Heart-rate adaptive match filter based procedure for automatic detection of T-wave alternans from 24-hour ECG recordings: Issues related to filter implementation

Twenty-four hour T-wave alternans (TWA) analysis is a promising approach for risk stratification, which still remains unpractical because TWA identification algorithms are complex and require long computation time (CT). The aim of the present study was to test the applicability to 24-hour ECG recordings of our heart-rate adaptive match filter (AMF) which allows TWA detection by submitting ECG data to a band-pass filter centered at the TWA fundamental frequency fTWA, equal to a half heart rate. Two implementations are possible: 1) the passing-band is adapted to a varying f TWA value (FA-AMF), and 2) the filter band is fixed while conditioning the ECG data (SA-AMF). Simulated ECG tracings, characterized by no TWA or by different kinds of TWA, and 24-hour ECG recordings from healthy subjects and coronary artery disease patients were used to identify the fastest of these two implementations. Our results yielded the conclusions that the CT of our AMF-based procedure is independent of the amount of TWA present in the tracing, but depends on ECG sample length and filter implementation. If filter-design tools are available while performing ECG analysis, the FA-AMF implementation is to be preferred because its CT is about one third of SA-AMF CT.