A con®dent decision support system for interpreting electrocardiograms

Computer-aided interpretation of electrocardiograms (ECGs) is widespread but many physicians hesitate to rely on the computer, because the advice is presented without information about the con®dence of the advice. The purpose of this work was to develop a method to validate the advice of a computer by estimating the error of an arti®cial neural network output. A total of 1249 ECGs, recorded with computerized electrocardiographs, on patients who had undergone diagnostic cardiac catheterization were studied. The material consisted of two groups, 414 patients with and 835 without anterior myocardial infarction. The material was randomly divided into three data sets. The ®rst set was used to train an arti®cial neural network for the diagnosis of anterior infarction. The second data set was used to calculate the error of the network outputs. The last data set was used to test the network performance and to estimate the error of the network outputs. The performance of the neural network, measured as the area under the receiver operating characteristic (ROC) curve, was 0á887 (0á845±0á922). The 25% test ECGs with the lowest error estimates had an area under the ROC curve as high as 0á995 (0á982±1á000), i.e. almost all of these ECGs were correctly classi®ed. Neural networks can therefore be trained to diagnose myocardial infarction and to signal when the advice is given with great con®dence or when it should be considered more carefully. This method increases the possibility that arti®cial neural networks will be accepted as reliable decision support systems in clinical practice.