Automatic detection of P, QRS and T patterns in 12 leads ECG signal based on CWT. (March 2016)

• Record Type: Journal Article
• Authors: Yochum, Maxime; Renaud, Charlotte; Jacquir, Sabir
• Is Part Of: Biomedical signal processing and control. Volume 25(2016)
• Page Start: 46
• Page End: 52
• Publication Date: 2016-03
• Subjects: ECG -- P, QRS and T waves -- Delineation -- Wavelet transform; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2015.10.011
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: In this paper, a new method based on the continuous wavelet transform is described in order to detect the QRS, P and T waves. QRS, P and T waves may be distinguished from noise, baseline drift or irregular heartbeats. The algorithm, described in this paper, has been evaluated using the Computers in Cardiology (CinC) Challenge 2011 database and also applied on the MIT-BIH Arrhythmia database (MITDB). The data from the CinC Challenge 2011 are standard 12 ECG leads recordings with full diagnostic bandwidth compared to the MITDB which only includes two leads for each ECG signal. Firstly, our algorithm is validated using fifty 12 leads ECG samples from the CinC collection. The samples have been chosen in the "acceptable records" list given by Physionet. The detection and the duration delineation of the QRS, P and T waves given by our method are compared to expert physician results. The algorithm shows a sensitivity equal to 0.9987 for the QRS complex, 0.9917 for the T wave and 0.9906 for the P wave. The accuracy and the Youden index values show that the method is reliable for the QRS, T and P waves detection and delineation. Secondly, our algorithm is applied to the MITDB in order to compare the detection of QRS wave to results of other some works in the literature.