Metraipolis › archive › dc_d80dc75ab054

The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning — arXiv:2608.12695

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12695
License (as archived)
CC0-1.0
Archived
2026-10-19T04:27:23.461Z
SHA-256 of the archived text
222ca69e9269cf17d2ac5a6cc2a2b3a68430eda5f40f63e5bee671636c78ca4a
Stable URL of this page
https://metraipolis.com/documento/dc_d80dc75ab054

How to cite

The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning — arXiv:2608.12695 — arXiv (en), https://arxiv.org/abs/2608.12695 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d80dc75ab054 (Metraipolis archive dc_d80dc75ab054, sha256 222ca69e9269cf17d2ac5a6cc2a2b3a68430eda5f40f63e5bee671636c78ca4a)
BibTeX
@misc{dcd80dc75ab054,
  title = {The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning — arXiv:2608.12695},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12695},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d80dc75ab054; sha256 222ca69e9269cf17d2ac5a6cc2a2b3a68430eda5f40f63e5bee671636c78ca4a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12695. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences. It remains unclear whether these choices sacrifice information needed for rhythm inference and longitudinal consistency in real-world ambulatory recordings. We present a controlled study on the Icentia11k single-lead dataset that varies (i) the input horizon (16 seconds, 1 minute, 5 minutes, and 10 minutes) and (ii) the front-end representation (continuous convolutional patch embeddings vs. fixed vector-quantized tokens), while holding the Transformer backbone and training protocol constant. Representations are assessed by downstream abnormal rhythm detection and by patient-level retrieval that probes cross-session stability. Our results show that increasing temporal context beyond 16-second snapshots yields stronger transfer and higher retrieval accuracy, with the strongest performance achieved by the 5- and 10-minute models, indicating improved capture of slow-varying rhythm dynamics and individual-specific structure. Across all evaluated horizons, continuous patch embeddings outperform discretized tokens, suggesting that quantization can discard clinically relevant waveform detail. These findings motivate ECG foundation models that emphasize extended context and continuous encoders for clinical prediction and similarity-based applications. Our code and pretrained models are publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2608.12695 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:20:35.822Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).