Recent advancements in Large Language Models (LLMs) have demonstrated significant promise in clinical diagnosis. However, current models struggle to emulate the iterative, diagnostic hypothesis-driven reasoning of real clinical scenarios. Specifically, current LLMs suffer from three critical limitations: (1) generating hallucinated medical content due to weak grounding in verified knowledge, (2) asking redundant or inefficient questions rather than discriminative ones that hinder diagnostic progress, and (3) losing coherence over multi-turn dialogues, leading to contradictory or inconsistent conclusions. To address these challenges, we propose MedKGI, a diagnostic framework grounded in clinical practices. MedKGI integrates a medical knowledge graph (KG) to constrain reasoning to validated medical ontologies, selects questions based on information gain to maximize diagnostic efficiency, and adopts an OSCE-format structured state to maintain consistent evidence tracking across turns. Experiments on clinical benchmarks show that MedKGI outperforms strong LLM baselines in both diagnostic accuracy and inquiry efficiency, improving dialogue efficiency by 30% on average while maintaining state-of-the-art accuracy.

翻译：近年来，大型语言模型（LLMs）在临床诊断领域展现出巨大潜力。然而，现有模型难以模拟真实临床场景中迭代的、基于诊断假设的推理过程。具体而言，当前LLMs存在三个关键局限：（1）由于缺乏对已验证知识的扎实基础，易生成虚构的医学内容；（2）倾向于提出冗余或低效的疑问，而非能推动诊断进程的鉴别性问题；（3）在多轮对话中丧失连贯性，导致矛盾或不一致的结论。为应对这些挑战，我们提出基于临床实践构建的诊断框架MedKGI。该框架整合医学知识图谱（KG）以将推理约束在已验证的医学本体范围内，依据信息增益选择问题以最大化诊断效率，并采用OSCE格式的结构化状态来维持跨轮次的一致性证据追踪。临床基准实验表明，MedKGI在诊断准确性与问询效率上均优于现有强LLM基线模型，在保持顶尖准确率的同时，平均提升对话效率30%。