Dr. Assistant: Enhancing Clinical Diagnostic Inquiry via Structured Diagnostic Reasoning Data and Reinforcement Learning

TL;DR

The paper introduces Dr. Assistant, a clinical diagnostic model enhanced with structured reasoning data and reinforcement learning, outperforming existing models in diagnostic inquiry guidance.

Contribution

It proposes a novel Clinical Diagnostic Reasoning Data structure and a two-stage training pipeline for an improved clinical diagnostic model.

Findings

Dr. Assistant outperforms open-source models in diagnostic reasoning.

The model achieves competitive performance with closed-source solutions.

The introduced benchmark effectively evaluates diagnostic reasoning and inquiry skills.

Abstract

Clinical Decision Support Systems (CDSSs) provide reasoning and inquiry guidance for physicians, yet they face notable challenges, including high maintenance costs and low generalization capability. Recently, Large Language Models (LLMs) have been widely adopted in healthcare due to their extensive knowledge reserves, retrieval, and communication capabilities. While LLMs show promise and excel at medical benchmarks, their diagnostic reasoning and inquiry skills are constrained. To mitigate this issue, we propose (1) Clinical Diagnostic Reasoning Data (CDRD) structure to capture abstract clinical reasoning logic, and a pipeline for its construction, and (2) the Dr. Assistant, a clinical diagnostic model equipped with clinical reasoning and inquiry skills. Its training involves a two-stage process: SFT, followed by RL with a tailored reward function. We also introduce a benchmark to evaluate both diagnostic reasoning and inquiry. Our experiments demonstrate that the Dr. Assistant outperforms open-source models and achieves competitive performance to closed-source models, providing an effective solution for clinical diagnostic inquiry guidance. Project information can be found at: https://github.com/YGswu/Dr.-Assistant .