迈向用于疾病管理的对话式人工智能
Towards Conversational AI for Disease Management
AI总结：
本文提出基于 LLM 的智能体系统 AMIE，结合 Gemini 长上下文检索与结构化推理对齐临床指南，在虚拟 OSCE 和 RxQA 用药推理基准上达到不劣于初级保健医生的表现，推动对话式 AI 用于疾病管理。
摘要：
虽然大语言模型（LLMs）在诊断对话中已展现出潜力，但它们在有效管理推理方面的能力——包括疾病进展、治疗反应和安全用药处方——仍未得到充分探索。我们通过一个基于 LLM 的新型智能体系统，推进了 Articulate Medical Intelligence Explorer（AMIE）此前已展示的诊断能力，该系统针对临床管理和对话进行了优化，融合了对疾病演变和多次患者就诊记录的推理、对治疗反应的推理，以及用药处方方面的专业能力。为了使推理建立在权威临床知识之上，AMIE 利用 Gemini 的长上下文能力，将上下文内检索与结构化推理相结合，使其输出与相关且最新的临床实践指南和药品处方集保持一致。在一项随机、设盲的虚拟客观结构化临床考试（OSCE）研究中，AMIE 与 21 名初级保健医生（PCPs）在 100 个多就诊病例场景中进行了比较，这些场景旨在反映英国 NICE 指南和 BMJ Best Practice 指南。经专科医生评估，AMIE 在管理推理方面不劣于初级保健医生，并且在治疗和检查的精确性，以及管理计划与临床指南的一致性和依据性方面得分更高。为了对用药推理进行基准测试，我们开发了 RxQA，这是一个多选题基准，来源于两个国家药品处方集（美国、英国），并由持证药剂师验证。虽然 AMIE 和初级保健医生都从获取外部药物信息的能力中受益，但 AMIE 在更高难度的问题上表现优于初级保健医生。尽管在向现实世界转化之前还需要进一步研究，但 AMIE 在各项评估中的强劲表现标志着对话式人工智能作为疾病管理工具迈出了重要一步。
英文摘要：
While large language models (LLMs) have shown promise in diagnostic dialogue, their capabilities for effective management reasoning - including disease progression, therapeutic response, and safe medication prescription - remain under-explored. We advance the previously demonstrated diagnostic capabilities of the Articulate Medical Intelligence Explorer (AMIE) through a new LLM-based agentic system optimised for clinical management and dialogue, incorporating reasoning over the evolution of disease and multiple patient visit encounters, response to therapy, and professional competence in medication prescription. To ground its reasoning in authoritative clinical knowledge, AMIE leverages Gemini's long-context capabilities, combining in-context retrieval with structured reasoning to align its output with relevant and up-to-date clinical practice guidelines and drug formularies. In a randomized, blinded virtual Objective Structured Clinical Examination (OSCE) study, AMIE was compared to 21 primary care physicians (PCPs) across 100 multi-visit case scenarios designed to reflect UK NICE Guidance and BMJ Best Practice guidelines. AMIE was non-inferior to PCPs in management reasoning as assessed by specialist physicians and scored better in both preciseness of treatments and investigations, and in its alignment with and grounding of management plans in clinical guidelines. To benchmark medication reasoning, we developed RxQA, a multiple-choice question benchmark derived from two national drug formularies (US, UK) and validated by board-certified pharmacists. While AMIE and PCPs both benefited from the ability to access external drug information, AMIE outperformed PCPs on higher difficulty questions. While further research would be needed before real-world translation, AMIE's strong performance across evaluations marks a significant step towards conversational AI as a tool in disease management.
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。
