Chaotic based reconstructed phase space features for detecting ventricular fibrillation

Among the variety of cardiac arrhythmias, ventricular fibrillation (VF) and ventricular tachycardia (VT) are life-threatening; thus, accurate classification of these arrhythmias is a crucial task for cardiologists. Nevertheless, VT and VF signals are very similar in the time domain and accurate distinguishing these signals with naked eyes in some cases is impossible. In this paper, a novel self-similarity image-based scheme is introduced to classify the underlying information of VT, VF and normal electrocardiogram (ECG) signals. In this study, VT, VF and normal ECG signals are selected from CCU of the Royal Infirmary of Edinburgh and MIT-BIH datasets. According to the time delay method, signal samples can be assigned to state variables and a trajectory can be achieved. To extract the proposed self-similarity feature, first, two different trajectories from each signal trial are drawn according to two different delay time values. The two-dimensional state space of each trial trajectory is considered as an image. Therefore, two trajectory images are produced for each signal. Number of visited pixels in the first image is determined and is subtracted from that of the second image as the self-similarity feature of that signal. Moreover, another scheme is proposed to have a better estimation of self-similarity in which the logical AND operator is applied to both images (matrices) of each ECG trial. The third proposed criterion is similar to box counting method by this difference that each pixel is assigned a weight according to the trajectory density at that point and finally visited weighted pixels are counted. To classify VF from VT and normal ECG, a threshold is determined through the cross validation phase under the Receiver Operating Characteristic (ROC) criterion. To assess the proposed methods, the mentioned signals are classified using the-state-of-art chaotic features such as correlation dimension, the largest Lyapunov exponent and Approximate Entropy (ApEn). Experimental results indicate superiority of the proposed method in classifying the VT, VF and normal ECG signals compared to present traditional schemes. In addition, computational complexity of the introduced methods is very low and can be implemented in real-time applications.