Metraipolis › archive › dc_24415df35a80
Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models — arXiv:2609.12277
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12277
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:03:17.792Z
- SHA-256 of the archived text
61d85ce36a26b1e6bfa8dd3bdf0a9c636da30192e5c3325c11d1efba3f816c8b- Stable URL of this page
https://metraipolis.com/documento/dc_24415df35a80
How to cite
Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models — arXiv:2609.12277 — arXiv (en), https://arxiv.org/abs/2609.12277 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24415df35a80 (Metraipolis archive dc_24415df35a80, sha256 61d85ce36a26b1e6bfa8dd3bdf0a9c636da30192e5c3325c11d1efba3f816c8b)
BibTeX
@misc{dc24415df35a80,
title = {Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models — arXiv:2609.12277},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12277},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24415df35a80; sha256 61d85ce36a26b1e6bfa8dd3bdf0a9c636da30192e5c3325c11d1efba3f816c8b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12277. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Electronic health record (EHR) foundation models trained on longitudinal patient trajectories have demonstrated strong performance across diverse clinical prediction tasks. However, their clinical reasoning capabilities remain constrained by next-token prediction on limited and incomplete EHR data. To address this, we propose a reinforcement learning (RL) fine-tuning framework that treats EHR foundation models as generative policies over patient trajectories. We formulate common clinical prediction problems (e.g., hospital readmission) as event-conditioned, time-windowed reasoning tasks. We then design time-aware, rollout-sensitive rewards to account for finite rollout lengths and temporally inconclusive outcomes. We find that RL fine-tuning consistently improves over pre-trained backbones and strong baselines. Notably, it enables smaller models to surpass larger pre-trained models in data-limited regimes and induces positive transfer across tasks. Further analysis shows that RL fine-tuned models generate trajectories with stronger structural and semantic alignment to ground truth and greater downstream utility. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2609.12277 — 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 2026-10-16T02:51:27.892Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).