← Back to all news
arXiv Machine Learning By Yuxin Xiao, Sheng Zhang, Chandan Singh, Tristan Naumann, Hoifung Poon, Jianfeng Gao, Xiaodong Liu

Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models

Read the original on arXiv Machine Learning →

The paper proposes a reinforcement learning (RL) fine‑tuning framework for electronic health record (EHR) foundation models, treating them as generative policies over patient trajectories. By framing clinical prediction tasks such as hospital readmission as event‑conditioned, time‑windowed reasoning problems and designing time‑aware, rollout‑sensitive rewards, the authors show that RL fine‑tuning consistently outperforms pre‑trained backbones and strong baselines. The approach enables smaller models to surpass larger pre‑trained models in data‑limited settings, induces positive transfer across tasks, and produces trajectories with stronger structural and semantic alignment to ground truth, improving downstream utility.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jun 3

ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning

arXiv:2606. 02802v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong natural-language reasoning abilities for clinical decision support, but struggle to effectively model structured longitudinal electronic health records (EHRs).

By Bo-Hong Wang, Baicheng Peng, Ruilin Wang, Jun Bai, Ziyang Song, Yue Li
llmsmultimodalbenchmarkssafety
More like this →
arXiv Computation and Language
Aug 28

CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models

CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models proposes a new framework to improve medical reasoning in LLMs. It introduces two key conditions—Causal Sufficiency and Proximal Learnability—to curate high-quality training trajectories, using agreement-based self-verification and dynamic entropy bounds. Experiments on medical multimodal and text-only benchmarks show that CARE outperforms competitors, reducing incorrect reasoning and enhancing training stability.

By Yucheng Zhou, Peng Luo, Qianning Wang, Chengzhong Xu, Jianbing Shen
llmsreinforcement-learningmultimodalbenchmarks
More like this →
arXiv AI
Oct 9

Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction

The paper introduces CARing, a framework that improves next‑visit diagnosis prediction by representing diagnoses with compositional Semantic IDs (SIDs) and optimizing multi‑label coverage through reinforcement learning. CARing encodes ontology‑enriched disease semantics into compact SIDs, aligns them with natural language and EHR contexts, and employs a coverage reward to encourage diverse diagnosis predictions. On MIMIC‑III and MIMIC‑IV datasets, CARing outperforms all EHR‑trained baselines in weighted F1 and achieves the highest top‑k recall, including R@30 scores above 46% in reasoning mode.

By Kaisong Zhang, Haotian Fang, Junmeng Zhou, Hang Lv, Yulan Pan, Yanchao Tan
llmsreinforcement-learningefficiencysafety
More like this →
arXiv Machine Learning
Jun 8

One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models

arXiv:2602. 00541v2 Announce Type: replace Abstract: Clinical events captured in Electronic Health Records (EHR) are irregularly sampled and may consist of a mixture of discrete events and numerical measurements, such as laboratory values or treatment dosages.

By Zilin Jing, Vincent Jeanselme, Yuta Kobayashi, Simon A. Lee, Chao Pang, Aparajita Kashyap, Yanwei Li, Xinzhuo Jiang, Shalmali Joshi
More like this →