Automatic Detection of the R Peaks in Single-Lead ECG Signal

The accurate delineation of R peaks in an ElectroCardioGram (ECG) is required for analysis and diagnosis of various cardiac abnormalities. Detection of the R peak is a challenging task due to the presence of various artifacts and varying morphology of the ECG signal in inter- and intrasubject. In this paper, an effective and novel algorithm for the accurate detection of R peaks in the single-lead ECG signal is proposed. The QRS complex is enhanced by removing P, T waves and other artifacts using combination of wavelet transform, derivatives and Hilbert transform. The enhanced QRS complex is detected by adaptive thresholding. This method is robust against inter- and intrasubject variations of the ECG signal morphology and also provides high degree of accuracy for very noisy signals. The algorithm is tested on all the signals of MIT-BIH arrhythmia Database, QT database and noise stress database taken from physionet.org (Massachusetts Institute of Technology, Biomedical Engineering Center, Cambridge, MA, 1992. www.physionet.org/physiobank/databse/html/mitdbdir/mitdbdir.htm). The performance of the algorithm is confirmed by sensitivity of 99.9%, positive predictivity of 99.9% and detection accuracy of 99.8% for R peaks detection.