Problem
Research questions and friction points this paper is trying to address.
Transformer
ECG
Tokenization
Heartbeat
Temporal Patching
Beat-Synchronous Tokenization for ECG Transformers
🤖 AI Summary
研究通过心搏同步标记法解决ECG模型中固定时间片段分割心搏结构的问题，实验表明该方法在保持形态的同时提高了分类性能。
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
beat-synchronous tokenization
resampled beats
R--R interval information
🔎 Similar Papers
No similar papers found.
