DiaLLMs: EHR Enhanced Clinical Conversational System for Clinical Test Recommendation and Diagnosis Prediction

2025-06-24

AI Summary

Existing large medical language models largely overlook the clinical utility of electronic health records (EHRs), focusing narrowly on diagnostic recommendations and thus suffering from limited practical applicability. To address this, we propose the first multi-task clinical dialogue system that deeply integrates heterogeneous EHR data to support laboratory test recommendation, result interpretation, and diagnosis prediction. Methodologically, we introduce a Clinical Test Reference (CTR) strategy—combining rejection sampling, class-sensitive reward shaping, and confirmation-based rewards—to enable EHR-grounded, precise diagnostic modeling. Additionally, we design a reinforcement learning framework tailored for large-scale action spaces, incorporating clinical code mapping, lab result classification, and efficient exploration strategies. Experiments demonstrate significant improvements over strong baselines in both test recommendation and diagnosis prediction, achieving superior clinical utility and diagnostic accuracy.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recent advances in Large Language Models (LLMs) have led to remarkable progresses in medical consultation. However, existing medical LLMs overlook the essential role of Electronic Health Records (EHR) and focus primarily on diagnosis recommendation, limiting their clinical applicability. We propose DiaLLM, the first medical LLM that integrates heterogeneous EHR data into clinically grounded dialogues, enabling clinical test recommendation, result interpretation, and diagnosis prediction to better align with real-world medical practice. To construct clinically grounded dialogues from EHR, we design a Clinical Test Reference (CTR) strategy that maps each clinical code to its corresponding description and classifies test results as "normal" or "abnormal". Additionally, DiaLLM employs a reinforcement learning framework for evidence acquisition and automated diagnosis. To handle the large action space, we introduce a reject sampling strategy to reduce redundancy and improve exploration efficiency. Furthermore, a confirmation reward and a class-sensitive diagnosis reward are designed to guide accurate diagnosis prediction. Extensive experimental results demonstrate that DiaLLM outperforms baselines in clinical test recommendation and diagnosis prediction.

Problem

• Integrates EHR data into medical dialogues for clinical tasks
• Improves clinical test recommendation and diagnosis prediction accuracy
• Addresses large action space with efficient exploration strategies

Innovation

• Integrates heterogeneous EHR data into dialogues
• Uses Clinical Test Reference strategy for test interpretation
• Employs reinforcement learning for evidence-based diagnosis