The determination of cardiac surgical risk using artificial neural networks

Background. In the study presented here, an artificial neural network was u sed to "learn" the relationship between 11 risk factors and patient surgica l outcome (survival or death). The network was then used to predict the sur gical outcome of other patients. Methods. Eleven risk factors were presented as inputs to an artificial neur al network (ANN). The ANN model was developed by training and testing on 18 75 patients, The results of the ANN were compared with the results from two versions of the VA surgical risk model (Denver model). Cutoffs were determ ined for each model in order to compare their results. Results. The ANN model gave the best results when compared with the new and old Denver models. The ANN model had the lowest overall percentage of erro r. It predicted living patients with an error of 14% and death with an erro r of similar to 31.0%. The old Denver model predicted living patients with an error of 15% and deaths with an error of 31%. The new Denver model predi cts living patients with an error around 18% and the deaths with an error o f 31%. Conclusions. The combined predictions of the ANN model were slightly more a ccurate than either the new or the old Denver models. The ANN model was cre ated from 1875 patients in about 1 month, while both of the Denver models w ere developed over a 3 year time period and used more than 12,000 patients. Additionally, the ANN model is easily modified, allowing instant addition or deletion of parameters to suit the users needs. (C) 2001 Academic Press.