Beat-Synchronous Tokenization for ECG Transformers
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 20 references that are in the map. First posted on arXiv 31 Aug 2026.
Builds on
12 of 20 references.
References · 12
- 2017Attention Is All You Needcited by 59,932
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2020CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patientscited by 170
- 2024ECG-FM: An Open Electrocardiogram Foundation Modelcited by 89
- 2024Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogramcited by 84
- 2021Self-supervised representation learning from 12-lead ECG datacited by 80
- 2025Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Modelcited by 36
- 2024An Electrocardiogram Foundation Model Built on over 10 Million Recordings with External Evaluation across Multiple Domainscited by 27
- 2021Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG Modelingcited by 24
- 2025From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretrainingcited by 15
- 2019Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discoverycited by 13
- 2026RhythmBERT: A Self-Supervised Language Model Based on Latent Representations of ECG Waveforms for Heart Disease Detectioncited by 3
Built on by
Not cited yet.