Performance of large language models in answering frequently‐asked questions on celiac disease
LLMs provide clear and generally accurate responses to CeD FAQs, particularly on management-related topics. While they represent a promising tool for patient education, variability in accuracy highlights the need for clinician oversight when interpreting artificial intelligence-generated medical information.
Authors
- Francesco Valitutti (ORCID: https://orcid.org/0000-0002-1473-2240)
- Peter Michael Gillett (ORCID: https://orcid.org/0000-0003-2294-4478)
- Nadav Peled
- Dror S Shouval
- Hania Szajewska
- Anat Guz-Mark
- Raanan Shamir
Institutions
- Tel Aviv University (IL)
- Medical University of Warsaw (PL)
- University of Perugia (IT)
- Schneider Children's Medical Center (IL)
- Children in Scotland (GB)
- Ariel University (IL)
- University of Edinburgh (GB)
Publication Details
- Journal
- Journal of Pediatric Gastroenterology and Nutrition
- Published
- 2026-02-09
- DOI
- https://doi.org/10.1002/jpn3.70375
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00