DongYuan: An LLM-Based Framework for Integrative Chinese and Western Medicine Spleen-Stomach Disorders Diagnosis

arXiv cs.CL / 3/31/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces DongYuan, an LLM-based framework aimed at diagnosing integrative Chinese and Western medicine (ICWM) spleen-stomach disorders by addressing data scarcity, cross-paradigm reasoning, and benchmark standardization challenges.
It curates three ICWM datasets (SSDF-Syndrome, SSDF-Dialogue, and SSDF-PD) to provide higher-quality training and conversational/clinical data for spleen-stomach diagnostic tasks.
The framework builds SSDF-Core, a core diagnostic LLM trained with a two-stage regimen—supervised fine-tuning followed by direct preference optimization—to better combine TCM syndrome differentiation logic with Western medicine disease diagnosis.
It also adds SSDF-Navigator, a pluggable model that guides clinical inquiry strategies, supporting more effective consultation flows.
The authors release SSDF-Bench, a dedicated evaluation benchmark for ICWM spleen-stomach diagnosis, reporting that SSDF-Core outperforms 12 mainstream baselines on this benchmark.

Abstract

The clinical burden of spleen-stomach disorders is substantial. While large language models (LLMs) offer new potential for medical applications, they face three major challenges in the context of integrative Chinese and Western medicine (ICWM): a lack of high-quality data, the absence of models capable of effectively integrating the reasoning logic of traditional Chinese medicine (TCM) syndrome differentiation with that of Western medical (WM) disease diagnosis, and the shortage of a standardized evaluation benchmark. To address these interrelated challenges, we propose DongYuan, an ICWM spleen-stomach diagnostic framework. Specifically, three ICWM datasets (SSDF-Syndrome, SSDF-Dialogue, and SSDF-PD) were curated to fill the gap in high-quality data for spleen-stomach disorders. We then developed SSDF-Core, a core diagnostic LLM that acquires robust ICWM reasoning capabilities through a two-stage training regimen of supervised fine-tuning. tuning (SFT) and direct preference optimization (DPO), and complemented it with SSDF-Navigator, a pluggable consultation navigation model designed to optimize clinical inquiry strategies. Additionally, we established SSDF-Bench, a comprehensive evaluation benchmark focused on ICWM diagnosis of spleen-stomach disorders. Experimental results demonstrate that SSDF-Core significantly outperforms 12 mainstream baselines on SSDF-Bench. DongYuan lays a solid methodological foundation and provides practical technical references for the future development of intelligent ICWM diagnostic systems.