Effective ECG Beat Classification and Decision Support System Using Dual-Tree Complex Wavelet Transform

Abstract

The valuable information about the conditions of heart of a patient can be obtained by the analysis of electrocardiogram (ECG) signal. The wavelet transform is a powerful time–frequency analysis tool for complex and nonstationary signals like ECG signal. Both the continuous and the discrete wavelet transforms have been found to be effective in ECG signal analysis. In this chapter, we presented a novel method based on multiresolution wavelet transform for detecting and decision-making process for automatic analysis of cardiac arrhythmia. Dual-tree complex wavelet transform (DT-CWT) is used for the detection of R-peaks and QRS complex. The time interval, morphological, and statistical features are used to classify the irregular heartbeats such as normal (N), left bundle branch block (LBBB), right bundle branch block (RBBB), atrial premature beats (APBs) and premature ventricular contractions (PVCs) using K-nearest neighbor (K-NN) classifier. MIT–BIH arrhythmia database has been used for the evaluation of effectiveness of our proposed method in terms of sensitivity (Se), specificity (Sp), positive predictivity (Pp), and accuracy (Acc). The best performance result was achieved at tenfold with an accuracy of 98.92% in K-NN. The classification accuracy of K-NN algorithm proves better in classifying arrhythmia beats using DT-CWT-based extracted features.