Predicting Postoperative Outcomes in Full-Thickness Macular Hole Repair Surgery: ChatGPT vs. Clinical Decision
ChatGPT-5 demonstrated apparent accuracy in predicting FTMH surgery outcomes; however, this was largely driven by an optimism bias that overestimated closure and visual recovery. This model still lack clinical judgment. Larger prospective studies are needed before clinical use.
Authors
- Maxim Bez (ORCID: https://orcid.org/0000-0002-9487-9479)
- Michaella Goldstein
- Aya Wattad
- Anat Loewenstein
- Razan Saadi
Institutions
- Tel Aviv University (IL)
- Tel Aviv Sourasky Medical Center (IL)
Publication Details
- Journal
- Retina
- Published
- 2026-01-21
- DOI
- https://doi.org/10.1097/iae.0000000000004779
- Primary Topic
- Retinal and Macular Surgery
- Type
- article
- Field-Weighted Citation Impact
- 0.00