Feature selection using genetic algorithms for premature ventricular contraction classification

Cardiac arrhythmia is one of the most important indicators of heart disease. Premature ventricular contractions (PVCs) are a common form of cardiac arrhythmia caused by ectopic heartbeats. The detection of PVCs by means of ECG (electrocardiogram) signals is important for the prediction of possible heart failure. This study focuses on the classification of PVC heartbeats from ECG signals and, in particular, on the performance evaluation of selected features using genetic algorithms (GA) to the classification of PVC arrhythmia. The objective of this study is to apply GA as a feature selection method to select the best feature subset from 200 time series features and to integrate these best features to recognize PVC forms. Neural networks, support vector machines and k-nearest neighbour classification algorithms were used. Findings were expressed in terms of accuracy, sensitivity, and specificity for the MIT-BIH Arrhythmia Database. The results showed that the proposed model achieved higher accuracy rates than those of other works on this topic.