Knowledge-Based QRS Detection Performed by a Cascade of Moving Average Filters

Abstract

The detection of QRS complexes is a crucial step since all the subsequent processing of the ECG signal is very sensitive to the accuracy of this detection. This study presents an accurate and computationally efficient approach to heartbeat detection based on preprocessing and enhancement of the QRS complexes by means of cascades of moving averages. Several derivative QRS-enhancing moving averages filters were defined which were characterized by different shapes of the impulsive response. In the initialization phase of the algorithm, the best filter for each record was selected by maximizing a specifically defined signal quality index. Detection of the QRS complex was based on a decision logic and a set of adaptive thresholds. The MIT-BIH, QTDB and EU ST-T databases were considered for performance evaluation and comparison with the output of some publicly available QRS Pan-Tompkins detectors, obtaining results comparable to the best reported in the literature (F1=99.84% and 98.46% on MIT-BIH channel 1 and 2 respectively).