Comparison of logistic regression and Bayesian-based algorithms to estimate posttest probability in patients with suspected coronary artery disease undergoing exercise ECG.

Two multivariate methods, a logistic regression-derived algorithm and a Bayesian independence-assuming method (CADENZA), were compared concerning their abilities to estimate posttest probability of coronary disease in patients with suspected coronary disease. All patients underwent exercise testing within 3 months prior to coronary angiography. Coronary disease was defined as the presence of one or more vessels with greater than or equal to 50% luminal diameter narrowing. A group of 300 patients (disease prevalence = 37%) was used to derive the algorithm. Another group of 950 patients was used to validate the algorithm and compare it to CADENZA. Seven variables (age, sex, symptoms, diabetes, mm ST depression, ST slope, and peak heart rate) were used to generate posttest probabilities for each method. The receiver operating characteristic curve area for the logistic regression method (0.81 +/- 0.01) was significantly higher than CADENZA (0.75 +/- 0.01; p less than 0.05). There was, however, no difference in the calibration of the two methods. When given equivalent variable information, the logistic regression algorithm had better discrimination than CADENZA for estimating the probability of coronary disease following exercise electrocardiography.

[1]  R. Detrano,et al.  Application of probability analysis in the diagnosis of coronary artery disease. , 1988, Chest.

[2]  C. Wells,et al.  A comparison of multivariable mathematical methods for predicting survival--II. Statistical selection of prognostic variables. , 1990, Journal of clinical epidemiology.

[3]  R. Detrano.  Optimal use of literature knowledge to improve the Bayesian diagnosis of coronary artery disease. , 1989, Journal of clinical epidemiology.

[4]  B. Chaitman,et al.  A logistic regression analysis of multiple noninvasive tests for the prediction of the presence and extent of coronary artery disease in men. , 1985, American heart journal.

[5]  G. Diamond.  Reverend Bayes' silent majority. An alternative factor affecting sensitivity and specificity of exercise electrocardiography. , 1986, The American journal of cardiology.

[6]  R. Detrano,et al.  Bayesian analysis versus discriminant function analysis: their relative utility in the diagnosis of coronary disease. , 1986, Circulation.

[7]  R. Helfant,et al.  Critical analysis of the application of Bayes' theorem to sequential testing in the noninvasive diagnosis of coronary artery disease. , 1984, The American journal of cardiology.

[8]  P. Greenberg,et al.  Comparison of the multivariate analysis and CADENZA systems for determination of the probability of coronary artery disease. , 1984, The American journal of cardiology.

[9]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[10]  S D Walter,et al.  A comparison of multivariable mathematical methods for predicting survival--III. Accuracy of predictions in generating and challenge sets. , 1990, Journal of clinical epidemiology.

[11]  G A Diamond,et al.  Future imperfect: the limitations of clinical prediction models and the limits of clinical prediction. , 1989, Journal of the American College of Cardiology.

[12]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[13]  S D Walter,et al.  A comparison of multivariable mathematical methods for predicting survival--I. Introduction, rationale, and general strategy. , 1990, Journal of clinical epidemiology.

[14]  G A Diamond,et al.  What price perfection? Calibration and discrimination of clinical prediction models. , 1992, Journal of clinical epidemiology.

[15]  J. Kassirer,et al.  Therapeutic decision making: a cost-benefit analysis. , 1975, The New England journal of medicine.

[16]  G A Diamond,et al.  Clinician decisions and computers. , 1987, Journal of the American College of Cardiology.

[17]  G. Diamond,et al.  Computer-assisted diagnosis in the noninvasive evaluation of patients with suspected coronary artery disease. , 1983, Journal of the American College of Cardiology.

[18]  R. Patterson,et al.  Practical diagnosis of coronary artery disease: a Bayes' theorem nomogram to correlate clinical data with noninvasive exercise tests. , 1984, The American journal of cardiology.

[19]  L. Leamy,et al.  Use of the multivariate approach to enhance the diagnostic accuracy of the treadmill stress test. , 1980, Journal of electrocardiology.

[20]  G. Diamond.  A clinically relevant classification of chest discomfort. , 1983, Journal of the American College of Cardiology.

[21]  G. Diamond,et al.  Analysis of probability as an aid in the clinical diagnosis of coronary-artery disease. , 1979, The New England journal of medicine.

[22]  R. Duval,et al.  Comparison of three Bayesian methods to estimate posttest probability in patients undergoing exercise stress testing. , 1989, The American journal of cardiology.

[23]  J. Hilden.  Statistical diagnosis based on conditional independence does not require it. , 1984, Computers in biology and medicine.

[24]  D. Fryback.  Bayes' theorem and conditional nonindependence of data in medical diagnosis. , 1978, Computers and biomedical research, an international journal.

[25]  L. Cupples,et al.  Multiple testing of hypotheses in comparing two groups. , 1984, Annals of internal medicine.

[26]  R. Kronmal,et al.  The effect of assuming independence in applying Bayes' theorem to risk estimation and classification in diagnosis. , 1983, Computers and biomedical research, an international journal.

[27]  R. Detrano,et al.  International application of a new probability algorithm for the diagnosis of coronary artery disease. , 1989, The American journal of cardiology.

[28]  D S Berman,et al.  A model for assessing the sensitivity and specificity of tests subject to selection bias. Application to exercise radionuclide ventriculography for diagnosis of coronary artery disease. , 1986, Journal of chronic diseases.

[29]  G. Diamond.  Affirmative Actions , 1991, Medical decision making : an international journal of the Society for Medical Decision Making.

[30]  R. Detrano,et al.  The Reliability of Probability Analysis in the Prediction of Coronary Artery Disease in Two Hospitals , 1989, Medical decision making : an international journal of the Society for Medical Decision Making.

[31]  R. Duval,et al.  The estimation of post-test probability of coronary disease following exercise testing using the sequential application of two Bayesian methods. , 1990, American heart journal.