Session S92.4

ECG Events Segmentation via Discrete-Wavelet Transform: Modified Detection-Delineation of Premature Contractions

A Ghaffari, MR Homaeinezhad*, M Atarod, M Akraminia, M Davaeeha

K. N. Toosi University of Technology
Tehran, Iran

An ECG wave detection-delineation algorithm which can be applied to all ECG leads is developed in this study on the basis of discrete-wavelet transform (DWT). By applying a new simple approach to a selected scale obtained from DWT, this method is capable of detecting QRS complex, P-wave and T-wave as well as determining parameters such as start time, end time, and wave sign (upward or downward). The presented algorithm is first applied to various databases and as a result, average values of Se = 99.84% and P+ = 99.80% are obtained for the detection of QRS complexes with the average maximum delineation errors of 13.7, 11.3 and 14.0 (msec) for P-wave, QRS Complex and T-wave, respectively. Next, using Binary Neyman-Pearson Radius test, an appropriate classifier is designed to categorize ventricular complexes into "Normal + Premature Atrial Contraction (PAC)" and "Premature Ventricular Contraction (PVC)" beats. Then, an innovative measure is defined based on wavelet transform of the delineated P-wave namely as P-Wave Strength Factor which is used for the evaluation of the P-wave power. Accordingly, P-waves are classified into "weak" and "strong" waves. Finally, ventricular contractions pursuing weak P-waves are categorized as PAC complexes; however, those ensuing strong P-waves are specified as normal complexes. The proposed algorithm was applied to Holter Data of the DAY Hospital (more than 1, 500, 000 beats) and the average values of Se = 99.73% and P+ = 99.58% were achieved for sensitivity and positive prediction, respectively.

(Abstract Control Number: 231)