PhysioCLR adds physiology-based positive/negative pair selection, heartbeat shuffling, and peak-aware reconstruction to ECG contrastive learning, improving downstream arrhythmia AUROC on Chapman, Georgia, and private ICU data.
Classification of 12- lead ECGs: The PhysioNet/Computing in Cardiology Challenge 2020,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Domain Knowledge is Power: Leveraging Physiological Priors for Self Supervised Representation Learning in Electrocardiography
PhysioCLR adds physiology-based positive/negative pair selection, heartbeat shuffling, and peak-aware reconstruction to ECG contrastive learning, improving downstream arrhythmia AUROC on Chapman, Georgia, and private ICU data.