Evaluation of the Mayo endoscopic score in ulcerative colitis using a multimodal large language model: a human-blinded accuracy study
ChatGPT-4o shows a mild potential in evaluating MES in endoscopic frames, but further refinements are mandatory.
Authors
- Raffaele Pellegrino (ORCID: https://orcid.org/0000-0001-5074-230X)
- Antonietta Gerarda Gravina (ORCID: https://orcid.org/0000-0001-8049-0115)
- S Pellegrino
- Ilaria De Costanzo
- Giuseppe Imperio (ORCID: https://orcid.org/0000-0002-4182-2858)
- Fabio Landa
- Michele Izzo
- Alessandro Federico
Institutions
- University of Campania "Luigi Vanvitelli" (IT)
Publication Details
- Journal
- Intestinal Research
- Published
- 2026-02-12
- DOI
- https://doi.org/10.5217/ir.2025.00138
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00