Learning ECG Representations for Multi-Label Classification of Cardiac Abnormalities

Jangwon Suh, Jimyeong Kim, Eunjung Lee, Jaeill Kim, Duhun Hwang, Jungwon Park, Junghoon Lee, JaeSeung Park, Seo-Yoon Moon, Yeonsu Kim, Min Kang, Soonil Kwon, Eue-Keun Choi, Wonjong Rhee

Abstract: The goal of PhysioNet/Computing in Cardiology Challenge 2021 was to identify clinical diagnoses from 12 -lead and reduced-lead ECG recordings, including 6-lead, 4-lead, 3-lead, and 2-lead recordings. Our team, snu_adsl, have used EfficientNet-B3 as the base deep learning model and have investigated methods including data augmentation, self-supervised learning as pre-training, label masking that deals with multiple data sources, threshold optimization, and feature extraction. Self-supervised learning showed promising results when the size of labeled dataset was limited, but the competition's dataset turned out to be large enough that the actual gain was marginal. In consequence, we did not include self-supervised pre-training in our final entry. Our classifiers received scores of 0.48, 0.48, 0.47, 0.47, and 0.45 (ranked 12th, 10th, 11th, 11th, and 13th out of 39 teams) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2 -lead versions of the hidden test set with the Challenge evaluation metric.