用大模型自动生成临床建议，辅助医生提高诊断准确率。
MedGellan: LLM-Generated Medical Guidance to Support Physicians
- 基于贝叶斯提示策略生成符合时间顺序的医疗建议
- 实验显示诊断召回率与F1分数显著提升
- 无需标注数据，适合临床快速部署
医疗决策是一项关键任务，错误可能导致严重甚至危及生命的后果。尽管完全自动化仍具挑战性，但结合机器智能与人工监督的混合框架提供了实用替代方案。本文提出MedGellan，一种轻量级、无需标注数据的框架，利用大语言模型（LLM）从原始病历中生成临床建议，供医生用于诊断预测。MedGellan采用受贝叶斯启发的提示策略，尊重临床数据的时间顺序。初步实验表明，使用MedGellan生成的建议能提升诊断性能，尤其在召回率和F1分数方面表现突出。
原文摘要 · Abstract (English)
Medical decision-making is a critical task, where errors can result in serious, potentially life-threatening consequences. While full automation remains challenging, hybrid frameworks that combine machine intelligence with human oversight offer a practical alternative. In this paper, we present MedGellan, a lightweight, annotation-free framework that uses a Large Language Model (LLM) to generate clinical guidance from raw medical records, which is then used by a physician to predict diagnoses. MedGellan uses a Bayesian-inspired prompting strategy that respects the temporal order of clinical data. Preliminary experiments show that the guidance generated by the LLM with MedGellan improves diagnostic performance, particularly in recall and $F_1$ score.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。