EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A decade of artificial intelligence research in ophthalmology: Global trends and transferable insights for medical AI

Ein Jahrzehnt Forschung zu künstlicher Intelligenz in der Ophthalmologie: Globale Trends und übertragbare Erkenntnisse für medizinische KI

Zeyue Fan, Yiming Qin, Luxiao Chen, Jixuan Yuan, Zhuxin Xiong, Xiaodong Chen, Shixin Lai, Yih Chung Tham, Bin Sheng, Xiaofei Wang, Andrzej Grzybowski, Aaron Y Lee und 5 weitere

PLOS Digital Health · 25.08.2026 · 5 (8) · e0001347

DOI: 10.1371/journal.pdig.0001347 ↗

Auf einen Blick

Eine bibliometrische Analyse von 12.911 Artikeln zeigt: Die ophthalmologische KI-Forschung nahm von 2015 bis 2025 stark zu und verlagerte sich von bildbasierter Deep Learning-Forschung zu breiterer klinischer Evaluation.

Fragestellung

Welche globalen Trends zeigt die KI-Forschung in der Ophthalmologie von 2015 bis 2025, und welche übertragbaren Einsichten ergeben sich für medizinische KI?

Methode

Systematische bibliometrische Analyse originaler KI-Artikel in Ophthalmologie aus Web of Science Core Collection, Scopus und PubMed von 2015 bis 2025; LLM-gestützte Klassifikation und Vergleich mit Human Grading.

Ergebnisse

12.911 Artikel. Jährliche Publikationen stiegen mit 39,7 % CAGR von 108 in 2015 auf 3.061 in 2025. Entwicklungstudien dominierten (88,3 %); Evaluationstudien traten ab 2019 auf.

Schlussfolgerung der Autor:innen

Die ophthalmologische KI-Forschung expandierte rasch und entwickelte sich von eng gefasster, bildbasierter Deep Learning-Forschung zu breiterer Arbeit mit Evaluation, Foundation Models, multimodalen Daten und mehr Krankheitsbildern.

Kernaussagen

  • Publikationen: 108 in 2015, 3.061 in 2025
  • Entwicklungsstudien dominierten mit 88,3 %
  • Foundation-Modelle nahmen 2024–2025 deutlich zu

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 25.08.2026. Verfasst von Zeyue Fan und 16 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Visual Science and Translational Eye Research Institute (BERI), Beijing Tsinghua Changgung Hospital Eye Center, Tsinghua Medicine, Tsinghua U…. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Research to Prevent Blindness Career Development Award, Gills AI Innovation Center, Johns Hopkins University.

Auf einen BlickAbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Autor:innen und Institutionen

  • Beijing Visual Science and Translational Eye Research Institute (BERI), Beijing Tsinghua Changgung Hospital Eye Center, Tsinghua Medicine, Tsinghua University, Beijing, China.
  • Beijing Key Laboratory of Intelligent Diagnostic Technology and Devices for Major Blinding Eye Diseases, Tsinghua Medicine, Tsinghua University, Beijing, China.
  • Key Laboratory for Biomechanics and Mechanobiology of Ministry of Education, Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beiji…
  • Singapore Eye Research Institute, Singapore National Eye Center, Singapore, Singapore.
  • Centre for Innovation and Precision Eye Health, Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
  • Ophthalmology and Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore, Singapore.

ORCID-Profile: Tien Yin Wong, Ya Xing Wang

Förderung

  • National Natural Science Foundation of China
  • Research to Prevent Blindness Career Development Award, Gills AI Innovation Center, Johns Hopkins University

Zitieren

APA

Fan, Z., Qin, Y., Chen, L., Yuan, J., Xiong, Z., Chen, X., Lai, S., Tham, Y. C., Sheng, B., Wang, X., Grzybowski, A., Lee, A. Y., Lee, C. S., Cheung, C. Y., Liu, T. Y. A., Wong, T. Y., & Wang, Y. X. (2026). A decade of artificial intelligence research in ophthalmology: Global trends and transferable insights for medical AI. PLOS Digital Health, 5(8), e0001347. https://doi.org/10.1371/journal.pdig.0001347

Vancouver

Fan Z, Qin Y, Chen L, Yuan J, Xiong Z, Chen X, et al. A decade of artificial intelligence research in ophthalmology: Global trends and transferable insights for medical AI. PLOS Digital Health. 2026;5(8):e0001347. doi:10.1371/journal.pdig.0001347

BibTeX
@article{Fan2026,
  author = {Fan, Zeyue and Qin, Yiming and Chen, Luxiao and Yuan, Jixuan and Xiong, Zhuxin and Chen, Xiaodong and Lai, Shixin and Tham, Yih Chung and Sheng, Bin and Wang, Xiaofei and Grzybowski, Andrzej and Lee, Aaron Y and Lee, Cecilia S and Cheung, Carol Y and Liu, T Y Alvin and Wong, Tien Yin and Wang, Ya Xing},
  title = {A decade of artificial intelligence research in ophthalmology: Global trends and transferable insights for medical AI},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {8},
  pages = {e0001347},
  doi = {10.1371/journal.pdig.0001347}
}
Kostenlos starten →