A Novel Detection of Ventricular Tachycardia and Fibrillation Based on Degree Centrality of Complex Network

Abstract

With the increasing number of cardiovascular disease, some scholars studied it deeply and found that vast majority of sudden cardiac death was due to ventricular fibrillation (VF) or sustained ventricular tachycardia (VT). However, they take different treatment measures. As for patients with VF, we must take defibrillation measure; and patients with VT, we should take low-energy complex heart rate measure. If we misjudge them, the result would be horrific even taking patients’ life. So in this paper, we put up with a novel detection based on degree centrality of complex network to distinguish the VT and VF signals. We utilize the characteristics of complex network to analyze the VF and VT signal. At first, we convert the time series into complex network domain by using horizontal visibility graph. Then we analyze the complex network and extract the degree centrality as the single feature to classify the VF and VT signals. Experimental results show that the classification accuracy is up to 99.5%.