Validity and reliability of ChatGPT's responses on dietary supplements in Japan: A quality assessment and content analysis
This is the first study to assess the validity and reliability of LLM-generated responses on dietary supplements using both quantitative and qualitative methods. We also developed a novel evidence-based framework to evaluate supplement effectiveness, providing a new tool for future research and supporting safer AI-assisted health communication.
Authors
- Yuriko Nishiie
- Xinyi Chang
- Tsuyoshi Okuhara (ORCID: https://orcid.org/0000-0002-6251-3587)
- Takahiro Kiuchi (ORCID: https://orcid.org/0000-0001-5934-0681)
- Ritsuko Shirabe (ORCID: https://orcid.org/0000-0001-6427-210X)
- Hiroko Okada
- Mingxin Liu
Institutions
- University of Tokyo Hospital (JP)
- University of Tokyo Health Sciences (JP)
- University hospital Medical Information Network (JP)
Publication Details
- Journal
- PEC Innovation
- Published
- 2026-02-21
- DOI
- https://doi.org/10.1016/j.pecinn.2026.100461
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00