Artificial intelligence is rapidly transforming ophthalmology research, with a surge in studies focused on retinal disease diagnosis, imaging, and personalized treatment strategies over the past decade, according to a new bibliometric analysis examining global trends in AI-driven eye care.¹

The study analyzed more than 20 years of scientific literature to map the intellectual and collaborative landscape of artificial intelligence applications in ophthalmology, particularly in retinal disease management. Researchers found that publication activity accelerated dramatically after 2015, fueled by advances in deep learning and medical imaging technologies.

The findings suggest AI is moving beyond experimental algorithms and becoming a central force in modern retinal diagnostics.

Researchers identified deep learning, optical coherence tomography (OCT), and diabetic retinopathy as the most influential and rapidly expanding areas of investigation.

The analysis highlighted strong collaboration networks among leading universities and research institutions, particularly in North America and Europe. Among the most influential contributors were the University of London and the University of California System, both of which emerged as major hubs for AI ophthalmology research.

Co-authorship and citation mapping revealed that much of the field’s development has been driven by concentrated institutional partnerships and regional research clusters. Researchers said these collaborative networks have accelerated innovation but also raised concerns about unequal global participation in AI development.

According to the study, ophthalmology research has evolved significantly from early algorithm-focused experimentation toward more clinically oriented applications.

Emerging themes now include:

• Explainable AI systems
• Telemedicine integration
• Personalized retinal diagnostics
• Multimodal imaging analysis
• AI-assisted therapeutic planning

The rise of explainable AI reflects growing concern among clinicians and regulators about transparency in machine learning systems used in healthcare.The research shows that ophthalmologists are increasingly seeking tools that not only produce accurate predictions but also provide understandable reasoning behind diagnostic decisions.

Despite rapid growth, researchers identified several major obstacles slowing widespread clinical adoption.

Key challenges include:

• Limited real-world implementation studies
• Unclear regulatory pathways
• Data privacy concerns
• Bias in training datasets
• Underrepresentation of low-resource regions

The study emphasized that much of the existing AI research has been conducted using datasets from high-income countries, potentially limiting the effectiveness of algorithms in more diverse global populations. Researchers warned that without broader representation and equitable deployment strategies, AI technologies could widen disparities in access to eye care rather than reduce them.

The authors concluded that future research should focus not only on improving algorithm performance but also on ensuring that AI systems are interpretable, clinically practical, and accessible across diverse healthcare settings.

Reference

1. Zhao R, Gillani S. AI in ophthalmology: a bibliometric analysis of retinal imaging research. Digital Health. 2026. doi:10.1016/j.dhjo.2026.100125.