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

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.