Metraipolis › archive › dc_0d98d4ecc85b

TRACE: Tractable Routing Autoencoder for Clinical ECG — arXiv:2609.23460

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23460
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:13.212Z
SHA-256 of the archived text
8edc78d7c7cd7008f96b74b2d91b9c3c8f82de341b4113abd3227d807b8b1ed9
Stable URL of this page
https://metraipolis.com/documento/dc_0d98d4ecc85b

How to cite

TRACE: Tractable Routing Autoencoder for Clinical ECG — arXiv:2609.23460 — arXiv (en), https://arxiv.org/abs/2609.23460 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d98d4ecc85b (Metraipolis archive dc_0d98d4ecc85b, sha256 8edc78d7c7cd7008f96b74b2d91b9c3c8f82de341b4113abd3227d807b8b1ed9)
BibTeX
@misc{dc0d98d4ecc85b,
  title = {TRACE: Tractable Routing Autoencoder for Clinical ECG — arXiv:2609.23460},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23460},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d98d4ecc85b; sha256 8edc78d7c7cd7008f96b74b2d91b9c3c8f82de341b4113abd3227d807b8b1ed9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23460. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep learning has advanced automated electrocardiogram (ECG) diagnosis, but the field's most accurate models, foundation models pretrained on millions of recordings, are not decision-pathway auditable: a clinician cannot trace a diagnosis to a physiological pathway or intervene on one. We propose TRACE, a Tractable Routing Autoencoder for Clinical ECG, whose 32-dimensional clinical latent space is specified in advance from domain knowledge rather than discovered by optimization. TRACE partitions this space into perfusion, structure, and conduction subspaces, routes each to its own diagnostic head by design, regularizes the partition with an orthogonality penalty, and reconstructs the ECG through a decoder that permits latent perturbation. On PTB-XL and Georgia, TRACE exceeds unconstrained classifiers and stays ahead of an ECG foundation model pretrained on ten million recordings, evaluated by linear probe on frozen features, at roughly an eighth of the parameter count. On the nine-label CPSC2018 cohort, which carries no structural class, the framework transfers with only the routing table re-specified to a perfusion/rhythm/conduction partition. Joint probe, erasure, and perturbation analyses verify the routing contract, and perturbing the depolarization and repolarization pathways modulates the reconstructed waveform. Removing the specified partition and its orthogonality penalty costs 1.70 AUC and 11.30 macro-F1 points on PTB-XL, and 2.76 AUC and 16.92 macro-F1 points on Georgia. A capacity-matched permutation control places arbitrary assignments within 0.34 AUC points of the ontology routing and leaves macro-F1 statistically level (p=0.619): the ontology supplies decision-pathway auditability at no macro-F1 cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.23460 — 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 2026-10-09T06:58:09.303Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).