Detection of Premature Ventricular Contraction for real-time applications

Abstract

This paper proposes a real-time algorithm of Premature Ventricular Contraction (PVC) detection based on a low computational method. This algorithm considers three time-domain features which are RR-interval, QRS-width and QRS-pattern. Simple decision rules are used in the classifier process which is suitable for embedded applications. The algorithm was tested with 26 ECG records from MIT-BIH Arrhythmia Database (MIT-DB). After evaluation, the performance of the proposed method has 91.05% of sensitivity and 99.55% of specificity.