Detection Ventricular Tachycardia and Fibrillation using the Lempel-Ziv complexity and Wavelet transform

Detection of ventricular tachycardia (VT) and ventricular fibrillation (VF) is crucial for the success of saving the patient’s life. The complexity of the heart signals has changed significantly when the heart state switches. In this study we proposed a novel method for detection of ventricular fibrillation (VF) and ventricular tachycardia (VT), based upon the Lempel-Ziv complexity and Wavelet transform. With Mallat’s pyramidal algorithms, first decomposed electrocardiogram (ECG) signals and reconstructed it into approximate and detail coefficients. Then the complexity of each scale was used as a feature to be sent to SVM classifiers. Furthermore, other classification VT and VF methods were used. The experimental results showed the proposed method could successfully distinguish VF from VT with the highest accuracy up to 99.50%. Key-words: Ventricular Fibrillation, Ventricular Tachycardia, the Lempel–Ziv Complexity, Mallat’s Pyramidal Algorithms.