Metraipolis › archive › dc_356d73da47ed

Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction — arXiv:2610.10641

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10641
License (as archived)
CC0-1.0
Archived
2026-10-09T05:53:52.410Z
SHA-256 of the archived text
49bcaa8d51a534a3635d6bdc46d9ecdd0daf090d9a25066d30661e7ca9341c57
Stable URL of this page
https://metraipolis.com/documento/dc_356d73da47ed

How to cite

Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction — arXiv:2610.10641 — arXiv (en), https://arxiv.org/abs/2610.10641 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_356d73da47ed (Metraipolis archive dc_356d73da47ed, sha256 49bcaa8d51a534a3635d6bdc46d9ecdd0daf090d9a25066d30661e7ca9341c57)
BibTeX
@misc{dc356d73da47ed,
  title = {Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction — arXiv:2610.10641},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10641},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_356d73da47ed; sha256 49bcaa8d51a534a3635d6bdc46d9ecdd0daf090d9a25066d30661e7ca9341c57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10641. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical evidence and reason over it in natural language. However, reinforcement learning for LLM reasoning commonly rewards each trajectory according to the correctness of its final answer. In next-visit diagnosis prediction, multiple diagnoses can be simultaneously valid, but independently rewarding one diagnosis per trajectory does not distinguish repeated hits from coverage of different diagnoses. The policy can therefore concentrate on a few correct diagnoses, leaving others uncovered. Meanwhile, LLM tokenizers can split ICD codes into several generic tokens with limited clinical meaning, requiring multiple decoding steps to predict each diagnosis and hindering reasoning over a large disease vocabulary. To address both challenges, we propose CARing, a framework that represents diagnoses with compositional Semantic IDs (SIDs) and optimizes reasoning trajectories for multi-label coverage. Concretely, we first encode ontology-enriched disease semantics into compact SIDs through residual quantization, and ground the resulting SID tokens in natural language and longitudinal EHR contexts through multi-task alignment and reasoning-enriched training to unlock transferable LLM reasoning. CARing further improves unordered multi-label prediction through a coverage reward for reinforcement learning and multi-positive supervision. At inference time, the model supports both efficient direct constrained decoding and multi-chain reasoning with rank fusion. On MIMIC-III and MIMIC-IV, CARing exceeds all EHR-trained baselines in weighted F1 and attains the highest top-k recall at every reported cutoff, including R@30 of 46.04% and 46.52% in reasoning mode. Our codes and logs are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.10641 — 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 2026-10-09T05:47:01.294Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).