State Key Laboratory of Respiratory Health and Multimorbidity, Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
Laboratory of Immune Cell Biology, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
Nat Med. 2024 Oct;30(10):2878-2885. doi: 10.1038/s41591-024-03148-7. Epub 2024 Jul 15.
Reception is an essential process for patients seeking medical care and a critical component influencing the healthcare experience. However, current communication systems rely mainly on human efforts, which are both labor and knowledge intensive. A promising alternative is to leverage the capabilities of large language models (LLMs) to assist the communication in medical center reception sites. Here we curated a unique dataset comprising 35,418 cases of real-world conversation audio corpus between outpatients and receptionist nurses from 10 reception sites across two medical centers, to develop a site-specific prompt engineering chatbot (SSPEC). The SSPEC efficiently resolved patient queries, with a higher proportion of queries addressed in fewer rounds of queries and responses (Q&Rs; 68.0% ≤2 rounds) compared with nurse-led sessions (50.5% ≤2 rounds) (P = 0.009) across administrative, triaging and primary care concerns. We then established a nurse-SSPEC collaboration model, overseeing the uncertainties encountered during the real-world deployment. In a single-center randomized controlled trial involving 2,164 participants, the primary endpoint indicated that the nurse-SSPEC collaboration model received higher satisfaction feedback from patients (3.91 ± 0.90 versus 3.39 ± 1.15 in the nurse group, P < 0.001). Key secondary outcomes indicated reduced rate of repeated Q&R (3.2% versus 14.4% in the nurse group, P < 0.001) and reduced negative emotions during visits (2.4% versus 7.8% in the nurse group, P < 0.001) and enhanced response quality in terms of integrity (4.37 ± 0.95 versus 3.42 ± 1.22 in the nurse group, P < 0.001), empathy (4.14 ± 0.98 versus 3.27 ± 1.22 in the nurse group, P < 0.001) and readability (3.86 ± 0.95 versus 3.71 ± 1.07 in the nurse group, P = 0.006). Overall, our study supports the feasibility of integrating LLMs into the daily hospital workflow and introduces a paradigm for improving communication that benefits both patients and nurses. Chinese Clinical Trial Registry identifier: ChiCTR2300077245 .
接待是患者寻求医疗服务的一个重要环节，也是影响医疗体验的关键因素。然而，当前的沟通系统主要依赖于人力，这既耗费劳动力又需要专业知识。一种有前途的替代方法是利用大型语言模型（LLMs）的能力来协助医疗中心接待处的沟通。在这里，我们整理了一个独特的数据集，其中包含来自两个医疗中心的 10 个接待处的 35418 例门诊患者与接待护士之间的真实对话音频语料库，以开发特定于站点的提示工程聊天机器人（SSPEC）。与护士主导的会话（50.5%≤2 轮）相比，SSPEC 高效地解决了患者的查询问题，在更少的查询和响应（Q&R）轮次中解决了更高比例的查询（68.0%≤2 轮）（P=0.009），涵盖行政、分诊和初级保健问题。然后，我们建立了护士-SSPEC 协作模型，监督在实际部署中遇到的不确定性。在一项涉及 2164 名参与者的单中心随机对照试验中，主要终点表明，护士-SSPEC 协作模型收到了患者更高的满意度反馈（护士组为 3.91±0.90，护士组为 3.39±1.15，P<0.001）。关键次要结果表明，重复 Q&R 的发生率降低（护士组为 3.2%，护士组为 14.4%，P<0.001），就诊期间的负面情绪减少（护士组为 2.4%，护士组为 7.8%，P<0.001），并且在完整性（护士组为 4.37±0.95，护士组为 3.42±1.22）、同理心（护士组为 4.14±0.98，护士组为 3.27±1.22）和可读性（护士组为 3.86±0.95，护士组为 3.71±1.07）方面的响应质量提高（P<0.001）。总体而言，我们的研究支持将大型语言模型集成到日常医院工作流程中的可行性，并介绍了一种改善医患沟通的模式。中国临床试验注册中心标识：ChiCTR2300077245。
JBI Database System Rev Implement Rep. 2015-1
Telemed J E Health. 2015-8
Cochrane Database Syst Rev. 2022-2-1
Intensive Crit Care Nurs. 2022-6
Aesthetic Plast Surg. 2025-8-8
NPJ Digit Med. 2025-8-4
NPJ Digit Med. 2025-6-20
NPJ Digit Med. 2025-5-6
EBioMedicine. 2025-5
Clin Anat. 2025-4-23
PLOS Digit Health. 2023-10-24
BMC Health Serv Res. 2023-8-22
Nat Med. 2023-8
Nature. 2023-8
N Engl J Med. 2023-3-30
NPJ Digit Med. 2022-12-26
Nat Med. 2022-1
Front Psychol. 2021-5-6
Zotero 插件