Artificial neural networks were created to predict the occurrence of coronary artery disease based on information from the serum lipid profile. The development of the networks involved a strategy which permitted learning from censored observations. The networks were developed with data from the Cholesterol Lowering Atherosclerosis Study, which followed serum lipoprotein levels and clinical events in 162 patients over a period of up to 10 years. Inputs consisted of seven different mean lipid values, and the desired output was the time period during which a complication of coronary artery disease was predicted to occur. Cross-validation was performed by splitting the data into separate training and testing sets, scoring the performance of the neural network strategy on the testing sets, and comparing scores with those obtained from Cox regression models developed on the same training data. Performance of the neural network strategy exceeded that of Cox regression in predicting clinical outcomes (66% vs 56%, McNemar's test P = 0.005). The network design provided an effective approach to predicting outcomes from a clinical trial with variable follow-up times.