
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.
Retinal vein occlusion (RVO) is a prevalent potentially blinding retinal vascular disease, with secondary macular edema, retinal ischemia, and ocular neovascular complications posing substantial threats to visual function. Supported by members of the Academy of Asia-Pacific Professors of Ophthalmology (AAPPO), Asia-Pacific Vitreo-retina Society (APVRS) and Academia Retina Internationalis (ARI), a consensus and guideline is provided for a comprehensive update on the etiology, diagnosis and management of RVO. An updated consensus was judged necessary following numerous recent results from epidemiology studies, evolution of advanced imaging technologies and novel pharmacotherapeutics from clinical trials, including an expanding portfolio of anti-vascular endothelial growth factor (anti-VEGF) agents, drug delivery systems, and emerging evidence on relevant artificial intelligence. The formulation of these consensus statements were based on the review and discussion of a systematic search for the latest evidence-based data and voting by an International Panel of Experts (IPE) in the following key areas: I) Diagnostic controversies around classification systems and imaging modalities; II) Treatment controversies regarding anti-VEGF therapy, corticosteroid treatments, laser therapy, and surgical interventions; III) Management paradigm between standardized protocols from clinical trials and individualized approaches and IV) Emerging controversies in novel therapeutics. The primary goal was to furnish ophthalmologists with standardized, yet individualized, management protocols to try to optimize treatment safety and efficacy, ensuring alignment with contemporary clinical practices in the Asia-Pacific region.
Purpose Primary angle-closure glaucoma (PACG) is a leading cause of irreversible blindness in Asia. Although traditionally considered an anatomical ocular disorder, the contribution of systemic metabolic, vascular, and lifestyle factors to PACG development remains unclear. Methods Using data from the China Kadoorie Biobank (CKB), involving 499,102 participants aged 30–79 years at baseline, we explored associations of 117 exposures, including socio-demographics, lifestyle patterns, medical history, and physical measurements, with probable PACG (prob PACG) incidence. Elastic-Net, XGboost, and Cox regression methods were employed. Results Over a median follow-up of 15.7 years, 3266 incident prob PACG cases were ascertained. After correcting for multiple testing, 26 factors were independently associated with prob PACG. Age, female sex, and postmenopausal status showed the strongest positive associations with pro PACG. Notably, several markers of metabolic and vascular ageing—including diabetes, higher random plasma glucose, larger waist circumference, and elevated pulse pressure—were independently associated with higher risk, whereas BMI was inversely associated (all P < 0.01). In addition, daily intake of dairy products and daily preserved vegetables, and peptic ulcer were associated with a higher risk, while higher physical activity and weekly tea consumption were associated with lower risk. No significant associations were found for hypertension, SBP, or DBP with prob PACG. Conclusions Our findings suggest that PACG may be influenced not only by anatomical susceptibility but also by broader metabolic, vascular, and lifestyle factors. The clustering of several strong associations around markers of metabolic and vascular ageing provides new insights into PACG aetiology and may help identify priorities for future studies of risk stratification and prevention.