In spite of great technological improvement in Ambulatory ECG Monitoring (AEM), there is still debate about its reliability in detecting ECG signs of myocardial ischemia and about the utility of AEM and Exercise Stress Testing (ET)--apart and/or in association--to predict Coronary Artery Disease (CAD). 50 consecutive male patients (pts) (mean age 51 +/- 69 years, 37 to 64 years) were studied for precordial chest pain. 17 had evidence of previous myocardial infarction. Resting ECG was normal in 21 pts and abnormal in 29; no pt received therapy during the examination period. ECG recordings were considered positive for ischemic ECG changes if there was greater than or equal to 1 mm of horizontal or down sloping ST-segment depression or ST-segment elevation of the same degree for greater than or equal to 0.08 sec in at least 15 consecutive beats; coronary arteriography was considered positive for significant CAD if any major vessel had greater than or equal to 75% luminal diameter narrowing. The percentage of false negative results was similar in AEM and ET (22.7% vs 22.2%); the false positives were few with both tests: 2 pts and 1 pt respectively; Bayesian probability (post-test likelihood for disease) calculated using the prevalence of CAD estimated from 2124 male pts who underwent coronary angiography in our Laboratory, for a given test result was very high: 97.1% +/- 1.3% (AEM), 98.6% +/- 1.1% (ET) and 98.1% +/- 1.1% (AEM & ET if concordant); post-test likelihood for CAD in a patient who did not show the given test result decreased to 67.8% +/- 1.3% (AEM), 60.9% +/- 1.1% (ET) and 52.1% +/- 1.1% (AEM & ET if concordant). The application of Bayes' theorem to these two non invasive tests improves the evaluation of patients with suspected CAD; the association of AEM and ET enhances the diagnostic accuracy.