arXiv cs.AI· Hongkang Chu, Yifan Shen, Tianjiao Yu, Zhuoqing Zhong, Jianguo Cao, Meihuan Huang, Xu Cao·· 2 小时前AI 评分36
MedCaseAgent：从多模态临床证据生成罕见病病例报告
MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports
AI 导读
研究者提出 MedCaseAgent，一种端到端智能体推理框架，可从非结构化临床笔记生成达到发表质量的罕见病病例报告，通过动态查询医学文献与知识库保持临床保真度，并支持即插即用的多种 backbone LLM。
正文 · 原文
Abstract:Although Large Language Models (LLMs) have demonstrated potential in clinical documentation, generating the rigorous, evidence-based reasoning required for unprecedented, atypical, and rare disease case reports remains a significant challenge. We present MedCaseAgent, an end-to-end agentic reasoning paradigm that bridges this gap by synthesizing publication-quality reports from unstructured clinical notes. MedCaseAgent leverages a hierarchical structure, integrating patient-level data mining with iterative, tool-integrated reasoning. By dynamically querying medical literature and knowledge bases, the agent maintains high clinical fidelity and assesses case novelty. The framework is inherently modular, supporting various backbone LLMs in a plug-and-play fashion. To facilitate this research, we release MedCase-150K, a large-scale multimodal clinical case-report corpus, and MedCase-Bench, a robust temporally held-out evaluation suite. We also introduce an open-source model post-trained from Qwen3.5-9B and optimized specifically for this task. Under both LLM-judged and rule-based evaluation, MedCaseAgent outperforms existing general-purpose and specialized medical LLMs and agents. Blinded expert reviews and ablations further support the system's clinical relevance and evidence grounding.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32258 [cs.AI] |
| (or arXiv:2610.32258v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32258 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xu Cao [view email]
[v1]
Fri, 23 Oct 2026 07:14:59 UTC (6,686 KB)
来源：arXiv cs.AI · arxiv.org