Classification of Ventricular Tachycardia and Fibrillation Based on the Lempel-Ziv Complexity and EMD

Detection of ventricular tachycardia (VT) and ventricular fibrillation (VF) in electrocardiography (ECG) has clinical research significance. The complexity of the heart signals has changed significantly, when the heart state switches from normal sinus rhythm to VT or VF. With the consideration of the non-stationary of VT and VF, we proposed a novel method for classification of VF and VT in this paper, based on the Lempel–Ziv (LZ) complexity and empirical mode decomposition (EMD). The EMD first decomposed ECG signals into a set of intrinsic mode functions (IMFs). Then the complexity of each IMF was used as a feature in order to discriminate between VF and VT. A public dataset was utilized for evaluating the proposed method. Experimental results showed that the proposed method could successfully distinguish VF from VT with the highest accuracy up to 97.08%.