Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning

• URL: http://arxiv.org/abs/2505.24105v1
• Date: Fri, 30 May 2025 01:13:22 GMT
• Title: Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning
• Authors: Jiacheng Lin, Zhenbang Wu, Jimeng Sun,
• Abstract summary: We present a practical recipe for adapting large language models (LLMs) to complex clinical reasoning tasks using reinforcement learning with verifiable rewards (RLVR)<n>We demonstrate the effectiveness of our method across diverse clinical applications, including medical calculations (MEDCALC), patient-trial matching (TREC CLINICAL TRIALS), and disease diagnosis (EHRSHOT)
• Score: 28.019558492081437
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present EHRMIND, a practical recipe for adapting large language models (LLMs) to complex clinical reasoning tasks using reinforcement learning with verifiable rewards (RLVR). While RLVR has succeeded in mathematics and coding, its application to healthcare contexts presents unique challenges due to the specialized knowledge and reasoning required for electronic health record (EHR) interpretation. Our pilot study on the MEDCALC benchmark reveals two key failure modes: (1) misapplied knowledge, where models possess relevant medical knowledge but apply it incorrectly, and (2) missing knowledge, where models lack essential domain knowledge. To address these cases, EHRMIND applies a two-stage solution: a lightweight supervised fine-tuning (SFT) warm-up that injects missing domain knowledge, stabilizes subsequent training, and encourages structured, interpretable outputs; followed by RLVR, which reinforces outcome correctness and refines the model's decision-making. We demonstrate the effectiveness of our method across diverse clinical applications, including medical calculations (MEDCALC), patient-trial matching (TREC CLINICAL TRIALS), and disease diagnosis (EHRSHOT). EHRMIND delivers consistent gains in accuracy, interpretability, and cross-task generalization. These findings offer practical guidance for applying RLVR to enhance LLM capabilities in healthcare settings.

Related papers

• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications [59.721265428780946]
  Large Language Models (LLMs) in medicine have enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning.<n>This paper provides the first systematic review of this emerging field.<n>We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies and test-time mechanisms.
  arXiv  Detail & Related papers  (2025-08-01T14:41:31Z)
• RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraints [0.0]
  Reasoning-Aware Reinforcement Learning framework enhances the reasoning capabilities of medical vision-language models.<n>Our approach fine-tunes a lightweight base model, Qwen2-VL-2B-Instruct, using Low-Rank Adaptation and custom reward functions.<n> Experimental results show RARL significantly improves VLM performance in medical image analysis and clinical reasoning.
  arXiv  Detail & Related papers  (2025-06-07T00:26:23Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models.<n>Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start.<n>Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• Structured Outputs Enable General-Purpose LLMs to be Medical Experts [50.02627258858336]
  Large language models (LLMs) often struggle with open-ended medical questions.<n>We propose a novel approach utilizing structured medical reasoning.<n>Our approach achieves the highest Factuality Score of 85.8, surpassing fine-tuned models.
  arXiv  Detail & Related papers  (2025-03-05T05:24:55Z)
• Bridging Stepwise Lab-Informed Pretraining and Knowledge-Guided Learning for Diagnostic Reasoning [20.369746122143063]
  We propose a dual-expertise framework that combines two complementary sources of information.<n>For external knowledge, we construct a Diagnosis Knowledge Graph (KG) that encodes both hierarchical language and semantic relations enriched by large models.<n>We introduce a lab-informed proxy task that guides the model to follow a clinically consistent stepwise reasoning process based on lab test signals.
  arXiv  Detail & Related papers  (2024-10-25T20:25:22Z)
• IntelliCare: Improving Healthcare Analysis with Variance-Controlled Patient-Level Knowledge from Large Language Models [14.709233593021281]
  The integration of external knowledge from Large Language Models (LLMs) presents a promising avenue for improving healthcare predictions. We propose IntelliCare, a novel framework that leverages LLMs to provide high-quality patient-level external knowledge. IntelliCare identifies patient cohorts and employs task-relevant statistical information to augment LLM understanding and generation.
  arXiv  Detail & Related papers  (2024-08-23T13:56:00Z)
• Ensuring Ground Truth Accuracy in Healthcare with the EVINCE framework [2.5200794639628032]
  The propagation of mislabeled data through machine learning models into clinical practice is unacceptable. This paper proposes EVINCE, a system designed to 1) improve diagnosis accuracy and 2) rectify misdiagnoses and minimize training data errors.
  arXiv  Detail & Related papers  (2024-05-20T18:26:36Z)
• XAI4LLM. Let Machine Learning Models and LLMs Collaborate for Enhanced In-Context Learning in Healthcare [16.79952669254101]
  We introduce a knowledge-guided in-context learning framework to enable large language models to process structured clinical data.<n>Our approach integrates domain-specific feature groupings, carefully balanced few-shot examples, and task-specific prompting strategies.
  arXiv  Detail & Related papers  (2024-05-10T06:52:44Z)
• Deep Reinforcement Learning for Personalized Diagnostic Decision Pathways Using Electronic Health Records: A Comparative Study on Anemia and Systemic Lupus Erythematosus [1.7965876401882177]
  We formulate the task of diagnosis as a sequential decision-making problem. We study the use of Deep Reinforcement Learning (DRL) algorithms to learn the optimal sequence of actions to perform. We develop two clinical use cases: Anemia diagnosis and Systemic Lupus Erythematosus diagnosis.
  arXiv  Detail & Related papers  (2024-04-09T00:07:16Z)
• Large Language Model Distilling Medication Recommendation Model [58.94186280631342]
  We harness the powerful semantic comprehension and input-agnostic characteristics of Large Language Models (LLMs)<n>Our research aims to transform existing medication recommendation methodologies using LLMs.<n>To mitigate this, we have developed a feature-level knowledge distillation technique, which transfers the LLM's proficiency to a more compact model.
  arXiv  Detail & Related papers  (2024-02-05T08:25:22Z)
• Natural Language Programming in Medicine: Administering Evidence Based Clinical Workflows with Autonomous Agents Powered by Generative Large Language Models [29.05425041393475]
  Generative Large Language Models (LLMs) hold significant promise in healthcare. This study assessed the potential of LLMs to function as autonomous agents in a simulated tertiary care medical center.
  arXiv  Detail & Related papers  (2024-01-05T15:09:57Z)
• Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing [62.9062883851246]
  Machine learning holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities. One potential driver of algorithmic unfairness, shortcut learning, arises when ML models base predictions on improper correlations in the training data. Using multi-task learning, we propose the first method to assess and mitigate shortcut learning as a part of the fairness assessment of clinical ML systems.
  arXiv  Detail & Related papers  (2022-07-21T09:35:38Z)
• MIMO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning [49.57261599776167]
  We propose an end-to-end robust Transformer-based solution, Mutual Integration of patient journey and Medical Ontology (MIMO) for healthcare representation learning and predictive analytics.
  arXiv  Detail & Related papers  (2021-07-20T07:04:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.