Towards Generalization of Cardiac Abnormality Classification Using ECG Signal

Xiaoyu Li, Chen Li, Xian Xu, Yuhua Wei, Jishang Wei, Yuyao Sun, Buyue Qian, Xiao Xu

Abstract: In the PhysioNet/Computing in Cardiology Challenge 2021, our team, DrCubic, develops a novel approach to classify cardiac abnormalities using reduced-lead ECG recordings. In our approach, we incorporate peak detection as a self-supervised auxiliary task. We build the model based on SE-ResNet, and integrate models of different input lengths and sampling rates. Inspired by last year's challenge results, we investigate various settings and techniques, and select the best ones, considering the intra-source performance and inter-source generalization simultaneously. Our classifiers receive scores of 0.49, 0.50, 0.50, 0.51, and 0.48 (ranked 9th, 8th, 7th, 5th, and 9th out of 39 scored teams) for the 12 -lead, 6-lead, 4-lead, 3-lead, and 2 -lead versions of the hidden test sets with the Challenge evaluation metric.