Beat-Synchronous Tokenization for ECG Transformers

August 31, 2026 ยท Grace Period ยท ๐Ÿ› the 2026 IEEE International Workshop on Machine Learning for Signal Processing

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Ahmed Sameh, Nolan Wilson, Max Enderlein, Yogatheesan Varatharajah arXiv ID 2608.30367 Category cs.LG: Machine Learning Cross-listed eess.SP Citations 0 Venue the 2026 IEEE International Workshop on Machine Learning for Signal Processing
Abstract
Transformer-based electrocardiogram (ECG) models commonly tokenize waveforms into fixed temporal patches. Though convenient, fixed patching can split heartbeat structures across token boundaries. We study beat-synchronous tokenization as a physiologically grounded alternative, comparing fixed patches with three beat-aligned strategies: resampled beats, adaptive pooled beats, and resampled beats augmented with R--R interval information. Experiments span two settings: 10-second 12-lead diagnostic classification on PTB-XL after MIMIC-IV-ECG masked pretraining, and 60-second single-lead rhythm classification on Icentia11k after patient-level contrastive pretraining. On PTB-XL, resampled beat tokens achieve the highest mean macro Area Under the ROC Curve (AUROC; 0.8945) and nearly match the best fixed-patch macro Area Under the Precision-Recall Curve (AUPRC; 0.7414), reducing average sequence length from 100 to 11.2 tokens. On Icentia11k, beat-synchronous tokenizers obtain comparable AUPRC to fixed patching with better stability across runs. These results suggest morphology-preserving beat tokenization is a compact, competitive alternative to fixed temporal patching.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning