Effect of a multi-lead PCA approach on modified moving average method for T-wave alternans detection

T-wave alternans, a beat-to-beat re-polarization pattern variation phenomenon, plays an important role in sudden cardiac death prediction. The proposed method modifies the currently available Modified Moving Average Method (MMAM) by a multi-lead principal component analysis (PCA) approach. Application of PCA will concentrate the alternans effect, which is supposed to be distributed on multiple leads in a single derived lead. MMAM is applied to the derived lead and alternans magnitude is measured. Results are compared with MMAM, implemented by the authors and by an open source tool, TWAnalyser. The TWA Physionet/CinC 2008 Challenge Database is used for testing. Performances are measured in terms of root mean square error (rmse) and correlation coefficients. The rmse is highest for TWAnalyser results and lowest for the proposed method. While the correlation coefficient is highest for the proposed method, 0.88, that for normal MMAM is 0.73 and for TWAnalyser is 0.75. The proposed multi-lead PCA approach provides improved performance of current MMAM.