Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.
World J Methodol. Sep 20, 2026; 16(3): 115265
Published online Sep 20, 2026. doi: 10.5662/wjm.115265
Published online Sep 20, 2026. doi: 10.5662/wjm.115265
Artificial intelligence in ophthalmology: From diagnostic accuracy to clinical application
Marco Zeppieri, Department of Ophthalmology, University Hospital of Udine, Udine 33100, Italy
Marco Zeppieri, Inferrera Leandro, Rosa Giglio, Daniele Tognetto, Department of Medicine, Surgery and Health Sciences, University of Trieste, Trieste 34129, Italy
Matteo Capobianco, Eye Clinic, Azienda Ospedaliero Universitaria Policlinico “G. Rodolico - San Marco” Catania, Catania 95121, Italy
Matteo Capobianco, Alessandro Avitabile, Faculty of Medicine, University of Catania, Catania 95123, Italy
Federico Visalli, Department of Ophthalmology, University of Catania, Catania 95123, Italy
Marieme Khouyyi, Department of Biomedical and Dental Sciences and Morphofunctional Imaging, University of Messina, Messina 98121, Italy
Mutali Musa, Department of Optometry, University of Benin, Benin 300283, Nigeria
Mutali Musa, Department of Ophthalmology, Africa Eye Laser Center Ltd., Benin 300211, Nigeria
Caterina Gagliano, Francesco Cappellani, Department of Medicine and Surgery, Kore University of Enna, Enna 94100, Italy
Caterina Gagliano, Fabiana D’Esposito, Francesco Cappellani, Mediterranean Foundation“G.B. Morgagni”, Catania 95125, Italy
Fabiana D’Esposito, Imperial College Ophthalmic Research Group Unit, Imperial College, London NW1 5QH, United Kingdom
Author contributions: Zeppieri M, Capobianco M, Visalli F, Khouyyi M, Musa M, Avitabile A, Leandro I, Giglio R, Tognetto D, Gagliano C, D’Esposito F, and Cappellani F wrote the outline, assisted in the writing and editing of the draft and final paper, making critical revisions of the manuscript and viewing all versions of the manuscript; Zeppieri M, Capobianco M, Visalli F, Khouyyi M, Musa M, Avitabile A, and Cappellani F did the research and writing of the manuscript; Zeppieri M, Capobianco M, Visalli F, Khouyyi M, Musa M, Gagliano C, D’Esposito F, and Cappellani F contributed to the scientific editing; Zeppieri M, Gagliano C, D’Esposito F, Cappellani F were responsible for the conception and design of the study. All authors provided the final approval of the article.
AI contribution statement: ChatGPT (OpenAI, GPT-5.3) and Grammarly were used to assist with summarizing existing literature, addressing issues in the rebuttal, and enhancing the flow and English language quality. No AI-generated images were used.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Corresponding author: Caterina Gagliano, MD, PhD, Department of Medicine and Surgery, Kore University of Enna, Viale delle Olimpiadi 1, Enna 94100, Italy.
Received: October 15, 2025
Revised: November 12, 2025
Accepted: January 21, 2026
Published online: September 20, 2026
Processing time: 270 Days and 22.5 Hours
Revised: November 12, 2025
Accepted: January 21, 2026
Published online: September 20, 2026
Processing time: 270 Days and 22.5 Hours
Core Tip
Core Tip: Artificial intelligence offers potential for enhancing ocular diagnoses; nevertheless, greater algorithmic accuracy at the image level rarely translates to improved patient outcomes. Obstacles, including data bias, domain shift, and label noise, coupled with a scarcity of prospective research and a lack of cost-effectiveness or equity evaluations, impede translation. Enhancing external validation, establishing predetermined thresholds, and incorporating human-factors engineering into healthcare workflows are imperative. Bridging this gap could convert algorithmic accuracy into significant diagnostic precision for glaucoma, diabetic retinopathy, and macular conditions.