Artificial neural networks in outcome prediction

Artificial neural networks have been successfully used for pattern recognition and outcome prediction in several clinical settings. The advantage of a neural network is the ability of the model to capture nonlinearities and complex interactions between factors related to the outcome of interest. Neural networks also differ from other decision support systems in that the learning occurs by example through training and not by programming or pre-defined rules. Promising surgical applications include preoperative estimation of surgical risk and quality control within a hospital or health care system. An optimal system would estimate the outcome for the individual patient using all the prognostic and risk information inherent in the available patient characteristics.