Probabilistic diagnosis and prognosis of coronary artery disease

More and more tests are being added to clinical practice, and the interpretation of these tests is becoming increasingly complicated. Multiple, even discordant, test results can be better interpreted using more sophisticated statistical methods that allow the physician to evaluate the cumulative effect of all available data. For example, a microcomputer program called CADENZA, which uses Bayes’ theorem, was developed to aid in the diagnosis and prognosis of coronary artery disease. Our experience with this program correlates well with the prediction of angiographic disease prevalence, the discrimination of multivessel disease from single-vessel disease, the incidence of coronary events (death and nonfatal infarction) in the year following testing, and the results of multivariate discriminant analysis.