English

MSDiagnosis: A Benchmark for Evaluating Large Language Models in Multi-Step Clinical Diagnosis

Artificial Intelligence 2024-12-17 v3

Abstract

Clinical diagnosis is critical in medical practice, typically requiring a continuous and evolving process that includes primary diagnosis, differential diagnosis, and final diagnosis. However, most existing clinical diagnostic tasks are single-step processes, which does not align with the complex multi-step diagnostic procedures found in real-world clinical settings. In this paper, we propose a Chinese clinical diagnostic benchmark, called MSDiagnosis. This benchmark consists of 2,225 cases from 12 departments, covering tasks such as primary diagnosis, differential diagnosis, and final diagnosis. Additionally, we propose a novel and effective framework. This framework combines forward inference, backward inference, reflection, and refinement, enabling the large language model to self-evaluate and adjust its diagnostic results. To this end, we test open-source models, closed-source models, and our proposed framework.The experimental results demonstrate the effectiveness of the proposed method. We also provide a comprehensive experimental analysis and suggest future research directions for this task.

Keywords

Cite

@article{arxiv.2408.10039,
  title  = {MSDiagnosis: A Benchmark for Evaluating Large Language Models in Multi-Step Clinical Diagnosis},
  author = {Ruihui Hou and Shencheng Chen and Yongqi Fan and Guangya Yu and Lifeng Zhu and Jing Sun and Jingping Liu and Tong Ruan},
  journal= {arXiv preprint arXiv:2408.10039},
  year   = {2024}
}
R2 v1 2026-06-28T18:16:51.723Z