Sudden Cardiac Arrest Detection by Feature Learning and Classification Using Deep Learning Architecture

Abstract

Ventricular tachycardia (VT) and ventricular fibrillation (VF) are known ventricular cardiac arrhythmias (VCA) that promote fast defibrillation treatment for the survival of patients and are defined as shock-oriented signals, perhaps the most common source of sudden cardiac arrest (SCA). The majority of existing VCA classifiers confront a difficult challenge of accuracy rate, which has generated the issue of continuous detection and classification approaches. In light of this, the authors present a feature learning strategy that uses the improved variational mode decomposition technique to detect VCA on ECG signals. The following SCA consists of a deep convolutional neural network (deep CNN) as a feature extractor and bat-rider optimization algorithm (BROA) as an optimized classifier. The MIT-BIH arrhythmia database is used to examine the approaches, and the analysis depends on performance indicators such as accuracy, specificity, sensitivity, recall, and F1-score.