Classification of Arrhythmia Using Machine Learning Algorithm

Abstract

Detection of Atrial fibrillation (AF) is more complex as compared to other cardiac diseases. It requires lengthy ECG signals and more time for visual inspection and analysis by the physicians. Automatic detection of AF using an expert system is essential for the investigation of ECG signals. In this study, the Physionet challenge 2017 dataset is used for the detection and classification of AF versus other signals. In this paper, ECG signals are segmented into a sample size of 250 samples for the detection of Wavelet Packet Decomposition (WPD) and approximate entropy (ApEn) features for classification. In addition to WPD and ApEn, statistical features were derived from ECG signals. The Principal Component Analysis (PCA) has been used to reduce the dimensionality of the features based on the rank. Ensemble classifiers such as AdaBoost, XGBoost and Random Forest (RF) are used for classification. The accuracy of 62.91%, 70.33% and 89% for the AdaBoost, XGBoost and Random Forest respectively. We found RF classifier is suitable for classifying AF, normal rhythm and other non-AF related abnormal heart rhythms.