Detection of acute myocardial ischemia based on support vector machines

Abstract

In patients with acute myocardial ischemia, chest pains together with changes in ST/T sections of ECG signal occur before the start of myocardial infarction. In this study, in order to diagnose acute myocardial ischemia, a technique which automatically detects changes in ST/T sections of ECG is developed. For this purpose, by using ECG recordings of STAFF III database, ECG features that are critical in the detection of acute myocardial ischemia are identified. By using support vector machines (SVM) operating with linear and radial basis function (RBF) kernels, classifiers that use two and four most discriminating features of ST/T sections of ECG signal are designed. As a result of implementing the developed technique on ECG recordings of STAFF III database, obtained results over a considerable number of patients indicate that the proposed technique provides highly reliable detection of acute myocardial ischemia. Therefore, by using the developed technique, early and accurate diagnosis of acute myocardial ischemia can be performed, which can lead to a significant decrease in morbidity and mortality rates.