Ren Yong, Kang Yue-Ning, Cao Shuang-Yan, Meng Fanxuan, Zhang Jingyu, Liao Ruyi, Li Xiaomin, Chen Yuling, Wen Ya, Wu Jiayun, Xia Wenqi, Xu Liling, Wen Shenghui, Liu Huifen, Li Yuanqing, Gu Jieruo, Lv Qing
Pazhou Lab, Guangzhou, Guangdong, China.
The Seventh Affiliated Hospital of Sun Yat-sen University, Shenzhen, Guangdong, China.
BMJ Open. 2025 Mar 21;15(3):e097528. doi: 10.1136/bmjopen-2024-097528.
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.
Cross-sectional, single-blind study.
Multiple centres in China.
182 volunteers, including 4 rheumatologists and 178 patients with AS/SpA.
Scientificity, precision and accessibility of the content of the answers provided by LLMs; patient acceptance of the answers.
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.
LLMs have significant potential in medical knowledge transmission and patient education, making them promising tools for future medical practice.
评估大语言模型（LLMs）在强直性脊柱炎（AS）/脊柱关节炎（SpA）患者健康教育中的潜力，重点关注信息传递的准确性、患者接受度以及不同模型之间的性能差异。
横断面单盲研究。
中国多个中心。
182名志愿者，包括4名风湿病学家和178名AS/SpA患者。
大语言模型提供答案内容的科学性、精确性和可及性；患者对答案的接受度。
大语言模型在科学性、精确性和可及性方面表现良好，ChatGPT-4o和Kimi模型优于传统指南。大多数AS/SpA患者对大语言模型的回答表现出更高的理解和接受程度。
大语言模型在医学知识传播和患者教育方面具有巨大潜力，使其成为未来医学实践中有前景的工具。
