Premature ventricular contraction arrhythmia detection using wavelet coefficients

Abstract

Premature ventricular contraction (PVC) detection is an important task in critical care medicine. However, making this task automatic is not that simple. In this paper, we are describing a method for PVC arrhythmia detection. This method is based on the use of wavelet detail coefficients to discriminate between normal beats and abnormal beats (PVCs). The proposed method was tested against selected records of the MIT-BIH Arrhythmia Database (MITDB). Results are very satisfactory and show that it is possible to detect PVC arrhythmia using wavelet detail coefficients applied to QRS complexes.