ArticlePLOS digital health2026
A decade of artificial intelligence research in ophthalmology: Global trends and transferable insights for medical AI.
Article in PLOS digital health, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
17 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
To characterize global trends in ophthalmic AI research from 2015-2025 and drive transferable insights into the broader evolution of AI in medicine, we conducted a systematic bibliometric analysis of original AI articles in ophthalmology indexed in the Web of Science Core Collection, Scopus, and Pubmed from 2015 to 2025. Publications were screened and categorized using an LLM-assisted pipeline with predefined labels, and agreement between LLM-assisted classifications and human grading was evaluated. We analyzed temporal trends and emergence patterns across study design, model architecture, disease focus, and data modalities. Among 12,911 included articles, annual publications increased at a compound annual growth rate of 39.7%, from 108 in 2015-3061 in 2025. Four key shifts were identified. Study design: Development studies (88.3%) dominated through the period, whereas evaluation studies (7.4%) began to emerge in 2019. Model architecture: Classical deep learning (71.8%) became the most prevailing approach from 2017, while foundation model studies (0.6%) increased sharply in 2024-2025. Disease focus: Diabetic retinopathy (32.9%), glaucoma (17.5%), and age-related macular degeneration (12.6%) remained the leading disease areas, while corneal diseases (7.0%), cataract (4.3%) and myopia (3.4%) emerged after 2019-2020 and grew rapidly. Data modalities: Among image-based modalities (84.1%), color fundus photography and retinal optical coherence tomography remained dominant but plateaued after 2019, whereas text-based modalities (5.5%) continued to rise after 2022. Over the past decade, ophthalmic AI research expanded rapidly and evolved from narrow image-based deep learning toward broader work spanning evaluation studies, foundation models, multimodal data integration, and a wider spectrum of eye diseases. These trajectories may extend beyond ophthalmology, offering broader insights into how medical AI matures toward clinical evaluation and translation.
Identifiers
What Socratic holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.