BMJ Open (Mar 2025)

Evaluating the performance of large language models in health education for patients with ankylosing spondylitis/spondyloarthritis: a cross-sectional, single-blind study in China

  • Yong Ren,
  • Yuanqing Li,
  • Jieruo Gu,
  • Qing Lv,
  • Wenqi Xia,
  • Jingyu Zhang,
  • Huifen Liu,
  • Ya Wen,
  • Liling Xu,
  • Yuling Chen,
  • Yue-ning Kang,
  • Shuang-yan Cao,
  • Fanxuan Meng,
  • Ruyi Liao,
  • Xiaomin Li,
  • Jiayun Wu,
  • Shenghui Wen

DOI
https://doi.org/10.1136/bmjopen-2024-097528
Journal volume & issue
Vol. 15, no. 3

Abstract

Read online

Objectives To evaluate the potential of large language models (LLMs) in health education for patients with ankylosing spondylitis (AS)/spondyloarthritis (SpA), focusing on the accuracy of information transmission, patient acceptance and performance differences between different models.Design Cross-sectional, single-blind study.Setting Multiple centres in China.Participants 182 volunteers, including 4 rheumatologists and 178 patients with AS/SpA.Primary and secondary outcome measures Scientificity, precision and accessibility of the content of the answers provided by LLMs; patient acceptance of the answers.Results LLMs performed well in terms of scientificity, precision and accessibility, with ChatGPT-4o and Kimi models outperforming traditional guidelines. Most patients with AS/SpA showed a higher level of understanding and acceptance of the responses from LLMs.Conclusions LLMs have significant potential in medical knowledge transmission and patient education, making them promising tools for future medical practice.