Scholarlink

<p>With a global shortage of primary healthcare physicians—particularly in resource-limited settings—large language models (LLMs) have the potential to support and enhance patients’ health awareness. Here we developed P&amp;P Care (Population Medicine and Public Health), an LLM-powered primary care chatbot using a dual-track role-play codesign framework where community stakeholders and researchers simulated each another’s perspectives across four phases: contextual understanding; cocreation; testing and refinement; and implementation and evolution. The codesigned chatbot was integrated with e-learning modules and tested in a randomized controlled trial. The trial included 2,113 participants (1,052 women and 1,061 men) from urban and rural areas across 11 Chinese provinces who were randomly assigned to receive a consultation either with preparatory e-learning via the P&amp;P Care or without. The study met its primary endpoint with the e-learning group showing significantly higher objective health awareness (mean score 2.95 ± 1.22) compared with the consultation-only group (mean score 2.34 ± 1.02; <i>P</i> &lt; 0.001). Codesign offers a scalable solution for deploying LLMs in resource-limited settings. Chinese Clinical Trial Registry identifier: <a href="https://www.chictr.org.cn/showprojEN.html?proj=251064">ChiCTR2500098101</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A community-codesigned LLM-powered chatbot for primary care: a randomized controlled trial

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月19日

查看全文
  • Sairan Li,
  • Yanzeng Li,
  • Shuya Zhou,
  • Xinge Tao,
  • Changjie Yu,
  • Muzi Shen,
  • Wangyue Chen,
  • En Meng,
  • Boyou Wu,
  • Qirui Huang,
  • Frances S. Mair,
  • Jinchao Zhang,
  • Jie Zhou,
  • Lei Zou,
  • Shasha Han

摘要

With a global shortage of primary healthcare physicians—particularly in resource-limited settings—large language models (LLMs) have the potential to support and enhance patients’ health awareness. Here we developed P&P Care (Population Medicine and Public Health), an LLM-powered primary care chatbot using a dual-track role-play codesign framework where community stakeholders and researchers simulated each another’s perspectives across four phases: contextual understanding; cocreation; testing and refinement; and implementation and evolution. The codesigned chatbot was integrated with e-learning modules and tested in a randomized controlled trial. The trial included 2,113 participants (1,052 women and 1,061 men) from urban and rural areas across 11 Chinese provinces who were randomly assigned to receive a consultation either with preparatory e-learning via the P&P Care or without. The study met its primary endpoint with the e-learning group showing significantly higher objective health awareness (mean score 2.95 ± 1.22) compared with the consultation-only group (mean score 2.34 ± 1.02; P < 0.001). Codesign offers a scalable solution for deploying LLMs in resource-limited settings. Chinese Clinical Trial Registry identifier: ChiCTR2500098101.