Finding Morphology Points of Electrocardiographic-Signal Waves Using Wavelet Analysis

Abstract

We propose a new algorithm for determining the basic significant points of various electrocardiographic-signal waves taking into account information from all available leads and ensuring a similar or higher accuracy compared with that of other up-to-date technologies. The test results of the algorithm efficiency for the QT data base [1] show a sensitivity above 97% when detecting the electrocardiographic-signal peaks, and 96% for their onsets and offsets, as well as the positive predictive value exceeding 97% for the peaks of the complexes, which is the best result compared with those of the previously known algorithms. As distinct from them, the proposed approach also allows one to determine the wave morphology. For the proposed algorithm, the delineation errors of all significant points are below the tolerances specified by the Committee of General Standards for Electrocardiography.