用多智能体增强知识图谱，实现零样本精准医疗诊断
KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs
- 多智能体协作：映射属性、提取知识、迭代推理
- 零样本诊断准确率显著提升，避免模型幻觉
- 适合医疗AI研究者和临床辅助系统开发者
医疗诊断预测在疾病检测与个性化医疗中至关重要。尽管机器学习模型广泛应用，但其依赖监督训练，难以泛化到未见病例，尤其受限于大规模标注数据的高成本。大语言模型（LLMs）虽具备语言能力和生物医学知识，却常出现幻觉、缺乏结构化医学推理，输出无效。为此，我们提出基于知识图谱（KG）增强的多智能体框架KERAP，包含链接代理（用于属性映射）、检索代理（提取结构化知识）和预测代理（迭代优化诊断结果）。实验表明，该方法显著提升了诊断可靠性，提供了一种可扩展、可解释的零样本医疗诊断方案。
原文摘要 · Abstract (English)
Medical diagnosis prediction plays a critical role in disease detection and personalized healthcare. While machine learning (ML) models have been widely adopted for this task, their reliance on supervised training limits their ability to generalize to unseen cases, particularly given the high cost of acquiring large, labeled datasets. Large language models (LLMs) have shown promise in leveraging language abilities and biomedical knowledge for diagnosis prediction. However, they often suffer from hallucinations, lack structured medical reasoning, and produce useless outputs. To address these challenges, we propose KERAP, a knowledge graph (KG)-enhanced reasoning approach that improves LLM-based diagnosis prediction through a multi-agent architecture. Our framework consists of a linkage agent for attribute mapping, a retrieval agent for structured knowledge extraction, and a prediction agent that iteratively refines diagnosis predictions. Experimental results demonstrate that KERAP enhances diagnostic reliability efficiently, offering a scalable and interpretable solution for zero-shot medical diagnosis prediction.
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。