Barriers to artificial intelligence applications in ophthalmology: beyond diagnostic accuracy toward patient outcomes, workflow integration, ethics, and trust
Asia-Pacific Journal of Ophthalmology · 2026-09 · 15 (5) · 100382
DOI: 10.1016/j.apjo.2026.100382 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Asia-Pacific Journal of Ophthalmology, 2026-09. Verfasst von Kai Jin und 1 weiteren Autor:innen. Beteiligte Einrichtung: Eye Center of the Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China; Zhejiang Provincial Key Laboratory of Ophthal…. Hauptthemen laut MEDLINE: Artificial Intelligence, Ophthalmology, Workflow, Eye Diseases. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Künstliche Intelligenz in der Pflege, Ethik in der Pflege
Abstract (Originalsprache)
Artificial intelligence (AI) has become a major area of ophthalmic innovation, with a rapidly expanding literature, yet routine clinical adoption remains limited. Diagnostic accuracy alone is an insufficient marker of clinical value because even technically strong systems may fail to improve referral, follow-up, treatment, clinician workload, or health-system value. This focused narrative review examines the barriers that separate ophthalmic AI performance from real-world implementation. We reviewed ophthalmic AI literature indexed in PubMed, Web of Science, and Google Scholar, with emphasis on studies published from January 2018 to September 2026 and on prospective, randomized, real-world, economic, governance, and patient-centred evidence. We organize translation across four linked domains: algorithmic validity, clinical utility, workflow integration, and health-system value, with ethical governance and trust as cross-cutting requirements. Diabetic retinopathy screening now provides a concrete translational example spanning large-scale retrospective validation, prospective deployment, workflow implementation, and economic evaluation. We also consider how foundation models and large language models alter evidence requirements because outputs can depend on prompts, retrieved context, tools, and model versions. For glaucoma, retinal disease management, retinopathy of prematurity, anterior segment applications, and automated reporting, evidence remains less mature. The central challenge for ophthalmic AI is therefore no longer model development alone, but disciplined clinical translation, including prospective evaluation, operational workflow measurement, equity assessment, lifecycle monitoring, transparent governance, and trustworthy implementation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Eye Center of the Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China; Zhejiang Provincial Key Laboratory of Ophthalmology; Zhejiang Provincial Clinical Research Center for Eye Diseases;…
- Institute for Research in Ophthalmology, Foundation for Ophthalmology Development, Poznan, Poland; University of Warmia and Mazury, Olsztyn, Poland. Electronic address: ae.grzybowski@gmail.com.
Zitieren
APA
Jin, K., & Grzybowski, A. (2026). Barriers to artificial intelligence applications in ophthalmology: beyond diagnostic accuracy toward patient outcomes, workflow integration, ethics, and trust. Asia-Pacific Journal of Ophthalmology, 15(5), 100382. https://doi.org/10.1016/j.apjo.2026.100382
Vancouver
Jin K, Grzybowski A. Barriers to artificial intelligence applications in ophthalmology: beyond diagnostic accuracy toward patient outcomes, workflow integration, ethics, and trust. Asia-Pacific Journal of Ophthalmology. 2026;15(5):100382. doi:10.1016/j.apjo.2026.100382
BibTeX
@article{Jin2026,
author = {Jin, Kai and Grzybowski, Andrzej},
title = {Barriers to artificial intelligence applications in ophthalmology: beyond diagnostic accuracy toward patient outcomes, workflow integration, ethics, and trust},
journal = {Asia-Pacific Journal of Ophthalmology},
year = {2026},
volume = {15},
number = {5},
pages = {100382},
doi = {10.1016/j.apjo.2026.100382}
}
EUVIMED