Detection and Classification of Cardiac Arrhythmias based on ECG and PCG using Temporal and Wavelet features

Abstract: Arrhythmias are abnormal rhythms of heart. Sudden Cardiac Arrest is most often caused by life threatening arrhythmias such as Ventricular Tachycardia (VT) and Ventricular Fibrillation (VF). Early detection of life threatening arrhythmias is crucial for successive defibrillation therapy. In general heart diseases have been investigated by various methods. Among these Electrocardiography (ECG) test is considered as the best noninvasive method of investigation. ECG test is varied if the heart sound from the Phonocardiogram shows any abnormalities. So Phonocardiography (PCG) is also considered for more efficiency. Commonly used arrhythmia detection and classification algorithms are only based on surface Electrocardiogram analysis. So an algorithm corresponds to multiresolution wavelet analysis using temporal and wavelet features of Electrocardiogram and Phonocardiogram along with Electrocardiogram-Phonocardiogram relationships is designed so as to increase the efficiency of the heart diagnostics. Temporal and wavelet features of ECG and PCG along with the linear prediction coefficients representing ECG and PCG are fed to the classifier for classification. The goal of this work is to achieve an efficient arrhythmia detection system that can lead to high performance heart diagnostics.

Keywords: DWT,ECG, HRV,LPC, Multiresolution, Massachusetts Institute of Technology/Beth Isrel Hospital (MIT-BIH) ECG arrhythmia database, PCG, SVM.