DocCHA：迈向LLM增强的交互式在线诊断系统
DocCHA: Towards LLM-Augmented Interactive Online diagnosis System
AI总结：
提出DocCHA，一个置信度感知的模块化框架，通过分解症状引出、病史获取和因果图构建三阶段模拟临床推理，在中文问诊数据集上显著提升诊断准确率和症状召回率，实现结构化透明的多轮诊断对话。
摘要：
尽管大型语言模型（LLMs）能力惊人，但现有的对话式健康代理（CHAs）仍是静态且脆弱的，无法进行自适应多轮推理、症状澄清或透明决策。这阻碍了其在临床诊断中的实际应用，因为迭代和结构化对话在此场景中至关重要。我们提出了DocCHA，一个置信度感知的模块化框架，通过将诊断过程分解为三个阶段来模拟临床推理：（1）症状引出，（2）病史获取，和（3）因果图构建。每个模块使用可解释的置信度分数来指导自适应提问、优先处理信息丰富的澄清，并细化薄弱的推理链。在两个真实世界的中文问诊数据集（IMCS21, DX）上评估，DocCHA始终优于基于提示的强大LLM基线（GPT-3.5, GPT-4o, LLaMA-3），诊断准确率高出5.18%，症状召回率提升超过30%，且对话轮数仅略有增加。这些结果证明了DocCHA在实现结构化、透明且高效的诊断对话方面的有效性——为在多语言和资源受限环境中构建值得信赖的LLM驱动的临床助手铺平了道路。
英文摘要：
Despite the impressive capabilities of Large Language Models (LLMs), existing Conversational Health Agents (CHAs) remain static and brittle, incapable of adaptive multi-turn reasoning, symptom clarification, or transparent decision-making. This hinders their real-world applicability in clinical diagnosis, where iterative and structured dialogue is essential. We propose DocCHA, a confidence-aware, modular framework that emulates clinical reasoning by decomposing the diagnostic process into three stages: (1) symptom elicitation, (2) history acquisition, and (3) causal graph construction. Each module uses interpretable confidence scores to guide adaptive questioning, prioritize informative clarifications, and refine weak reasoning links. Evaluated on two real-world Chinese consultation datasets (IMCS21, DX), DocCHA consistently outperforms strong prompting-based LLM baselines (GPT-3.5, GPT-4o, LLaMA-3), achieving up to 5.18 percent higher diagnostic accuracy and over 30 percent improvement in symptom recall, with only modest increase in dialogue turns. These results demonstrate the effectiveness of DocCHA in enabling structured, transparent, and efficient diagnostic conversations -- paving the way for trustworthy LLM-powered clinical assistants in multilingual and resource-constrained settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
