An LLM chatbot to facilitate primary-to-specialist care transitions: a randomized controlled trial.

We developed the preassessment (PreA), an LLM chatbot co-designed with local stakeholders, to perform the general medical consultations for history-taking, preliminary diagnoses, and test ordering that would normally be performed by primary care providers and to generate referral reports for specialists.

我们开发了预评估（PreA），这是一种与当地利益相关者共同设计的LLM聊天机器人，用于执行通常由初级保健提供者进行的病史采集、初步诊断和测试订购的普通医疗咨询，并为专科医生生成转诊报告。

PreA was tested in a randomized controlled trialinvolving 111 specialists from 24 medical disciplines across two health centers, where 2,069 patients (1,141 women; 928 men) were randomly assigned to use PreA independently (PreA-only), use it with staff support (PreA-human), or not use it (No-PreA) before specialist consultation.

PreA 在一项涉及两个卫生中心的 24 个医学专业领域的 111 名专家的随机对照试验中进行了测试，其中 2,069 名患者（1,141 名女性；928 名男性）被随机分配独立使用 PreA（仅 PreA），在工作人员支持下使用它（PreA-人类），或在专家咨询前不使用它（无 PreA）。

The trial met its primary end points with the PreA-only group showing significantly reduced physician consultation duration (28.7% reduction; 3.14 ± 2.25 min) compared to the No-PreA group (4.41 ± 2.77 min; P < 0.001), alongside significant improvements in physician-perceived care coordination (mean scores 113.1% increase; 3.69 ± 0.90 versus 1.73 ± 0.95; P < 0.001) and patient-reported communication ease (mean scores 16.0% increase; 3.99 ± 0.62 versus 3.44 ± 0.97; P < 0.001).

该试验达到了其主要终点，与无 PreA 组相比，仅使用 PreA 组的医生咨询时间显著减少（减少了 28.7%；3.14 ± 2.25 分钟）至（4.41 ± 2.77 分钟；P < 0.001），同时在医生感知的护理协调方面有显著改善（平均得分增加了 113.1%；3.69 ± 0.90 与 1.73 ± 0.95；P < 0.001）以及患者报告的沟通便利性（平均得分增加了 16.0%；3.99 ± 0.62 与 3.44 ± 0.97；P < 0.001）。

Equivalent outcomes between the PreA-only and PreA-human groups confirmed the autonomous operation capability.

PreA-only 和 PreA-human 组之间的等效结果证实了自主操作的能力。

Co-designed PreA outperformed the same model with additional fine-tuning on local dialogues across clinical decision-making domains.

共同设计的PreA在临床决策领域的表现优于同一模型在本地对话上进行额外微调的版本。

Co-design with local stakeholders, compared to passive local data collecting, represents a more effective strategy for deploying LLMs to strengthen health systems and enhance patient-centered care in resource-limited settings.

与被动收集本地数据相比，与当地利益相关者共同设计是一种更有效的策略，用于在资源有限的环境中部署大型语言模型（LLMs），以加强卫生系统并提升以患者为中心的护理。

Chinese Clinical Trial Registry identifier: ChiCTR2400094159 .

中国临床试验注册中心标识：ChiCTR2400094159。