Principal Component Analysis for detection and assessment of T-wave alternans

T wave alternans (TWA) is an electrophisiologic phenomenon associated with a risk factor of sudden cardiac death. In the framework of Physionet/Cinc Challenge, a set of 100 ECG recordings were collected in order to test different algorithms for the detection and the quantification of TWA. The ECG were processed for power line interference, electromyographic noise and baseline wander suppression. Two kind of algorithm were tested, considering the temporal domain: 1) the T wave amplitude computed in a combined lead, and 2) the principal component analysis for quantifying the complexity index of the T waves. The detection of possible alternans was performed by a paired non parametric statistical test. Our study proved a high correlation between alternans of T amplitude and the alternans of T wave complexity index. The results of an algorithm combining the outcome of the two methods for the detection of TWA showed a score of 0.890, second best in the Challenge.