以患者为中心的 AI 用于就诊准备的前瞻性随机研究
A prospective randomized study of patient-centered AI for clinical visit preparation
Xincheng Tan · Matthew Thompson · Xiang Ji · Angelica Willis · Will Vaughan · Roma Ruparel · et al.
中文摘要
患者常在短暂、时间受限的就诊中不清楚该期待什么或该问什么，如今数百万成年人会事先求助于通用 AI 聊天机器人做准备。但对话式 AI 能否改善就诊准备度仍不明确。研究设计了一个基于大语言模型(LLM)的就诊准备智能体，在预约前引导患者：收集临床背景、设定就诊预期、提供相关健康信息、构建按优先级排序的向临床医生提问清单，并生成摘要。在 Google Health 应用中开展前瞻性知情同意随机研究，802 名美国成年人进行了 866 次健康相关对话，分别使用就诊准备智能体(标准版或简洁版)或基于同一 LLM 的轻度提示对照聊天机器人。在盲法临床医生评估和患者自报中，该智能体显著优于对照。临床医生对完成会话的评审(n = 272)显示，智能体的全面准备率高出 16.6%(67.2% vs. 50.6%；P < 0.05)，与患者健康背景的一致性高出 8.5%(98.9% vs. 90.4%；P < 0.01)，同时所有研究组均保持较高的医疗安全性与适当性。患者后测问卷(n = 460)显示，就诊准备度高出 16.8%(73.8% vs. 57.0%；P < 0.01)，知道该问什么的信心高出 14.3%(81.4% vs. 67.1%；P < 0.01)，总体满意度高出 12.0%(74.0% vs. 62.0%；P < 0.05)。临床医生与参与者指标无显著相关性，表明专家评审与患者自评捕捉的是面向患者 AI 的互补维度。这些发现提示，LLM 聊天机器人可以安全地帮助患者准备就诊，遵循结构化工作流时获益更大，并推动未来关于就诊中沟通与临床结局的研究。
关键要点
- 01问题：患者就诊前准备不足，通用 AI 聊天机器人能否改善就诊准备度尚不明确。
- 02方法：设计基于 LLM 的就诊准备智能体，在 Google Health 应用中开展 802 人随机研究。
- 03结果：临床医生评审全面准备率 67.2% vs 50.6%，患者准备度 73.8% vs 57.0%。
- 04结果：医疗安全性与适当性在各组均保持较高水平，结构化工作流获益更大。
- 05局限：临床医生与患者指标不相关，需未来研究就诊中沟通与临床结局。
解读
尚无解读。
原始英文摘要
arXiv:2610.41437v1 Announce Type: cross Abstract: Patients often arrive at brief, time-constrained clinical visits unsure of what to expect or ask, and millions of adults now turn to general-purpose AI chatbots to prepare beforehand. Yet whether conversational AI improves visit readiness remains unclear. We designed a large language model (LLM)-based visit preparation agent to guide patients before an appointment by gathering clinical context, setting visit expectations, providing relevant health information, building a prioritized list of questions for their clinician, and generating a summary. In a prospective consented randomized study in the Google Health app, 802 U.S. adults held 866 health-related conversations with the visit preparation agent (standard or concise variant) or a minimally prompted control chatbot built on the same LLM. The visit preparation agent significantly outperformed the control across blinded clinician evaluations and patient self-reports. In clinician reviews of completed sessions (n = 272), the agent achieved a 16.6% higher rate of comprehensive preparation (67.2% vs. 50.6%; P < 0.05) and an 8.5% higher rate of alignment with patients' health context (98.9% vs. 90.4%; P < 0.01), while maintaining high medical safety and appropriateness across all study arms. Patient post-surveys (n = 460) showed 16.8% higher visit preparedness (73.8% vs. 57.0%; P < 0.01), 14.3% higher confidence in knowing what to ask (81.4% vs. 67.1%; P < 0.01), and 12.0% higher overall satisfaction (74.0% vs. 62.0%; P < 0.05). Clinician and participant metrics were not significantly correlated, indicating that expert review and patient self-assessment capture complementary dimensions of patient-facing AI. These findings suggest that LLM chatbots can safely help patients prepare for clinical visits, with greater benefit when following a structured workflow, and motivate future studies on in-visit communication and clinical outcomes.