\nIn \nFigure 12\n is shown the ECG from a 67 year old woman with a history of hypertension and chronic chest pain. Exercise myocardial perfusion scan was normal, with normal left ventricular wall motion and ejection fraction of 68 percent. Premature atrial beats were conducted with a consistent aberrancy showing shift in initial QRS forces to the left and inferiorly; tiny q waves replaced initial r waves in leads V2 and V3. In these beats there was also left and superior deviation of the middle portion of the QRS, and rightward and anterior deviation of slowly inscribed terminal forces. The aberrant beats were consistent with LAFB combined with RBBB. However the leftward shift of initial forces and resulting loss of q wave in lead I was slightly atypical for LAFB, raising the possibility that it was combined with some degree of LSFB. Development of tiny initial q waves in V2 and V3 can result from uncomplicated LAFB, supposedly due to markedly inferior orientation of initial forces in the face of a heart that lies low in the chest relative to right precordial electrode placement [\n5\n]. Such right precordial q waves are reportedly rarely seen in LAFB in young persons [\n4\n], increasing the likelihood that, when present in the face of initial QRS forces pointing leftward, they could result from a posterior direction of initial forces [\n4\n,\n77\n], related to coexistent LSFB.\nConclusions\nThat the examples illustrated above represent LSFB is predicated on the accuracy of the hypothetical models of altered ventricular activation shown in \nFigure 2B\n-\n2D\n, on which \nTable 1\n is based. Proof that this condition is met will require additional investigation, including correlation of surface ECG patterns with electrophysiological studies of interventricular septal activation in intact humans.\nIntraventricular conduction abnormalities consistent with LSFB exist and seem to be more common than has been previously recognized. As mid-late QRS forces may be minimally affected by LSFB, its diagnosis requires particular attention to changes in the direction of the initial forces of ventricular activation. Mild degrees of LSFB can mimic a normal variation [\n52\n]. Thus, comparison of ECGs taken before and after its development are usually needed for diagnosis. When the only clue to infarction limited to the interventricular septum is disappearance of septal q waves [\n9\n], it would be difficult to determine whether their loss was due to the infarction itself or to LSFB caused by the infarction.\nThe various electrocardiographic presentations of LSFB can tie together an assortment of otherwise inadequately explained phenomena: 1) the loss of septal q waves by leftward shift of initial QRS forces, transiently following short R-R intervals in some cases, permanently in others; 2) loss of initial r waves in right precordial leads accompanied by loss of septal q waves (which implies posterior as well as leftward orientation of initial QRS forces), either transiently or permanently as can occur with severe LVH in the absence of incomplete or compete LBBB [\n59\n,\n60\n], and in some cases of LAFB or RBBB; 3) some cases of transient right precordial Q waves during myocardial ischemia in the absence of infarction; 4) chronic QS deflections in right precordial leads in the absence of LBBB or infarction in that area; 5) atypical cases of incomplete LBBB in which left ventricular activation time remains normal and the sense of initial septal activation may not be strictly right-to-left [\n38\n,\n78\n].\nThis study has not addressed many important questions about the potential clinical significance of LSFB. Does the alteration of activation pattern of the interventricular septum in LSFB produce recognizable changes in its pattern of contraction? A study of this might require an analysis of septal motion more sophisticated than is currently employed in clinical echocardiography or other imaging methods [\n79\n-\n82\n]. Are there prognostic implications to the presence of LSFB? If permanent, it certainly implies the presence of disease involving at least a portion of the left bundle branch system. However, It remains for further study to show whether it is a harbinger of more advanced disease of the conduction system or myocardium, whether there are histopathologic correlations to its presence, and whether it carries prognostic significance similar to that of LAFB or LPFB [\n3\n,\n5\n].\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
89
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nUse of conventional and alternative treatment strategies for a case of low back pain in a F/A-18 aviator\n\n**Article Abstract:**\n\nBackground\nLow back pain can diminish jet pilot concentration and function during flight and be severe enough to ground pilots or cause decreased flying time. The objective of this case report is to present an example of the integration of chiropractic care with conventional treatments for the management of low back pain in a F/A-18 aviator.\nCase presentation\nThe patient had insidious severe low back pain without radiation or neurological deficit, resulting in 24 hours of hospitalization. Spinal degeneration was discovered upon imaging. Four months later, it still took up to 10 minutes for him to get out of bed and several minutes to exit the jet due to stiffness and pain. He had discontinued his regular Marine Corps fitness training due to pain avoidance. Pain severity ranged from 1.5–7.1 cm on a visual analog scale. His Roland Morris Disability Questionnaire score was 5 out of 24. The pilot's pain was managed with the coordinated efforts of the flight surgeon, physiatrist, physical therapist, and doctor of chiropractic. Following this regimen he had no pain and no functional disability; he was able to fly multiple training missions per week and exercise to Marine Corps standards.\nConclusion\nA course of care integrating flight medicine, chiropractic, physical therapy, and physiatry appeared to alleviate pain and restore function to this F/A-18 aviator with low back pain.\n\n**Article Body:**\n\nBackground\nLow back pain (LBP) is a common problem associated with significant losses in work time in the general population [\n1\n]. While LBP has been studied extensively in the literature for many populations, few clinical studies discuss LBP in fighter jet aviators. Neck pain in fighter pilots receives much attention, yet spinal disorders leading to back pain are reported to be 2 times more common in fighter aviators than other pilots [\n2\n]. One survey reports that fighter pilots have a significantly greater prevalence of chronic LBP, pain requiring bed rest and pain radiating into the leg compared to fixed wing transport and helicopter pilots [\n3\n]. Spinal pain can be serious for high performance aviators and severe enough to ground pilots or cause decreased flying time (17% for fighter pilots) [\n4\n]. Spinal disorders and LBP are reported to be exacerbated by flight, result in disability [\n5\n] and in non-waiver of flight disqualification in approximately 25% of US Navy and US Marine Corps (USMC) aviators applying for it [\n6\n]. Back pain diminishes pilot concentration and function during flight [\n2\n]. Drew [\n4\n] reports that spinal pain significantly limits flying performance for 20% of the fighter pilots he studied.\nInvestigators are curious about aviators' use of alternative treatments to medicine to manage LBP, however little research is reported in this area. Three studies mention alternative management strategies and chiropractic care is mentioned briefly in 2 of these. Simon-Arndt et al [\n2\n] state that there is anecdotal evidence that pilots visit doctors of chiropractic. Drew [\n4\n] specifically queried aviators on their use of chiropractic care and found that doctors of chiropractic were in fact used by some pilots for spinal pain management. Although chiropractic services have been integrated into several US military treatment facilities since 1995 [\n7\n], the role of chiropractic care and how it is integrated with other health care services for military aviators is unreported. This case describes an example of such integration provided at a military treatment facility to manage LBP in a fighter pilot.\nCase presentation\nA 36-year-old male USMC F/A-18 aviator instructor with 15 years of flying experience had a severe episode of acute LBP without radiation or neurological deficit. The patient did not recall any specific traumatic incident that initiated the pain, but he did have a history of multiple LBP events, some of which included radiation into the legs. When the LBP began he immediately consulted the squadron flight surgeon and was prescribed naprosyn, diazepam and hydrocodone/acetaminofen for pain control, confined to quarters to rest and imaging was obtained. The pain worsened, resulting in hospitalization later that day. He was observed for 24 hours and given a methylprednisone dosepack. Upon discharge from the hospital, he was confined to quarters for 72 hours and not allowed to return to flying until cleared by the flight surgeon. The flight surgeon cleared the patient to fly and ordered consults to neurosurgery and physical therapy for further evaluation and treatment.\nPlain film radiographs showed mild narrowing of the L4–L5 intervertebral disc space and mild sclerotic changes of the posterior elements of L5. MRI demonstrated a loss of normal height and signal involving the L4–L5 disc and a broad-based left paracentral disc bulge contacting the thecal sac and causing mild narrowing of the central spinal canal at the L4–L5 level with mild to moderate left neural foraminal narrowing and L5 nerve root contact (Fig \n1\n). A lesser degree of L5-S1 disc degeneration was present with a broad-based disc bulge causing no central canal or neural foraminal narrowing.\nFigure 1\nT2 weighted sagittal MRI demonstrating a loss of normal height and signal involving the L4–L5 disc and a broad-based paracentral disc bulge that contacted the thecal sac (arrow). L5-S1 disc degeneration was also present.\nThe flight surgeon coordinated the ordering and follow up of the patient's various clinical consults. The flight surgeon instructed the patient to take the anti-inflammatory medication as needed and gradually returned him to non-impact exercise, including walking and working out on an elliptical machine to pain tolerance.\nFollowing neurosurgical evaluation the patient was provided concurrent consultations with the hospital physiatrist and physical therapist. The physiatrist provided osteopathic manipulation and home exercises, including prolonged prone lumbar extension and hip adductor stretching, which provided some pain diminishment. Acupuncture was attempted once, wherein he reported an increased sensation of lumbar muscle spasm. Acupuncture was discontinued.\nThe physical therapy regimen was begun 2 weeks after hospitalization and included McKenzie exercises (standing and prone repetitive standing lumbar extension), stretching (hamstrings, single knee-to-chest, quadriceps, gluteals, hip flexors) and an educational self-treatment booklet. The patient experienced some relief with the McKenzie exercises, hamstring stretching and self mobilization/stretching of the gluteal muscles and spine by drawing his leg over to the opposite side of his trunk. His pain and range of motion improved approximately 50%. A course of moist heat packs and mechanical lumbar traction (15 min, supine position with hips and knees flexed 90 degrees, intermittent pull for 15 s, starting at 10 lbs greater than 50% body weight and increasing 10 lbs each treatment) was attempted to further his progress. He continued doing the prescribed exercises and noted some improvement but pain elimination was refractory. At this time, the physical therapist discussed the case with the chiropractor, who is located in the same clinic at the air station, and subsequently ordered a consultation for chiropractic.\nDuring the chiropractic consultation, the patient's pain was located in the lumbar region bilaterally, described as \"intense spasm\", and without any radiation or symptoms of neurological involvement. His pain was consistently worse in the morning; he reported that it would take up to 10 minutes for him to get out of bed due to stiffness and pain. He was concerned because this episode of LBP was of longer duration (4 months) than any prior episodes. He had discontinued his regular Marine Corps fitness training (running, sit-ups, pull-ups) because of pain exacerbation. He experienced increased pain after basic fighter maneuver flights, reporting that it would take as long as 15 minutes to get out of the jet and climb to the ground after flying. He stated that even though he was on flying status he would sometimes ask to be removed from the flight schedule because his back hurt too much to fly; on these days he would stay at work and perform other tasks. He rated the severity of pain at 1.5 cm on a 10 cm visual analog scale [\n8\n], 7.1 cm upon waking and (in retrospect) 9.5 cm on the visual analog scale as the pain experienced during hospitalization. His modified Roland Morris Disability Questionnaire [\n9\n] score was 5 out of 24 functional disability indicators. Lumbar spine active ranges of motion were full with pain at the end range of flexion and extension and when returning to a neutral posture from these end ranges. Hamstring length was approximately 60 degrees bilaterally and the gluteus medius had approximately 50% of its normal passive length. Trigger points were palpated in the right gluteus medius and bilateral lumbar paravertebral and quadratus lumborum muscles. There were no indicators of lumbosacral nerve root or cord compression (ie, negative Valsalva, Kemp's test, straight leg raise). Lower extremity sensation, motor and deep tendon reflex testing were normal. Given his age, nature of the clinical findings, and the imaging results, it was assumed that he was experiencing phase II spinal degeneration (clinical instability) as described by Kirkaldy-Willis [\n10\n].\nThe chiropractor and flight surgeon discussed the case to insure that the flight surgeon was informed of the course of care. The chiropractor and the physical therapist discussed the case to insure that the care that the patient was receiving was complimentary and that any duplicate home exercises were planned redundancy. Thus, at this point in time, the patient was receiving care from the flight surgeon, physical therapist, and chiropractor and had 1 follow up visit scheduled with the physiatrist.\nThe 3 goals of chiropractic care were: 1) pain control; 2) ability to continue flight duties and USMC fitness training; 3) maintenance of aerobic fitness. Table \n1\n summarizes the chiropractic treatment interventions and outcome measures at periodic reassessments. Details regarding treatment are presented below. Directions of force for chiropractic manipulation were selected by identifying areas of tenderness, asymmetry, restricted planes of active and passive range of motion, motion palpation, tight musculature and other indicators as described by Bergman and colleagues [\n11\n]. Chiropractic manipulation of the thoracolumbar junction, L5-S1 level and the sacroiliac joint typically involved a side-posture high-velocity, low-amplitude short lever maneuver [\n11\n]. Grade IV mobilization [\n11\n] was used on several occasions when joint endfeel was not extremely stiff or if the patient was unable to tolerate a high velocity force. Active myofascial release treatment and ischemic compression as described by Barnes and Leahy were used to treat tight muscles and trigger points [\n12\n,\n13\n]. These muscles and surrounding joints were also stretched using the proprioceptive neurological facilitation maneuvers of post-contraction stretch and post-isometric relaxation [\n14\n]. The patient was instructed to self-administer trigger point ischemic compression to the gluteus medius by lying in the lateral recumbent position on top of a tennis ball and to stretch the muscle immediately afterward. He was instructed to continue the helpful stretches provided by the physiatrist and physical therapist, to stretch his low back before flying and to see his flight surgeon if his pain worsened.\nTable 1\nOutcome measures and treatment strategies during chiropractic care.\nTx#/Wk#\nFunctional Outcomes\nPain Control\nFlight/USMC Fitness Training\n1/1\n• VAS = 1.5 current, 7.1 upon waking, 9.5 worst •Medication needed for pain control\n• RMDQ = 5/24\n• Significant pain with flight\n• Unable to run/do sit-ups\n• HVLAM [11] (T11-L2 & SI joint)\n• AMRT [12,13] & PIR or PCS [14] of (g. medius, g. max, QL and PVTs)\n• Home TrP Tx (g. medius)\n• Moist heat pack\n• See flight surgeon if pain increased\n• G. medius stretch (2 @ 30 sec)\n• Double knee-chest stretches (10 reps @ 10 sec each)\n• Continue stretches recommended by PT and DO\n• Walking, elliptical and bicycle to tolerance\n5/5\n• No sharp pain\n• No medication needed to control pain\n• Mild ache after flying high G several times per week\n• Minimal pain with activities of daily living\nSame as above\nAs above +\n• Supine leg raises (Dead Bugs 50 reps)\n• Static crunch to tolerance (90 sec)\n• Prone isometric core endurance (plank) for 90 sec\n11/15\n• Verbal pain scale = 0\n• Mild tightness associated with prolonged sitting\n• Full activities\n• Able to perform plank exercise > 2 minutes\n• No pain with running\nPeriodic HVLAM, PCS and AMRT as necessary\nAs above +\n• Oblique crunches (50/side)\n• Isometric side bridge (60 sec)\n• Static lunge psoas stretch\n• Oblique crunches on gym ball\n• Latissimus pull downs\n• Seated rows\n• Gradual return to running\n16/30\n• VAS = 0\n• RMDQ = 0/24\n• Able to perform plank exercise > 120 sec, side-bridges > 60 sec, 100 crunches in < 120 sec, 50 oblique crunches per side\n• Able to fly multiple times/wk including long and high G flight with only mild tightness afterward\n• Passed required physical fitness test with no pain\nNo treatment required\n• Maintain core stability and coordination exercises as part of routine exercise\n• 3 mi run 3x/wk, elliptical or stationary bike on other days\nTx = treatment; Wk = week; VAS = visual analog scale; RMDQ = Roland Morris disability questionnaire; HVLAM = high velocity low amplitude manipulation; T = thoracic; L = lumbar; AMRT = active myofascial release technique; PIR = post-isometric relaxation; PCS = post-contraction stretch; QL = quadratus lumborum; PVT = paravertebral muscles; TrP Tx = trigger point therapy\nBy the 5\nth \nchiropractic treatment the patient reported there were no episodes of sharp \"muscle spasm\" pain in the previous week but periodic stiffness was experienced upon waking in the morning or after long periods of time in the jet. He was on regular flying status and he had discontinued taking any medication. The patient reported that the physiatrist had provided him with a home TENS unit for pain control, which provided relief at the end of long days in the jet or after prolonged sitting. At this point in time he was released from care by both the physiatrist and physical therapist and instructed to continue his home exercises and to return for care if symptoms worsened. Functional spinal stability was assessed by the chiropractor at the fifth office visit and the patient exhibited difficulty stabilizing his spine when asked to perform simple non-weight bearing movements called dead bug exercises [\n15\n]. He had no pain while performing a static crunch core endurance exercise. Treatment was modified to include core stabilizing exercises (Table \n1\n).\nSubsequent chiropractic office visits focused on furthering the patient's torso function and insuring coordinated care between the flight surgeon and the chiropractor. These office visits were supplemented with some form of manipulation/mobilization as deemed necessary. Therapeutic exercises were made more difficult and targeted strength, endurance and proprioception of the lumbar extensors, oblique abdominal muscles and other torso stabilizers [\n15\n]. Tight psoas muscles were also addressed with home-based stretching (Table \n1\n). Summarily, the patient had 15 chiropractic office visits where he received care over a 26 week period. Office visits progressed from passive pain control techniques to active functional rehabilitation procedures and included the following treatments (frequency): high-velocity, low-amplitude manipulation (10); grade IV mobilization (8); proprioceptive neurological facilitation (6); myofascial release/ischemic compression (14); therapeutic exercise (7); moist heat pack application (2).\nAt a follow-up visit 1 month after his last treatment he was pain free and had full function. He was flying multiple training missions per week including high G flights and sorties of several hours in duration and had passed his required physical fitness test (100 sit-ups in 2 minutes, 3 mile run in less than 29 minutes and a minimum of 3 pull-ups) the week prior with no pain. He felt that the only provocative factor for minimal LBP at that time was flying the jet. The physical examination was normal; he was released from care and encouraged to maintain his core stabilization and overall fitness program.\nDiscussion\nThe physical demands of the F/A-18 aviator are extreme. In addition to the physical requirements necessary to pilot the jet, US Marines must also maintain a high degree of physical fitness that is tested twice a year in a physical fitness test. Therefore, the management plan for this patient was directed at restoring his work capacity both in the jet and on the ground without having him restricted from flight by a light or limited duty status. Strategies to develop fitness of the lumbar region of aviators have been suggested, including postural, stretching exercises and core stability exercises [\n2\n]. Yet, no reports were found in the peer-reviewed literature to describe the content or effectiveness of such programs for jet aviators. Drew [\n4\n] reported that 54 of 79 high performance pilots used some form of stretching or exercise to prevent spinal symptoms. However, it is unknown how these pilots derived such programs (ie, self-taught vs. provided by health care provider) or if the exercises performed were actually appropriate for the spine. This case illustrates the rationale and types of prescribed therapeutic exercise for an aviator with LBP. Further research to investigate the use of lumbar exercises for pilots is necessary.\nG forces are commonly cited as a cause of back pain in high performance aircraft pilots [\n2\n,\n16\n]. However, there is controversy. Voge et al [\n5\n] found no significant differences between aircrew and non-aircrew individuals until 1985, when the rates for aircrew fell below those of non-rated officers. They concluded that moderate G exposure did not seem to be a predictor of back disability. Summarily, there is no confluence of high quality evidence about this topic. Simon-Arndt et al [\n2\n] postulate that problems involving the back involve many microtraumas incurred during flight. They state that the G forces affect the pilot by compressing and jolting the spinal column and that the effects of G forces have been linked to lesions in the ligaments around the vertebrae and to the manifestation of latent thoracic and lumbar arthritis [\n2\n]. The present case shows a degenerative spine, but it is unknown if flying the F/A-18 was the cause.\nTime and resources allocated to training and maintaining fighter aviators are extensive. For these reasons, as well as peer-pressure, self-esteem and pay, pilots are reluctant to disclose back pain for fear of being grounded [\n2\n]. Flight surgeons are designated first points of contact for pilots and it has been found that when high performance aviators do relent to seeking medical care for spinal problems, the flight surgeon is usually the first person they see [\n4\n]. Flight surgeons are trained extensively in the nuances of aviation medicine and the numerous regulations pertaining to aviation. Most flight surgeons are accustomed to collaborating with physical therapists and physiatrists but not necessarily doctors of chiropractic. Chiropractors are trained extensively in musculoskeletal pain management and managing non-surgical spinal conditions without the use of pharmaceutical agents [\n17\n]. Thus, it seems that these providers can serve as valuable allies to aviators experiencing spinal problems as long as there is clear communication between the various providers during patient management. It has been the experience of the authors that such communication is easily maintained in a branch medical clinic environment.\nThe natural history of LBP must be considered as a plausible explanation for this patient's recovery. There is relatively little quality information available on the natural history of LBP [\n18\n]. Patients usually experience rapid improvement in the first 3 months after LBP has occurred. However, of those patients initially off work because of LBP, 16% remain off work 6 months later and 62% still have pain at 12 months. Recurrences of pain and work absence are common in the year following the onset of LBP [\n18\n,\n19\n]. Comparing the patient in this case to what is known of the natural history of LBP, his initial improvement followed the trend for patients to experience rapid improvement in the first 3 months, and he did experience recurrences of pain in the ensuing 12 months. However, he was able to return to work quickly, even if it meant doing non-flying tasks, and continued to demonstrate improvements after the third month with LBP while he continued to fly and subject the spine to peak forces. It is conceivable that a multitude of variables, or combination of them, influenced his improvement, including the following: chance, chiropractic intervention, multidisciplinary management, natural remission, dose-response effect, placebo effect. As a retrospective case report, this case does not attempt to control for all variables. Its purpose is merely to describe and discuss a previously unreported intervention for pilots; the case suggests that a traditional course of care augmented with chiropractic treatment available at Department of Defense military treatment facilities may be of benefit to US fighter aviators with LBP. It is recognized that some treatment methods presented in this case report are not novel and other providers care for aviators using similar methods or practice models, but to date none have been reported in MEDLINE. It is hoped that this paper will stimulate further discussion on this topic.\nConclusion\nThe addition of chiropractic care to the multidisciplinary management of this F/A-18 aviator with chronic LBP appeared to help alleviate pain and restore function. An appropriately powered prospective study would help determine the value of this type of treatment approach in this unique population.\nCompeting interests\nThe first author is a contracted health care provider to the US Navy; there are no other competing interests to declare.\nAuthors' contributions\nBNG conducted the literature review and drafted the manuscript. JS and RA assisted in drafting the manuscript. All authors read and approved the final manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
90
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nPrognosis of acute low back pain: design of a prospective inception cohort study\n\n**Article Abstract:**\n\nBackground\nClinical guidelines generally portray acute low back pain as a benign and self-limiting condition. However, evidence about the clinical course of acute low back pain is contradictory and the risk of subsequently developing chronic low back pain remains uncertain. There are few high quality prognosis studies and none that have measured pain, disability and return to work over a 12 month period. This study aims to provide the first estimates of the one year prognosis of acute low back pain (pain of less than 2 weeks duration) in patients consulting primary care practitioners. A secondary aim is to identify factors that are associated with the prognosis of low back pain.\nMethods/Design\nThe study is a prospective inception cohort study. Consecutive patients consulting general medical practitioners, physiotherapists and chiropractors in the Sydney metropolitan region will complete a baseline questionnaire regarding their back pain. Subsequently these patients will be followed up by telephone 6 weeks, 3 months and 12 months after the initial consultation. Patients will be considered to have recovered from the episode of back pain if they have no pain and no limitation of activity, and have returned to pre-injury work status. Life tables will be generated to determine the one year prognosis of acute low back pain. Prognostic factors will be assessed using Cox regression.\nDiscussion\nThis study will provide the first estimates of the one year prognosis of acute low back pain in a representative sample of primary care patients.\n\n**Article Body:**\n\nBackground\nIt is widely agreed that acute low back pain is common, can be seriously disabling, and imposes an enormous social and economic burden on the community [\n1\n]. To improve the management of this condition clinical practice guidelines have been developed in at least 12 countries. In general the guidelines provide similar information [\n2\n]. A common theme is that acute low back pain should be managed in primary care because it is generally benign: recovery tends to be both rapid and complete, and the few cases of serious disease can be readily detected with a clinical assessment [\n2\n].\nWhile most of the low back pain guidelines review the evidence prior to making recommendations for therapy, few have adopted an evidence-based approach to making recommendations on prognosis. The guidelines often do not refer to original research but instead have relied upon narrative review papers or previous guidelines. For example the commonly cited statistic on prognosis in the 2000 UK Guideline [\n3\n] \"90% recover within 6 weeks\" is attributed to page 26 of the 1996 UK guideline [\n4\n], even though the 1996 guideline provides no source for this information. Despite the lack of supporting evidence [\n5\n], this statistic is still widely reported. Without a comprehensive understanding of the clinical course of low back pain, clinicians will be unable to provide accurate information to patients regarding their prognosis [\n5\n].\nAlthough most current guidelines suggest a favourable prognosis, recent systematic reviews suggest that while patients with an acute episode of low back pain may improve rapidly, the risk of developing chronic low back pain (i.e. pain persisting longer than 3 months) is uncertain [\n5\n,\n6\n]. Studies have reported estimates of the risk of developing chronic low back pain that range from 2% [\n7\n] to 56% [\n8\n]. This inconsistency has been attributed to methodological shortcomings of the prognostic studies or to the recruitment of an unrepresentative cohort of low back pain patients [\n6\n,\n9\n]. It may also be due to heterogeneity in outcome measurements used in these studies [\n10\n]. One systematic review on the prognosis of acute low back pain [\n6\n] found 15 studies which met the inclusion criteria, but only two of the studies reported data beyond the 3 month follow-up. The same review found only three studies which reported on prognostic factors for at least 80% of the sample. No study measured pain, disability, or return to work in a primary care setting and followed patients for one year.\nThe notion that acute low back pain has a favourable prognosis, a view common to all guidelines, should be reconsidered because of the inconsistency in the outcomes reported and the lack of long-term follow-up data. Acute low back pain may not be a benign, self-limiting condition. Our paper reports the design of a study which will determine the medium-term (1 year) prognosis for people with acute low back pain presenting to community primary care providers (general medical practitioners, physiotherapists and chiropractors). The outcomes of interest will be time to recovery, which is defined by measures of pain, disability and work status. A secondary aim is to develop a prognostic model of acute low back pain.\nMethods/Design\nThe study will be an inception cohort study. It is part of a larger cohort study which will also assess the accuracy of the diagnostic triage for detecting serious spinal pathology in patients presenting with acute low back pain. Only the prognosis component of the study is described here.\nThe target population is patients with acute low back pain who consult practitioners from three major primary care professions, namely chiropractors, physiotherapists and general medical practitioners. Consecutive patients will be invited to complete a baseline assessment and have a series of three follow-up assessments performed via telephone calls over a 12-month period.\nStudy population\nA cohort of 1,000 subjects with acute low back pain will be recruited from the Sydney metropolitan region. Data from the 2001 Australian Census will be used to characterize the socioeconomic levels of postcode (zipcode) areas within the Sydney Metropolitan region. A number of postcode areas will be recruited to the study in order to achieve a range of socio-economic levels.\nAll practitioners within the study area will be invited to participate in the study. Practitioner names and clinic addresses will be extracted from telephone directories, professional registry listings and through professional associations of the three practitioner groups. Every practitioner identified within the study area will be sent a letter of invitation and a reply paid postcard, enabling them to indicate whether they intend to participate in the study, or whether they require further information. Three weeks after the letters are mailed out, all practitioners who have not replied via postcard will be contacted by telephone and invited to participate in the study. Practitioners will be excluded if they are not current primary care providers, e.g. specialists or retired practitioners, are not practising within the study area, or the practitioner details are not sufficient to contact them regarding the study. A record will be kept of practitioners who choose not to participate and where given, the reasons for their decisions.\nParticipating practitioners will be trained in either small groups or individual sessions. Training involves an explanation of the purpose and methods of the study and instruction on how to perform a standardized diagnostic triage. The practitioners will be asked to identify all eligible patients presenting at their clinics, assist patients to complete the baseline questionnaire, record the results of 25 clinical assessment \"red flags\", and record their diagnoses based on the AHCPR clinical practice guidelines [\n11\n]. Practitioners will also be given a copy of current guidelines for the management of acute low back pain and asked to follow them when appropriate.\nInclusion and exclusion criteria\nParticipating practitioners will be asked to screen all patients with the primary complaint of low back pain who present to their clinics. To be eligible for inclusion, patients must consult one of the practitioners for management of an episode of acute low back pain. We have used the definition for an episode of acute low back pain proposed by de Vet and colleagues [\n12\n]. This is defined by pain in the area bounded superiorly by T12 and inferiorly by the buttock crease [\n13\n] (Figure \n1\n), lasting for more than 24 hours but less than two weeks, and preceded by a period of at least one month without back pain [\n12\n]. Participants remain eligible if they have pain referred beyond this region. To be included, participants must be at least 14 years old, provide written consent to participate in the study, and be able to speak and read English. Potential subjects will be excluded if a serious pathology (e.g. cancer, spinal infection, spinal fracture, inflammatory disorder) has already been diagnosed as the cause of this episode of low back pain prior to the presentation of the patient in primary care.\nA record will be kept of patients who choose not to participate and their reasons for doing so, as well as patients with back pain who are ineligible to participate, and the reasons for exclusion. Recruitment will continue at all sites from the date of training until the target sample of 1,000 participants is achieved. With this sample size, the 95% confidence interval for an observed proportion of 5% extends from 3.8% to 6.5%, and the 95% confidence interval for an observed proportion of 50% extends from 46.9% to 53.1%. Practitioners will be contacted every two weeks to ensure that they are adhering to the study protocol. Also, practitioners will be reminded to recruit all eligible patients so that the cohort consists as far as possible of a consecutive sample.\nBaseline measures\nBaseline data will be used to comprehensively describe the inception cohort and test putative predictors of prognosis. The specific classes of predictors being measured are socio-demographic characteristics, general health, previous history, and psychological characteristics (see additional file 1).\nAs there is no universally accepted single measure of recovery from low back pain, we will sample three dimensions of recovery: pain intensity, disability due to pain, and work status. The first two questions are adaptations of items 7 and 8 of the SF-36 [\n14\n]: \"How much low back pain have you had in the past week?\", and \"During the past week, how much did low back pain interfere with your normal work (including both work outside the home and housework?)\". The original wording was changed from 'bodily pain' to 'low back pain' to reflect our specific interest in low back pain. The subset of participants employed at the time of onset of symptoms will be asked to rate their work status on a 9 point scale adapted from the scale developed by Kenny [\n15\n].\nFollow-up procedure\nCompleted assessment booklets will be collected every two weeks from study practitioners by a research assistant. When the booklets have been retrieved, the data concerning the participant contact details, assessment date and baseline data will be entered into a database. Any missing or conflicting data from the assessment booklet will be checked immediately, with every attempt made to contact the participant as soon after collection of the booklet as possible. Follow-up assessments will be conducted 6 weeks, 3 months and 12 months after the initial assessment.\nAt each follow-up time point, participants will be asked whether they have become pain-free, have no disability due to back pain, and returned to their pre-injury work status. Only when participants report achieving one of these points and remained there for a whole month, are they considered \"recovered\" in this dimension at the beginning of that month [\n12\n]. Participants will also be asked about their current status of pain, function, and work status and whether a serious spinal pathology has been diagnosed as the cause of their low back pain episode.\nFor participants, there will be a A$10 (incl. GST) compensation for time and inconvenience for each of the telephone follow-ups with an additional A$10 (incl. GST) payment if all telephone follow-ups are completed, to be paid following the 12 month follow-up. Practitioners will also be compensated A$50 (incl. GST) for each eligible patient enrolled, and A$10 (incl. GST) for each patient who is screened but ineligible.\nSeveral mechanisms will be used to ensure study data are of high quality. First, participating practitioners will be trained in the trial protocol and the Agency for Health Care Policy and Research (AHCPR) clinical assessment [\n11\n] in a standardised format. To maximise compliance with the clinical assessment, summaries of the AHCPR examination will be provided for display in each clinic. The research assistant who collects the data sheets will provide feedback to practitioners if there is evidence that the protocol is not being followed. Data will be entered and double checked by two people, and inconsistencies resolved by contacting the participant where appropriate, or via consensus.\nData analysis\nData will be collected on when people return to pre-injury work status and/or had no disability and/or had no pain, to enable construction of life tables. The life tables will be used to describe the prognosis of patients with non-specific low back pain presenting to primary care practitioners. Median survival times (days to recovery) will be determined for each of the three recovery measures.\nCox regression will be used to evaluate putative prognostic factors. The independent variables for the regression will be chosen from among those collected at baseline (see additional file 1). A correlation matrix will be inspected to determine relationships between candidate variables and outcome. Variables with strong correlations (p < 0.10) will be identified and entered into the regression model.\nLinear regression will be used to predict continuous outcomes such as days off work. If necessary, dependent variables will be transformed so that they satisfy assumptions of normality of residuals and heteroscedasticity. If there is evidence of non-linear effects, quadratic or higher order terms will be added to the regression model.\nDiscussion\nPatients with acute low back pain of less than 2 weeks duration will be recruited from the three primary care professions who most frequently manage low back pain in Australia. This will provide a representative cohort of patients to allow better provision of prognostic information to primary care providers. The choice of outcome measures reflects a standardised definition for an episode of low back pain [\n12\n] proposed to lead to more uniform reporting of the course of low back pain. By measuring three dimensions of recovery (pain, disability, and work status), a complete description of the impact of low back pain can be determined.\nThis study has been designed to include key methodological features that have been recognised as minimising bias in prognostic studies. These features include sampling of a representative inception cohort with a high rate of follow-up [\n16\n]. The proposed study will provide the first estimate of the one year prognosis of acute low back pain, measured in terms of pain, disability, and return to work, for patients presenting to primary care.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nAll authors participated in the design of the study. NH drafted the manuscript with input from the other authors. All authors read, revised and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
91
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nInterest in healthy living outweighs presumed cultural norms for obesity for Ghanaian women\n\n**Article Abstract:**\n\nBackground\nCultural norms indicate that obesity reflects increased wealth and prosperity. Yet obesity is linked to serious medical illnesses. The purpose of this study was to determine if Ghanaian women would change their body image if it meant a healthier life.\nMethods\nA questionnaire was administered to 305 Ghanaian women waiting for clinic appointments at Korle Bu Teaching Hospital, Accra Ghana. This survey included questions on current health, selection of figural stimuli, decision making on health and social determinants and 5 questions on self-perception of health from SF-36. Anthropometric measures were taken and body mass index calculated. Women were also provided with health related information at the conclusion of the interview.\nResults\nThe majority of all women surveyed would reduce their current body image if it meant that they would have an overall healthier life and reduce the risks of obesity-linked illnesses and complications. Currently obese women were significantly more likely than non-obese women to reduce their body image to reduce the risk of hypertension (OR 2.03 [1.64 – 2.51],<0.001); cardiovascular accident (OR 1.96 [1.61 – 2.38],<0.001); diabetes (OR 2.00 [1.63 – 2.44],<0.001); myocardial infarction (OR 2.27 [1.80 – 2.86],<0.001); if requested by a spouse(OR 2.64 [1.98 – 3.52],<0.001); and to improve overall health (OR 1.95 [1.60 – 2.37], <0.001). There was no association with current body image and responses to SF-36. The decision to select a new body image was not influenced by education, income, marital status or parity. Age 50 years old and less was significantly associated with the body image size reduction to reduce the risk of hypertension, diabetes, and a cardiovascular accident.\nConclusion\nThe Ghanaian women interviewed in this study are interested in living a healthy life and are willing to reduce their body size to reduce the risk of obesity-linked illnesses. The target group for any interventional studies and measures to reduce obesity appears to be women age 50 and younger.\n\n**Article Body:**\n\nBackground\nIt is estimated that over 115 million people suffer from obesity related health conditions in the developing nations [\n1\n-\n3\n]. Obesity is a marker or risk factor for several illnesses, including hypertension, type 2 diabetes and cardiovascular disease [\n4\n]. An increase in body weight with an increase in age was an uncommon occurrence in Sub Saharan African populations just over a little more than a generation ago [\n5\n]. However, recent studies have shown that particularly in the urban environment the prevalence of obesity and obesity linked illnesses are increasing [\n6\n,\n7\n].\nThe etiology of obesity in all populations is complex [\n8\n]. The causes include genetics, diet, activity level and cultural norms as a sign of wealth and prosperity [\n9\n,\n10\n]. In a recent study of 305 women using culturally adapted figural stimuli, we found that Ghanaian women view their current body image (CBI) as overweight or obese [\n11\n]. However, 94.9% stated that they were aware of health risks associated with obesity and 47.8% selected the ideal body image (IBI) of a Ghanaian woman to be smaller than her own CBI. Of the 106 women who were obese by body mass index measurements, 88.2% preferred a smaller IBI in comparison to her own CBI. The majority of women also selected the figure representing morbid obesity as the least healthy and the healthiest figures were 2 that represented normal to slightly overweight women. The purpose of this study is to determine if women would alter their body image for specific health and/or social conditions.\nMethods\nFigural Stimuli – body images\nThe prototype of a culturally adapted Figural Stimuli for Ghanaian women was developed using a computerized body morph assessment tools (Adobe Photoshop and Abrosoft Fanta Morph3) [\n12\n-\n15\n]. A hand drawn figure representative of a Ghanaian woman was drawn from a combination of photographs, then scanned and morphed to include select body images that included a range of shapes to represent very thin to morbidly obese. The images were printed in color on a single placard for use in the study [\n11\n].\nSurvey\nA verbally administered survey was conducted that included queries on age, area of residence, ethnicity, marital status, parity, income and education level, a previous history of intentional weight gain or loss, diet and exercise habits, family or peer pressure to change their weight as an adult or child and interest in participating in a trial to reduce weight and promote healthy living [\n11\n]. The women reviewed the placard and selected her CBI and her choice of the IBI. She was also asked to decide if she would change her CBI to another body image if it meant that she would be healthier and then to select that new image. Medical conditions that are linked to obesity and two medical conditions not linked to obesity as well as one social determinant were used individually to assess the conditions that may cause the participant to change her CBI. The survey also included food access questions and questions from the Short Form 36 – a standardized self assessment of health [\n16\n].\nAnthropometric measurements\nAnthropometric measurements were obtained with the women wearing lightweight street clothes without shoes. Weight was measured on a calibrated Salter scale to the nearest 0.1 kilogram (kg). Height was measured to the nearest 0.5 cm with the women standing upright with the head in the Frankfurt position [\n17\n]. Body mass index (BMI) was calculated as weight (kg) divided by height squared (meter\n2\n). Body mass index (BMI) was defined as BMI ≤ 18.5 underweight; BMI 18.5 – 24.9 normal weight; BMI 25.0 – 29.9 overweight; and ≥ 30.0 obese. Morbid obesity is defined as BMI ≥ 40.0 [\n18\n]. Unless specifically stated, the obese weight category refers to all those with a BMI ≥ 30.0 kg/m\n2\n. Waist circumference was measured in centimeters (cm) at the mid-point between the lower ribs and the iliac crest. Hip measurements were taken at the maximal circumference of the buttocks. The waist to hip ratio (WHR) was calculated from the waist and hip measurements. A WHR > 0.8 has been associated with increased risks for type 2 diabetes, coronary artery disease and hypertension [\n19\n].\nAt the end of the interview, the women were provided with a written copy of their measurements, the calculated Body Mass Index and an interpretation. They were also provided with a pamphlet on diet, exercise and healthy living. The length of interview ranged from 10 minutes to one hour, providing each woman with sufficient time to complete the questionnaire.\nEligibility\nAll of the women who were attending the gynecologic clinic or the radiology clinic at Korle Bu Teaching Hospital, Accra, Ghana were asked to participate in the study. The women, who were otherwise waiting for the clinics to start, were required to sign an informed consent, be at least age 18 years or older, not be pregnant or breast feeding and be able to communicate with the interviewers. The interviews for the most part were conducted in English, the official language in Ghana. Occasionally the head nurse (matron) of the clinic would assist with terms if not understood by the participant.\nStatistical analysis\nThe data was coded and entered into SPSS version 13 for Windows (SPSS, Inc., Chicago, IL.). Analysis included frequency distributions, a dissatisfaction score (CBI-IBI), and binary logistic regression analysis. A p value of < 0.05 was considered significant. The strength of association is expressed as the Odds Ratio with a 95% confidence interval.\nInstitutional reviews\nThe study was approved by the Committee for Clinical Investigations, Beth Israel Deaconess Medical Center; Institutional Review board, Harvard Medical School; Human Subjects Committee, Harvard School of Public Health; and the Institutional Review Board, Noguchi Memorial Institute of Medical Research, University of Ghana.\nResults\nDemographic characteristics\nA total of 305 women completed the study, conducted between July and August 2005. The mean age was 35.9 years (range 19 to 74 years) with 71.1% being married, 48.2% were nulliparous, 37.1% multiparous, 94.4% receiving some level of formal education and 15.2% had no regular monthly income. There was no woman in this study who was unfamiliar with the illnesses of hypertension, diabetes, cerebral vascular accident, myocardial infarction, or malaria when asked about these conditions in local lay terms.\nClinical characteristics\nAnthropometric measurements were available for 305 women. Based on the BMI category, 1.3% (4) of the women in this study were underweight, 33.1% (101) were normal weight, 30.8% (94) were overweight and 34.8% (106) were obese. Of the 127 women in the obese BMI category, 10 met the criteria for morbid obesity. They represent 3.3% of the total women. The WHR of 172 women (56.5%) was in the obese range, indicating an even greater percentage of obesity and higher risk of obesity-linked illnesses by this alternate measure. The assessment of the participants' overall general health revealed that 18.6% were previously diagnosed as hypertensive, 2.3% were diabetics, 1.3% had suffered a previous myocardial infarction, 1.0% had suffered a previous cerebral vascular accident. 14% of the women interviewed states that they were diagnosed with obesity by a physician, most of whom offered that they were told to lose weight, and 79.5% reported at least one previous episode of malaria.\nHealth and social determinants affecting change of CBI\nThe length of time to administer the questionnaire ranged from 10 minutes to one hour. Each woman was allowed sufficient time for her to comfortably answer the questions. Two hundred and ninety-nine women answered the health determinant questions, the women who did not had been summoned for their medical appointment before the survey was completed.\nA series of health conditions and social situations were used to determine if the women would change their CBI if there was a link between the CBI and the determinant. The women were asked: 1) \"If you were told that your current figure (CBI) was associated with an increased chance of developing hypertension, stroke, heart attack, diabetes, poor vision, malaria, would you change it?\", and 2) \"Would you change your figure if your husband or significant other asked you to do so?\". If the response was \"yes\", the woman was asked to select the new body image (NBI) model. The scores were calculated by subtracting the NBI from the CBI, with a positive value indicating the NBI to be smaller than the CBI and a negative value indicates that the NBI is larger than the CBI.\nTable \n1\n shows the number and percent of women who selected a NBI and the average change for each health and social determinant. The majority of women selected a NBI for all health determinants evaluated that are linked to obesity. Over one-half of the women recognized that malaria and poor vision are not linked to obesity and did not select a NBI. A surprising 63.4% of women stated that they would change their body size if requested by their husband – to an average change of 2 sizes smaller than their CBI. Only 7.7% stated that the change would be to a larger size.\nTable 1\nHealth and social determinants affecting change in CBI\nDeterminant\nFrequency of Change to a New Body Image \n(n = 299 total)\nAverage Change in Figures\nn\n%\nMean\nsd\nHypertension\n224\n74.9\n2.0\n1.9\nStroke\n224\n75.9\n2.1\n1.9\nDiabetes\n218\n72.9\n2.4\n2.0\nHeart Attack\n221\n73.9\n2.3\n2.1\nPoor Vision\n169\n56.5\n2.3\n2.1\nMalaria\n184\n61.5\n2.4\n2.1\nSpouse/SO*\n201\n73.4\n2.0\n2.1\nImprove overall health\n226\n75.6\n2.0\n2.1\n* 25 had no spouse or significant other\nTable \n2\n shows the range and degree of change in NBI for each determinant. Greater than 90% of the women who would change their figure for health or social circumstances selected a smaller model as her new figure for each determinant For each obesity-linked and both non-linked health conditions and the social condition determinants, the majority of the NBIs selected were from 1 to 4 sizes smaller than the CBI.\nTable 2\nRange and Degree of Changes in Current Body Image to a New Body Image for each Determinant\nDeterminant\nDegree of Change*\nHypertension\nStroke\nDiabetes\nMyocardial Infarction\nPoor Vision\nMalaria\nSpouse/SO**\nImprove Overall Health\nn\n%\nn\n%\nn\n%\nn\n%\nn\n%\nn\n%\nn\n%\nn\n%\n-6\n0.0\n0.0\n0\n0.0\n0\n0.0\n0.0\n0.0\n0\n0.0\n0\n0.0\n1\n0.4\n0\n0.0\n-5\n1\n0.3\n0\n0.0\n0\n0.0\n0.0\n0.0\n0\n0.0\n0\n0.0\n1\n0.4\n0\n0.0\n-4\n1\n0.3\n0\n0.0\n1\n0.3\n0.0\n0.0\n0\n0.0\n0\n0.0\n1\n0.4\n5\n1.7\n-3\n2\n0.7\n2\n0.7\n3\n1.0\n5\n1.7\n2\n0.7\n3\n1.0\n5\n1.8\n3\n1.0\n-2\n7\n2.3\n5\n1.7\n4\n1.3\n4\n1.3\n6\n2.0\n5\n1.7\n4\n1.5\n7\n2.3\n-1\n9\n3.0\n9\n3.0\n10\n3.3\n9\n3.0\n6\n2.0\n12\n4.0\n8\n2.9\n12\n4.0\nCBI\n0\n78\n26.1\n75\n25.1\n81\n27.1\n78\n26.1\n130\n43.5\n115\n38.5\n96\n34.9\n73\n24.4\n1\n78\n26.1\n59\n19.7\n56\n18.7\n72\n24.1\n45\n15.1\n46\n15.4\n52\n18.9\n70\n23.4\n2\n45\n15.1\n57\n19.1\n58\n19.4\n52\n17.4\n39\n13.0\n46\n15.4\n38\n13.8\n48\n16.1\n3\n36\n12.0\n31\n10.4\n34\n11.4\n33\n11.0\n27\n9.0\n27\n9.0\n25\n9.1\n34\n11.4\n4\n22\n7.4\n32\n10.7\n24\n8.0\n27\n9.0\n22\n7.4\n20\n6.7\n29\n10.5\n24\n8.0\n5\n10\n3.3\n19\n6.4\n14\n4.7\n10\n3.3\n9\n3.0\n12\n4.0\n9\n3.3\n13\n4.3\n6\n7\n2.3\n2\n0.7\n5\n1.7\n3\n1.0\n5\n1.7\n5\n1.7\n3\n1.1\n5\n1.7\n7\n1\n0.3\n3\n1.0\n5\n1.7\n4\n1.3\n5\n1.7\n6\n2.0\n2\n0.7\n3\n1.0\n8\n2\n0.7\n5\n1.7\n3\n1.0\n2\n0.7\n2\n0.7\n2\n0.7\n1\n0.4\n2\n0.7\n9\n0\n0.0\n0\n0.0\n1\n0.3\n0\n0.0\n1\n0.3\n0\n0.0\n.0\n0.0\n0\n0.0\nTotal\n299\n100\n299\n100\n299\n100\n299\n100\n299\n100\n299\n100\n274\n100\n299\n100\n*A negative value reflects the selection of a new body image that is larger than the current body image. **25 women had no spouse or significant other.\nA comparison of obese to non-obese women was performed to assess if BMI influenced the decisions to select a NBI for each health and social determinant as shown in Table \n3\n. When a NBI was selected, most women chose a figure 1 to 4 sizes smaller than her CBI. Table \n4\n shows the Odds Ratio and 95% confidence interval for each determinant. Obese women were significantly more likely to select a NBI in comparison to non-obese women for each determinant.\nTable 3\nRange of selected changes for a new body image for each determinant by Body Mass Index\nDeterminant\nDegree of Change*\nHypertension\nStroke\nDiabetes\nMyocardial Infarction\nPoor Vision\nMalaria\nSpouse/SO**\nImprove Overall Health\nNon obese\nObese\nNon obese\nObese\nNon obese\nObese\nNon obese\nObese\nNon obese\nObese\nNon obese\nObese\nNon obese\nObese\nNon obese\nObese\n%\n%\n%\n%\n%\n%\n%\n%\n%\n%\n%\n%\n%\n%\n%\n%\n-6\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n1.1\n0.0\n0.0\n0.0\n-5\n0.0\n0.5\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n1.1\n0.0\n0.0\n0.0\n-4\n1.0\n0.0\n0.0\n0.0\n1.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0.0\n1.1\n0.0\n1.9\n1.5\n-3\n1.9\n0.0\n1.9\n0.0\n2.9\n0.0\n3.9\n0.5\n1.9\n0.0\n2.9\n0.0\n5.6\n0.0\n2.9\n0.0\n-2\n4.9\n1.0\n3.9\n0.5\n2.9\n0.5\n3.9\n0.0\n4.9\n0.5\n3.9\n0.5\n3.3\n0.5\n5.8\n0.5\n-1\n7.8\n0.5\n7.8\n0.5\n6.8\n1.5\n7.8\n0.5\n4.9\n0.5\n8.7\n1.5\n7.8\n0.5\n8.7\n1.5\nCBI\n0\n42.7\n17.4\n35.9\n19.0\n42.7\n18.5\n40.8\n18.5\n61.2\n33.8\n53.4\n30.3\n52.2\n26.1\n37.9\n16.9\n1\n30.1\n23.6\n29.1\n14.9\n25.2\n15.4\n28.2\n21.5\n13.6\n15.9\n19.4\n13.3\n22.2\n17.4\n28.2\n21.0\n2\n6.8\n19.5\n14.6\n21.5\n11.7\n23.6\n11.7\n20.5\n8.7\n15.4\n6.8\n20.0\n3.3\n19.0\n11.7\n18.5\n3\n2.9\n16.9\n3.9\n13.8\n5.8\n14.4\n2.9\n15.4\n2.9\n12.3\n1.9\n12.8\n0.0\n13.6\n1.9\n16.4\n4\n0.0\n11.3\n1.0\n15.9\n0.0\n12.3\n1.0\n13.3\n1.0\n10.8\n1.0\n9.7\n2.2\n14.7\n1.0\n11.8\n5\n0.0\n5.1\n1.9\n8.7\n0.0\n7.2\n0.0\n5.1\n0.0\n4.6\n1.0\n5.6\n0.0\n4.9\n0.0\n6.7\n6\n1.9\n2.6\n0.0\n1.0\n0.0\n2.6\n0.0\n1.5\n0.0\n2.6\n1.0\n2.1\n0.0\n1.6\n0.0\n2.6\n7\n0.0\n0.5\n0.0\n1.5\n0.0\n2.6\n0.0\n2.1\n0.0\n2.6\n0.0\n3.1\n0.0\n1.1\n0.0\n1.5\n8\n0.0\n1.0\n0.0\n2.6\n1.0\n1.0\n0.0\n1.0\n0.0\n1.0\n0.0\n1.0\n0.0\n0.5\n0.0\n1.0\n9\n0.0\n0.0\n0\n0.0\n0.0\n0.5\n0.0\n0.0\n1.0\n0.0\n0.0\n0.0\n0.0\n0.0\n0\n0.0\nTotal n\n103\n195\n103\n195\n103\n195\n103\n195\n103\n195\n103\n195\n90\n184\n103\n195\n*A negative value reflects the selection of a new body image that is larger than the current body image. ** 25 women had no spouse or significant other.\nTable 4\nComparison of Obese Women to Non-obese Women Selecting a New Body Image for Health and Social Determinants\nDeterminant\nOdds Ratio\n95.0% C.I.\np value\nHypertension\n2.03\n1.64 – 2.51\n<0.001\nStroke\n1.96\n1.61 – 2.38\n<0.001\nDiabetes\n2.00\n1.63 – 2.44\n<0.001\nMyocardial Infarction\n2.27\n1.80 – 2.86\n<0.001\nPoor Vision\n1.87\n1.51 – 2.30\n<0.001\nMalaria\n1.96\n1.59 – 2.43\n<0.001\nSpouse/SO\n2.64\n1.98 – 3.52\n<0.001\nImproved Overall Health\n1.95\n1.60 – 2.37\n<0.001\nThe decision to select a NBI for each determinant was not influenced by increasing education, income, marital status or parity. Women age 19 to 50 years old were significantly more likely than older women to select a NBI if it would reduce the risk of hypertension (85.3% vs. 14.7%, respectively, p = 0.017), stroke (85.1% vs. 14.9%, respectively, p = 0.01), diabetes (85.1% vs. 14.9%, respectively, p = 0.012); a myocardial infarction (85.3% vs. 14.7%, respectively, p = 0.017); and poor vision (83.9% vs. 16.1%, respectively, p = 0.012).\nShort-Form 36 results – health self-assessment\nFive questions from Short Form 36 were included in this survey. These questions were included to provide an assessment of the women's perception of her own health. In general, their overall health was perceived as excellent (15.8%), very good (25.2%), good (46.6%), and poor (12.4%). Compared to one year ago, they report that their health is much better (22.5%), somewhat better (22.5%), same (35.6%), somewhat worse (13.8%) and much worse (5.7%). Over the next year, the women would expect their health to much improve (70.1%), somewhat improve (14.8%), stay the same 14.8% or get somewhat worse (0.3%). Compared to her friends, the women felt that her own health was much better (36.0%), somewhat better (25.6%), same (28.3%), somewhat worse (8.7%) or much worse (1.4%). When asked to describe the statement \"I expect my health to worsen over the next year\", the women reported that it was mostly true (1.0%), somewhat true (0.7%), neither true nor false (0.7%), somewhat false (8.1%) and mostly false (89.6%). For each of the SF-36 questions, there was no significant difference between women who selected a NBI and those who did not for each health and social determinant.\nFood security and preparation\nLess than 1% of the women stated that they often did not have enough food to eat, 58.7% had enough to eat and enough of the types of food they wanted to eat, while 27.5% had enough to eat but not always the types of food they desired. In general, either the woman (78.1%) or her female elder relative (9.4%) did the food shopping and prepared the meals (92.3%) for the family.\nInterest in future diet and exercise program\nA total of 279 women (94.9%) stated that they were aware that there was health risks associated with being overweight or obese. One hundred and 84 (86%) of the 214 overweight or obese women stated that they would be willing to decrease their body weight by dietary and exercise interventions if it meant that they would lead a healthier life. 186 of these women stated that they would be interested in participating in a weight reduction clinical trial. Two hundred and nine women said that most likely their spouse or significant other would not object if they would want to lose weight.\nDiscussion\nFigural stimuli are an easy to administer self-report of body image [\n20\n]. The scale is highly robust, highly correlated with measured weight, a reliable predictor of obesity and has been widely used in epidemiologic investigations as an adjunct to measured or self-reported height and weight [\n21\n].\nBody image assessment techniques include perceptual measures and attitudinal measures [\n12\n]. These measures assess the size perception accuracy and the subjective component of body image. Figural stimuli was the body image assessment tool chosen to evaluate in this investigation. Consideration was given to computerized morph models, but because of the research setting where electrical power is not always dependable, a more portable model was selected. When designing the Ghanaian figural stimuli, the models were created on a computerized interval scale rather than an ordinal scale and we also included models that represented the far extremes of weight from cachexia to morbidly obesity.\nYounger women were significantly more likely than women age 51 years and older to change their current body image to reduce the risk of hypertension, diabetes, myocardial infarction, stroke and poor vision. This may reflect an attitude of older women that it is too late to improve their health or younger women hoping to maintain good health and are willing to make sacrifices to do so. This point should be further evaluated in future studies.\nInterest in health conditions associated with obesity and improving their health was keen in this group of Ghanaian women. Most of the women were in good to excellent health, and with the exception of malaria, few had reported serious health problems. Most also reported that they had enough food and of the type they wished to eat. Many women had already made attempts to lose weight by diet and/or exercise. Use of diet medications is not yet popular in this culture. Known obesity-linked illnesses (hypertension, stroke, myocardial infarction, diabetes and two non-related medical conditions (malaria and poor eyesight) were used as a means to determine if women would change their own BMI for health related reasons. Over 75% of the women expressed an interest in changing her CBI for the improvement of health. Two-thirds of the women would also change their body size if requested by a spouse or significant other to improve their health.\nThe high percentage of women preferring a smaller figure for a healthier life was not anticipated based on purported cultural norms that suggest women prefer to be of a larger figure, so called \"traditionally built\" as a sign of wealth and prosperity and as a means to secure a husband. When the women agreed that they would change their figure if asked by their husband or significant other, the majority indicated that the new figure would be smaller than their current one. This indicates that their perception is that the spouse prefers slimmer women. This information is important in planning future health initiatives to reduce obesity, hypertension and diabetes in this population. While there may exist some resistance to lose weight because of the cultural value on weight and the impact of the husband's preference, most women would lose weight to live a healthier life.\nEvery attempt was made to select all women at the Gynecology and Radiology clinics who would be willing to participate. The limitations for patient selection included communication barriers in the various local languages and hence some interested women could not be interviewed. It is uncertain if this would have affected the final results of the study, but the presumption is that a greater cultural influence would have been captured if we were able to interview a broader section of the population. Hence, this study is not representative of all Ghanaian women in Accra, but rather represents a cross section of women who tend towards being more educated and comfortable conversing in English.\nBecause of the manner in which women were selected for the study, this is not a prevalence study for obesity. But the high percentage of women who were found to be overweight or obese is not surprising. The Women's Health Study of Accra, a representative sampling of 1300 adult women residing in Accra in 2003, found that 57.2% were either overweight or obese by anthropometric measurements [\n7\n]. The result from this present study also identified a high proportion of women who are overweight and obese.\nConclusion\nThis information on ideal body size is important not only for promoting a healthy BMI for an individual woman, but also in establishing acceptable health policies for women's health in general. No longer can the excuse be made against weight reduction programs to reduce hypertension and diabetes risk that the women prefer to be of a large size. With this information as ammunition, plans can go forward to initiate diet and exercise programs to reduce the risks of obesity and obesity-linked illnesses. Particularly in resource limited countries, an adherence to a healthy lifestyle is less expensive than life long medication or complications as a result of obesity-linked illnesses. It appears that the ideal group of women to target initially are women age 50 years and younger for health improvement strategies. An educational program that explains the association between obesity and heart disease and diabetes would be of benefit to women of all age groups.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nRBD concept, supervision, interviews, data analysis, writing manuscript; NAJ contributed to study design, conducted most of the interviews, contributed to writing manuscript; JF contributed to study design, supervision of NAJ, contributed to writing manuscript, facilitated permission to conduct interviews at Korle Bu Teaching Hospital and University of Ghana IRB approval process; AH assisted with concept, design, data analysis and review of manuscript; RB contributed to study design, supervision of NAJ, contributed to writing manuscript, facilitated University of Ghana IRB approval process\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
92
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nAcute respiratory failure in the elderly: etiology, emergency diagnosis and prognosis\n\n**Article Abstract:**\n\nIntroduction\nOur objectives were to determine the causes of acute respiratory failure (ARF) in elderly patients and to assess the accuracy of the initial diagnosis by the emergency physician, and that of the prognosis.\nMethod\nIn this prospective observational study, patients were included if they were admitted to our emergency department, aged 65 years or more with dyspnea, and fulfilled at least one of the following criteria of ARF: respiratory rate at least 25 minute\n-1\n; arterial partial pressure of oxygen (PaO\n2\n) 70 mmHg or less, or peripheral oxygen saturation 92% or less in breathing room air; arterial partial pressure of CO\n2 \n(PaCO\n2\n) ≥ 45 mmHg, with pH ≤ 7.35. The final diagnoses were determined by an expert panel from the completed medical chart.\nResults\nA total of 514 patients (aged (mean ± standard deviation) 80 ± 9 years) were included. The main causes of ARF were cardiogenic pulmonary edema (43%), community-acquired pneumonia (35%), acute exacerbation of chronic respiratory disease (32%), pulmonary embolism (18%), and acute asthma (3%); 47% had more than two diagnoses. In-hospital mortality was 16%. A missed diagnosis in the emergency department was noted in 101 (20%) patients. The accuracy of the diagnosis of the emergency physician ranged from 0.76 for cardiogenic pulmonary edema to 0.96 for asthma. An inappropriate treatment occurred in 162 (32%) patients, and lead to a higher mortality (25% versus 11%; \np \n< 0.001). In a multivariate analysis, inappropriate initial treatment (odds ratio 2.83, \np \n< 0.002), hypercapnia > 45 mmHg (odds ratio 2.79, \np \n< 0.004), clearance of creatinine < 50 ml minute\n-1 \n(odds ratio 2.37, \np \n< 0.013), elevated NT-pro-B-type natriuretic peptide or B-type natriuretic peptide (odds ratio 2.06, \np \n< 0.046), and clinical signs of acute ventilatory failure (odds ratio 1.98, \np \n< 0.047) were predictive of death.\nConclusion\nInappropriate initial treatment in the emergency room was associated with increased mortality in elderly patients with ARF.\n\n**Article Body:**\n\nIntroduction\nIn Western countries the population is getting older, and it is projected that the number of people between the age of 65 and 80 years will double by the year 2030 [\n1\n,\n2\n]. It is estimated that more than 10% of the population over the age of 80 years have heart failure [\n1\n]. Acute respiratory failure (ARF) is one of the major causes of consultation of elderly patients in emergency departments (EDs) and is the key symptom of most cardiac and respiratory diseases, such as cardiogenic pulmonary edema (CPE), and of exacerbation of chronic respiratory disease (CRD) including chronic obstructive pulmonary disease (COPD), community-acquired pneumonia (CAP) and pulmonary embolism (PE), which are associated with a high morbidity and mortality [\n3\n-\n8\n]. In elderly patients, differentiating CPE from respiratory causes is difficult for several reasons. Cardiac and respiratory diseases frequently coexist. Atypical clinical presentation, such as wheezing in CPE (cardiac asthma) or lack of infectious signs in pneumonia, is confusing [\n5\n,\n7\n,\n8\n]. In the oldest patients, autopsy studies have demonstrated that the main causes of death were CPE, CAP, and PE, which are frequently underestimated [\n9\n]. There is little knowledge of the presentation, clinical characteristics and outcomes of ARF in elderly patients. Furthermore, two studies suggested that prognosis was improved when early diagnostic and treatments were accurate [\n10\n,\n11\n].\nThe objectives of this study were therefore to determine the causes of ARF in elderly patients, the accuracy of the initial diagnosis suspected by the emergency physician, the impact of initial diagnosis and treatment, and variables associated with in-hospital death.\nMethods\nStudy design and setting\nThis epidemiological study of ARF in elderly patients was a single-center prospective study performed from February 2001 to September 2002. It took place in the ED of an urban teaching hospital (2,000 beds), in whom contrast-enhanced helicoidal computed tomography (CT) scan and ultrasonography are available 24 hours a day. Conversely, Doppler echocardiography and other investigations (such as pulmonary function tests (PFTs) or lung scintigraphy) are not easily available in our ED. There is no cardiologist or pulmonologist assessment in the emergency room. During the study period, 90,547 patients have consulted in our ED, of whom 10,156 (11%) were aged more than 65 years. This study was approved by our Ethical Committee, and waived informed consent was authorized because routine care of the patient was not modified.\nPatients\nThe criteria for inclusion in the study were the following: emergency admission to our ED; age at least 65 years; acute dyspnea of less than two weeks' duration, a subjective criterion defined by the patient (the dyspnea was present if the patient answered one of the following questions in the affirmative: Are you breathless? Do you feel short of breath? Do you experience air hunger? Do you feel increased effort of breathing?); and one of the following objective criteria of ARF: a respiratory rate at least 25 minute\n-1\n, an arterial partial pressure of oxygen (PaO\n2\n) of 70 mmHg or less, a peripheral oxygen saturation (SpO\n2\n) of 92% or less while breathing room air, and an arterial partial pressure of CO\n2 \n(PaCO\n2\n) of 45 mmHg or more with an arterial pH of 7.35 or less. There were no exclusion criteria.\nRoutine clinical assessment\nFor every patient, standard medical care provided by the emergency physician (resident or senior) in charge included the following: medical history, physical examination findings including signs of acute ventilatory failure (use of accessory respiratory muscles, paradoxical abdominal respiration), arterial blood gas analysis while breathing room air, 12-lead electrocardiogram, chest X-ray and the usual blood tests. Creatinine levels were measured, and creatinine clearance was estimated with the Cockcroft formula. Dependence and quality of life were assessed by the activity of daily living score [\n12\n]. As usual, after the initial presentation in the emergency room, all the patients were reviewed with one of the senior staff members. Thus, depending on the suspected diagnoses, emergency treatment and admission were decided by the emergency physician in accordance with normal practice and recommendations [\n4\n,\n7\n,\n13\n,\n14\n]. Usually, dyspneic patients stay for less than eight hours in the emergency room before their admission into another ward.\nIn accordance with standard practice in our institution for ARF in elderly patients, the performance of thoracic high-resolution computed tomography (HRCT) without contrast iodine medium, of transthoracic Doppler echocardiography with emphasis on diastolic function, and of PFTs was encouraged whenever possible and as quickly as possible during hospitalization. We did not conduct all examinations on every patient because the emergency physician decided whether they were appropriate or not. Almost all thoracic HRCTs were performed less than 12 hours after admission. Slices of 1 mm every 30 mm were performed on inspiration with lung and soft kernels, and read on lung and mediastinal windows respectively. All the CT scans were interpreted again by a radiologist (CB) blinded for any clinical information and medical chart (especially the results of echocardiography and PFTs), and only this interpretation was taken into account by the panel of experts. Transthoracic Doppler echocardiography included two-dimensional and M-mode examination, pulsed Doppler analysis of mitral flow, and continuous Doppler analysis of tricuspid regurgitation. Systolic pulmonary arterial pressure was calculated from the velocity of tricuspid or pulmonary regurgitation, when present. The left ventricular ejection fraction was estimated by visual inspection. PFTs included the measurement of lung volumes and flow-volume loop. In some cases, spirometry was performed at the bedside (\nn \n= 14) with a validated portable spirometer (Easyone™; Dyn'air, Muret, France) [\n15\n]. All PFTs were interpreted again by a pulmonologist (MHB) blinded for any clinical information and medical chart, and only this interpretation was taken account by the panel of experts. Results from various other investigations decided by the physician in charge (in the emergency room or in another medical ward) were also recorded, such as ultrasonography of the lower limbs, contrast-enhanced thoracic CT scan, pulmonary arterial catheter in intensive care unit (ICU), and other relevant results. During this study, levels of B-type natriuretic peptide (BNP) (Triage BNP; Biosite, San Diego, CA, USA) and NT-proBNP (Elecsys 2010 analyse; Roche Diagnostics, Meylan, France) were evaluated in separate studies [\n16\n], and the emergency physicians were not aware of the results. As we demonstrated previously in an elderly population, the cutoff values of 250 pg ml\n-1 \nfor BNP and 1,500 pg ml\n-1 \nfor NT-proBNP were used in the analysis [\n16\n]. The length of hospitalization, admission to the ICU in the first 24 hours, the number of hospital-free days within one month after admission, and the in-hospital mortality during a short stay were also recorded. The final diagnosis of ARF was then determined by two independent senior experts (pulmonologist, cardiologist, general-medicine internist, intensivist, geriatric or emergency physician) from an examination of the complete medical chart including all initial clinical findings, emergency laboratory tests, X-ray chest data, and the results of thoracic HRCT, transthoracic Doppler echocardiography, PFT (or bedside spirometry), and BNP and/or NT-proBNP levels when available. In cases of disagreement between the two experts, a consensus was reached by a third expert. The main final proposed diagnoses were CPE including left heart failure, CAP, acute exacerbation of CRD, PE, acute asthma, bronchitis, and other main diagnoses not listed above, and lack of any diagnosis. The use of validated criteria, response to diuretic or vasodilator, results of echocardiography Doppler, and BNP and NT-proBNP levels performed at admission in the emergency room, and other cardiac tests were specifically analyzed for CPE [\n5\n,\n13\n,\n17\n]. Results from PFT or bedside spirometry, thoracic HRCT and response to bronchodilator or steroids or antibiotics were specifically analyzed for respiratory disorders [\n7\n,\n18\n]. Results of ultrasonography, contrast-enhanced helical CT scan and perfusion/ventilation nuclear lung scan were specifically analyzed for PE, as recommended [\n14\n].\nEmergency physicians were asked for their diagnosis just before the patient was leaving the emergency room for either the observation unit of our ED or another ward, including the ICU. According to the final diagnosis made by the experts, an inaccurate emergency physician diagnosis was recorded only if one of the following diagnoses was missed: PE, CPE, CAP, and acute asthma. This was because all these causes of ARF are thought to be linked to increased mortality when initial early treatment is inappropriate, thus requiring early diagnosis. The emergency diagnosis was recorded before thoracic CT scan, Doppler echocardiography or PFT was performed.\nThe initial specific treatment was defined as that administered when the patient was still in the emergency room. In the same manner, an inaccurate initial treatment was recorded when PE was diagnosed by the experts without initial anticoagulation, when CPE was diagnosed without initial administration of nitrate and/or diuretics, when CAP was diagnosed without initial antibiotics, and when acute asthma was diagnosed without β\n2\n-agonist administration. Oxygen was considered as a symptomatic treatment not a specific treatment (for example, initial anticoagulation for PE). When patients had two or more causes of ARF, they required treatment for both (for example, diuresis and antibiotics for a patient with congestive heart failure and acute pneumonia) to be considered appropriate.\nAt the time of the study, non-invasive ventilation or continuous positive airway pressure was not performed in the elderly in the ED, but they were performed in the ICU when the patients were transferred.\nStatistical analysis\nThe data were collected by three research assistants and verified by one of us (PR). Consistency checks between data entered in the database and searches for erroneous values were performed by one of us (BR) before closing the database and performing statistical analysis. Data are expressed as means ± SD or medians and 95% confidence intervals (CIs) for non-Gaussian variables (Kolmogorov-Smirnov test). Comparison of two means was performed with Student's \nt \ntest, comparison of two medians with the Mann-Whitney test, and comparison of two proportions with Fisher's exact method.\nAssessment of the diagnostic performances of the emergency physicians was performed by calculating the sensitivity, specificity, positive and negative predictive values, and accuracy (defined as the sum of concordant cells divided by the sum of all cells in the 2 × 2 table) and their 95% CIs were calculated. The reference diagnosis was that of the experts.\nTo enable us to compare the length of hospitalization in a short stay in different groups while taking mortality into account, we calculated the number of hospital-free days within one month after admission, as reported previously [\n19\n]. Because some of our elderly patients were sent to chronic care before returning home, we considered only hospitalization into an acute care setting for this calculation, and all dead patients were scored 0 hospital-free days.\nWe performed a multivariate analysis to assess variables associated with missed diagnosis. We also performed a multiple backward logistic regression to assess variables associated with death. To avoid overfitting, we used a conservative approach and included only the significant preoperative variables in the univariate analysis (\np \nvalue of entry < 0.10), except for some variables that were thought to be prognostic or had been demonstrated to be prognostic in previous studies (MacCabe score 3 (death expected in one year) elevated troponin value, elevated natriuretic peptides and clinical signs of acute ventilatory failure). Interactions were not tested. The receiver operating characteristic (ROC) curve was used to determine the best threshold for continuous variables to predict death. The best threshold was the one that minimized the distance to the ideal point (sensitivity = specificity = 1) on the ROC curve. The Spearman coefficient matrix correlation was used to identify significant collinearity (more than 0.70) between variables. Odds ratios and their 95% confidence interval of variables selected by the logistic model were calculated. The discrimination of the model was assessed with the ROC curve and the calculation of the area under the ROC curve [\n20\n]. The percentage of patients correctly classified by the logistic model was calculated by using the best threshold determined by the ROC curve. Calibration of the model was assessed with Hosmer-Lemeshow statistics [\n21\n].\nAll statistical tests were two-sided, and \np \n< 0.05 was required to reject the null hypothesis. Statistical analysis was performed with NCSS 2001 software (Statistical Solutions Ltd, Cork, Ireland).\nResults\nWe included 514 patients with ARF; their main characteristics are summarized in Table \n1\n. In our ED, the prevalence of acute dyspnea in patients older than 65 years who consulted at our ED was 5%. All the patients experienced an ED visit and acute dyspnea, and 80% of them had a respiratory rate of at least 25 minute\n-1\n. Table \n2\n summarizes the additional inclusion criteria and the clinical severity criteria. Previous medications included diuretics in 167 patients (33%), nitrates in 127 (25%), calcium channel blockers in 130 (25%), inhaled bronchodilatators in 120 (23%), beta-blockers in 72 (14%), angiotensin-converting enzyme inhibitors in 136 (26%), anticoagulation in 53 (10%), and oral corticosteroids in 21 (4%); 23 patients (4%) received home oxygen. A cough was noted in 222 patients (43%), expectoration in 91 (18%), chest pain in 33 (6%), and hemoptysis in 6 (1%) patients. Most of the patients had a normal Glasgow coma scale (\nn \n= 481 (94%)). The mean serum creatinine was 110 ± 75 μmol l\n-1 \n(\nn \n= 484), with an estimated creatinine clearance of 52 ± 24 ml minute\n-1\n, 239 of 484 patients (49%) had an estimated creatinine clearance of 50 ml minute\n-1 \nor less. An elevated troponin Ic level was observed in 83 of 356 patients (23%).\nThoracic HRCT was performed in 275 patients (54%). Transthoracic Doppler echocardiography was performed in 230 patients (45%), and was performed in 152 of the 212 patients with final diagnostic of CPE PFTs or spirometry was performed in 180 patients (35%), of whom 164 were patients with exacerbation of CRD. Measurements of NT-proBNP or BNP levels were performed in 375 patients (73%).\nThere was good agreement between experts for the diagnosis of CPE (82%), CAP (87%), PE (91%), acute exacerbation of CRD (83%), and acute asthma (98%). The final diagnoses defined by the experts and their mortality are reported in Table \n3\n; 244 patients (47%) had more than two diagnoses of ARF. Other diagnoses included severe sepsis other than acute pneumonia (\nn \n= 30), malignancy (\nn \n= 15), pleural effusion (\nn \n= 11), tense ascitis (\nn \n= 5), pneumothorax (\nn \n= 4), neurologic diseases (\nn \n= 2), and various other medical diagnoses (\nn \n= 11). The main causes of CPE that were clearly determined were concomitant exacerbation of COPD in 55 cases, rapid atrial fibrillation in 43, acute coronary syndrome (including 2 with ST-segment elevated myocardial infarction) in 40, CAP in 38, anemia in 20, and associated PE in 11.\nAll patients except two were admitted to the hospital; 289 patients (56%) were initially admitted to the observation unit of our ED before they were hospitalized in a medical ward, and 74 were admitted directly to a medical ward (14%). During the first 24 hours, 151 patients were admitted to an ICU (29%). The median length of stay in the hospital was 12 days (95% CI 11 to 13) (range 0 to 87). Eighty patients (16%) died in hospital (95% CI 13 to 19). The mortality of patients with two or more final diagnoses was not significantly different from that of patients with only one final diagnosis (18% versus 14%, \np \n= 0.11).\nThe diagnostic performance of the emergency physicians is reported in \n4\n. A missed diagnosis of CPE (\nn \n= 56), CAP (\nn \n= 26), PE (\nn \n= 23) or asthma (\nn \n= 5) in the ED was noted in 101 (20%) patients. The number of hospital-free days within one month after admission was significantly lower and mortality was significantly higher in patients with a missed diagnosis (Figure \n1a\n). Patients with a missed diagnosis were not different from patients with appropriate diagnosis performed in the emergency ward, in terms of medical past history, clinical signs, and results of laboratory tests. In the multivariate analysis, three variables were significantly associated with a missed diagnosis: final diagnosis of CPE, final diagnosis of PE, and final diagnosis of CAP (\n5\n). Conversely, systemic arterial hypertension was associated with fewer missed diagnoses. The Hosmer-Lemeshow statistic was 7.38 (\np \n= 0.39), indicating appropriate calibration. The area under the ROC curve was 0.775 ± 0.027 (\np \n< 0.05); the accuracy of the logistic model was 0.80 (95% CI 0.72 to 0.82). BNP and NT-proBNP levels were significantly higher in the group of patients with a missed diagnosis, namely 143 pgml\n-1 \n(95% CI 101 to 171) versus 403 pg ml\n-1 \n(95% CI 337 to 503; \np \n< 0.001) and 1,181 pg ml\n-1 \n(95% CI 781 to 1,700) versus 3,555 pg ml\n-1 \n(95% CI 1,735 to 6,330; \np \n= 0.01), respectively.\nOxygen was given in 444 patients (86%) in the ED, but was considered a symptomatic rather than a specific treatment. Inappropriate initial treatment of CPE (\nn \n= 93), CAP (\nn \n= 56), PE (\nn \n= 36), or asthma (\nn \n= 0) was noted in 162 patients (32%). Seventy-nine patients (15%) with a missed diagnosis had also an inappropriate treatment in the emergency room. The number of hospital-free days within one month after admission was significantly lower, and the rates of admission into ICU and mortality (25% versus 11%, \np \n< 0.001) were significantly higher, in patients with an inappropriate initial treatment (Figure \n1b\n). Most of the difference in mortality occurred within few days after admission (Figure \n2\n). The following variables were considered in the logistic model to predict death: previous cancer, McCabe score less than one year, any previous cardiac disease, hypotension (systolic arterial pressure less than 90 mmHg), acidosis (pH less than 7.35), hypercapnia (PaCO\n2 \nmore than 45 mmHg), peripheral hypoxia (SpO\n2 \nless than 92%), elevated serum creatinine (more than 120 μmol l\n-1\n), low estimated creatinine clearance (less than 50 ml minute\n-1\n), elevated troponin Ic, elevated NT-proBMP or BNP, hyperkalemia (more than 5 mmol l\n-1\n), mottling, ventilatory rate more than 30 minute\n-1\n, clinical signs of ventilatory failure (the use of accessory respiratory muscles and/or abdominal paradoxical respiration), missed diagnosis, and inappropriate treatment in the emergency room. No significant collinearity was noted between these variables. Missing values were observed for natriuretic peptides values (\nn \n= 139 (27%)), estimated creatinine clearance (\nn \n= 30 (6%)), and hypercapnia and acidosis (\nn \n= 24 (5%)). Thus, the final logistic model was performed in 347 (68%) patients. In the multivariate analysis, five variables were significantly associated with mortality: inappropriate initial treatment in the emergency room, hypercapnia, low estimated clearance of creatinine, elevated NT-proBNP or BNP, and clinical signs of ventilatory failure (\n6\n). The Hosmer-Lemeshow statistic was 2.22 (\np \n= 0.99), indicating appropriate calibration. The area under the ROC curve was 0.767 ± 0.040 (\np \n< 0.05). The best threshold for the probability of death was 0.21 with a sensitivity of 0.68 (95% CI 0.42 to 0.68), a specificity of 0.80 (95% CI 0.75 to 0.84). The accuracy of the logistic model was 0.76 (95% CI 0.71 to 0.80). Figure \n3\n represents the mortality according to the number of variables previously associated with death in the multivariate analysis. The in-hospital mortality varied from 5% when patients had less than two of these variables (\nn \n= 151) to 52% when patients had four or more variables associated with death (\nn \n= 27) (Figure \n3\n).\nDiscussion\nIn this large prospective study, which evaluated ARF in elderly patients, the in-hospital mortality was 16%. We observed that predictive variables of mortality were the following: initial inappropriate treatment, hypercapnia at least 45 mmHg, clearance of creatinine 50 ml minute\n-1 \nor less, clinical signs of acute ventilatory failure, and elevated BNP or NT-proBNP levels. Inappropriate initial treatment occurred in one-third of cases, and the in-hospital mortality was double that of patients with appropriate treatment.\nBoth the incidence and prevalence of heart failure, COPD, CAP, and PE are increasing with age [\n1\n,\n7\n]. Previous studies have reported that CPE is one of the main causes of hospitalization in elderly patients and has a high mortality rate [\n1\n,\n4\n-\n6\n,\n22\n]. This was confirmed in our study. However, we also showed that almost half of the patients had more than two causes of ARF. Landahl and colleagues [\n23\n] reported that the main causes of dyspnea in 70-year-old people were heart failure, bronchitis, and emphysema. However, this phone-call study evaluated stable dyspnea. In a recent study that evaluated the usefulness of BNP in acute dyspnea, heart failure was the main cause, followed by exacerbation of COPD [\n10\n]. All studies that evaluated the accuracy of physical examination in diagnosing causes of dyspnea have also demonstrated that CPE, acute exacerbation of CRD, or respiratory infection were the primary causes of dyspnea [\n24\n-\n30\n]. In contrast with a younger population, the rate of acute asthma and bronchitis were low [\n24\n]. Nevertheless it should noted that all these previous studies had several differences from our study or various biases, namely: various settings (ED, pulmonary clinic, community cohort population sample); middle aged population studied; the number of patients; the numbers of patients excluded from the analysis; the absence of standardized methodology to determine the final diagnosis of acute dyspnea; low mortality; difference in inclusion criteria between isolated dyspnea and ARF; and no emphasis on risk factors of deaths.\nOur study demonstrated an in-hospital mortality of 16% (95% CI 13 to 19), with a higher mortality in patients with CPE (21%). These results are similar to previous studies that demonstrated a mortality of severe CPE from 13 to 29% [\n10\n,\n22\n,\n31\n,\n32\n]. In a multivariate analysis, we observed that three predictive variables of mortality were easily evaluated in emergency room: hypercapnia at least 45 mmHg, clearance of creatinine 50 ml minute\n-1 \nor less, and clinical signs of acute ventilatory failure. Thus, physicians should focus more on these criteria to evaluate the severity of illness in elderly patients with ARF. We also confirmed that elevated BNP or NT-proBNP levels should also be considered prognostic variables [\n16\n,\n33\n]. Thus, their measurement should be developed in the emergency room, because rapid measurement of BNP in the ED improved the evaluation and treatment of patients with dyspnea, especially in the elderly [\n10\n,\n32\n].\nIn our study, the sensitivity of the diagnostic performance of the emergency physician varied from 0.67 for acute asthma to 0.86 for CAP, and the accuracy of the diagnosis of CPE (0.76) was quite similar to that in another study [\n33\n]. Several reasons explain the difficulties in assessing causes of ARF in elderly patients. For CPE, atypical presenting symptoms are frequent, such as cardiac asthma presenting as obstructive airways disease or fatigue or leg swelling [\n5\n]. Furthermore, classical radiological signs of CPE are sometimes confusing. In cases of CAP, up to 50% of elderly patients had attenuated respiratory symptoms and non-respiratory symptoms such as confusion or falls, and over one-third had no systemic signs of infection [\n7\n,\n8\n].\nWe wished to estimate the diagnostic accuracy of the emergency physician and to test whether missed diagnosis and/or inappropriate treatment could be of any prognostic value. In our study three variables were significantly associated with missed diagnosis: a final diagnosis of CPE, PE, or CAP. This result confirms a previous autopsy study [\n9\n] that analyzed the clinical and autopsy records of 234 elderly patients: the most common causes of death included bronchopneumonia (33%), congestive heart failure (15%), and PE (8%). Furthermore, the highest diagnostic error rate was in the underdiagnosis of PE (39% ante-mortem accuracy rate only). Conversely, systemic arterial hypertension was significantly associated with fewer missed diagnoses, suggesting that emergency physicians more frequently evoked the diagnosis of CPE in patients with ARF and known hypertension. A missed diagnosis in the emergency room was noted in 20% of patients, leading to a smaller number of hospital-free days within one month after admission and to higher mortality. Interestingly, age over 75 years, dementia, previous quality of life, fatal disease, and clinical presentation were not significantly associated with missed diagnosis. The higher level of BNP and NT-proBNP in the group of patients with a missed diagnosis is probably explained by the fact that CPE represented more than half of the missed diagnoses. Wuerz and Meador [\n11\n] suggested in a retrospective pre-hospital study that mortality was reduced in treated patients with CPE in comparison with untreated patients (odds ratio for survival, 2.51 (95% CI 1.37 to 4.55)). We confirmed that undertreatment of the causes of ARF was associated with higher morbidity and mortality (Figure \n1b\n) with a close odds ratio for improved survival (2.83 (95% CI 1.48 to 5.41), \np \n< 0.002). Again, age, sex, previous quality of life, respiratory rate, initial severity of hypoxemia, and admission to ICU were not significantly associated with mortality.\nOur study has several limitations. We included patients aged more than 65 years although some geriatric physicians now define elderly patients as being more than 75 years. Nevertheless, the median age was 80 years and most of our patients were aged more than 70 years. Our study was monocentric but included consecutively a large cohort of elderly dyspneic patients. Our results, especially the diagnostic performance of emergency physicians and outcomes, could have been modified if the study had taken place in other medical department (a respiratory unit or ICU, for example) or in another country where the medical care of patient is different, whether with cardiologists and pulmonologists in the assessment of the patients in the ED and hospital admission, or if Doppler echocardiography or natriuretic peptides levels were available 24 hours a day, or if non-invasive ventilation was performed in the ED. As one of the inclusion criteria was acute dyspnea (a subjective symptom), it means that patients should have expressed their shortness of breath, which might have excluded some patients with severe neurological diseases but who had ARF. This might explain the good health-related quality of life and the relatively low rate of institutionalized patients in our study population. Nevertheless, the incidences of neurological diseases and other coexisting non-cardiovascular diseases in our patients were similar to those observed previously [\n10\n,\n21\n,\n31\n,\n32\n].\nSome argue that ARF is usually identified by a PaO\n2 \nbelow 60 mmHg and/or a PaCO\n2 \nabove 45 mmHg (irrespective of the degree of respiratory acidosis), and we agree that these usual criteria are stricter than ours. Thus, we used a different cut off point to select ARF from that which is usually considered, with mild hypoxemia (70 mmHg or less). However, some previous studies have already used other criteria in selecting patients for randomized clinical trials in non-invasive ventilation [\n22\n], with the use of clinical inclusion criteria (such as polypnea at least 25 per minute or contraction of the accessory muscles of respiration), not only gas exchange impairment. Moreover, it should be noted that we studied elderly patients in whom the capacity to face a respiratory distress is markedly reduced because of the ageing process and/or frequently associated chronic disease. In fact, we believe that our definition was sufficiently large to encompass all causes of ARF that cannot be reduced to those associated with hypoxemia below 60 mmHg. Furthermore, the rate of patients with clinical severity criteria (73%) and ICU admission (29%) observed in our cohort was relatively high, and the mortality was similar to that of elderly patients requiring treatment in the ICU for CAP or for CPE, indicating that we did indeed select a critically ill population [\n7\n,\n22\n].\nThe method used in our study to diagnose the cause of ARF requires comment. As in most EDs, Doppler echocardiography is not immediately available and in any case is rarely performed on elderly patients in clinical practice [\n5\n,\n31\n,\n34\n]. Thus, we encouraged, as soon as possible after hospitalization, the use of several non-invasive investigations including HRCT without contrast iodine medium, Doppler echocardiography, and PFTs. Furthermore, to determine the final diagnosis, the experts also had the results of BNP or NT-proBNP levels performed blind at admission, within the framework of a published study [\n16\n]. For an evident ethical reason, these investigations were not performed on all patients. In fact, almost all the patients had one of these investigations. Because the agreement between experts was above 85%, we suggest that the final diagnoses by experts were appropriate. Unfortunately, because it is rarely feasible in our country we did not perform an autopsy, which should be considered as the definitive diagnostic test in deceased patients [\n9\n]. In our study, the rate of patients with an initial inappropriate treatment (32%) was higher than the rate of patients with an initial missed diagnosis (14%). It should be noted that we recorded the initial treatment administered during the first hours in the emergency room, whereas the diagnosis of the emergency physician was recorded when the patient left the ED. A noticeable delay occurred between these two records, particularly in patients admitted into our observation unit before being sent to another department, usually within less than 24 hours. Although inappropriate treatment in the ED was the main factor associated with increasing mortality, we cannot demonstrate a link of causality between inappropriate initial treatment and outcomes. Thus, because our study was observational, we can only suggest that early appropriate treatments could improve prognosis, and that further studies are merited to confirm that hypothesis. Nevertheless, a prospective randomized controlled study in elderly patients suggested that rapid measurement of BNP in the ED reduced the time to discharge and the total treatment cost, and seemed to reduce 30-day mortality [\n32\n].\nConclusion\nWe have demonstrated in a large sample of elderly patients with ARF that mortality of patients with inappropriate treatment in the ED was double that of patients with appropriate treatment. To evaluate the severity of illness of elderly patients with ARF, physicians should focus more on easily available criteria associated with higher mortality: hypercapnia, a creatinine clearance of 50 ml minute\n-1 \nor less, elevated levels of BNP or NT-proBNP, and clinical signs of acute ventilatory failure. As the size of the geriatric population increases, the medical care of elderly patients with ARF needs to be improved.\nKey messages\n• \tThe mortality of elderly patients with acute respiratory failure was high (16%).\n• \tCPE was the main cause of ARF in elderly patients; however, half of the patients had more than two diagnoses.\n• \tAn inappropriate initial treatment was associated with increased mortality.\n• \tTo evaluate the severity of illness of elderly patients with ARF, physicians should focus on available criteria: PaCO\n2\n, creatinine clearance, levels of BNP or NT-proBNP, and clinical signs of acute ventilatory failure.\nAbbreviations\nARF = acute respiratory failure; BNP = B-type natriuretic peptide; CAP = community-acquired pneumonia; CI = confidence interval; COPD = chronic obstructive pulmonary disease; CPE = cardiogenic pulmonary edema; CRD = chronic respiratory disease; CT = computed tomography; ED = emergency department; HRCT = high-resolution computed tomography; ICU = intensive care unit; PaCO\n2 \n= arterial partial pressure of CO\n2\n; PaO\n2 \n= arterial partial pressure of oxygen; PE = pulmonary embolism; PFT = pulmonary function test; ROC = receiver operating characteristic; SpO\n2 \n= peripheral oxygen saturation.\nCompeting interests\nThe authors declare that they have no competing interests. The manufacturers (Biosite and Roche Diagnostics) provided the diagnostic tests free of charge.\nAuthors' contributions\nPR, SB, YL and JB were responsible for study concept and design, acquisition of subjects and/or data, interpretation of data, and preparation of the manuscript.\nM-HB, MA, CB, AT, and RI were responsible for acquisition of subjects and/or data, and interpretation of data. BR was responsible for statistical analysis and interpretation of data, and preparation of the manuscript. All authors read and approved the final manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
93
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nLack of MEF2A Δ7aa mutation in Irish families with early onset ischaemic heart disease, a family based study\n\n**Article Abstract:**\n\nBackground\nIschaemic heart disease (IHD) is a complex disease due to the combination of environmental and genetic factors. Mutations in the MEF2A gene have recently been reported in patients with IHD. In particular, a 21 base pair deletion (Δ7aa) in the MEF2A gene was identified in a family with an autosomal dominant pattern of inheritance of IHD. We investigated this region of the MEF2A gene using an Irish family-based study, where affected individuals had early-onset IHD.\nMethods\nA total of 1494 individuals from 580 families were included (800 discordant sib-pairs and 64 parent-child trios). The Δ7aa region of the MEF2A gene was investigated based on amplicon size.\nResults\nThe Δ7aa mutation was not detected in any individual. Variation in the number of CAG (glutamate) and CCG (proline) residues was detected in a nearby region. However, this was not found to be associated with IHD.\nConclusion\nThe Δ7aa mutation was not detected in any individual within the study population and is unlikely to play a significant role in the development of IHD in Ireland. Using family-based tests of association the number of tri-nucleotide repeats in a nearby region of the MEF2A gene was not associated with IHD in our study group.\n\n**Article Body:**\n\nBackground\nThe search for novel polymorphisms that increase the likelihood of IHD has recently led to the discovery of a potentially important role of the myocyte enhancing factor 2A gene (MEF2A). In 2003, Wang and colleagues [\n1\n] reported that they had identified a 21 base pair (bp) deletion (Δ7aa) of the MEF2A gene in a family with IHD, where the disease appeared to have an autosomal dominant pattern of inheritance. Subsequent investigation by the same research group revealed 3 further mutations in a separate part of the MEF2A gene. These authors suggest that mutations in the MEF2A gene may play a substantial role in the development of IHD.\nAttempts to confirm this association to date have not been successful in case-control studies in both a Canadian [\n3\n] and, more recently, a Japanese population [\n4\n]. We sought to investigate the role of the Δ7aa mutation in a large family based study of patients with early-onset IHD in Ireland.\nMethods\nSubjects\nRecruitment of the study population took place between August 1999 and October 2004. The inclusion criteria are described in detail in a previous publication [\n5\n]. Briefly, individuals were Caucasian with all four grandparents born in Ireland. Each family was required to have at least one family member affected with proven premature IHD (disease onset ≤ 55 years for males and ≤ 60 years for females) and at least one unaffected sibling and/or both parents surviving. Proven IHD was defined by one or more of the following: previous myocardial infarction (MI), previous unstable angina (typical chest pain with dynamic ECG changes or minor elevation of cardiac markers) or stable angina with angiographic evidence of obstructive coronary disease (>70% stenosis). Unaffected siblings were required to be 3 years older than the affected sibling at age of diagnosis of IHD and have no evidence of previous IHD using the \"Rose chest pain on effort and possible infarction questionnaire\" [\n6\n] and a standard 12 lead electrocardiogram independently coded using the \"Minnesota code\" [\n7\n].\nWritten informed consent was obtained from each patient. The study was approved by the Research Ethics Committee of Queen's University Belfast and the investigation conforms to the principles outlined in the Declaration of Helsinki.\nStatistical analysis\nTwo family based tests of association were used to analyse the data: the combined transmission disequilibrium test (TDT)/sib-TDT and the pedigree disequilibrium test (PDT) [\n8\n,\n9\n]. These tests avoid the problem of population stratification that is found in case-control studies.\nGenotyping\nPolymerase chain reaction (PCR) amplification of the Δ7aa region was undertaken, using a fluorescently labelled primer (MWG Biotech Ebersberg, Germany). The PCR conditions were as previously described [\n5\n]. The forward primer sequence was GCATCAAGTCCGAACCGATT and the reverse primer sequence was GGAGCGACCCATTTCCTGTC. Amplification products were run on a capillary ABI PRISM\n® \n3100 Genetic Analyser with a commercially available size standard (ROX 400™, Applied Biosystems). Sequencing of a random sample of 10 individuals was performed on a capillary ABI PRISM\n® \n3100 Genetic Analyser. Results were analysed by Sequencher™ (Gene Codes Corporation, Michigan, USA).\nResults\nThe risk factors for both probands and siblings are shown below in Table \n1\n. Of note, there are more male probands, and more female siblings, this reflects the earlier onset of IHD in men compared with women. Smoking and diabetes are more common in the probands. However, hypertension and elevated levels of lipoproteins were less common in the probands probably reflecting the use of vasoactive drugs to reduce blood pressure and the widespread use of lipid lowering agents in this population.\nTable 1\nRisk factors in probands and their siblings with premature onset IHD.\nRisk factor\nProbands\nSiblings\nAge\n52.0\n56.0\nFemale\n113 (19.5%)\n429 (54.6%)\nMale\n467 (80.5%)\n357 (45.4%)\nBody mass index\n28.5\n28.2\nNon smoker\n116 (20.0%)\n328 (41.7%)\nEx smoker (≥ 1 year)\n249 (42.9%)\n224 (28.5%)\nCurrent smoker\n215 (37.1%)\n235 (29.9%)\nHypertension treatment\n148 (25.5%)\n177 (22.5%)\nSystolic BP ≥ 140 mmHg\n30 (5.2%)\n239 (30.4%)\nDiastolic BP ≥ 95 mmHg\n1 (0.2%)\n2 (0.3%)\nTotal hypertension\n179 (30.9%)\n418 (53.2%)\nKnown diabetes\n53 (9.1%)\n43 (5.5%)\nRandom blood sugar ≥ 11.1 mmol/l\n2 (0.3%)\n6 (0.7%)\nTotal cholesterol (mmol/l)\n4.9\n5.8\nLow density lipoprotein (mmol/l)\n2.9\n3.4\nTriglycerides (mmol/l)\n2.4\n2.3\nHigh density lipoprotein (mmol/l)\n1.3\n1.2\nA total of 1494 individuals from 580 families were included (803 discordant sib-pairs and 64 parent-child trios). Due to incomplete genotyping 13 individuals from 7 families were removed, leaving 1481 individuals from 573 families. Analysis was based on amplicon size of the Δ7aa region of the MEF2A gene.\nThe Δ7aa mutation was not found in any individual in the study sample. Differences in amplicon size were identified and were due to variation in the numbers of triplet repeats in a nearby region coding for glutamate or proline residues, as previously reported [\n3\n]. Using the TDT/sib-TDT and PDT (352 informative families), the number of triplet repeats was not found to be associated with disease in our study group (Table \n2\n).\nTable 2\nFragment size and association with IHD using the TDT.\nFragment size\nTDT\nSib-TDT\nCombined TDT/sib-TDT\np value\nObserved\nExpected\nObserved\nExpected\nObserved\nExpected\n138\n0\n1\n2\n1.8\n2\n2.3\nn/a\n141\n0\n0\n1\n1.0\n1\n1.0\nn/a\n144\n0\n0\n0\n1.0\n0\n1.0\nn/a\n147\n29\n29\n209\n209.7\n238\n238.7\n0.98\n150\n25\n17\n133\n132.5\n158\n158.5\n0.59\n153\n29\n36\n287\n186.9\n316\n319.4\n0.75\n156\n1\n0\n3\n2.0\n4\n2.5\nn/a\n159\n0\n1\n1\n1.0\n1\n1.5\nn/a\nDiscussion\nAlthough the majority of researchers working in the field of complex traits propose a common-variant, small-effect model, the possibility also exists of a rare- variant, large-effect model. Wang and colleagues [\n1\n] reported the Δ7aa mutation in a family of 13 patients who exhibited an autosomal dominant inheritance pattern of IHD. Subsequent work by the same group [\n2\n] was undertaken in 207 unrelated patients, with a diagnosis of IHD based on angiography or development of MI, and 191 control subjects. Three novel mutations in exon 7 were found in four patients and in none of their control subjects. However, other groups have not confirmed this work. Weng and co-workers [\n3\n] did identify the Δ7aa mutation in 3 individuals without evidence of IHD and further work within their families did not show any evidence for cosegregation of the mutation with early onset IHD. Similarly, Kajimoto and colleagues, in a Japanese population, screened the MEF2A gene in 379 patients with MI and 589 control individuals. They identified one nonsense mutation (R447X) but were uncertain regarding the significance of this finding, as the patient was elderly and had other conventional risk factors for ischaemic heart disease. Research performed by other groups have also identified similar variations in the number of glutamate residues, they to have not found this to be associated with IHD; however, other mutations may be [\n10\n].\nConclusion\nOur research suggests that the Δ7aa mutation of the MEF2A gene is unlikely to play a significant role in the development of IHD in the Irish population. In addition, statistical analysis using family-based methods suggests that the triplet repeat polymorphism in this gene is not associated with IHD in our study group.\nAbbreviations\nIschaemic heart disease: IHD\nMyocardial infarction: MI\nTransmission disequilibrium test: TDT\nPedigree disequilibrium test: PDT\nPolymerase chain reaction: PDT\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nPaul G Horan: Recruited subjects and processed samples, laboratory analysis and wrote the paper.\nAdrian R Allen: designed laboratory processes and results collection.\nAnne E Hughes: Supervised all laboratory procedures.\nChris C Patterson: Provided statistical analysis.\nMark S Spence: Recruited subjects and processed samples form 1999–2001.\nPaul G McGlinchey: Recruited subjects and processed samples from 2000–2002.\nChristine Belton: Performed the majority of laboratory work.\nTracy CL Jardine: Recruited subjects 2002–2004.\nPascal P McKeown: Supervising consultant 1999–2004.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
94
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nTransthoracic Doppler echocardiography – noninvasive diagnostic window for coronary flow reserve assessment\n\n**Article Abstract:**\n\nThis review focuses on transthoracic Doppler echocardiography as noninvasive method used to assess coronary flow reserve (CFR) in a wide spectrum of clinical settings. Transthoracic Doppler echocardiography is rapidly gaining appreciation as popular tool to measure CFR both in stenosed and normal epicardial coronary arteries (predominantly in left anterior descending coronary artery). Post-stenotic CFR measurement is helpful in: functional assessment of moderate stenosis, detection of significant or critical stenosis, monitoring of restenosis after revascularization. In the absence of stenosis in the epicardial coronary artery, decreased CFR enable to detect impaired microvascular vasodilatation in: reperfused myocardial infarct, arterial hypertension with or without left ventricular hypertrophy, diabetes mellitus, hypercholesterolemia, syndrome X, hypertrophic cardiomyopathy. In these diseases, noninvasive transthoracic Doppler echocardiography allows for serial CFR evaluations to explore the effect of various pharmacological therapies.\n\n**Article Body:**\n\nIntroduction\nCoronary flow reserve (CFR) is defined as a ratio of maximal (stimulated) to baseline (resting) coronary blood flow. CFR evaluation is important for the understanding of the pathophysiology of coronary circulation. CFR measurement is used both to assess epicardial coronary stenoses and to examine the integrity of microvascular circulation. An appreciation of coronary physiology is an integral part of clinical decision-making for cardiologists treating patients with coronary artery disease. In the absence of stenosis in epicardial coronary artery, the CFR may be decreased when coronary microvascular circulation is compromised by arterial hypertension with or without left ventricular hypertrophy, diabetes mellitus, hypercholesterolemia, syndrome X, hypertrophic cardiomyopathy or other diseases [\n1\n].\nMethods to assess CFR\nSeveral methods have been established for measuring CFR (table \n1\n). However, these methods are either invasive (intracoronary Doppler flow wire), highly expensive and scarcely available (Positron Emission Tomography) or semi-invasive and scarcely feasible (transesophageal Doppler), thus their clinical use is limited. In addition, PET and intracoronary Doppler flow wire involve radiation exposure, with inherent risk, environmental impact and biohazard connected with use of ionizing testing [\n2\n].\nTable 1\nComparison of methods to measure CFR\nMethodolgy\nAdvantages\nLimitation\nPET\nNon-invasive, global and regional CFR measurable\nExpensive, scarce, radiation exposure\nIntra-Coronary Doppler\nCFR supplemented by measurement of fractional flow reserve provide stenosis-specific assessment\nInvasive, expensive, radiation exposure\nTDE\nNoninvasive, cheap especially without contrast agents,\nOnly regional flow velocity, mainly in the LAD is measured (lower feasibility of flow imaging in Cx and RCA), Difficult measurement of volumetric (absolute) coronary flow\nPET – positron emission tomography, TDE-transthoracic Doppler echocardiography\nBecause of the clinical importance of CFR there is a need for a simple, non-invasive, repeatable and inexpensive tool capable of this functional evaluation. The value of absolute coronary blood flow may be substituted by the value of coronary blood flow velocity [\n3\n-\n6\n] measurable by Doppler technique not only invasively but also using a non-invasive approach (figure \n1\n,\n2\n,\n3\n). The present review discusses the assessment of CFR using transthoracic Doppler echocardiography, a technique which has been validated in a series of clinical studies [\n1\n,\n5\n,\n7\n-\n23\n]. Recently the usefulness of transthoracic Doppler echocardiography to assess CFR has been reported in various clinical settings in a large general referral population. The method provides reliable measurements of CFR in the distal or middle segment of left anterior descending coronary artery (LAD), using pulsed wave Doppler echocardiography under the guidance of color Doppler flow mapping. The development of the transthoracic imaging technique (exploring various transducer beam orientations) extended the possibilities of imaging blood flow in the circumflex coronary artery [\n1\n] and right coronary artery (RCA) [\n24\n-\n26\n]. As regards the transthoracic Doppler assessment of CFR in the RCA we are able to measure the coronary flow velocity in proximal RCA and in its distal branch i.e. right posterior descending artery. Due to the fact that most relevant RCA stenoses are located proximal to the crux cordis the assessment of CFR in the right posterior descending artery usually provide post-stenotic values. The feasibility of CFR measurement with transthoracic Doppler echocardiography is improved by contrast enhancement combined with second-harmonic imaging technique. Consequently, in some reports the feasibility of transthoracic Doppler echocardiography to assess CFR achieved 100% [\n7\n,\n9\n].\nFigure 1\nLeft main stem coronary artery and proximal segment of LAD in color-coded transthoracic Doppler echocardiography.\nFigure 2\nSpectral Doppler coronary blood flow by sampling in proximal segment of LAD.\nFigure 3\nDirect visualization of coronary artery stenosis. The portion of mid segment of LAD with color mosaic (a sign of high-velocity, turbulent flow) at stenotic site.\nReview\nClinical Application\nThere are two most relevant clinical application of transthoracic Doppler echocardiography to assess reduced CFR due to: stenosis of epicardial LAD and impairment of coronary microvascular vasodilatation.\nCoronary angiography provides a limited insight into the physiological significance of coronary stenoses. Therefore, the CFR is a useful parameter in the several important clinical setting summarized in table \n2\n.\nTable 2\nCRF for assessment of epicardial coronary artery stenosis\n• Functional assessment of intermediate stenosis (40–70%)\n• Detection of critical stenosis (>90%)\n• Combined assessment of coronary flow and wall motion\n• Monitoring the changes of CFR in the early, post-PTCA period to detect artery occlusion, microvascular stunning\n• Serial CFR examination after PTCA to predict restenosis\n• Postinfarction coronary flow reserve assessment\n• Assessment of coronary graft patency\nFunctional assessment of intermediate stenosis (40–70%)\nUnderstanding the functional impact of stenosis is important for clinical decision making (for example to refer or defer patients with intermediate stenosis to percutaneous transluminal coronary angioplasty [PTCA]). The treatment of patients with moderate stenoses is challenging, and CFR measured distally to stenosis precisely defines the hemodynamic significance of stenosis. In studies using transthoracic Doppler echocardiography, CFR <2 is associated with stress-induced ischemia [\n11\n,\n27\n] and reduced CFR is considered as manifestation of functionally important stenosis even if coronary angiography reveals intermediate severity [\n7\n-\n9\n,\n16\n]. In contrast, in patients with intermediate stenosis but an adequate CFR value, PTCA can be safely deferred. The measurement of CFR by transthoracic Doppler echocardiography provides data equivalent to those obtained by thallium-201 scintigraphy for physiologic estimation of the severity of LAD stenosis [\n11\n,\n27\n].\nDetection of critical stenosis (>90%)\nUsing transthoracic Doppler echocardiography it is possible to detect severe LAD stenosis >90%. The CFR <1, suggesting coronary steal may be a predictor of critical coronary stenosis [\n23\n]. Coronary steal is defined as a decrease of CFR to a certain vascular region in favor of another area during maximal coronary vasodilatation, that is, CFR <1.\nCombined assessment of coronary flow and wall motion\nThe CFR findings is additive and complementary to the information provided by 2DE on regional wall motion abnormalities. Combined assessment of CFR and wall motion was performed dipyridamole echocardiographic stress test. According to data from Rigo et al. report [\n28\n] coronary flow and contractile function of myocardium can be complementary in terms of predicting underlying angiographic anatomy, because abnormal wall motion can include coronary artery disease, and negative CFR can exclude it. In this study, sensitivity for detecting LAD disease was 74% for 2-dimensional echocardiography and 81% for CFR <1.9 specificity was 91% for 2-dimensional echocardiography and 84% for CFR. Accuracy was 86% for 2-dimensional echocardiography and 83.5% for CFR. When 2-dimensional echocardiography and CFR criteria were considered, sensitivity increased to 93%, with 80.6% specificity. The recent, ground-breaking findings of Rigo et al [\n28\n] have already been confirmed by other studies from Argentina [\n29\n] and Japan [\n30\n], consistently showing that CFR, when assessed simultaneously with regional wall motion during dipyridamole stress-echocardiography, increase the sensitivity of the test, particularly in patients who are receiving beta-blockers or in patients with single vessel LAD disease, i.e., patients who are more likely to have false negative tests.\nMonitoring the changes of CFR in the early, post-PTCA period to detect artery occlusion, microvascular stunning\nIntracoronary Doppler has been introduced to optimize the results of PTCA [\n31\n-\n33\n] but it has shown a surprisingly high rate of impaired CFR after balloon angioplasty or stenting, even in the absence of any residual angiographic stenosis [\n34\n-\n36\n]. This phenomenon may be explained by the two following theories. Firstly, PTCA may induce microvascular stunning due to microembolization, thrombogenicity (by thrombin release) and vasoconstriction (by endothelin release). Alternatively, temporary reactive hyperemia, where high post-ischemic baseline flow velocity masks normal reserve. Invasive CFR is obtained after multiple balloon inflations, injection of contrast agent and administration of vasoactive drugs that may produce immediate post-procedural vasomotion instability. For these reasons, the measurement of CFR should be delayed several days after PTCA. At this time, the influence of pharmacological, metabolic, humoral or myogenic factors affecting coronary flow autoregulation is negligible, possibly explaining the lower rate of post-procedural impaired CFR in a recent study using transthoracic Doppler echocardiography [\n23\n]. The noninvasive, repeatable, inexpensive and accessible transthoracic Doppler echocardiography is especially helpful in this clinical setting. Early reoclussion of the coronary artery is another complication after PTCA detectable by transthoracic Doppler echocardiography.\nSerial CFR examination after PTCA to predict restenosis\nSerial CFR examination after PTCA may be also feasible in mid- and long-term follow-up to monitor restenosis [\n37\n,\n38\n]. The decrease of CFR <2 during follow-up was proposed as a sensitive and specific predictor of restenosis [\n37\n,\n38\n]. This method may be complementary to exercise test, or may be its substitute if patients are unable to perform adequate exercise test.\nInstead of CFR measurements distally to stenosis another methods has been developed to detect restenosis after PTCA. In some patients direct imaging of the stenosis/restenosis site in LAD is possible if a sufficiently long portion of LAD is visible [\n39\n,\n40\n]. The (re)-stenotic site is identified as localized color aliasing corresponding to local flow acceleration with turbulences. It is proposed to quantify the severity of restenosis by measuring the increase of coronary blood flow velocity (ratio of pre-stenotic to stenotic velocities) [\n39\n,\n40\n].\nPostinfarction CFR assessment\nThere are several recent reports concerning the value of CFR measured transthoracically after reperfused acute anterior myocardial infarct [\n41\n,\n42\n]. In the study of Ueno et al. [\n41\n] the decreased CFR <1,5 was identified to predict an increase in left ventricular volume (remodeling) after reperfused myocardial infarct. A significant negative correlation was found between CFR and progression of left ventricular dilatation at 6-month follow-up. In the study of Colonna et al [\n42\n] it was shown that preconditioning due to preinfarction angina had a protective role on microvascular function as demonstrated by CFR preservation (>2,5) after myocardial infarct.\nAssessment of coronary graft patency\nAnother application of transthoracic Doppler echocardiography is the assessment of the patency of internal mammary artery and saphenous vein to coronary artery grafts [\n12\n,\n43\n]. In the largest study [\n43\n] the identification rate for mammary artery grafts was 100%, for saphenous vein grafts to LAD coronary artery 91%, for the vein grafts to the right coronary artery 96% and for the vein grafts to circumflex artery 90% [\n43\n]. CFR <1,9 had 100% sensitivity, 98% specificity for mammary artery graft stenosis [\n43\n]. CFR <1,6 had 91% sensitivity, 87% specificity for significant vein graft stenosis [\n43\n].\nImpairment of coronary microvascular vasodilatation\nThe second application of transthoracic Doppler echocardiography is the detection of reduced CFR due to impaired microvascular vasodilatation despite angiographically normal epicardial coronary arteries. It is well known that several diseases such as hypertrophy (due to aortic stenosis, hypertrophic cardiomyopathy, hypertension), diabetes mellitus, smoking, menopause cause structural and/or functional abnormalities in the microcirculation. The invasive Doppler measurement of CFR is not routinely performed in patients with chest pain and normal coronary arteries. Therefore, the extent of such microvascular disease appears to be underestimated. Accordingly, recent studies [\n4\n,\n44\n]. have demonstrated that up to 50% of the patients with chest pain and normal or near normal coronary angiograms have reduced CFR. Noninvasive assessment of CFR using transthoracic Doppler echocardiography has been performed in patients with hypertrophic cardiomyopathy [\n45\n], aortic stenosis [\n46\n] and smokers (both active and passive) [\n17\n]. In these studies CFR was measured using adenosine (standard vasodilator to test endothelium-independent vasodilatation). In patients with hypertrophic cardiomyopathy additionally the vasomotor response to stressors testing endothelium-dependent vasomotion was studied [\n18\n-\n22\n,\n47\n]. Cold pressor test [\n20\n,\n21\n], handgrip [\n22\n,\n47\n] and pacing [\n19\n] was used as stressing stimuli. Importantly, the noninvasive approach provides an opportunity to assess asymptomatic patients [\n18\n,\n20\n] and to recruit healthy subjects to form adequate control groups [\n13\n,\n18\n,\n19\n,\n21\n,\n22\n], which is impossible in an invasive study. Additionally, the effect of physiological hypertrophy on CFR is measurable by transthoracic Doppler echocardiography [\n13\n], which could prove useful in differentiating athlete's hypertrophic heart – in which CFR is in normal to supranormal range – from hypertrophic cardiomyopathy, in which CFR is markedly attenuated.\nMoreover, noninvasive transthoracic Doppler echocardiography allows for serial CFR evaluations to explore the effect of various pharmacological therapies [\n18\n] or to assess effect of aortic valve replacement for aortic stenosis [\n19\n-\n22\n].\nThe clinical applications of CFR measurement are summarized in table \n3\n.\nTable 3\nProposed scheme of application of transthoracic Doppler echocardiography (with or without wall motion assessment) in diagnosis of epicardial or microvascular coronary vessel disease\nBefore coronary angiography (nondiagnostic or equivocal exercise stress ECG)\n• Suspected epicardial coronary stenosis (LAD, Cx, RCA)\n• Suspected microvascular abnormalities\n (young patients with chest pain despite no risk factor for epicardial CAD)\n1. WM (LV global) assessment (if negative)\nCFR in LAD\n2. CFR (regional assessment of LAD)\nAfter coronary angiography\nAbnormal coronary angiogram\nNormal coronary angiogram\n• Functional assessment of intermediate stenosis\n• Confirmation or exclusion of\n microvascular dysfunction in patients with chest pain\n1. Flow acceleration at stenotic site (if not possible)\nCFR\n2. Dual assessment of WM + CFR\nControl during follow-up after initial coronary angiogram\n• Patients deferred from PTCA due to intermediate stenosis\n• Verify the benefit of pharmacological interventions\n• Patients with suspected restenosis\n1. Flow acceleration at stenotic site (if not possible)\nCFR\n2. Dual assessment of WM + CFR\nWM – wall motion, LV – left ventricular\nChoosing the appropriate stimuli\nThere are two pharmacological vasodilators: adenosine and dipyridamole used to recruit CFR. Both agents are compared in table \n4\n. Both adenosine and dipyridamole have an advantage over exercise and dobutamine, which are submaximal stimuli for coronary flow reserve and are more technically demanding for imaging of CFR [\n1\n,\n48\n].\nTable 4\nComparison between adenosine and dipyridamole\nAdenosine\nDipyridamole\nDosage\nIntravenous (i.v.) – 140 μg/kg/min\nIntravenous – 0,56–0,84 mg/kg\nDuration of action\n30 sec\n30 min\nTime to max. effect\n30–55 sec\n6–16 min\nAdvantage\nShort action, short-lasting adverse effects\nprolonged action allow to assess CFR and wall motion abnormalities during single examination\nDisadvantage\nAV conduction delay (including complete heart block), Hyperventilation, hypotension, flushing, headache,\npossibility of antidote-resistance prolonged ischemia, hypotension, flushing, headache, hyperventilation,\nLimitations of transthoracic Doppler echocardiography measurement of CFR\nAbsolute volumetric flow versus flow velocity\nAlthough the left anterior descending artery was detected with combined Doppler and two-dimensional imaging, the images were not of sufficient clarity to allow for accurate measurement of the vessel diameter in a substantial portion of the examined subjects. Without estimation of the coronary artery diameter we can measure changes only in coronary blood flow velocity, but not changes in coronary blood flow. Therefore CFR assessment by transthoracic Doppler echocardiography is limited to measurements of coronary blood flow velocity in majority of studies. However, it has been shown that CFR measured using both parameters is closely correlated (1–4). Moreover, even in large invasive studies DEBATE [\n49\n] and DESTINI [\n31\n,\n33\n] the CFR derived from changes only in the velocity of coronary blood flow was accepted instead of the absolute coronary blood flow, which is measurable during invasive studies.\nRegarding the accuracy of transthoracic Doppler measurement of CBFV, its comparison with intracoronary measurement provided a highly satisfying correlation between non-invasive and invasive measurements [\n7\n,\n14\n].\nContrast enhancement versus non-contrast study: learning curve and cost-effectiveness\nAnother limitation is the feasibility of transthoracic coronary blood flow velocity measurement. In assessment of coronary flow in LAD, the learning curve effect was seen in most centers in which contrast agents were not used. In studies by Shapiro and coworkers, which were initiated in the beginning of the 90s, the capacity of detecting coronary flow increased from 34% to 77% [\n10\n,\n46\n,\n50\n,\n51\n]. Voci and coworkers were able to increase the capacity of coronary blood flow imaging from 76% [\n52\n] to 96% [\n23\n]. This result is fully comparable with the results of studies using contrast agents. In personal studies the capacity of detection increased with time and experience from 71% to 87% [\n18\n,\n20\n,\n21\n]. Only Hozumi et al. [\n15\n] achieved a very high feasibility of coronary flow imaging already in their first study, i.e. 94%. This limitation may be minimized by using echo-contrast agents enhancing Doppler signal intensity [\n7\n], which are however expensive. As regard cost-effectiveness balance it was calculated [\n23\n] that using 90-s noncontrast/adenosine vasodilator approach the cost of the test was 14 times less expense than 7-min contrast-enhanced approach. As regard vasodilator agents, dipyridamole is cheaper than adenosine and therefore the best cost-effectiveness profile is achieved with dipyridamole stress without contrast enhancement.\nPitfalls and trouble-shooting\nCFR must be measured distally to stenosis, because erroneous CFR assessment at stenosis site is underestimated due to increased baseline flow velocity. Additionally, the flow in LAD branches could be erroneously interpreted as the flow in LAD main trunk.\nConclusions\nTransthoracic Doppler echocardiography is rapidly gaining appreciation as popular tool to measure CFR both in stenosed and normal epicardial coronary arteries (predominantly in left anterior descending coronary artery). Post-stenotic CFR measurement is helpful in: functional assessment of moderate stenosis, detection of significant or critical stenosis, monitoring of restenosis after revascularization. In the absence of stenosis in the epicardial coronary artery, decreased CFR enable to detect impaired microvascular vasodilatation in: reperfused myocardial infarct, arterial hypertension with or without left ventricular hypertrophy, diabetes mellitus, hypercholesterolemia, syndrome X, hypertrophic cardiomyopathy. In these diseases, noninvasive transthoracic Doppler echocardiography allows for serial CFR evaluations to explore the effect of various pharmacological therapies.\nList of Abbreviations\nCFR – coronary flow reserve\nLAD – left anterior descending coronary artery\nRCA – right coronary artery\nPTCA – percutaneous transluminal coronary angioplasty\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** definitely relevant"
}
] |
definitely relevant
|
95
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nA simple statistical model for prediction of acute coronary syndrome in chest pain patients in the emergency department\n\n**Article Abstract:**\n\nBackground\nSeveral models for prediction of acute coronary syndrome (ACS) among chest pain patients in the emergency department (ED) have been presented, but many models predict only the likelihood of acute myocardial infarction, or include a large number of variables, which make them less than optimal for implementation at a busy ED. We report here a simple statistical model for ACS prediction that could be used in routine care at a busy ED.\nMethods\nMultivariable analysis and logistic regression were used on data from 634 ED visits for chest pain. Only data immediately available at patient presentation were used. To make ACS prediction stable and the model useful for personnel inexperienced in electrocardiogram (ECG) reading, simple ECG data suitable for computerized reading were included.\nResults\nBesides ECG, eight variables were found to be important for ACS prediction, and included in the model: age, chest discomfort at presentation, symptom duration and previous hypertension, angina pectoris, AMI, congestive heart failure or PCI/CABG. At an ACS prevalence of 21% and a set sensitivity of 95%, the negative predictive value of the model was 96%.\nConclusion\nThe present prediction model, combined with the clinical judgment of ED personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.\n\n**Article Body:**\n\nBackground\nUnstable angina pectoris and acute myocardial infarction (AMI), together denoted acute coronary syndrome (ACS), are consequences of acute coronary artery disease with myocardial ischemia. Despite considerable progress in the treatment of ACS with antithrombotic drugs and catheter-based interventions (balloon angioplasty), the ability to diagnose ACS in the emergency department (ED) remains relatively poor. Since missed cases of ACS carry a high morbidity and mortality from heart failure and arrhythmia, the number of \"rule-out\" admissions are high, and some 7 or more out of 10 patients admitted with the suspicion of ACS do no not have it [\n1\n,\n2\n]. This large overadmission implies a unsatisfactory quality of care for the patients and a high cost for the health care system [\n3\n,\n4\n]. To improve the situation, new diagnostic methods such as immediate stress tests [\n5\n], myocardial perfusion imaging [\n6\n], echocardiography [\n7\n], and new blood tests have been suggested. In addition, decision support tools in the form of prediction models have been developed to help the physician handle the clinical information, and thereby to better triage and treat the patient. A large number of such models have been presented [\n8\n-\n24\n], and most of them have been focused on the detection of AMI. With the current ACS paradigm, however, models that predict the probability of AMI are less useful in routine ED care, where the likelihood of ACS (rather than AMI) is normally decisive for admission or discharge, and for immediate treatment. Also, many of these models need substantial input from the ED personnel [\n8\n-\n12\n,\n18\n], and hence are not ideally suited for implementation in standard care at a busy ED. Only one previous model, the ACI-TIPI [\n14\n], has been both easy to use and predictive of ACS.\nThe aim of this study was to develop a simple statistical model, based on ECG and clinical data available immediately at presentation, which predicts the likelihood for ACS among chest pain patients in the ED. The intention was to include ECG data in the form of simple amplitude measurements to allow for machine reading. A prediction model of this type could form the basis for development of a user-friendly decision support system for ED personnel.\nMethods\nSetting and patient material\nLund University Hospital, Sweden, is a 1200 bed institution which serves as the primary hospital for some 250,000 inhabitants, has a cardiac intensive care unit with 19 beds and an intermediate care ward with ECG monitoring at 19 beds. Percutaneous coronary intervention (PCI) and coronary bypass surgery (CABG) are available 24 hours/day. There is a traditional ED with approximately 50000 patients per year. During the patient inclusion period, there was no systematic diagnostic protocol for patients with suspected ACS, and no dedicated chest pain unit.\nSix hundred and sixty-five consecutive visits for chest pain for which electronic ECG data could be retrieved were retrospectively included at the ED of Lund University Hospital from July 1 to November 20, 1997. Characteristics of the 634 unique patients are presented in table \n1\n. From the clinical data collected for each patient, 18 variables available immediately at ED presentation (table \n1\n) were chosen for further study based on their likely importance for ACS prediction.\nTable 1\nCharacteristics of patients who come to the emergency department with acute chest pain, due to acute coronary syndrome (ACS; n = 130) or other causes (n = 504).\nACS\n n (%)\nOther causes\n n (%)\nOR\n95% CI\nAge\n ≥ 80 years\n35 (26.9)\n86 (17.1)\n10\n2.9 – 34\n 70 – 79 years\n39 (30.0)\n103 (20.4)\n9.3\n2.8 – 31\n 60 – 69 years\n26 (20.0)\n98 (19.4)\n6.5\n1.9 – 22\n 50 – 59 years\n22 (16.9)\n89 (17.7)\n6.1\n1.8 – 21\n 40 – 49 years\n5 (3.8)\n54 (10.7)\n2.3\n0.52 – 10\n < 40 years\n3 (2.3)\n74 (14.7)\n1.0\n-\nMale\n83 (63.8)\n279 (55.4)\n1.4\n0.96 – 2.1\nSmoking status\n Current\n29 (22.3)\n98 (19.4)\n1.3\n0.78 – 2.3\n Former\n50 (38.5)\n155 (30.8)\n1.5\n0.91 – 2.3\n Unknown\n12 (9.2)\n74 (14.7)\n0.74\n0.36 – 1.5\n Non-smoker\n39 (30.0)\n177 (35.1)\n1.0\n-\nHypertension\n Yes\n47 (36.2)\n114 (22.6)\n2.0\n1.3 – 3.0\n Unknown\n8 (6.2)\n27 (5.4)\n1.4\n0.63 – 3.3\n No\n75 (57.7)\n363 (72.0)\n1.0\n-\nDiabetes\n19 (14.6)\n57 (11.3)\n1.3\n0.77 – 2.4\nAngina pectoris\na\n Yes, ≤ 1 month\n4 (3.1)\n5 (1.0)\n3.8\n1.0 – 15\n Yes, > 1 month\n56 (43.8)\n174 (34.5)\n1.5\n1.0 – 2.3\n No\n68 (53.1)\n325 (64.5)\n1.0\n-\nCongestive heart failure\n20 (15.4)\n79 (15.7)\n0.98\n0.57 – 1.7\nPrevious myocardial infarction\n Yes, ≤ 6 months\n13 (10.0)\n19 (3.8)\n3.2\n1.5 – 6.8\n Yes, > 6 months\n37 (28.5)\n107 (21.2)\n1.6\n1.0 – 2.6\n No\n80 (61.5)\n378 (75.0)\n1.0\n-\nPrevious PCI\n4 (3.1)\n21 (4.2)\n0.73\n0.25 – 2.2\nPrevious CABG\n10 (7.7)\n55 (10.9)\n0.68\n0.34 – 1.4\nTreated with cardiac drugs\nb\n85 (65.4)\n282 (56.0)\n1.5\n0.99 – 2.2\nChest discomfort at presentation\n85 (65.4)\n238 (47.2)\n2.1\n1.4 – 3.2\nSymptom duration\nc\n 0 – 6 h\n100 (76.9)\n261 (52.0)\n5.4\n2.7 – 11\n 7 – 12 h\n16 (12.3)\n59 (11.8)\n3.8\n1.6 – 8.8\n 13 – 24 h\n4 (3.1)\n42 (8.4)\n1.3\n0.40 – 4.5\n > 24 h\n10 (7.7)\n140 (27.9)\n1.0\n-\nTachypnea\n13 (10.0)\n27 (5.4)\n2.0\n0.98 – 3.9\nLung rales\n12 (9.2)\n23 (4.6)\n2.1\n1.0 – 4.4\nSystolic bp < 100 mmHg\nd\n4 (3.1)\n4 (0.8)\n3.9\n0.97 – 16\nDiastolic bp < 70 mmHg\ne\n16 (12.9)\n36 (7.3)\n2.0\n1.0 – 3.7\nHeart rate\nf\n > 120 bpm\n4 (3.1)\n12 (2.4)\n1.3\n0.41 – 4.1\n < 50 bpm\n3 (2.3)\n10 (2.0)\n1.2\n0.32 – 4.3\n 50 – 120 bpm\n123 (94.6)\n480 (95.6)\n1.0\n-\na \nData on angina pectoris were missing for two patients with ACS.\nb \nACE-inhibitors, ASA, Calcium antagonists, Betablockers, Long-acting Nitrates or Diuretics.\nc \nData on symptom duration were missing for two patients without ACS.\nd \nData on systolic blood pressure were missing for 8 patients (one with and 7 without ACS).\ne \nData on diastolic blood pressure were missing for 15 patients (6 with and 9 without ACS).\nf \nData on heart rate were missing for 2 patients without ACS.\nReference standard\nThe ED visit ended in hospitalization in 422 (67%) cases, and among these a discharge diagnosis of ACS was assigned in only 130 (31%), of which 28 (22%) had Q-wave AMI, 53 (41%) had non-Q-wave AMI and 49 (38%) unstable angina. Discharge diagnoses were made by the senior ward physician or the ED physician (in cases discharged from the ED), reviewed by a senior research nurse, and when ambiguous, further reviewed by a senior cardiologist (HÖ). In the review of diagnoses for cases discharged from the ED, available data from the patient records indicated that the rate of missed diagnosis of ACS was low (not more than 2%). AMI was defined by the WHO criteria [\n25\n] where the biochemical criterion was at least one measurement of CK-MB>10 μg/l or Troponin T>0.1 μg/l. The criteria for unstable angina were ischemic symptoms (chest pain >15 min., syncope, acute heart failure or pulmonary edema) together with at least one of the following: a) Electrocardiogram (ECG) changes: transient or persisting ST segment depression (≥ 1 mm) and/or T-wave inversion (≥ 1 mm) without developing Q waves or loss of R wave height, or b) Biochemical markers: CK-MB 5–10 μg/l or Troponin T 0.05–0.1 μg/l.\nThis study was approved by the Lund University Research Ethics Committee.\nElectrocardiogram\nTwo methods of ECG analysis were used, machine reading and expert reading.\nMachine reading\nThe 12-lead ECGs were recorded by the use of computerized ECG recorders (Siemens-Elema AB, Solna, Sweden). The ECG measurements were obtained from the measurement program of the ECG recorders. From the leads I, aVF and V2, the two measurements ST-J amplitude and ST amplitude 3/8 were selected for further analysis. These measurements were selected to detect ST-elevation patterns caused by ischemia in the anterior, septal, inferior or lateral wall. The ST amplitude 3/8 was obtained by dividing the interval between ST-J point and the end of the T wave into eight parts of equal duration. The amplitudes at the end of the third interval were denoted ST amplitude 3/8. ECG data were entered in the logistic regression models as categorical variables, with the grouping defined in Table \n2\n. The categorisation was based on widely used ECG criteria for ST-elevation and depression [\n26\n].\nTable 2\nCharacteristics of the electrocardiogram for patients who come to the emergency department with acute chest pain, due to acute coronary syndrome (ACS; n = 130) or other causes (n = 504). I-STamp, ST amplitude in lead I; aVF-STamp, ST amplitude in lead aVF; V2-STamp, ST amplitude in lead V2; STamp38, ST amplitude at the end of the third out of eight equal intervals between the ST-J point and the end of the T wave.\nACS\n n (%)\nOther causes\n n (%)\nOR\n95% CI\nI-Stamp\n I-STamp > 50 and I-STamp38 > I-STamp\n7 (5.4)\n12 (2.4)\n2.4\n0.94 – 6.3\n I-STamp < -100 and I-STamp38 < I-STamp\n7 (5.4)\n6 (1.2)\n4.9\n1.6 – 15\n None of above\n116 (89.2)\n486 (96.4)\n1.0\n-\naVF-STamp\na\n aVF-STamp > 100 and aVF-STamp38 > aVF-STamp\n13 (10.1)\n4 (0.8)\n14\n4.6 – 45\n aVF-STamp < -100 and aVF-STamp38 < aVF-STamp\n4 (3.1)\n3 (0.6)\n5.9\n1.3 – 27\n None of above\n112 (86.8)\n497 (98.6)\n1.0\n-\nV2-STamp\nb\n V2-STamp > 200 and V2-STamp38 > V2-STamp\n17 (13.2)\n27 (5.4)\n3.0\n1.5 – 5.7\n 100 < V2-STamp ≤ 200 and V2-STamp38 > V2-STamp\n26 (20.2)\n95 (18.9)\n1.3\n0.78 – 2.1\n V2-STamp < -100 and V2-STamp38 < V2-STamp\n6 (4.7)\n5 (1.0)\n5.6\n1.7 – 19\n None of above\n80 (62.0)\n376 (74.8)\n1.0\n-\na \nOne patient with ACS had missing value on aVF-STamp.\nb \nTwo patients (one with and one without ACS) had missing value on V2-STamp.\nExpert reading\nFor comparison, ECG for 628 of the 634 unique patients were retrieved at a later point in time, and 608 of these ECGs were possible to assess. Two physician experts first classified the 608 ECGs, which originated from 120 patients with ACS and 488 patients without ACS, independently of each other and then agreed on a consensus classification using four categories (\"ACS and Transmural ischemia (TMI)\", \"ACS but not TMI\", \"Probably ACS\", and \"No signs of ACS\"). The experts did not strictly apply conventional criteria such as ST-segment elevation of >0.1 mV in two adjacent limb leads or >0.2 mV in two adjacent precordial leads. Instead, they also considered the configuration of the ST-segment and the shape of the QRS complex, i.e. a pattern recognition analysis was applied as in the clinical routine interpretation of ECGs.\nStatistical analyses\nThe statistical analyses were conducted using SPSS release 12.0.1 (SPSS Inc, Chicago, U.S.). Odds ratios (OR) were calculated for the association between each potential risk factor and ACS. We regarded 95% confidence intervals (CIs) that excluded unity, or, equivalently, p < 0.05, as statistically significant. In the multivariable analysis, the probability of ACS was predicted using multiple logistic regression [\n27\n]. All independent variables except age were entered in the regression models as categorical variables, categorized as shown in tables \n1\n, \n2\n. In order to obtain meaningful baseline odds for ACS in the models, we chose 40 years old as reference value for age. Thus, we used the number of years above 40 as age variable in the models and allowed for both positive (patients above 40) and negative (patients below 40) numbers. Starting with the full multivariable model with all independent variables included, we excluded one insignificant independent variable at a time, starting with the variable with highest p-value, until only significant and important predictors remained. Categorical variables with more than two categories were kept in the model if the OR associated with any of the categories was significant. Variables with estimated OR of at least 2.5 (or, equivalently, at most 0.4) were considered as important predictors and thus kept in the model even if they were not statistically significant. The ECG variables were not considered for exclusion. For the final set of independent variables, categories with ORs close to one were collapsed with the reference category for that variable. Unknown response to one of the variables (hypertension) was also added to the reference category. We then assessed the significance of the interaction with age, implemented as cross-product terms together with main effects, for the following variables: sex, chest discomfort at presentation, symptom duration, and previous myocardial infarction. For comparison, we also established a prediction model where we replaced the ST amplitude characteristics of the ECG with the consensus ECG assessments by the two experts (LE and HÖ). Differences in specificity between the two models were tested using McNemar's test for correlated proportions.\nThe area under the receiver-operating-characteristic curve (ROC) was used as an overall measure of the discrimination abilities of the prediction models [\n28\n]. The area under ROC, measured in percent, can be interpreted as the probability that a randomly chosen patient with ACS has a higher outcome probability than a randomly chosen patient without ACS. For calculation of specificity and predictive values, the sensitivity was set to 95%. This somewhat arbitrary level was chosen because with current standard evaluation, some 2–5% of the ACS patients are erroneously discharged from the ED [\n29\n,\n30\n], which implies a sensitivity of at least 95 % for the routine ED work-up. In order to get more correct estimates of the generalization performance, i.e. the performance of the prediction models on an unseen study population, we used a \nk\n-fold cross-validation procedure [\n31\n]. Here we repeated times estimated the regression parameters based on randomly chosen training sets, comprising approximately 80% of all patients, and then evaluated the obtained model by calculating the area under ROC as well as the specificity at 95% sensitivity among the remaining 20% patients in a validation set kept completely isolated from the corresponding training set. This \nk\n-fold cross-validation procedure was implemented as follows: 1) the data set was randomly split in 5 groups of approximately equal size 2) the parameters of each model were estimated based on the patients of the training set only, which was established by excluding group \nk \n[\nk \n= 1, 2, ...., 5] 3) the group left out from parameter estimation was used as a validation set. We repeated the steps 1–3 above 20 times, which implied 20 * 5 = 100 sets of validations sets, 100 areas under ROC, and 100 estimates of the specificity at 95% sensitivity. Median values, together with 2.5 – 97.5 percentiles, from these 100 validation sets were used as measures of the generalization performance of the prediction models.\nResults\nWhen each potential risk factor was considered separately, significant associations with ACS were observed for age, hypertension, previous myocardial infarction, chest discomfort at presentation, and symptom duration (table \n1\n). Associations with ACS were also indicated for gender, angina pectoris, treatment with cardiac drugs, tachypnea, lung rales, and blood pressure, whereas no clear associations with smoking status, diabetes, congestive heart failure, previous PCI, previous CABG and heart rate were discerned. All ECG characteristics, ST amplitudes in leads I, aVF and V2, were markedly associated with ACS (table \n2\n).\nMany of the potential risk factors were strongly interrelated. In the multivariable analysis, older age, hypertension, angina pectoris, previous myocardial infarction, chest discomfort at presentation, short symptom duration, and abnormal ECG characteristics were associated with increased ACS risk (Table \n3\n). Moreover, congestive heart failure and previous CABG were inversely associated with ACS. The prediction model based on these variables yielded a high discrimination percentage (area under ROC 80.6%; figure \n1\n). For this model, hospitalizing all patients with a probability of ACS of at least 8.6%, corresponding to 65% of all patients, would yield a sensitivity of 95% and a specificity of 43%. This sensitivity-specificity pair would, with an ACS prevalence of 21% like in the present material, produce a negative predictive value (NPV) of 97% and a positive predictive value (PPV) of 30%. Adding the interaction terms related to age did not lead to any significant improvement of the model (results not shown).\nTable 3\nMultiple logistic regression model based on ECG and other clinical characteristics of patients (n = 627\na\n) who come to the emergency department with acute chest pain and acute coronary syndrome (ACS). I-STamp, ST amplitude in lead I; aVF-STamp, ST amplitude in lead aVF; V2-STamp, ST amplitude in lead V2; STamp38, ST amplitude at the end of the third out of eight equal intervals between the ST-J point and the end of the T wave.\nEstimate\n95% CI\nBaseline odds for ACS\nb\n0.0163\n0.0073 – 0.0362\nOdds ratios\n Age (no. of years above 40)\n1.031\n1.014 – 1.047\n Hypertension\n1.7\n1.1 – 2.8\n Angina pectoris ≤ 1 month\n4.1\n0.97 – 17\n Congestive heart failure\n0.48\n0.24 – 0.94\n Previous myocardial infarction\n Yes, ≤ 6 months\n2.7\n1.2 – 6.4\n Yes, > 6 months\n2.1\n1.2 – 3.8\n No\n1.0\n-\n Previous CABG\n0.23\n0.09 – 0.60\n Chest discomfort at presentation\n1.9\n1.2 – 3.1\n Symptom duration\n 0 – 6 h\n3.8\n2.0 – 7.1\n 7 – 12 h\n2.8\n1.2 – 6.5\n > 12 h\n1.0\n-\n I-Stamp\n I-STamp > 50 and I-STamp38 > I-Stamp\n2.4\n0.74 – 7.7\n aVF-Stamp\n aVF-STamp>100 and aVF-STamp38>aVF-Stamp\n9.4\n2.7 – 33\n aVF-STamp < -100 and aVF-STamp38 < aVF-STamp\n4.1\n0.72 – 23\n None of above\n1.0\n V2-Stamp\n V2-STamp > 200 and V2-STamp38 > V2-Stamp\n3.4\n1.5 – 7.4\n 100 < V2-STamp ≤ 200 and V2-STamp38 > V2-STamp\n1.6\n0.90 – 2.8\n V2-STamp < -100 and V2-STamp38 < V2-Stamp\n2.6\n0.54 – 13\n None of above\n1.0\n-\na \nData on at least one of characteristics were missing for 7 (4 with ACS and 3 without ACS) of the original 634 patients.\nb \nBaseline odds for ACS for a 40-year old patient who belongs to the reference category with respect to all other characteristics. The corresponding risk (probability) for ACS can be calculated as Odds/(1+Odds).\nFigure 1\nReceiver-operating-characteristic curves (ROCs) for the prediction model with ECG and other clinical characteristics (black curve; area under ROC = 80.6%, n = 627\na\n) and for the prediction model based on expert assessment of the ECG together with clinical characteristics (gray curve; area under ROC = 88.0%, n = 605\nb\n)\n. \na \nData on at least one of the characteristics were missing for 7 (4 with ACS and 3 without ACS) of the original 634 patients. \nb \nData on at least one of the clinical characteristics were missing for 3 (1 with and 2 without ACS) of the 608 patients with ECG assessed by the experts.\nAs an illustration of how the statistical model of table \n3\n can be used, consider patient A, a 72-year old female patient who seeks emergency care with ongoing chest discomfort that has lasted for 7 hours (table \n4\n). She has undergone CABG previously and has had angina pectoris in connection with physical effort the last month. The ECG shows an elevation of the ST-amplitude above 200 in lead V2. The patient is 32 years above our chosen reference value for age (40 years old) and we therefore use 1.031\n72–40 \n= 1.031\n32 \nas age factor. Multiplying the ORs for the risk factors of this patient, the estimated odds for ACS can be obtained as 0.0163 × 1.031\n32 \n× 4.1 × 0.23 × 1.9 × 2.8 × 3.4 ≈ 0.7385. Thus, the estimated probability of ACS for patient A is 0.7385/(1 + 0.7385) ≈ 0.42 = 42%. Patient B is a male 35-year old patient with chest discomfort for the last 72 hours and without any ST-elevations according to the ECG. This patient is 5 years below the reference value for age and we therefore use 1.031\n35–40 \n= 1.031\n-5 \nas age factor. The estimated odds for ACS for patient B is calculated as 0.0163 × 1.031\n-5 \n× 1.9 ≈ 0.0266, which corresponds to a probability of ACS of 0.0266/(1 + 0.0266) ≈ 0.026 = 2.6% (table \n4\n).\nTable 4\nOdds ratios for ACS for two hypothetical patients, A and B, used as examples. Patient A is female, 72 years old, and seeks emergency care with ongoing chest discomfort that has lasted for 7 hours. She has undergone CABG previously and has had angina pectoris in connection with physical effort the last month. The ECG shows an elevation of the ST-amplitude above 200 in lead V2 only. Patient B is male, 35-year old, and with chest discomfort for the last 72 hours but without any ST-elevations according to the ECG.\nModel Estimate\nPatient A\nOR\nPatient B\nOR\nBaseline odds for ACS\n0.0163\n0.00163\n0.00163\nOdds ratios\n Age (no. of years above 40)\n1.031\n72\n1.031\n32\n35\n1.031\n-5\n Hypertension\n1.7\nNo\n1.0\nNo\n1.0\n Angina pectoris ≤ 1 month\n4.1\nYes\n4.1\nNo\n1.0\n Congestive heart failure\n0.48\nNo\n1.0\nNo\n1.0\n Previous myocardial infarction\nNo\n1.0\nNo\n1.0\n Yes, ≤ 6 months\n2.7\n Yes, > 6 months\n2.1\n No\n1.0\n Previous CABG\n0.23\nYes\n0.23\nNo\n1.0\n Chest discomfort at presentation\n1.9\nYes\n1.9\nYes\n1.9\n Symptom duration\n7 hours\n2.8\n72 hours\n1.0\n 0 – 6 h\n3.8\n 7 – 12 h\n2.8\n > 12 h\n1.0\n-\n I-STamp\nNo\n1.0\nNo\n1.0\n I-STamp > 50 and I-STamp38 > I-STamp\n2.4\n aVF-STamp\nNo\n1.0\nNo\n1.0\n aVF-STamp>100 and aVF-STamp38>aVF-STamp\n9.4\n aVF-STamp < -100 and aVF-STamp38 < aVF-STamp\n4.1\n None of above\n1.0\n V2-STamp\n> 200\n3.4\nNo\n1.0\n V2-STamp > 200 and V2-STamp38 > V2-Stamp\n3.4\n 100 < V2-STamp ≤ 200 and V2-STamp38 > V2-STamp\n1.6\n V2-STamp < -100 and V2-STamp38 < V2-STamp\n2.6\n None of above\n1.0\n-\nECG assessments by experts\nThe ECG assessments made in consensus by the two experts were strong predictors of ACS (table \n5\n), yielding an area under ROC of 76.1% with no other variables included in the prediction model. Adding other clinical data yielded markedly higher discriminating percentage (area under ROC 88.0%; table \n6\n and figure 2). For this model, a sensitivity of 95% would yield a specificity of 50%, which at an ACS-prevalence of 21% would produce a NPV of 98% and a PPV of 33%. The specificity in this model (50%) was significantly higher (p = 0.001) than in the model based on ECG amplitude data (43%). The discriminating percentage increased only marginally when the interaction terms related to age were incorporated (area under ROC 88.3%; regression model and ROC curve not shown).\nTable 5\nExpert assessment of the ECG for patients who come to the emergency department with acute chest pain, due to acute coronary syndrome (ACS; n = 120) or other causes (n = 488).\nAssessment\nACS\n n (%)\nOther causes\n n (%)\nOR\n95% CI\nACS and TMI\na\n30 (25.0)\n3 (0.6)\n94\n28 – 320\nACS but not TMI\na\n10 (8.3)\n9 (1.8)\n10\n4.0 – 27\nProbably ACS\n36 (30.0)\n61 (12.5)\n5.6\n3.3 – 9.3\nNo signs of ACS\n44 (36.7)\n415 (85.0)\n1.0\n-\na\nTMI = Transmural ischemia\nTable 6\nMultiple logistic regression model based on expert assessment of the ECG together with clinical characteristics (n = 605)\na \nfor the association between characteristics of ED chest pain patients and acute coronary syndrome (ACS).\nEstimate\n95% CI\nBaseline odds for ACS\nb\n0.0066\n0.0024 – 0.0178\nOdds ratios\n Age (no. of years above 40)\n1.036\n1.016 – 1.057\n Hypertension\n2.3\n1.3 – 4.1\n Angina pectoris ≤ 1 month\n2.8\n0.58 – 14\n Congestive heart failure\n0.55\n0.26 – 1.2\n Previous myocardial infarction\n Yes, ≤ 6 months\n3.4\n1.3 – 8.7\n Yes, > 6 months\n1.9\n0.99 – 3.7\n No\n1.0\n-\n Previous CABG\n0.28\n0.10 – 0.75\n Chest discomfort at presentation\n1.8\n1.0 – 3.1\n Symptom duration\n 0 – 6 h\n4.6\n2.2 – 9.6\n 7 – 12 h\n3.7\n1.4 – 10\n > 12 h\n1.0\n-\n ECG expert assessment\n ACS and TMI\n97\n26 – 360\n ACS but not TMI\n11\n3.5 – 37\n Probably ACS\n5.8\n3.2 – 11\n No signs of ACS\n1.0\n-\na \nData on at least one of characteristics were missing for 3 (1 with and 2 without ACS) of the 608 patients with ECG assessed by the experts.\nb \nBaseline odds for ACS for a 40-year old patient who belongs to the reference category with respect to all other characteristics. The corresponding risk (probability) for ACS can be calculated as Odds/(1+Odds).\nCross-validation\nCross-validating the model including clinical and ECG amplitude data decreased the area under ROC from 80.6% to 76.8% in median (2.5 – 97.5 percentiles 69.1 – 84.1%), and lowered the specificity from 43% to 35% in median (2.5 – 97.5 percentiles 13 – 60%) if the sensitivity was set to 95%. This median specificity at 95% sensitivity would, with a prevalence of ACS of 21%, diminish the NPV from 97% to 96% (2.5 – 97.5 percentiles 91 – 98%) and the PPV from 30% to 27% (2.5 – 97.5 percentiles 22 – 38%). Cross-validating the corresponding model based on expert ECG assessments lowered the area under ROC from 88.0% to 85.7% in median (2.5 – 97.5 percentiles 78.5 – 93.0%). By contrast, the specificity at 95% sensitivity was unchanged (50% in median, 2.5 – 97.5 percentiles 21 – 74%), yielding the same NPV (98% in median; 2.5 – 97.5 percentiles 94 – 98%) and the same PPV (33% in median; 2.5 – 97.5 percentiles 24 – 49%) as before.\nDiscussion\nThe present study was undertaken to develop a simple and user-friendly statistical model for ACS prediction in the ED. The model was developed using logistic regression on clinical and ECG data from chest pain patients at the ED of a university hospital. Simple categorized ECG amplitude data were included, which allows automated ECG reading, makes ACS prediction stable, and makes the model useful for personnel inexperienced in ECG reading. To keep the model simple and immediately usable in the ED, results from blood samples were not included. Besides ECG, the following 8 variables were found to be important for ACS prediction, and included in the model: age, chest discomfort at presentation, symptom duration and previous hypertension, angina pectoris, AMI, congestive heart failure or PCI/CABG. The interaction terms, which involved only clinical characteristics and not the ECG amplitude data, did not improve the performance substantially and were therefore not included in the final model.\nMany of the variables included in the present model have previously appeared in models for AMI or ACS prediction. All previous models have included the ECG, and there is a general consensus that the ECG is the most important clinical variable to predict ACS in the ED [\n32\n,\n33\n]. Most models have also had a factor for previous coronary artery disease, e.g[\n13\n,\n15\n,\n18\n-\n21\n], many have included age[\n12\n,\n14\n,\n18\n,\n19\n,\n23\n] and pain duration [\n12\n,\n14\n,\n18\n,\n23\n], but few have included congestive heart failure [\n19\n] or hypertension [\n18\n]. Other variables that have appeared in previous models are diabetes [\n12\n,\n18\n,\n19\n], sex [\n14\n,\n18\n], pain localization [\n12\n,\n14\n,\n15\n,\n18\n,\n20\n,\n22\n] pain similar to previous angina or AMI [\n15\n,\n18\n], the quality of the pain [\n12\n,\n15\n,\n18\n], and previous use of nitrates [\n18\n,\n20\n]. A systematic review of studies on AMI probability [\n34\n] has shown that additional variables with predictive power may be a third heart sound, hypotension, chest pain reproduced by palpation and positional chest pain.\nWith current standard evaluation in the ED, some 2–5% of the ACS patients are erroneously discharged from the ED [\n29\n,\n30\n], which indicates a sensitivity of at least 95 % for the routine ED work-up. Set to this level of sensitivity, our simple model reached a specificity of about 35%, and a PPV and NPV of 96% and 27%, respectively, in the cross-validation. In the present patient material, a sensitivity of 95% could be reached by admitting all patients with an ACS probability above 8.6%, which would not imply a significant change of the actual admission rate. A PPV of 27% may seem very low, but it is likely at a level similar to that of the ED physician's decision after the current standard ED assessment, where some 70% of those admitted for suspected ACS prove not to have it [\n1\n,\n2\n,\n35\n]. We have been unable to find any published data on the PPV of standard ED assessment for possible ACS. Thus, our model did not seem to perform any better than the average physician, and will therefore likely not be useful for the expert physician in the ED. However, if a simple prediction model with automated ECG reading, like ours, can maintain a NPV of 96% in a larger prospective study, we believe it can be useful in real-life routine care. In addition, in healthcare settings with an ACS prevalence below 21% among chest pain patients [\n2\n,\n36\n], NPV may increase. Seemingly better performances have been reported for previous ACS prediction models [\n8\n,\n12\n,\n14\n,\n24\n], but some of these models were both developed and tested in chest pain populations with clearly higher prevalence of ACS than ours. Further, with the exception of the ACI-TIPI [\n14\n], these models required the input of a large number of variables, and also ECG interpretation by the ED physician.\nThe model in the present study with ECG interpretation by experts had much higher overall discrimination ability (area under ROC) and specificity at 95% sensitivity, whereas its predictive ability was only somewhat better than the model based on ST amplitude data, with PPV and NPV of 33 vs 27% and 96 vs 98%. The significance of these differences, translated into a real-world clinical practice, is probably small. It is worth noting that basing a prediction model only on the categorized ST amplitude data would not yield sufficient predictive power since about half (52%; not in results) of the ACS patients were in fact normal according to the used cut-offs for the ST amplitudes in all three leads (I, aVF and V2). However, the combination of simple categorized ST amplitude data and clinical characteristics resulted in almost as much predictive power as expert interpretation of the entire ECG. Further, since the average ED physician is less experienced in ECG interpretation than our experts, the model with computerized ECG reading is probably a better choice for clinical implementation. ACS prediction will be more stable, and personnel with little or no experience in ECG reading, e.g. triage nurses, can use the model with no loss in predictive power. Incorporating ST amplitude data as numeric measurements rather than as categorizations and then allowing for interaction between the ECG measures would most likely increase the predictive power of the statistical model further. In addition, since we did not test all theoretically possible ECG measurements, it may be that additional ECG variables or combinations of variables could have increased the predictive power of the ECG and the entire model further. An important disadvantage of a more complex prediction model is however that the rationale behind its output will be much more difficult to understand by potential users.\nA model for ACS prediction based on automated ECG reading together with clinical characteristics can probably be applied in many different settings. For the present model, it seems wise to exploit the NPV, since PPV was low at a sensitivity of 95%. If our model can be validated in prospective studies, it is thus probably best used as support for discharging patients in settings where the ACS prevalence is low, e.g. in primary care, in the initial ED triage or in telemedicine situations, where information is limited. It would also seem possible to use the model as support for the early discharge of low risk patients after a brief observation in the ED or in a chest pain unit, or to assist inexperienced junior staff in the ED, as a means to improve quality of care. Adding results of blood samples, repeated ECGs and physician judgment would probably increase NPV to close to 100%. Whatever the use of our model, a good feature is the limited number of variables, which implies a small need for manual input, and an increased likelihood that the model will actually be used in a busy healthcare environment. With the exception of the ACI-TIPI model [\n14\n], the need for a time-consuming large input has been a weak point of several earlier prediction models [\n8\n-\n12\n,\n18\n], where up to 40 questions need to be answered before the model gives decision support. Our model needs answers to 8 questions.\nLimitations of the study\nThe patients included in the present model were retrospectively collected and from one center only. Because of the retrospective nature of the study, there may of course be errors despite a careful collection of all data. For example, the diagnoses of the patients discharged from the ED were not tested with routine post-discharge ECG or blood samples for cardiac markers. Therefore, before clinical implementation, the model clearly needs to be validated prospectively, preferably at multiple centers. An old definition of AMI was used in the present study. Newer definitions of AMI have lower cut-off values for biochemical markers, and some of the unstable angina diagnoses in this study would currently be classified as AMI [\n37\n]. However, the total number of ACS cases would probably be little changed. Furthermore, the baseline risk (odds) for ACS of the model has to be tuned in each population before implementation. Since it is impossible to analyze all information with a potential impact on the likelihood of ACS, it is of course possible that variables in addition to those included in our model could be important for ACS prediction. The size of the sample might also have limited our abilities to detect clinical or ECG characteristics of low prevalence that nevertheless are important for ACS classification.\nConclusion\nPrevious studies have shown that decision support systems are an effective means of improving patient care [\n38\n]. The aim of this study was to create a simple and practical statistical model for ACS prediction that could be used in routine care at a busy ED. The model includes simple ECG data (suitable for computerized reading) and 8 clinical variables and can be used immediately on patient arrival by personnel inexperienced in ECG interpretation. At the set sensitivity of 95% and an ACS prevalence of 21%, the NPV was 96%. We believe that this prediction model, combined with the judgment of trained healthcare personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS. However, the model must be prospectively validated before it can be used in clinical practice.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nAll authors participated in the design of the study. JB performed the statistical analyses and drafted the manuscript. JLF was involved in data acquisition and assisted in drafting the manuscript. MO assisted in the statistical analyses. LE and HÖ performed the ECG assessments. UE coordinated the study team, was involved in data acquisition, and drafted the manuscript. All authors read the manuscript critically and approved the final version.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** definitely relevant"
}
] |
definitely relevant
|
96
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nPrevalence of self-reported hypertension and its relation to dietary habits, in adults; a nutrition & health survey in Greece\n\n**Article Abstract:**\n\nBackground\nHypertension leads to many degenerative diseases, the most common being cardiovascular in origin. This study has been designed to estimate the prevalence of self-reported hypertension in a random nationwide sample of adult Greek population, while focus was set to the assessment of participants' nutritional habits in relation to their hypertension status.\nMethods\nA random-digit dialed telephone survey. Based on a multistage, stratified sampling, 5003 adults (18 – 74 yr) participated (men: 48.8%, women: 51.2%). All participants were interviewed via telephone by trained personnel who used a standard questionnaire. The questionnaire included demographic and socioeconomic characteristics, medical history, lifestyle habits and nutritional assessment.\nResults\nThe prevalence of self-reported hypertension was 13.3% in men and 17.7% in women (P < 0.001). Furthermore, women reported higher values of systolic blood pressure (180 ± 27 mmHg) than men (169 ± 24 mmHg). Positive relationships were found between hypertension status and the prevalence of the rest investigated health conditions (i.e. hypercholesterolaemia, diabetes mellitus, renal failure and obesity). Nutritional assessment showed that consumption of fish, fruits and juices, cereals, and low fat milk and yogurt was significantly higher among hypertensive subjects while the opposite was observed for food items as red meat, pork, egg, pasta and rice, full fat dairy products and desserts.\nConclusion\nHypertension seems to be a serious public health problem in Greece. It is encouraging that hypertensives may have started adopting some more healthy nutritional behaviour compared to normotensive ones. However, they can gain significant benefits regarding to blood pressure control, if they increase the level of compliance with dietary recommendations.\n\n**Article Body:**\n\nBackground\nHigh blood pressure [\n1\n] has been identified as a major risk factor for stroke, congestive heart failure, renal disease and myocardial infarction [\n2\n,\n3\n]. According to World Health Organization the number of people with high blood pressure levels, worldwide, is estimated to be about 600 million and the annual mortality attributable to hypertension is estimated to be about 7.14 million deaths. As far as the European developed countries is concerned, it is estimated that hypertension is responsible for about 17% of total annual mortality or in other words, for approximately 680 thousands deaths annually [\n4\n]. However, the prevalence of hypertension shows a significant variability among different countries. For instance, according to the work of Wolf-Maier and colleagues [\n5\n] prevalence of hypertension was found to be 37.7% in Italy, 38.4% in Sweden, 41.7% in England, 48.7% in Finland, 46.8% in Spain, and 55.3% in Germany. In the same review paper, it is stated that the mean prevalence of hypertension is higher in Europe (approximately 44%) compared to the US (approximately 28%). Despite the motivational finding, that treating hypertension is associated with about a 40% reduction in the risk of stroke and about a 15% reduction in the risk of myocardial infarction [\n6\n], only approximately 12.5% of hypertensive subjects show adequate control of their blood pressure [\n7\n-\n9\n]. The risk of cardiovascular complications and organ damage in persons with high blood pressure is increased when other risk factors such as smoking, obesity, inappropriate dietary habits and physical inactivity are also present. In the opposite, the benefits from healthy dietary patterns on blood pressure control have been reported in several studies [\n10\n-\n15\n]. Therefore, appropriate nutrition related life-style modifications should be employed at all stages of high blood pressure managing. This is in accordance with the National High Blood Pressure Education Program [\n16\n] in US which emphasizes 6 approaches with proven efficacy for prevention of hypertension: engage in moderate physical activity; maintain normal body weight; limit alcohol consumption; reduce sodium intake; maintain adequate intake of potassium; and consume a diet rich in fruits, vegetables, and low-fat dairy products and reduced in saturated and total fat.\nCurrent data regarding the epidemiology of hypertension in the Greek population are lacking. Therefore the primary aim of this study was to evaluate the prevalence of hypertension in a representative nationwide sample of Greek adults and to investigate the nutritional habits of the participants in relation to their hypertension status.\nMethods\nStudy sample\nDuring autumn of 2004, 62,538 men and women from all Greek regions were randomly selected through telephone catalogues in order to participate in a random-digit dialed (RDD) telephone survey. From the design of the study it has been decided that the sample should be stratified by age group, sex and Greek region in order to be more representative. The randomized procedure was based on the following rule: we selected 1 every 10 names of each particular area using a sequence of random numbers. Furthermore, only one person per household was decided to be interviewed, by trained personnel who used a standard questionnaire. Of the contacted people, 48% did not answer the telephone-call because of various reasons (i.e. 39.1% absences, 4.5% occupied phones, 3.9% wrong numbers recorded in the catalogues); 14.3% of the contacted persons were not suitable for interviewing (i.e. children or house girls etc); 11% were not suitable based on the quotas (i.e. they did not correspond to the sampling targets we had pre-designed for each area, in order the stratified sample to be as much representative as we can) and 0.4% were calls were interrupted due to unknown reasons. Thus, 16,760 of the contacted adult people were eligible for the study. Of them, 5003 (18 – 74 years, men: 48.8%) agreed to participate (participation rate: 30%); the participation rate is considered acceptable since according to the Council of American Survey Research Organizations (CASRO) the response rate estimation of a RDD telephone surveys [\n17\n], based on our data, should be 29.59%. All participants were informed by the interviewer about the aims and procedures of the study. However, since this was a telephone interview no written informed consent was obtained from the participants. The ethical committee of our Institution approved the design of the study.\nInvestigated measurements\nThe questionnaire addressed individuals' demographic and socioeconomic characteristics (age, sex, years of education, type of occupation and residence), information relevant to health status with focus on arterial hypertension (defined as: systolic/diastolic blood pressures > 140/90 mmHg [\n1\n] or use of anti-hypertensive treatment), hypercholesterolemia (defined as: total serum cholesterol levels > 200 mg/dl [\n18\n] or use of lipid lowering agents) and diabetes mellitus (defined as: fasting blood glucose > 125 mg/dl [\n19\n] or use of hypoglycemic treatment), food consumption pattern, other lifestyle habits, such as smoking habits, level of physical activity as well as characteristics related to body composition (recalled weight and height). Family history of all the aforementioned health problems was also recorded (type of answer: yes/no/don't know for father, mother, brother and sister).\nSpecifically for the assessment of hypertension status, the subjects were considered as hypertensive if they were reporting that they had been previously diagnosed by a registered physician (type of answer: yes/no). In case of positive answer, they were asked to report an average value of their systolic blood pressure during hypertensive episodes and to provide data relevant to the selected way of treatment (antihypertensive medication or/and diet or no treatment, years of treatment).\nRelatively to the nutritional component of the questionnaire, the participants were asked to report their average weekly consumption (in servings) of a list of food items of all different food groups. The educational level of the participants was measured by the years of schooling (Group I: < 9 years, Group II: up to high school or technical colleges (10 – 14 years) and Group III: university). Current smokers were defined as those who smoked at least one cigarette per day; never smokers those who have never tried a cigarette in their life and former smokers were defined as those who had stopped smoking in the past. Physically active were considered all the participants who reported either that they participated in an exercise program (such as gym, sports, jogging etc.) during their leisure time at least once a week, or that their occupation presupposes certain level of physical fatigue. The rest of the subjects were defined as physically inactive. Finally, we used data of self reported weight and height to calculate body mass index (BMI). Participants were classified as obese if BMI was ≥ 30 kg/m\n2\n.\nStatistical analysis\nContinuous variables are presented as mean values ± standard deviation, while qualitative variables are presented as absolute and relative frequencies. Relationships between categorical variables were tested by the use of contingency tables and the calculation of Pearson's chi-squared test. All comparisons among paired groups of sample (males – females, normotensives – hypertensives) in relation to normally distributed continuous variables were performed using the student t-test. Every reported P-value is based on two-sided tests and compared to a significance level of 1%. SPSS version 13 (Statistical Package for Social Sciences, SPSS Inc, Chicago, Illinois, U.S.A.) software was used for all the statistical calculations.\nResults\nThe proportional distribution of the present study's participants and of the Greek population (provided by the National Statistical Service according to the census of 2001), by sex and age, is presented in Table \n1\n. No differences were observed regarding age-sex between the sampled and the population distribution (chi-square for men = 0.006, p > 0.99 and chi-square for women = 0.005, p > 0.99), indicating that the stratified by region sample was representative of the total population in terms of age and sex.\nThe characteristics (demographic characteristics, lifestyle habits and information from the medical history) of the study's participants in relation to sex are presented in Table \n2\n. The mean age of men was slightly smaller than that of the women (43.7 ± 16.1 and 44.7 ± 16.0 years, respectively). Additionally, men were more educated and physically active, as well as more frequently current and former smokers.\nAnalysis of data relevant to the medical history showed statistically significant difference among men and women in relation to hypertension status and prevalence of hypercholesterolaemia, but not to prevalence of obesity, diabetes mellitus and renal failure. In particular, 325 men (13.3%) and 455 women (17.7%) reported that they were hypertensive, while 400 men (16.4%) and 560 women (21.8%) reported that they had hypercholesterolaemia. Strong positive relations were found between hypertension status and the prevalence of the rest investigated health conditions (i.e. hypercholesterolaemia, diabetes mellitus, renal failure and obesity) in the overall sample. The prevalence's values of these health conditions among normotensive and hypertensive subjects are presented in Table \n3\n (all \nP\ns < 0.001).\nThe distribution of hypertensive study's participants by age group is presented in Table \n4\n. Ío significant difference was found among men and women in the first five age groups (total range 18 – 64yr) while in the older age group examined (65 – 74yr), hypertension was significantly more prevalent in women comparing to men.\nStatistically significant difference (P < 0.001) was observed among women and men participants in relation to the reported values of blood pressure, when they faced episodes of hypertension. In particular, women had higher values of systolic blood pressure (180 ± 27 mmHg) than men (169 ± 24 mmHg). However, no difference was found relatively to parameters as \"number of years that they have the problem\" (men: 8.6 ± 7.8 yr, women: 9.4 ± 8.2 yr, P = 0.155) and \"number of years that they use antihypertensive medication\" (men: 7.5 ± 6.7 yr, women: 8.4 ± 7.6 yr, P = 0.126). Furthermore, analysis of participants' family history of hypertension showed a positive association (P < 0.001) only between brothers (independently of sex) and not between parents and descendants. Specifically, only 1.32% of normotensive participants have a hypertensive brother or a sister, while 6.56% of hypertensive participants have a brother or a sister who faces the same problem.\nSeveral associations were also detected between nutritional habits and hypertension status. The average weekly consumption (expressed in servings) of the investigated food groups by normotensive and hypertensive subjects is presented in Table \n5\n. With the exception of some food groups or items i.e. chicken (P = 0.298), vegetables (P = 0.272), white cheese (P = 0.055) and legumes (P = 0.063), hypertensive participants differ significantly when compared to normotensive ones in relation to consumption of the food groups tested. In details, data came out after the analysis of the semi-quantitative food frequency questionnaires showed that hypertensives consume more frequently items from the groups of fish (P < 0.001), bread and cereals (P = 0.011), fruits and juices (P < 0.001) and low fat milk and yogurt (P < 0.001), while normotensive participants have greater consumption of red meat (P < 0.001), pork (P < 0.001), egg (P < 0.001), pasta and rice (P < 0.001), potatoes (P < 0.001), full fat milk and yogurt (P < 0.001), yellow cheese (P <0.001) and desserts or ice creams (P < 0.001).\nDiscussion\nThis study provided data on the prevalence of self – reported hypertension among a nationwide sample of about 5000 Greek adults. Furthermore the nutritional habits of the participants were evaluated in relation to their blood pressure status. The prevalence of self-reported hypertension was about 13% in men and 18% in women, denoting a serious public health problem in Greece. However, it is encouraging that hypertensive subjects may have started adopting some more healthy nutritional behaviour compared to normotensive ones.\nOnly a few epidemiological studies [\n20\n-\n23\n] have provided data regarding the prevalence of hypertension in Greek population. Two of them, the ATTICA study [\n20\n] and the Greek EPIC study [\n21\n], are well organized and large – scale health surveys and provided information about the prevalence and awareness of high blood pressure levels in representative Greek samples. In particular, the ATTICA study is a health and nutrition survey that enrolled 3042 adult men and women, without clinical evidence of cardiovascular disease, from the province of Attica in which Athens, the capital of the country, is located. The sampling was random and multistage, and was based on the age-sex distribution of the province of Attica, provided by the National Statistical Service according to the census of 2001. Additionally, the EPIC study is a multi-country, prospective cohort study that was conducted in 22 research centres in 10 European countries, examining the role of dietary, lifestyle, and environmental factors in the aetiology of cancer and other chronic diseases. In Greece, the EPIC study started in 1994 and is being conducted by the Department of Hygiene and Epidemiology of the University of Athens. The subjects of the EPIC study were volunteers (n = 26,913), aged 20–86 years and recruited from several regions of Greece. Arterial blood pressure measurements were taken in both of the aforementioned studies in order to diagnose hypertension among participants.\nAccording to the ATTICA study, the prevalence of hypertension was 37.5% for men and 25% for women, while according to the Greek EPIC study, the respective figures were 40.2% and 38.9%. Another local, small – scale, observational study (Didima study) [\n22\n], showed similar to the ATTICA study results when evaluated the prevalence of hypertension (30% in men and 27% in women). The present study estimated that the prevalence of self-reported hypertension was much lower comparing to data provided from the studies mentioned above (13.3% for men and 17.7% for women). This large difference among these specific studies can be possibly ascribed to the selected way of identifying hypertensive participants in the present study. Due to the fact that the participants self – reported whether they are hypertensives (without clinical examination), it is actually likely that the prevalence's figures were underestimated as it is generally accepted that there is a large group of hypertensive subjects unaware of their condition (according to the ATTICA study: 68% in men and 54% in women [\n24\n]). However, studying population-based surveys the calculated prevalence may be an overestimate, as blood pressure measurement was performed once during the study and numerous reasons for elevated blood pressure readings may have been present, including the white coat phenomenon [\n25\n].\nIt is also noteworthy the finding that hypertension is more prevalent in women than in men, something that is in contrast with the results from the other similar surveys (ATTICA, EPIC and Didima). However, in the EPIC study it is stated that although the prevalence of hypertension before the age of 55 years is higher among men than among women, it is slightly higher among women thereafter. A different explanation of the above finding could possibly be the different level of high blood pressure awareness between the two sexes, as it has been suggested that hypertensive women show higher level of awareness than men [\n26\n]. Another finding of this study, which is in accordance with the results from the aforementioned studies, is that the prevalence of the discussed condition increases with age (Table \n4\n). Particularly, distribution of hypertensive study's participants by age showed that prevalence's figures among consecutive age groups (decades) differ approximately per 15 percentage units, with highest values observed in the older age group (65 – 74 yr) examined (men: 39.5%, women: 49.6%).\nThe significant strong relationship observed between prevalence of hypertension and hypercholesterolaemia, diabetes mellitus and obesity (Table \n3\n) confirm the frequent conclusion from other studies [\n27\n-\n29\n], that hypertensives usually, apart from high blood pressure, have additional cardiovascular risk factors. Although elevated levels of blood pressure and cholesterol are known as two of the most important risk factors of coronary heart disease [\n29\n], the strong relationships detected between hypertension and diabetes mellitus should not be underestimated, because evidence of diabetes substantially increases cardiovascular disease risk in hypertensive [\n30\n] while the risk of vascular complications in diabetes is related to the level of blood pressure [\n31\n]. Furthermore, obesity which was found to be more prevalent in the present survey's subgroup of hypertensive participants, also enhances total cardiovascular risk possibly by increasing low density lipoproteins-cholesterol (LDL-C) levels, reducing high density lipoproteins – cholesterol (HDL-C) levels, diminishing glucose tolerance and predisposing to the development of left ventricular hypertrophy, according to previous studies [\n32\n,\n33\n]. Above findings in combination to one of the conclusions from ATTICA study, that only about one out of six Greek hypertensives is adequately controlled, emphasize in the need for policies in Greece for the detection and control of hypertension similar to those that US as well as some other countries have adopted for years [\n7\n,\n34\n,\n35\n].\nDiet and nutrition have been extensively investigated as risk factors for major cardiovascular diseases like coronary heart disease and stroke and are also linked to other cardiovascular risk factors like diabetes, high blood pressure and obesity [\n7\n,\n8\n,\n10\n,\n11\n]. Furthermore, arterial pressure regulation has been linked to a variety of nutrients and nutritional issues. Current guidelines for the management of hypertension emphasize the importance of achieving several nutritional goals simultaneously. In particular, according to the recent \"2004 Canadian recommendations for the management of hypertension\"[\n36\n], apart from suggestions relevant to improvement of physical fitness and stress management, nutritional guidelines are highlighted. Specifically, key recommendations include the following: an ideal body weight (BMI: 18.5 kg/m\n2 \nto 24.9 kg/m\n2\n) should be maintained and weight loss strategies should use a multidisciplinary approach; alcohol consumption should be limited to two drinks or fewer per day, and weekly intake should not exceed 14 standard drinks for men and 9 standard drinks for women; a reduced fat, low cholesterol diet that emphasizes fruits, vegetables and low fat dairy products, and maintains an adequate intake of potassium, magnesium and calcium, should be followed; salt intake should be restricted to 65 mmol/day to 100 mmol/day in hypertensive individuals and less than 100 mmol/day in normotensive individuals at high risk for developing hypertension. It is also stated that the above lifestyle modifications should be extended to non-hypertensive individuals who are at risk for developing high blood pressure.\nIn the present study, the expected higher prevalence of obesity in the subgroup of hypertensive participants was confirmed, as well as the greater values of BMI in the same subgroup (Table \n3\n). This finding shows that although hypertensive participants are aware of their hypertensive status, they have not managed yet to approach an ideal body weight. However, data came out after the analysis of food frequency questionnaires reveal that they may have started adopting some more healthy nutritional behaviour compared to normotensive ones. As it was mentioned in the results section, consumption of fish, fruits and juices, cereals, and low fat milk and yogurt was found to be higher among hypertensive subjects while the opposite was observed for food items as red meat, pork, egg, pasta and rice, full fat dairy products and desserts (Table \n5\n), something that is encouraging relatively to their attempts of controlling their blood pressure in a better way. However, the reported quantities consumed are quite different than recommended ones, according to the beneficial dietary pattern of Mediterranean Diet [\n14\n,\n15\n,\n37\n] which among others highlights the importance of adequate consumption of vegetables and legumes.\nIt is noteworthy that eggs and full fat dairy products are included in the list of food items preferred more by present study's subgroup of normotensives. A first possible explanation could be that hypertensive participants try to follow more strictly the recommendations of nutritional experts. However, composition of these specific food items may reveal a better explanation of the observed relationships. In particular, peptides formed during the digestion of milk [\n38\n-\n41\n] and egg proteins [\n42\n] and oligopeptides from chicken egg yolk [\n43\n,\n44\n], have been demonstrated to have a blood pressure lowering effect in human, possibly via their strong angiotensin I – converting enzyme (ACE) inhibitory activity. So, it is possible this dietary habit observed among normotensive subjects to be able of providing a prophylactic effect against hypertension. Taking under consideration recent studies which demonstrated that there are no convincing evidence of an increased risk of vascular disease from milk [\n45\n,\n46\n] and egg [\n47\n] consumption, future focused research is needed before a possible update of global recommendations in relation to optimum consumption of egg and dairy products takes place.\nLimitations\nThis study as a cross-sectional one cannot establish causal relations, but only generate hypothesis that could be evaluated by future prospective randomized trials. Additionally, the applied method of self – reporting hypertension status neither is able to provide data in relation to level of hypertension's awareness (thus the evaluated prevalence of hypertension may be underestimated), nor can be as accurate as clinical examination. However, validity studies suggest that self – reported hypertension may be used for surveillance of hypertension trends in the absence of measured blood pressure [\n48\n]. For example, according to a recent survey [\n49\n], the results of which were based on blood pressure measurements, it was estimated that approximately 27 % of the US adults had hypertension and that among them about 69 % were aware of their status (corresponding to about 19 % of the study sample). In another study (with no blood pressure measurements) Ayala and colleagues [\n50\n] reported a prevalence of 20 % for self-reported hypertension among US adults, which is close with the expected value of 19%. Meanwhile, caution has to be given when interpreting results derived from self-reporting quantifiable variables, due to low reliability and validity of the self-reporting method. For instance, self-reported BMI tends to be underestimated in those with higher values. Thus, the rate of obesity is most probably underestimated [\n51\n,\n52\n]. Another methodological limitation of the present study is that semi-quantitative food frequency questionnaires in general cannot be used for subsequent analysis of specific nutrients, so conclusions can be expressed only in relation to food groups or items tested. Finally, the participation rate, although small (i.e. 30%) is considered acceptable in RDD telephone surveys. Unfortunately, no sensitivity analysis could be performed since no information was recorded by the people that they did not want to participate. Moreover, the statistical analysis showed that the selected sample shares the same distribution of age-group and sex as the total population.\nConclusion\nAccording to presented data, hypertension can be considered as a major public health problem in Greece, albeit the estimated prevalence is relatively low when compared with the rest European developed countries. Possibly the adoption of \"western\" dietary patterns by Greeks during last decades, had a strong causative role for this phenomenon. However, this problem can be prevented or controlled by complementary to clinical management application of strategies that target the general population. Among non – pharmacological approaches, nutritional interventions, that will incorporate the newest relevant scientific knowledge, are extremely challenging in the primary and secondary prevention of hypertension. Moreover a finding of this work, which implies certain actions towards health policy and quality improvement, is that although hypertensive participants seem to be aware of their condition, they have not managed as yet to approach an ideal body weight. All these carry an important message for primary care physicians and other health care scientists and reveals the value of the spread and understanding of European guidelines on cardiovascular disease prevention [\n53\n]. This study opens also room for further research with the same methodology that will explore whether patients with hypertension were seeking proper care by their personal physician and discuss to what extent they complied with their physicians' recommendations.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nCP: had the conception of the study, drafted the manuscript and given the final approval of the version to be published, GM: has been involved in concept of the study, performed the data analysis, and drafted the manuscript, DP: had the conception and design of the study, performed the data analysis and interpretation of the results, drafted the manuscript and given the final approval of the version to be published, DX, GP, CS: have made substantial contributions to conception and design of the study, have been involved in revising the manuscript critically for important intellectual content; and have given final approval of the version to be published.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
97
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nSoy isoflavones increase preprandial peptide YY (PYY), but have no effect on ghrelin and body weight in healthy postmenopausal women\n\n**Article Abstract:**\n\nBackground\nSoy isoflavones show structural and functional similarities to estradiol. Available data indicate that estradiol and estradiol-like components may interact with gut \"satiety hormones\" such as peptide YY (PYY) and ghrelin, and thus influence body weight. In a randomized, double-blind, placebo-controlled, cross-over trial with 34 healthy postmenopausal women (59 ± 6 years, BMI: 24.7 ± 2.8 kg/m\n2\n), isoflavone-enriched cereal bars (50 mg isoflavones/day; genistein to daidzein ratio 2:1) or non-isoflavone-enriched control bars were consumed for 8 weeks (wash-out period: 8-weeks). Seventeen of the subjects were classified as equol producers. Plasma concentrations of ghrelin and PYY, as well as energy intake and body weight were measured at baseline and after four and eight weeks of each intervention arm.\nResults\nBody weight increased in both treatment periods (isoflavone: 0.40 ± 0.94 kg, P < 0.001; placebo: 0.66 ± 0.87 kg, P = 0.018), with no significant difference between treatments. No significant differences in energy intake were observed (P = 0.634). PYY significantly increased during isoflavone treatment (51 ± 2 pmol/L vs. 55 ± 2 pmol/L), but not during placebo (52 ± 3 pmol/L vs. 50 ± 2 pmol/L), (P = 0.010 for treatment differences, independent of equol production). Baseline plasma ghrelin was significantly lower in equol producers (110 ± 16 pmol/L) than in equol non-producers (162 ± 17 pmol/L; P = 0.025).\nConclusion\nSoy isoflavone supplementation for eight weeks did not significantly reduce energy intake or body weight, even though plasma PYY increased during isoflavone treatment. Ghrelin remained unaffected by isoflavone treatment. A larger and more rigorous appetite experiment might detect smaller differences in energy intake after isoflavone consumption. However, the results of the present study do not indicate that increased PYY has a major role in the regulation of body weight, at least in healthy postmenopausal women.\n\n**Article Body:**\n\nBackground\nSeveral intervention studies in humans and animals suggest that consumption of soy and isoflavone-rich soy protein may decrease body weight [\n1\n,\n2\n]. Postmenopausal women with relatively high isoflavone consumption in their normal diet showed an inverse association with obesity in a cross-sectional study [\n3\n]. However, the protein content of soy may be at least partly responsible for the observed effects, and the contribution of soy isoflavones such as genistein and daidzein remains uncertain [\n4\n,\n5\n]. There is some evidence that may link isolated isoflavone consumption \nper se \nto the regulation of body weight. Soy isoflavones show functional and structural similarities to estradiol [\n6\n], mainly by binding to the estrogen receptor β [\n7\n]. In ovariectomized mice, loss of circulating estrogen increases body weight and fat mass, and this is reversed by estrogen replacement [\n8\n,\n9\n]. Similar effects have been observed in ovariectomized mice treated with oral genistein [\n10\n,\n11\n]. Even though the role of postmenopausal hormone replacement in modulating body weight is controversial [\n12\n,\n13\n], some studies indicate that the activation of the estrogen receptor interferes with the regulation of gut hormones commonly thought to be involved in the regulation of food intake. Food intake decreases during the high estrogen period in the estrous cycle in rats, and estradiol replacement in ovariectomized rats increased the satiating effect of the gut hormone cholecystokinin [\n14\n]. Estrogen replacement in hysterectomized postmenopausal women also increased peripheral concentrations of the orexigenic gut hormone ghrelin [\n15\n]. Peptide YY (PYY), a member of the neuropeptide Y (NPY) family and another gut derived \"satiety hormone\", is assumed to have potent anorexigenic properties, with potential therapeutic use in obese humans [\n16\n]. Human PYY has been shown to be regulated in a gender specific manner, with higher PYY secretion in females than in males [\n17\n]. Treatment of ovariectomized rodents with estradiol increases the number of receptors of several neuropeptides, including NPY receptors in the brain [\n18\n]. To date, potential effects of isolated isoflavones on PYY have not been reported, and only one study investigated effects of isolated isoflavones on total ghrelin concentrations [\n19\n]. In addition, no long-term randomized controlled studies have investigated whether changes in PYY concentrations influence food intake in free living humans. The hypothesis of the present study was that estradiol-like properties of isolated isoflavones may influence PYY and ghrelin, and thus energy intake and body weight.\nResults\nResults of biomarkers are given as postabsorptive concentrations, measured after a standardized low-fat evening meal and after 12 h overnight fasts. P values for PYY, glucose, insulin and ghrelin are given for the treatment effect within a linear mixed model. Differences from baseline were used as response variable after adjustment for changes in BMI.\nDietary intake and body weight\nDietary intake was assessed at baseline and after four weeks of each intervention arm. Macronutrient intake at baseline was 15% of energy as protein, 34% as fat, and 47% as carbohydrate. Even though participants were instructed to replace snacks by the cereal bars, body weight increased moderately, but significantly, during both intervention periods (placebo + 0.66 ± 0.87 kg, (P = 0.018); isoflavones + 0.40 ± 0.94 kg, (P < 0.001)). There was no significant difference in body weight and body mass index (P > 0.331) between treatments (table \n1\n). There were no significant differences in energy intake or macronutrient intake, both across the treatments and compared to baseline (wk4 - wk0; interaction treatment vs. time, P = 0.634).\nTable 1\nPlasma PYY, body weight, and urinary isoflavone concentrations in postmenopausal women, at baseline (t0) and after 8 weeks (t8) of isoflavone or placebo consumption (n = 34)\nIsoflavones\nPlacebo\nP value\n1\nt0\nt8\nt0\nt8\nTotal PYY (pmol/L)\n51 ± 2\n55 ± 2\n52 ± 3\n50 ± 2\n0.010\nBMI (kg/m\n2\n)\n24.5 ± 2.7\n24.6 ± 2.7\n24.5 ± 2.8\n24.7 ± 2.8\n0.331\nGlucose (mmol/L)\n5.7 ± 0.1\n5.6 ± 0.1\n5.7 ± 0.1\n5.6 ± 0.1\n0.641\nInsulin (pmol/L)\n37 ± 3\n39 ± 3\n38 ± 3\n34 ± 3\n0.231\nTotal ghrelin (pmol/L)\n129 ± 12\n131 ± 12\n133 ± 13\n123 ± 11\n0.297\nData are given as mean ± SEM except for BMI which is presented as mean ± SD. BMI = body mass index.\n1 \nP values are shown for the treatment effect within a linear mixed model. Differences from baseline were used as response variable after adjustment for changes in BMI.\nEffect of isoflavone consumption on PYY\nDuring isoflavone consumption, PYY concentrations increased by eight percent, and during placebo consumption, PYY concentrations decreased by four percent (P = 0.010 for treatment differences) (table \n1\n).\nChanges in PYY levels were independent of changes in BMI, and were negatively correlated with baseline PYY (r = -0.67; P < 0.001). PYY concentrations were not significantly different between equol producers and equol non-producers.\nEffect of isoflavone consumption on ghrelin\nAt baseline, ghrelin was significantly lower in equol producers (110 ± 16 pmol/L) than in equol non-producers (162 ± 17 pmol/L); (P = 0.025), independent of BMI. However, isoflavone treatment did not affect ghrelin concentrations (table \n1\n).\nOther parameters\nDuring isoflavone treatment, urinary genistein and daidzein excretion increased 15 fold and 24 fold, respectively. There was no significant increase in urinary genistein and daidzein concentrations following placebo treatment. According to the cut-offs used in the present study [\n20\n], 50 percent of the participants (n = 17) were classified as equol producers. Equol production increased 35 fold in equol producers during the active treatment, compared to an 1.7 fold increase in equol non-producers (table \n2\n).\nTable 2\nUrinary isoflavone concentrations in postmenopausal women at baseline (t0) and week 8 (t8) of isoflavone and placebo arms (n = 34)\nIsoflavones\nPlacebo\nP \nvalue\n1\nt0\nt8\nt0\nt8\nGenistein (nmol/L)\n808 ± 134\n12266 ± 852\n655 ± 68\n647 ± 73\n<0.001\nDaidzein (nmol/L)\n334 ± 88\n8146 ± 651\n315 ± 82\n223 ± 40\n<0.001\nEquol, (nmol/L)\n154 ± 12\n3040 ± 713\n162 ± 15\n198 ± 23\n<0.001\n Equol producers (n = 17)\n164 ± 11\n5834 ± 749\n179 ± 16\n237 ± 29\n<0.001\n Equol non-producers (n = 17)\n143 ± 14\n245 ± 16\n145 ± 13\n160 ± 12\n<0.001\nData are given as mean ± SEM.\n1 \nP values are shown for the treatment effect within a linear mixed model. Differences from baseline were used as response variable.\nPlasma glucose and insulin were unaffected by isoflavone treatment (table \n1\n).\nPower analysis\nA between-treatment difference in body weight > 500 g after 8 weeks intervention was assumed to be relevant. The estimated power of this study was 94 percent to detect a difference of 500 ± 900 g in body weight between treatments with a sample size of 34 subjects and a significance level of 0.05.\nDiscussion\nConsumption of soy derived food rich in isoflavones has been suggested to have favorable effects on energy intake and body weight [\n5\n]. However, soy derived food is also rich in protein, and an increased protein intake might be responsible for the observed effects. The potential contribution of isolated isoflavones to the regulation of energy and body weight remains uncertain. In the present study, isoflavone treatment for eight weeks did not significantly influence energy intake, macronutrient intake, or body weight, both across the treatments or compared to baseline. Isoflavone treatment did not affect preprandial ghrelin, which seems to be in contrast to results of a previous study that investigated effects of isoflavone treatment on ghrelin concentrations [\n19\n]. However, the observed differences in the mentioned study are mainly due to increased ghrelin concentrations in the placebo group rather than altered ghrelin concentrations after isoflavone intake. In addition, high within and between subject variations in preprandial ghrelin concentrations have been reported, which may lead to the detection of random effects rather than of true treatment effects [\n21\n]. Despite unchanged ghrelin concentrations during isoflavone treatment in the present study, the ability of producing equol, a gut bacterial metabolite of daidzein with higher binding affinity to estrogen receptors compared with its precursor [\n22\n], was associated with lower ghrelin concentrations at baseline. The capability to produce equol is greatly varying between individuals, with about 30–40% equol producers in the Western population [\n22\n]. It is speculated that equol producers may have an increased benefit from soy consumption [\n20\n,\n23\n]. However, even though the ability of producing equol was associated with lower ghrelin concentrations at baseline, ghrelin responses remained unaffected during isoflavone treatment in the present study. This indicates that equol may have a long-term suppressive effect on ghrelin concentrations, which probably will not respond to further and relatively short-term increases of equol concentrations. In contrast to unchanged ghrelin in the present study, isolated soy isoflavones significantly increased plasma PYY concentrations. Given the assumed potent anorexigenic properties of PYY [\n16\n], our data do not suggest a major role of PYY on the regulation of body weight. Notably, power analysis indicated that even a moderate difference in body weight between treatments was highly likely to be detected. Only moderate effects of PYY on the regulation of body weight may contribute to the explanation of controversial findings in the literature. In humans, short-term intravenous administration of PYY [3-36] in supraphysiological [\n24\n,\n25\n], but not in physiological doses [\n25\n] reduces appetite and food intake. Long-term studies in humans are not available to date. A two weeks continous PYY infusion in colectomized rats did not affect food intake and body weight [\n26\n], and data obtained from other animal studies are controversially discussed [\n27\n]. The duration of the present study may have been too short to detect relevant differences in body weight. However, most studies linking physiological ghrelin and PYY responses to food intake investigated the effects of only one meal. A relatively small but well performed study over 16 weeks did not show an effect of macronutrient intake and energy intake on preprandial ghrelin [\n21\n]. It needs, however, to be emphasized that food diaries, and not weighed food intake were used to assess energy intake in the present study, and a more rigorous appetite experiment might detect smaller effects. In addition, adaptation processes and counter regulatory responses in other satiety hormones than total ghrelin, such as acylated ghrelin, glucagon-like peptide (GLP-1), or cholecystokinin may have masked detectable differences in energy intake or body weight.\nConclusion\nIsoflavone treatment had no effect on energy intake and body weight, despite significantly increased preprandial PYY concentrations. The findings indicate that PYY is not a major factor in the regulation of body weight. Preprandial ghrelin was not affected by isoflavone consumption. The isoflavone contents are not likely to explain the observed beneficial effects of soy consumption on energy intake and body weight.\nMethods\nSubjects\nThis study was part of a multi-center intervention located in Frederiksberg (Denmark), Reading (UK), Rome (Italy), and Potsdam (Germany). Potential effects of isoflavones on gut satiety hormones and body weight were investigated in the German population. Thirty-six healthy postmenopausal women (age 59 ± 6 y, BMI 24.7 ± 2.8 kg/m\n2\n), defined as at least 12 months since the last menstrual cycle, were recruited by advertisement in the local media. Thirty-four of the subjects completed the intervention. One of the subjects was excluded because of a prolonged respiratory infection, the other one because of start of a treatment with an angiotensin-converting-enzyme inhibitor. None of the volunteers had used hormone replacement therapy for six months, antibiotics for three months, or isoflavone, vitamin, or mineral containing supplements for two months. All volunteers were non-smokers. Parameters of renal and liver function were within normal range. Subjects were classified as equol producers, when equol in a 24 h urine sample exceeded 936 nmol/liter during isoflavone treatment, which corresponds to an urinary equol excretion of > 0.45 mg/day [\n20\n]. The study protocol was approved by the Ethics Committee of the University of Potsdam, Germany. All volunteers gave written informed consent prior to the study.\nStudy design\nThis was a randomized, double-blind, placebo-controlled, 2 × 8-wk crossover study, separated by an 8-wk washout period. Subjects were invited to the metabolic unit on 6 occasions (t0, t4, and t8 on each intervention arm), after 12-h overnight fasts. To exclude potential second-meal effects, a set low-fat evening meal (< 10 g fat) was consumed the evening before each of the study days. Recipes for the preparation of the meals were provided to the participants. Energy contents of the meals were comparable. Subjects were asked to consume two fruit cereal bars/d (Health & Diet Food, Manchester, UK), one in the morning and one in the afternoon, in addition to their normal diet. During the treatment period, cereal bars were enriched with 2 × 25 mg isoflavones/d, with a genistein to daidzein ratio of 2:1 (\"Solgen 40\", Solbar Plant Extracts, Ashdod, Israel). Thus, isoflavone intake in the treatment group of the present study was in the upper range of the daily isoflavone intake in traditional Asian diets (15 – 50 mg/d) [\n28\n]. The product was tested before packaging and during the study by HPLC, to ensure stability of the isoflavones [\n29\n]. Placebo did not contain any isoflavones. Each cereal bar (40 g) had an average nutrient content of energy (652 kJ); protein 2.6 g; carbohydrate 17.3 g; fat 8.5 g; fiber 1.8 g; sodium 0.012 g. Subjects perceived the isoflavone-enriched and placebo cereal bars as identical in taste and visual appearance. Habitual diet was assessed by estimated 3-d food records three times during the study. Diet diaries were completed at baseline (t0) and after 4 weeks (t4) of each intervention arm. All food records included two week days and one weekend day. Nutrient intake was calculated based on the German Food and Nutrient Data Base Bundeslebensmittelschlüssel BLS II.3 [\n30\n]. To avoid weight gain, subjects were advised to replace snacks with the cereal bars. Subjects kept daily records of cereal bar consumption and well-being in a study diary. Dietary compliance was further assessed by measurement of phytoestrogen concentrations in 24-hour urine [\n31\n], which was collected at start and end of each intervention period. Body weight was measured at each visit.\nBiochemical parameters\nBlood was collected in ice-chilled EDTA tubes for the analysis of glucose, ghrelin, and PYY. Following centrifugation at 1600 g for 10 minutes at 4°C, aliquots were immediately frozen at -20°C until assayed. All samples from individual subjects were measured in the same assay. Immunoreactive total ghrelin was measured by a commercially available radioimmunoassay (Phoenix Pharmaceuticals, Mountain View, CA, USA), as previously described [\n32\n]. Immunoreactive total human PYY was measured by a commercially available radioimmunoassay (LINCO Research, Missouri, USA), using\n125\nI-labeled bioactive PYY as tracer and a PYY antiserum to determine the level of active PYY by the double antibody/PEG technique. The PYY antibody is raised in guinea pigs and recognizes both the PYY 1–36 and PYY 3–36 forms of human PYY. Intra- and inter-assay coefficient of variation was 5.3% and 7.0%, respectively. Insulin, and glucose, and urinary phytoestrogens (genistein, daidzein, equol) were analyzed as previously described [\n33\n].\nStatistical analyses\nData are given as mean ± SEM, anthropometric data are given as mean ± SD. Changes from baseline, e.g. week-8 compared to week-0 (t8-t0), were used as the dependent variables. Data were calculated as changes from baseline on the original scale, when normally distributed. Skewed data where log transformed, and changes from baseline on the log scale were calculated, and these changes now correspond to a multiplicative change from baseline on the original scale. Subjects were included as a random factor within a linear mixed model. Fixed effects included in the final model were: baseline parameters, treatment, treatment order, and changes in BMI. Further exploratory investigation of equol group was included in the model. Pearson's correlation coefficient was calculated between baseline PYY and changes in PYY. Statistical analysis was performed using SAS 8.4 (SAS Institute Inc., Cary, NC).\nAbbreviations\nBMI: body mass index; PYY: peptide YY.\nCompeting interests\nThis study was carried out with financial support from the Commission of the European Communities, ISOHEART QLK1-2001-00221. It does not necessarily reflect its views and in no way anticipates the Commission's future policy in this area. The authors declare that they have no competing interests.\nAuthors' contributions\nMOW, BO, CK, and MR were responsible for data analysis and writing of the manuscript. S B, CMW, and HJZ were responsible for the study design and were involved in all aspects of the study as well as manuscript review. MR, JH and MF, and KV were involved in the collection of the data. BO, WLH, and DT were responsible for laboratory analysis. All authors contributed to the manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
98
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nPsychosis with paranoid delusions after a therapeutic dose of mefloquine: a case report\n\n**Article Abstract:**\n\nBackground\nConvenient once-a-week dosing has made mefloquine a popular choice as malaria prophylaxis for travel to countries with chloroquine-resistant malaria. However, the increased use of mefloquine over the past decade has resulted in reports of rare, but severe, neuropsychiatric adverse reactions, such as anxiety, depression, hallucinations and psychosis. A direct causality between mefloquine and severe reactions among travelers has been partly confounded by factors associated with foreign travel and, in the case of therapeutic doses of mefloquine, the central nervous system manifestations of \nPlasmodium \ninfection itself. The present case provides a unique natural history of mefloquine-induced neuropsychiatric toxicity and revisits its dose-dependent nature.\nCase presentation\nThis report describes an acute exacerbation of neuropsychiatric symptoms after an unwarranted therapeutic dose (1250 mg) of mefloquine in a 37-year-old male previously on a once-a-week prophylactic regimen. Neuropsychiatric symptoms began as dizziness and insomnia of several days duration, which was followed by one week of escalating anxiety and subtle alterations in behaviour. The patient's anxiety culminated into a panic episode with profound sympathetic activation. One week later, he was hospitalized after developing frank psychosis with psychomotor agitation and paranoid delusions. His psychosis remitted with low-dose quetiapine.\nConclusion\nThis report suggests that an overt mefloquine-induced psychosis can be preceded by a prodromal phase of moderate symptoms such as dizziness, insomnia, and generalized anxiety. It is important that physicians advise patients taking mefloquine prophylaxis and their relatives to recognize such symptoms, especially when they are accompanied by abrupt, but subtle, changes in behaviour. Patients with a history of psychiatric illness, however minor, may be at increased risk for a mefloquine-induced neuropsychiatric toxicity. Physicians must explicitly caution patients not to self-medicate with a therapeutic course of mefloquine when a malaria diagnosis has not been confirmed.\n\n**Article Body:**\n\nBackground\nMefloquine, a 4-quinoline methanol structurally related to quinine, has a long elimination half-life of 14 to 41 days [\n1\n], which allows for once-a-week dosing and makes it a popular choice as malaria prophylaxis for travelers to malaria endemic areas. Along with atovaquone/proguanil and doxycycline, mefloquine is currently recommended as malaria prophylaxis for travel in areas with chloroquine-resistant \nPlasmodium falciparum \nby health authorities in the United States, the United Kingdom, and Canada [\n2\n,\n3\n]. The current recommended prophylactic dose is 250 mg once a week for adults. Since mefloquine was introduced in 1985, the most commonly reported adverse events have been gastrointestinal and neuropsychiatric events [\n4\n,\n5\n]. It is the latter that has been the most concerning to the public. Common neuropsychiatric adverse events include dizziness, insomnia, and strange or vivid dreams. The increased use of mefloquine over the past two decades, due to increased international travel to malaria endemic areas, has resulted in reports of less common, but more severe, neuropsychiatric reactions such as anxiety, depression, hallucinations and psychosis. Due to the relative rarity of events, the causal relationship between mefloquine and these severe reactions among travelers is tenuous, often confounded by factors associated with foreign travel and, in the case of therapeutic doses of mefloquine, the central nervous system (CNS) manifestations of \nPlasmodium \ninfection itself.\nThis report describes an acute exacerbation of neuropsychiatric symptoms after an unwarranted therapeutic dose (1250 mg) of mefloquine in a 37-year-old male previously on a once-a-week prophylactic regimen. The case demonstrates the time course of mefloquine-induced neuropsychiatric toxicity, revisits the dose dependent nature of such adverse events, and reviews the current literature.\nCase presentation\nMr. A, a 37-year-old Nigerian male who has lived in the United States for ten years, traveled to Nigeria for one week with his wife to visit family. He had never taken mefloquine prophylaxis before this trip, but his childhood was remarkable for multiple episodes of malaria treated with various anti-malarial regimens. His previous psychiatric history was significant for a single panic attack experienced in his early twenties. He had no medical diagnoses prior to these events. He used no alcohol or other substances and had no known drug allergies.\nMr. A began his malaria prophylaxis regimen of once-a-week, 250 mg mefloquine two weeks prior to traveling to Nigeria. He and his wife spent a week in urban regions of his native country without incident. He discontinued his malaria prophylaxis upon returning to the United States. Two weeks later, Mr. A began experiencing fatigue and a mild headache and presented to a university-affiliated travel clinic. He denied fever, chills, night sweats, or nausea. Chemistries and cell blood count were within normal limits, and a blood smear showed no evidence of parasitaemia.\nTwo weeks after his visit to the travel clinic, Mr. A, still concerned that he might have malaria, took a one-time therapeutic dose of 1250 mg mefloquine. The next day, he began experiencing vertigo and insomnia, both which lasted for several days. While at work that same week, he experienced chest pain radiating down his left arm with concomitant diaphoresis and tachycardia in what the patient described as \"an ACS picture,\" referring to acute coronary syndrome. He felt intense anxiety at this time. Mr. A's blood pressure taken in his office was 210/110. He then went to the emergency department of an outside hospital and was admitted for a hypertensive emergency. Cardiac work-up for ACS, including an exercise stress test, was negative and head computerized tomography showed no abnormalities other than a left maxillary mucosal inclusion cyst suggestive of sinusitis. Mr. A was diagnosed with hypertension and, incidentally, with Type II diabetes mellitus. He was held overnight for observation and discharged the following morning on metoprolol 100 mg qd, lisinopril 10 mg qd, rosiglitazone 1 mg bid, and metformin 500 mg bid, and zolpidem 10 mg qhs. The following Monday morning, he returned to work at his office, but left midday because he was experiencing anxiety and nervousness. He did not return to work the rest of the week and tried to relieve his anxiety with exercise and outdoor activities. During this week, he began having unusual conversations about spirituality and religion with his wife. His wife reported that he had difficulty following conversations and was remarkably suspicious of her as well, with numerous inquiries into her activities and friends.\nNine days after the previous hospital discharge, Mr. A became abruptly anxious and agitated with delusions that his wife was having an extramarital affair and began \"talking out of his head.\" His wife, fearful of his increasing agitation and paranoia, finally coaxed Mr. A into going to the emergency department at a university-affiliated hospital. He became severely agitated and paranoid in the emergency department, becoming highly suspicious of the one-to-one sitter ordered for his safety after he had reported suicidal ideation. He attempted to escape from the hospital. Eventually, Mr. A had to be restrained to his bed due to profound psychomotor agitation. His vital signs were remarkable for a blood pressure of 157/97, and physical examination was significant only for altered mental status. Serum electrolytes, renal function, and cell blood count were within normal limits. Blood glucose was mildly elevated at 146 mg/dL. Urine drug screen was negative. Urinalysis was positive for bacteriuria, and a course of levofloxacin was initiated. Mr. A was admitted to the general medicine service, where overnight he had another acute episode of agitation, becoming increasingly argumentative with the staff. Intramuscular haloperidol was administered to treat his acute psychotic agitation.\nMr. A was transferred to the medical psychiatry inpatient unit with the DSM-IV-TR diagnosis of Psychotic Disorder, Not Otherwise Specified. His vital signs remained stable. Rapid plasma reagin test, cobalamin and folate levels, liver transaminase levels, and thyroid stimulating hormone levels were within normal limits. Mr. A complained of intense anxiety with no identifiable precipitant on the first day of his hospital course. He demonstrated paranoid behaviour and was highly suspicious of the staff, frequently checking identification badges and quizzing the staff in order to verify their background and knowledge. Although generally cooperative, he questioned the utility of all procedures indicated in his treatment. He was started on quetiapine 25 mg qhs, alprazolam 0.5 mg bid and zolpidem 5 mg qhs. The latter two medicines were both started during his previous hospitalization for hypertensive crisis. He was also maintained on his previous anti-hypertensive (metoprolol 100 mg qd and lisinopril 10 mg qd) and diabetic (rosiglitazone 1 mg bid, and metformin 500 mg bid) regimens. An electroencephalogram was performed, and the results were negative and inconsistent with delirium or encephalopathy. His vital signs were stable and within normal limits.\nThe next day, he reported that he refused quetiapine the previous night (confirmed with the nursing staff), citing that his paranoia and delusions had resolved. His claims were incongruent with his behaviour, as he was even more inquisitive than previously, again challenging the staff on their medical knowledge and questioning the rationale behind his medical treatment. He requested that he see his medications delivered in their original packaging before taking them. He eventually took his psychotropic medications but refused diabetic management on grounds that he wanted a subspecialist to manage his diabetes. Work-up for pheochromocytoma, porphyria, and heavy metal toxicity was negative. Over the next couple days, Mr. A's paranoia remitted in response to low dose quetiapine, and he became more pleasant, agreeable, and less suspicious. He eventually agreed to the nursing staff dispensing all his medications and to routine management of his diabetes. On day six of admission, Mr. A stated that he felt more trusting and was completely agreeable to the treatment and discharge plan, although he still found it difficult to follow conversations. After confirming follow-up appointments with Mr. A and his wife and obtaining assurances that he would not return to work until after clearance by an outpatient psychiatrist, Mr. A was discharged on quetiapine 100 mg qhs, metoprolol 100 mg qd, lisinopril 10 mg qd, rosiglitazone 1 mg bid, and metformin 500 mg bid.\nConclusion\nMr. A's initial presenting symptoms in the travel clinic were fatigue and a mild headache, both non-specific symptoms that may or may not be attributable to mefloquine. One can assume that Mr. A tolerated the prophylactic mefloquine regimen relatively well as evidenced by the absence of serious neuropsychiatric symptoms during and immediately after his three-week course. However, these lingering non-specific symptoms prompted him to take a therapeutic dose of mefloquine despite a negative blood smear. His neuropsychiatric symptoms appeared the next day, concomitant with the presumed peak of mefloquine, which reaches maximum concentration in the blood within 24 hours of an oral dose [\n1\n].\nMr. A's risk factors for mefloquine-induced psychosis include previous use of anti-malarials for childhood malaria and a single panic attack that occurred ten years prior to this psychotic episode. Drug interactions between mefloquine and anti-hypertensive or anti-diabetic medications may have contributed to the psychosis, but this is unlikely given that Mr. A experienced sleep disturbances, vertigo, anxiety and a panic attack prior to being diagnosed with diabetes and hypertension. Current literature lacks evidence of such interactions aside from one study which demonstrated that mefloquine inhibited the metabolism of metoprolol [\n6\n]. Similarly, the contribution of incidental bacteriuria to Mr. A's altered mental status is plausible but unlikely, given that he had neither pre-existing cognitive impairment nor clinical findings that would suggest a complicated urinary tract infection. Levofloxacin was used to treat his bacteriuria after the initial onset of neuropsychiatric symptoms. Interestingly, levofloxacin is a fluoroquinolone antibiotic structurally related to mefloquine but has a low overall rate of serious CNS adverse events, with such events occurring in only 4 per 100 000 treated patients [\n7\n]. Whether levofloxacin can contribute to pre-existing neuropsychiatric symptoms in an additive manner has yet to be formally investigated. Mr. A's psychotropic medications should not have contributed significantly to his psychotic presentation. Both alprazolam and zolpidem are short-acting drugs that were well tolerated at low doses for one week prior to the acute psychotic episode. In addition, alprazolam, as are other benzodiazepines, has an insignificant risk of inducing psychosis; in fact, this class of drugs has been used in the treatment of acute psychosis [\n8\n-\n10\n]. It is important to note that zolpidem has been reported to induce psychosis at much higher doses, but this phenomenon has been limited to women [\n11\n].\nA review of neuropsychiatric adverse events in an estimated 1.2 million mefloquine prophylaxis users from continental Europe demonstrated only 278 adverse events (0.023%), with the most commonly reported being dizziness, neuropathies, headaches, and psychiatric disorders of affect [\n12\n]. The study was limited by its reliance on self-reporting of adverse events and the use of a crude, overestimated denominator derived from drug sales rather than actual compliance rates. More recent studies have consistently demonstrated that neuropsychiatric adverse events associated with prophylaxis are usually limited to dizziness, bizarre or vivid dreams, and insomnia, but with incidence rates of 10–40% [\n4\n,\n5\n,\n13\n]. Anxiety is less common, with one trial (n = 483) reporting an incidence of 4% in non-immune travelers receiving mefloquine prophylaxis [\n4\n]. Mefloquine-induced panic attacks and psychosis appear to be even rarer events; an observational study of 16,491 subjects on mefloquine prophylaxis described only 9 and 3 events, respectively, during the course of mefloquine use [\n14\n].\nNeuropsychiatric adverse events after \ntherapeutic \ndoses of mefloquine have been difficult to study mainly because malaria itself often causes CNS symptoms, and current practices in endemic regions require mefloquine/artesunate combination therapy due to increasing mefloquine resistance [\n15\n]. Nevertheless, in a limited study of 22 healthy volunteers, almost all participants experienced vertigo, nausea, or headache after a therapeutic dose of mefloquine. Less common events included anxiety, depression, confusion and hallucinations [\n16\n]. An earlier risk analysis of malaria cases in Germany suggested that therapeutic mefloquine increased the risk of neuropsychiatric adverse events by 60-fold over prophylactic doses [\n17\n]. In the treatment of uncomplicated falciparum malaria with mefloquine regimens, randomized, controlled trials in Thailand have consistently shown dose-related increases in both moderate and severe neuropsychiatric adverse events [\n18\n-\n21\n]. Pronounced CNS toxicity was seen in two cases of inadvertent mefloquine overdose secondary to dispensing errors [\n22\n]. One patient developed confusion, agitation, ataxia, dizziness, speech difficulties, and high-frequency hearing loss after taking 15 250 mg of mefloquine over two months. The other patient complained of persistent weakness, depression, disorientation, and paresthesia after taking 16 250 mg of mefloquine within a six month period. In both cases, mefloquine (Lariam) was mistakenly substituted for terbinafine (Lamisil). These data suggest that the incidence and severity of neuropsychiatric events associated with mefloquine use is dose-dependent. Interestingly, serious adverse events do not seem to correlate with mefloquine levels in the blood [\n23\n], implying that the risk of developing neuropsychiatric symptoms may be related to an individual's threshold for mefloquine rather than absolute mefloquine blood levels. The case presented here supports a dose-dependent effect of mefloquine neurotoxicity, as Mr. A developed profound anxiety and subsequent paranoid psychosis only after his dose was escalated from 250 mg to a one-time dose of 1250 mg.\nTo date, the effects of mefloquine on the CNS remain unclear, given the limited literature on this topic. On a biochemical level, there is evidence that mefloquine may disrupt calcium homeostasis and induce a stress response in rat neurons \nin vitro \n[\n24\n]. Also, mefloquine has been shown to inhibit electrical coupling between interneurons in slices of rat neocortex via blockade of gap junctional channels [\n25\n]. At the clinical level, Croft and Herxheimer critically reviewed 516 case reports and proposed that mefloquine exerts its CNS effects via primary hepatotoxicity and symptomatic thyroid dysfunction [\n26\n]. In the present report, work up for hepatic and thyroid dysfunction was negative.\nThis case reveals a unique and insidious natural history of mefloquine neurotoxicity. Prior to developing overt psychosis, Mr. A had initially experienced vertigo and insomnia for several days followed by a full week of escalating anxiety and subtle alterations in behaviour. His anxiety culminated into a panic episode with profound sympathetic activation within a week of taking therapeutic mefloquine. This suggests that an overt mefloquine-induced psychosis can be preceded by a prodromal phase of moderate symptoms such as dizziness, insomnia, and generalized anxiety. Taylor and White reviewed several studies assessing the effect of mefloquine on psychomotor performance and fine motor skills and concluded that mefloquine did not significantly interfere with higher mental function despite causing adverse effects such as sleep disturbances and changes in affect [\n20\n]. The fact that mefloquine toxicity does not usually hinder daily function may mask its potential severity. It is important that physicians advise patients taking mefloquine and their relatives to recognize specific symptoms, especially when they are accompanied by abrupt but subtle changes in behaviour.\nAlthough psychosis is usually self-limited after mefloquine is discontinued, its adverse effects on the CNS may continue for several weeks due to a long elimination half-life. Therapy with atypical antipsychotics, such as risperidone, has shown to be effective in several cases, with psychosis remitting within a few days [\n27\n-\n29\n]. Mr. A responded within two days to low-dose quetiapine with complete resolution of his psychomotor agitation and paranoid delusions. Therefore, recognition of specific neuropsychiatric symptoms and behavioural changes in a patient taking mefloquine may prompt physicians to more carefully assess the patient and intervene if necessary before severe psychosis develops.\nAuthors' contributions\nTT, JB, and MD were involved in the management and care of the patient. TT prepared the manuscript with contribution from MD. All authors read and approved the final manuscript.\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
99
|
[
{
"role": "system",
"content": "You are a medical expert tasked with performing clinical decision support (CDS) to a doctor, by reading a Patient Description and a article of biomedical literature, determining wether that article is relevant to the Patient Description and the Question. \n\nYour task is to evaluate the relevance of the article based on the provided information, including the **Article Title:**, **Article Abstract:** and **Article Body:**, and relating that information with the **Clinical Question:** in the context of the the **Patient Description:**.\n\nYour relevance output will be one of the following, preceded by **Answer:**: \"not relevant\", \"possibly relevant\", or \"definitely relevant\", based on how well the Clinical Trial aligns with the Patient Description.\n\nBe as accurate as possible in your evaluation."
},
{
"role": "user",
"content": "**Article Title:**\n\nPrimary PEComa of the bladder treated with primary excision and adjuvant interferon-alpha immunotherapy: a case report\n\n**Article Abstract:**\n\nBackground\nPerivascular epithelioid cell tumors (PEComas) are rare mesenchymal neoplasms of uncertain malignant potential, which have in common the co-expression of muscle and melanocytic immunohistochemical markers.\nCase presentation\nA 48-year-old man presented with dysuria, passage of urinary sediment and lower abdominal discomfort. A three centimeter mass was identified by cystoscopy in the posterior midline of the bladder. Computerized tomography suggested an enterovesical fistula. The patient underwent laparotomy, partial cystectomy and partial small bowel resection. Pathological examination revealed PEComa of the bladder. The patient underwent adjuvant interferon-α immunotherapy. Subsequent follow-up procedures, including cystoscopy and imaging, have not revealed evidence of recurrence. The patient is clinically free of disease 48 months after surgery.\nConclusion\nThis case represents the second documented PEComa of bladder and demonstrates that adjuvant therapies, including anti-angiogenic and immunotherapy, may be considered for patients with locally advanced or metastatic genitourinary PEComa.\n\n**Article Body:**\n\nBackground\nPrimary perivascular epithelioid cell tumors (PEComas) are a rare and unusual group of mesenchymal neoplasms with unpredictable malignant potential. The term \"PEComa\" was originally coined by Zamboni et al and is the current nomenclature for tumors composed of PECs other than angiomyolipoma (AML), clear cell sugar tumor of lung (CCST) and lymphangioleiomyomatosis (LAM), which are related lesions with distinct clinical features [\n1\n]. Consequent to the World Health Organization's (WHO) endorsement of PEComa as a bonafide entity, an increasing number of reports have documented PEComas arising in varied anatomic locations, including bladder, kidney and prostate [\n2\n-\n8\n]. Despite increasing awareness of this entity, accurately predicting the biological behavior of PEComas remains difficult and contemporary reports are limited by short clinical follow-up. Herein, we report the diagnosis, management and four-year follow-up of the second documented case of primary PEComa of the urinary bladder [\n8\n].\nCase presentation\nA 48-year-old man presented with dysuria, passage of urinary sediment and lower abdominal discomfort. A three-centimeter (cm) smooth, lobular mass with mild bullous edema was identified by cystoscopy in the posterior midline of the bladder. Laboratory and staging investigations were negative and computerized tomography (CT) suggested an enterovesical fistula. The patient underwent laparotomy, partial cystectomy and partial small bowel resection. Pathological examination revealed PEComa of the bladder. A search for primary melanoma was negative and there were no stigmata of tuberous sclerosis. The patient underwent adjuvant interferon (IFN)-α immunotherapy for primary PEComa of the bladder. Subsequent follow-up evaluations were performed 3 monthly for the first 12 months, then 6 monthly thereafter. Routine follow-up procedures included clinical examination, cystoscopy, chest roentgenography, CT of abdomen and pelvis and routine blood work. On one occasion, positron emission tomography was performed in order to detect neoplastic metabolic activity. None of these follow-up procedures revealed evidence of recurrence. The patient is clinically free of disease 48 months after surgery.\nPathology\nA fragmented specimen, 11 cm in aggregate, containing pieces of friable, tan-colored tumor, as well as bladder and small bowel tissue, was received for pathological examination. Histologically, the tumor was located in the bladder wall, but also showed infiltration into subserosal, muscularis propria and submucosal layers of the small bowel. The neoplastic cells were mainly epithelioid but occasionally spindled, with abundant cytoplasm that varied from eosinophilic and granular to clear (Figure \n1\n). The nuclei were round with little pleomorphism; they often contained discernible nucleoli and occasional nuclear inclusions were present. Mitoses were rare to absent and necrosis was inconspicuous. There was no evidence of fat or thick-walled vessels. Periodic acid-Schiff staining, with and without diastase digestion, confirmed the presence of abundant intracytoplasmic glycogen.\nImmunohistochemically, >80% of the tumor cells demonstrated strong positivity for HMB45 (cytoplasmic), Melan-A (cytoplasmic) and smooth muscle actin (membranous), while smooth muscle myosin heavy chain, desmin and CD117 were weakly positive in <20% of the tumor cells (Figures \n2\n &\n3\n). The neoplastic cells failed to stain with antibodies against S100 protein, cytokeratin (AE1/AE3, 8/18), vimentin, muscle specific actin, myoglobin, CD31, CD34 and WT-1. Positive controls were used for all markers as follows: HMB45 and Melan-A – melanoma; S100 – schwannoma; desmin, smooth muscle actin, muscle specific actin, smooth muscle myosin heavy chain and myoglobin – gastrointestinal (GI) smooth muscle; CD117 – GI mast cells and Cajal cells; cytokeratin – GI epithelia; vimentin – GI mesenchyma; CD34 and CD31 – tonsillar endothelia; WT-1 – renal glomeruli. Slides stained omitting the primary antibody were used as negative controls.\nDiscussion\nThe WHO has offered formal recognition to a group of neoplasms with perivascular epithelioid cell differentiation [\n2\n]. These tumors have in common the presence of epithelioid to spindle cells with eosinophilic to clear cytoplasm that, with few exceptions, demonstrate positive immunostaining for markers of both myoid (smooth muscle actin, desmin) and melanocytic (HMB45, Melan-A, tyrosinase) differentiation. Pathologically, the main differential diagnoses include paraganglioma, melanoma, clear cell sarcoma of soft parts (CCSSP), metastatic carcinoma (especially from kidney or adrenal gland) and epithelioid sarcoma.\nWhile distinct clinicopathological entities included within the PEComa group include AML, LAM and CCST, other PEC-derived tumors have been documented at an increasing number of anatomical sites, including pancreas, small and large intestine, ligamentum teres/falciform ligament, common bile duct, bladder, prostate, breast, uterus, cervix, vulva, ovary, broad ligament, heart, base of skull, and soft tissue [\n3\n-\n8\n]. The term \"PEComa\" has become the popular umbrella term for this latter list of lesions. Only one case of primary bladder PEComa has been described previous to ours. Pan et al reported a case of PEComa occurring in the deep detrusor muscle of the bladder in a 33-year-old woman, which was an incidental discovery during work-up for dysmenorrhea [\n8\n]. While there were no worrisome clinicopathological features of the tumor and the patient remained tumor free during the entire six-year follow-up period, there was no description of post-operative treatment.\nPEComas demonstrate uncertain tumor biology and unpredictable clinical behavior. While the majority of reported \"PEComas\" have behaved in a benign fashion, an important minority have demonstrated malignant behavior with locally destructive recurrences, distant metastases and patient death, underscoring the need for accurate identification and effective treatment strategies [\n4\n,\n5\n,\n7\n]. When Folpe et al combined results of 24 of their own cases of PEComa of soft tissue and gynecological origin with data from 45 previously reported cases of PEComa, they found that recurrence and metastasis were associated with tumor size >5 cm, infiltrative growth pattern, high nuclear grade, necrosis and a mitotic index of >1 per 50 high power fields [\n9\n,\n10\n]. However, other authors feel that accurate criteria which reliably predict the behavior of PEComas remain lacking [\n10\n]. In the present case, the surgical margins were not evaluable, due to the fragmented nature of the specimen, and lymph nodes were not sampled, since the intraoperative impression was that of a benign enterovesical fistula, rather than a potentially malignant neoplasm.\nOptimal treatment for PEComas is not known at this time. Primary excision is usually curative, as most tumors are benign. However, locally advanced or metastatic disease portends a poor prognosis and strategies incorporating chemotherapy, radiation and immunotherapy have been reported. In this patient, a one-year course of adjuvant IFN-α 2b at 10 million units given subcutaneously three times per week was initiated based on the vascular nature of this tumor and IFN-α's additional anti-angiogenic effect [\n11\n]. While IFN-α 2b therapy for the management of PEComa remains experimental, other authors have described the efficacy of IFN-α 2a in causing regression of life-threating hemangiomas in infants [\n12\n,\n13\n]. While fever, neutropenia and skin necrosis have been reported as uncommon, short-term side effects of IFN-α 2a, no such effects were seen in the present case [\n12\n]. As there was no evidence of residual tumor in the present case, a limitation of our report would be that the effect of IFN-α on PEComa morphology could not be documented. Thus, further studies are needed to clarify the clinical and pathological effects of IFN-α therapy in patients with PEComa and the risks of IFN therapy should be weighed against the potential benefits in any patient lacking detectable residual tumor. Partial, complete and absent responses have also been noted for dacarbazine, vincristine and imatinib mesylate, a tyrosine-kinase inhibitor [\n14\n]. Adjuvant radiation for CCSSP has also been reported following wide surgical excision, with primary site irradiation appearing to confer a survival benefit for disease located in soft tissue of the extremities [\n15\n].\nConclusion\nIn summary, we report the first case of PEComa of the bladder treated with adjuvant IFN-α immunotherapy, with long-term follow-up. Given the uncertainty of PEComa tumor biology, adjuvant therapies, including anti-angiogenic and immunotherapy, may be considered for patients with locally advanced or metastatic genitourinary PEComa.\nCompeting interests\nThe author(s) declare that they have no competing interests.\nAuthors' contributions\nJRP prepared the manuscript.\nAJB helped to provide patient history and helped in the writing of the manuscript.\nBMW was involved with diagnosis of the pathologic specimen and contributed to the writing of the manuscript.\nJII performed the surgery, provided patient history, obtained patient consent and contributed to the writing of the manuscript.\nAll authors read and approved the final manuscript.\nPre-publication history\nThe pre-publication history for this paper can be accessed here:\n\n**Clinical Question:**\n\nWhat is the patient's diagnosis?\n\n**Patient Description:** \n\n58-year-old woman with hypertension and obesity presents with exercise-related episodic chest pain radiating to the back.\n\nBased on the above information, provide your judgement wether the Article is relevant to answer the Clinical Question, within the context of the Patient Description.\n\nPlease provide your judgement in short form, using \"not relevant\", \"possibly relevant\" and \"definitely relevant\"."
}
] |
[
{
"role": "assistant",
"content": "**Answer:** not relevant"
}
] |
not relevant
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.