A Bayesian expert system for clinical detecting coronary artery disease

Chi Ming Chu, Wu Chien Chien, Ching Huang Lai, Hans Bernd Bludau, Huei Jane Tschai, Lu Pai, Shih Ming Hsieh, Nian Fong Chu, Angus Klar, Reinhold Haux, Thomas Wetter

研究成果: 雜誌貢獻文章

11 引文 (Scopus)

摘要

Background: The purpose of this study was to use a data mining technique to develop an expert system of the Bayesian model for detecting coronary artery disease (CAD). In addition, this study provides an evaluation of CAD detection before an invasive cardiac angiography as well as a paradigm for implementing relevant expert systems in the future. Methods: The study samples were drawn from all patients with cardiac angiography between August 1, 2005 and July 31, 2006, from the cardiac department in a medical center (Tri-Service General Hospital, TSGH), excluding samples with acute myocardial infarction, dilated cardio myopathy and rheumatic heart disease. A total of 415 samples were studied. All CAD-related risk factors were data-mined using a training set of randomly extracted 204 samples. All risk factors were calculated for sensitivity and specificity for Bayesian modeling and the implementation of the localized rules of a knowledge based. Furthermore, this study also quoted the epidemiological results of the knowledge based external rules from the PROspective Cardiovascular Münster study (PROCAM). Two knowledge bases, the TSGH base and the PROCAM base, were validated by a testing set of 211 samples. Results: The accuracy rates of the TSGH and PROCAM bases were as high as 70%. For detecting CAD, the localized data mining of the TSGH-based AUC was more stable at 86.2%, outperforming the PROCAM-based AUC of 82.2%. Conclusions: In this study, an evidence-based clinical expert system of the Bayesian model provides an evaluation for detecting CAD before an invasive cardiac angiography as well as a paradigm for relevant expert systems.
原文英語
頁(從 - 到)187-194
頁數8
期刊Journal of Medical Sciences (Taiwan)
29
發行號4
出版狀態已發佈 - 八月 2009

指紋

Expert Systems
Coronary Artery Disease
General Hospitals
Angiography
Data Mining
Area Under Curve
Rheumatic Heart Disease
Knowledge Bases
Muscular Diseases
Myocardial Infarction
Sensitivity and Specificity

ASJC Scopus subject areas

  • Medicine(all)

引用此文

Chu, C. M., Chien, W. C., Lai, C. H., Bludau, H. B., Tschai, H. J., Pai, L., ... Wetter, T. (2009). A Bayesian expert system for clinical detecting coronary artery disease. Journal of Medical Sciences (Taiwan), 29(4), 187-194.

A Bayesian expert system for clinical detecting coronary artery disease. / Chu, Chi Ming; Chien, Wu Chien; Lai, Ching Huang; Bludau, Hans Bernd; Tschai, Huei Jane; Pai, Lu; Hsieh, Shih Ming; Chu, Nian Fong; Klar, Angus; Haux, Reinhold; Wetter, Thomas.

於: Journal of Medical Sciences (Taiwan), 卷 29, 編號 4, 08.2009, p. 187-194.

研究成果: 雜誌貢獻文章

Chu, CM, Chien, WC, Lai, CH, Bludau, HB, Tschai, HJ, Pai, L, Hsieh, SM, Chu, NF, Klar, A, Haux, R & Wetter, T 2009, 'A Bayesian expert system for clinical detecting coronary artery disease', Journal of Medical Sciences (Taiwan), 卷 29, 編號 4, 頁 187-194.
Chu CM, Chien WC, Lai CH, Bludau HB, Tschai HJ, Pai L 等. A Bayesian expert system for clinical detecting coronary artery disease. Journal of Medical Sciences (Taiwan). 2009 8月;29(4):187-194.
Chu, Chi Ming ; Chien, Wu Chien ; Lai, Ching Huang ; Bludau, Hans Bernd ; Tschai, Huei Jane ; Pai, Lu ; Hsieh, Shih Ming ; Chu, Nian Fong ; Klar, Angus ; Haux, Reinhold ; Wetter, Thomas. / A Bayesian expert system for clinical detecting coronary artery disease. 於: Journal of Medical Sciences (Taiwan). 2009 ; 卷 29, 編號 4. 頁 187-194.
@article{dd431870eeaa4261bb45ca6562bbf8a6,
title = "A Bayesian expert system for clinical detecting coronary artery disease",
abstract = "Background: The purpose of this study was to use a data mining technique to develop an expert system of the Bayesian model for detecting coronary artery disease (CAD). In addition, this study provides an evaluation of CAD detection before an invasive cardiac angiography as well as a paradigm for implementing relevant expert systems in the future. Methods: The study samples were drawn from all patients with cardiac angiography between August 1, 2005 and July 31, 2006, from the cardiac department in a medical center (Tri-Service General Hospital, TSGH), excluding samples with acute myocardial infarction, dilated cardio myopathy and rheumatic heart disease. A total of 415 samples were studied. All CAD-related risk factors were data-mined using a training set of randomly extracted 204 samples. All risk factors were calculated for sensitivity and specificity for Bayesian modeling and the implementation of the localized rules of a knowledge based. Furthermore, this study also quoted the epidemiological results of the knowledge based external rules from the PROspective Cardiovascular M{\"u}nster study (PROCAM). Two knowledge bases, the TSGH base and the PROCAM base, were validated by a testing set of 211 samples. Results: The accuracy rates of the TSGH and PROCAM bases were as high as 70{\%}. For detecting CAD, the localized data mining of the TSGH-based AUC was more stable at 86.2{\%}, outperforming the PROCAM-based AUC of 82.2{\%}. Conclusions: In this study, an evidence-based clinical expert system of the Bayesian model provides an evaluation for detecting CAD before an invasive cardiac angiography as well as a paradigm for relevant expert systems.",
keywords = "Bayesian expert system, Coronary Artery Disease (CAD), Cut-off point, Hospital-based epidemiology",
author = "Chu, {Chi Ming} and Chien, {Wu Chien} and Lai, {Ching Huang} and Bludau, {Hans Bernd} and Tschai, {Huei Jane} and Lu Pai and Hsieh, {Shih Ming} and Chu, {Nian Fong} and Angus Klar and Reinhold Haux and Thomas Wetter",
year = "2009",
month = "8",
language = "English",
volume = "29",
pages = "187--194",
journal = "Journal of Medical Sciences",
issn = "1011-4564",
publisher = "國防醫學院",
number = "4",

}

TY - JOUR

T1 - A Bayesian expert system for clinical detecting coronary artery disease

AU - Chu, Chi Ming

AU - Chien, Wu Chien

AU - Lai, Ching Huang

AU - Bludau, Hans Bernd

AU - Tschai, Huei Jane

AU - Pai, Lu

AU - Hsieh, Shih Ming

AU - Chu, Nian Fong

AU - Klar, Angus

AU - Haux, Reinhold

AU - Wetter, Thomas

PY - 2009/8

Y1 - 2009/8

N2 - Background: The purpose of this study was to use a data mining technique to develop an expert system of the Bayesian model for detecting coronary artery disease (CAD). In addition, this study provides an evaluation of CAD detection before an invasive cardiac angiography as well as a paradigm for implementing relevant expert systems in the future. Methods: The study samples were drawn from all patients with cardiac angiography between August 1, 2005 and July 31, 2006, from the cardiac department in a medical center (Tri-Service General Hospital, TSGH), excluding samples with acute myocardial infarction, dilated cardio myopathy and rheumatic heart disease. A total of 415 samples were studied. All CAD-related risk factors were data-mined using a training set of randomly extracted 204 samples. All risk factors were calculated for sensitivity and specificity for Bayesian modeling and the implementation of the localized rules of a knowledge based. Furthermore, this study also quoted the epidemiological results of the knowledge based external rules from the PROspective Cardiovascular Münster study (PROCAM). Two knowledge bases, the TSGH base and the PROCAM base, were validated by a testing set of 211 samples. Results: The accuracy rates of the TSGH and PROCAM bases were as high as 70%. For detecting CAD, the localized data mining of the TSGH-based AUC was more stable at 86.2%, outperforming the PROCAM-based AUC of 82.2%. Conclusions: In this study, an evidence-based clinical expert system of the Bayesian model provides an evaluation for detecting CAD before an invasive cardiac angiography as well as a paradigm for relevant expert systems.

AB - Background: The purpose of this study was to use a data mining technique to develop an expert system of the Bayesian model for detecting coronary artery disease (CAD). In addition, this study provides an evaluation of CAD detection before an invasive cardiac angiography as well as a paradigm for implementing relevant expert systems in the future. Methods: The study samples were drawn from all patients with cardiac angiography between August 1, 2005 and July 31, 2006, from the cardiac department in a medical center (Tri-Service General Hospital, TSGH), excluding samples with acute myocardial infarction, dilated cardio myopathy and rheumatic heart disease. A total of 415 samples were studied. All CAD-related risk factors were data-mined using a training set of randomly extracted 204 samples. All risk factors were calculated for sensitivity and specificity for Bayesian modeling and the implementation of the localized rules of a knowledge based. Furthermore, this study also quoted the epidemiological results of the knowledge based external rules from the PROspective Cardiovascular Münster study (PROCAM). Two knowledge bases, the TSGH base and the PROCAM base, were validated by a testing set of 211 samples. Results: The accuracy rates of the TSGH and PROCAM bases were as high as 70%. For detecting CAD, the localized data mining of the TSGH-based AUC was more stable at 86.2%, outperforming the PROCAM-based AUC of 82.2%. Conclusions: In this study, an evidence-based clinical expert system of the Bayesian model provides an evaluation for detecting CAD before an invasive cardiac angiography as well as a paradigm for relevant expert systems.

KW - Bayesian expert system

KW - Coronary Artery Disease (CAD)

KW - Cut-off point

KW - Hospital-based epidemiology

UR - http://www.scopus.com/inward/record.url?scp=69549098251&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69549098251&partnerID=8YFLogxK

M3 - Article

VL - 29

SP - 187

EP - 194

JO - Journal of Medical Sciences

JF - Journal of Medical Sciences

SN - 1011-4564

IS - 4

ER -