The advancement of medical artificial intelligence (AI) has set the stage for
the realization of conversational diagnosis, where AI systems mimic human
doctors by engaging in dialogue with patients to deduce diagnoses. This study
introduces an innovative approach using external planners augmented with large
language models (LLMs) to develop a medical task-oriented dialogue system. This
system comprises a policy module for information gathering, a LLM based module
for natural language understanding and generation, addressing the limitations
of previous AI systems in these areas. By emulating the two-phase
decision-making process of doctors disease screening and differential
diagnosis. we designed two distinct planners. The first focuses on collecting
patient symptoms to identify potential diseases, while the second delves into
specific inquiries to confirm or exclude these diseases. Utilizing
reinforcement learning and active learning with LLMs, we trained these planners
to navigate medical dialogues effectively. Our evaluation on the MIMIC-IV
dataset demonstrated the system's capability to outperform existing models,
indicating a significant step towards achieving automated conversational
disease diagnostics and enhancing the precision and accessibility of medical
diagnoses.

通过利用大型语言模型来开发一个医学任务导向的对话系统，该系统模拟人类医生与患者对话以推断诊断结果，研究使用外部规划器和大型语言模型改进了先前人工智能系统在信息收集和自然语言理解等方面的局限性。通过模拟医生的疾病筛查和鉴别诊断的两阶段决策过程，我们设计了两个不同的规划器，以有效地引导医疗对话。采用强化学习和大型语言模型进行主动学习，我们训练了这些规划器，并在 MIMIC-IV 数据集上对系统进行评估，结果表明该系统能够胜过现有模型，这是实现自动对话式疾病诊断并提高医学诊断的精确性和可访问性的重要一步。