Detection of Acute Coronary Syndrome Based on Support Vector Machines and ECG

摘要

In patients with acute coronary syndrome (ACS), transient chest pains together with changes in ST segment and T wave of ECG signal occur before the start of myocardial infarction. In this study, a technique which detects the anomalies in ST segment and T wave of ECG signal by using the state-of-theart signal processing and machine learning methods is developed to perform the robust detection of ACS. For this purpose, by using the wideband recordings on STAFF III database, a novel feature extraction technique which obtains the most discriminative ECG features for the detection of ACS is developed. By using the critical features, a supervised learning technique based on support vector machines (SVM) and kernel functions which performs the robust detection of ACS is developed. The performance results of the proposed technique obtained from a considerable number of patients on STAFF III database indicate that the technique provides highly reliable detection of ACS.