A Diagnostic System for Detection of Atrial and Ventricular Arrhythmia Episodes from Electrocardiogram

Cardiac arrhythmias, with each passing day, are becoming highly prevalent in modern society. The ever increasing number of patients added to the sheer amount of data that is recorded from a patient during monitoring limits the ability of a medical practitioner to diagnose these problems quickly. Therefore, an intelligent system is required which can produce a reliable diagnosis in a short period of time. In this paper, a new intelligent diagnostic system for detection of atrial arrhythmia (atrial flutter and atrial fibrillation) and ventricular arrhythmia (premature ventricular contractions, ventricular bigeminy, ventricular escape rhythm, ventricular tachycardia and ventricular fibrillation) episodes from Electrocardiogram (ECG) is proposed. This system is based on the non-linear analysis of the variational modes of ECG. Variational mode decomposition is used for decomposition of ECG signal into several modes. Then, the non-linear features namely, the distribution entropy and the sample entropy are evaluated from the modes of ECG. The performance of variational mode distribution entropy (VMDE) and variational mode sample entropy (VMSE) features is assessed using support vector machine (SVM) and adaptive neuro-fuzzy inference system classifiers. Experimental results reveal that, the combination of VMDE and VMSE features, and the radial basis function kernel based multi-class SVM classifier are suitable for detection of arrhythmia episodes from ECG with an average accuracy value of 95.60%.