Assessing the Quality of AI Responses to Patient Concerns About Axial Spondyloarthritis: Delphi-Based Evaluation
Needs assessment across age groups and observed divergences between clinicians and patients underline the necessity for customized patient education. LLMs performed robustly on most evaluation metrics, and GPT-4.0 achieved 94% overall agreement with clinical guidelines. These tools hold promise as scalable adjuncts for ongoing axSpA support, provided complex clinical decision-making remains under human oversight. Nevertheless, the prevalence of artificial intelligence hallucinations remains a critical barrier. Only through comprehensive mitigation of such risks can LLM-based medical support be safely accelerated.
Authors
- Yufei Guo (ORCID: https://orcid.org/0000-0001-7002-1710)
- Xiaojian Ji (ORCID: https://orcid.org/0000-0003-4753-191X)
- Jiali Yu (ORCID: https://orcid.org/0000-0001-9302-077X)
- Jianguo Zhu (ORCID: https://orcid.org/0000-0002-8036-6058)
- Jin Lan Bai (ORCID: https://orcid.org/0009-0002-9328-8391)
- Yiwen Wang (ORCID: https://orcid.org/0000-0003-2069-6685)
- Wenrui Zhang (ORCID: https://orcid.org/0000-0002-0223-1924)
- Chao Xue (ORCID: https://orcid.org/0000-0002-6528-3975)
Institutions
- Chinese PLA General Hospital (CN)
- People's Liberation Army No. 150 Hospital (CN)
- Chinese People's Liberation Army (CN)
- Chinese People’s Liberation Army 263 hospital (CN)
Publication Details
- Journal
- JMIR AI
- Published
- 2025-10-31
- DOI
- https://doi.org/10.2196/79153
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00