EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis

• URL: http://arxiv.org/abs/2510.25628v1
• Date: Wed, 29 Oct 2025 15:32:47 GMT
• Title: EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis
• Abstract summary: We present EHR-Ins, a large-scale, comprehensive EHR reasoning instruction dataset.<n>We also develop EHR-R1, a series of reasoning-enhanced LLMs with up to 72B parameters tailored for EHR analysis.<n>Finally, we introduce EHR-Bench, a new benchmark curated from MIMIC-IV, spanning 42 tasks.
• Score: 78.05962117947259
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Electronic Health Records (EHRs) contain rich yet complex information, and their automated analysis is critical for clinical decision-making. Despite recent advances of large language models (LLMs) in clinical workflows, their ability to analyze EHRs remains limited due to narrow task coverage and lack of EHR-oriented reasoning capabilities. This paper aims to bridge the gap, specifically, we present EHR-Ins, a large-scale, comprehensive EHR reasoning instruction dataset, comprising 300k high-quality reasoning cases and 4M non-reasoning cases across 42 distinct EHR tasks. Its core innovation is a thinking-graph-driven framework that enables to generate high-quality reasoning data at scale. Based on it, we develop EHR-R1, a series of reasoning-enhanced LLMs with up to 72B parameters tailored for EHR analysis. Through a multi-stage training paradigm, including domain adaptation, reasoning enhancement, and reinforcement learning, EHR-R1 systematically acquires domain knowledge and diverse reasoning capabilities, enabling accurate and robust EHR analysis. Lastly, we introduce EHR-Bench, a new benchmark curated from MIMIC-IV, spanning 42 tasks, to comprehensively assess reasoning and prediction across EHR scenarios. In experiments, we show that the resulting EHR-R1 consistently outperforms state-of-the-art commercial and open-source LLMs (including DeepSeek-V3 and GPT-4o), surpassing GPT-4o by over 30 points on MIMIC-Bench and achieving a 10\% higher zero-shot AUROC on EHRSHOT. Collectively, EHR-Ins, EHR-R1, and EHR-Bench have significantly advanced the development for more reliable and clinically relevant EHR analysis.

Related papers

• EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs [51.129595320595094]
  Clinical decision-making (CDM) is central to real-world clinical, where clinicians infer diagnoses, select treatments, or anticipate future health outcomes under incomplete evidence.<n>LLM models are increasingly used to support these decisions due to strong language capabilities, broad biomedical knowledge, and efficiency.<n>The reliability of LLMs on real-world clinical decision tasks remains insufficiently understood.
  arXiv  Detail & Related papers  (2026-05-28T22:38:26Z)
• ReMedi: Reasoner for Medical Clinical Prediction [70.84466325266068]
  We present ReMedi, a framework for improving clinical outcome prediction from EHR.<n>ReMedi generates rationale-answer pairs using a challenging sample regeneration mechanism for complex clinical questions.<n> Experiments on multiple EHR prediction tasks demonstrate substantial gains of up to 19.9 percent over state-of-the-art baselines in terms of F1 score.
  arXiv  Detail & Related papers  (2026-05-02T14:44:49Z)
• EviCare: Enhancing Diagnosis Prediction with Deep Model-Guided Evidence for In-Context Reasoning [62.61394722212386]
  EviCare is an in-context reasoning framework that integrates deep model guidance into large language models.<n>It consistently outperforms both LLM-only and deep model-only baselines in experiments on two real-world EHR benchmarks.
  arXiv  Detail & Related papers  (2026-04-12T04:35:14Z)
• EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generation [8.087606137290217]
  EHR-RAG is a retrieval-augmented framework designed for accurate interpretation of long-horizon structured EHR data.<n>Experiments across four long-horizon EHR prediction tasks show that EHR-RAG consistently outperforms the strongest LLM-based baselines.
  arXiv  Detail & Related papers  (2026-01-29T07:06:34Z)
• ReToP: Learning to Rewrite Electronic Health Records for Clinical Prediction [1.0874597293913013]
  Large Language Models (LLMs) allowed progress towards addressing this challenge by parametric medical knowledge data for clinical prediction tasks.<n>Most of the existing approaches are fundamentally task-agnostic in the sense that they deploy LLMs as EHR encoders or EHR completion modules without fully integrating signals from the prediction tasks.<n>We propose Rewrite-To-Predict (ReToP), an LLM-based framework that addresses this limitation through an end-to-end training of an EHR rewriter and a clinical predictor.
  arXiv  Detail & Related papers  (2026-01-27T07:20:46Z)
• Integrating Genomics into Multimodal EHR Foundation Models [56.31910745104141]
  This paper introduces an innovative EHR foundation model that integrates Polygenic Risk Scores (PRS) as a foundational data modality.<n>The framework aims to learn complex relationships between clinical data and genetic predispositions.<n>This approach is pivotal for unlocking new insights into disease prediction, proactive health management, risk stratification, and personalized treatment strategies.
  arXiv  Detail & Related papers  (2025-10-24T15:56:40Z)
• R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth? [63.51955244144878]
  R-HORIZON is a method designed to stimulate long-horizon reasoning behaviors in Large Reasoning Models (LRMs)<n>Based on R-HORIZON, we construct a long-horizon reasoning benchmark, comprising complex multi-step reasoning tasks with interdependent problems that span long reasoning horizons.<n>Our analysis reveals that LRMs exhibit limited effective reasoning length and struggle to allocate thinking budget across multiple problems appropriately.
  arXiv  Detail & Related papers  (2025-10-09T13:16:22Z)
• Toward Better EHR Reasoning in LLMs: Reinforcement Learning with Expert Attention Guidance [9.106439376182513]
  Large language models (LLMs) for electronic health record ( EHR) reasoning are essential for enabling accurate and generalizable clinical predictions.<n>We propose EAG-RL, a novel two-stage training framework designed to intrinsically enhance LLMs' EHR reasoning ability.<n>EAG-RL first constructs high-quality, stepwise reasoning trajectories using expert-guided Monte Carlo Tree Search.
  arXiv  Detail & Related papers  (2025-08-19T07:24:48Z)
• R-PRM: Reasoning-Driven Process Reward Modeling [53.06844294668382]
  Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step.<n>Existing PRMs typically output evaluation scores directly, limiting both learning efficiency and evaluation accuracy.<n>We propose Reasoning-Driven Process Reward Modeling (R-PRM)<n>R-PRM generates seed data from limited annotations, effectively bootstrapping our model's reasoning capabilities.
  arXiv  Detail & Related papers  (2025-03-27T09:23:08Z)
• Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG [79.61269381878547]
  High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs)<n>This paper shifts away from prior dedicated approaches and revisits the most fundamental idea to HR perception by enhancing the long-context capability of MLLMs.<n>We propose Retrieval-Augmented Perception (RAP), a training-free framework that retrieves and fuses relevant image crops while preserving spatial context.
  arXiv  Detail & Related papers  (2025-03-03T06:40:21Z)
• 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)
• Multi-task Heterogeneous Graph Learning on Electronic Health Records [22.218522445858344]
  We propose a novel framework for EHR modeling, namely MulT-EHR (Multi-Task EHR) We introduce a denoising module based on the causal inference framework to adjust for severe confounding effects. We design a multi-task learning module to leverage the inter-task knowledge to regularize the training process.
  arXiv  Detail & Related papers  (2024-08-14T14:06:13Z)
• ICU Bloodstream Infection Prediction: A Transformer-Based Approach for EHR Analysis [0.0]
  We introduce RatchetEHR, a novel framework designed for the predictive analysis of electronic health records (EHR) data in intensive care unit (ICU) settings. R RatchetEHR demonstrates superior predictive performance compared to other methods, including RNN, LSTM, and XGBoost. A key innovation in RatchetEHR is the integration of the Graph Convolutional Transformer (GCT) component, which significantly enhances the ability to identify hidden structural relationships.
  arXiv  Detail & Related papers  (2024-05-01T19:00:30Z)
• RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs [49.386699863989335]
  Training large language models (LLMs) to serve as effective assistants for humans requires careful consideration. A promising approach is reinforcement learning from human feedback (RLHF), which leverages human feedback to update the model in accordance with human preferences. In this paper, we analyze RLHF through the lens of reinforcement learning principles to develop an understanding of its fundamentals.
  arXiv  Detail & Related papers  (2024-04-12T15:54:15Z)
• Machine Learning for Administrative Health Records: A Systematic Review of Techniques and Applications [5.353552655309808]
  Administrative Health Records (AHR) are a subset of EHR collected for administrative purposes. This paper systematically reviews AHR-based research, analysing 70 relevant studies and spanning multiple databases. We find that while AHR-based studies are disconnected from each other, the use of AHRs in health informatics research is substantial and accelerating.
  arXiv  Detail & Related papers  (2023-08-27T22:34:10Z)
• SANSformers: Self-Supervised Forecasting in Electronic Health Records with Attention-Free Models [48.07469930813923]
  This work aims to forecast the demand for healthcare services, by predicting the number of patient visits to healthcare facilities. We introduce SANSformer, an attention-free sequential model designed with specific inductive biases to cater for the unique characteristics of EHR data. Our results illuminate the promising potential of tailored attention-free models and self-supervised pretraining in refining healthcare utilization predictions across various patient demographics.
  arXiv  Detail & Related papers  (2021-08-31T08:23:56Z)

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.