Quantitative methods to enhance clinical judgment would be of tremendous benefit to physicians caring for the critically ill. The ability of physicians to predict outcome is a logical standard on which to base the prospective evaluation of a prediction rule intended for this clinical use. The APACHE (acute physiology and chronic health evaluation)-II score was compared with critical care physicians' prediction of outcome for a group of patients in a medical intensive care unit. Physicians were significantly better in predicting outcome in the critically ill. However, the APACHE-II score was still a good predictor of outcome in the intensive care unit and, according to analysis using Bayes' theorem, might still be a useful test to support physicians' judgment, especially in patients with a predicted mortality risk of less than 30%.