Scholarlink

Objective <p>A significant gap exists in medical support for organ transplant patients during out-of-hours&#xa0;(OOH). General large language models (LLMs), affected by AI hallucinations, are unsuitable for complex post-transplant care. We built the first post-transplant AI agent based on LLMs to address these issues.</p> Methods <p>We constructed a specialized “post-transplant AI agent” (named&#xa0;Doctor Xiao Yi) and conducted a mixed-methods study comparing it to a hospital-wide general AI agent (named&#xa0;Nan Xiao Yi). Data included 20,176 real-world logs (June–December 2025) and a cross-sectional survey of 152 transplant patients. We examined patterns of use over time, the types of questions raised, and the factors influencing patient behavior.</p> Results <p>Unlike Nan Xiao Yi, Doctor Xiao Yi remained active during OOH, with a peak at 4:00 AM (<i>P</i> &lt; 0.001). The general agent handled admin tasks like appointments, while the specialist agent provided clinical support such as diet, symptoms, and medication. Survey found 60.5% of OOH use by transplant patients due to reluctance to disturb human doctors. Furthermore, 63.8% of transplant patients were satisfied with the specialist agent's responses, and 48% reported they would decide on further hospital treatment based on AI suggestions.</p> Conclusions <p>The specialist AI agent effectively fills the gap in medical and psychological services during OOH for transplant recipients. Based on the “dual-source knowledge base + GraphRAG&#xa0;+ multi-agent framework” architecture, our specialist AI agent offers safe, reliable post-transplant care.</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

Real-World Analysis of Organ Transplantation-Specific Agent Based on Large Language Model in Post-Transplant Self-Management During Off-Hours: A Mixed-Methods Study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月1日

查看全文
  • Cheng Zeng,
  • Xin Zhou,
  • Hong-yun Xu,
  • Xiao-ping Zhu,
  • Yue Shi,
  • Guang-le Dai,
  • Zhi-gao Deng,
  • Yan Xu,
  • Li Xu,
  • Hui Xiao,
  • Shao-jun Ye

摘要

Objective

A significant gap exists in medical support for organ transplant patients during out-of-hours (OOH). General large language models (LLMs), affected by AI hallucinations, are unsuitable for complex post-transplant care. We built the first post-transplant AI agent based on LLMs to address these issues.

Methods

We constructed a specialized “post-transplant AI agent” (named Doctor Xiao Yi) and conducted a mixed-methods study comparing it to a hospital-wide general AI agent (named Nan Xiao Yi). Data included 20,176 real-world logs (June–December 2025) and a cross-sectional survey of 152 transplant patients. We examined patterns of use over time, the types of questions raised, and the factors influencing patient behavior.

Results

Unlike Nan Xiao Yi, Doctor Xiao Yi remained active during OOH, with a peak at 4:00 AM (P < 0.001). The general agent handled admin tasks like appointments, while the specialist agent provided clinical support such as diet, symptoms, and medication. Survey found 60.5% of OOH use by transplant patients due to reluctance to disturb human doctors. Furthermore, 63.8% of transplant patients were satisfied with the specialist agent's responses, and 48% reported they would decide on further hospital treatment based on AI suggestions.

Conclusions

The specialist AI agent effectively fills the gap in medical and psychological services during OOH for transplant recipients. Based on the “dual-source knowledge base + GraphRAG + multi-agent framework” architecture, our specialist AI agent offers safe, reliable post-transplant care.