Key points are not available for this paper at this time.
Artificial intelligence (AI) has emerged as a transformative force in modern ophthalmology, enabling rapid advances in disease detection, clinical decision support, workflow optimization, and tele-ophthalmology. Ophthalmology is particularly suited for AI integration because of its reliance on imaging modalities such as fundus photography, optical coherence tomography (OCT), and visual field testing. Over the past decade, deep learning algorithms have demonstrated high diagnostic accuracy in identifying retinal diseases including diabetic retinopathy, age-related macular degeneration, and glaucoma. The approval of autonomous AI diagnostic systems for diabetic retinopathy screening marked a significant milestone in clinical adoption. Beyond diagnostics, AI is increasingly influencing surgical planning, predictive analytics, education, and patient engagement. Despite these promising advances, significant challenges remain regarding algorithm generalizability, ethical considerations, regulatory approval, data privacy, and integration into routine clinical practice. This perspective article reviews current innovations in AI applications within ophthalmology and discusses their clinical impact while outlining future directions for research and implementation. We argue that the next phase of AI in ophthalmology will involve multimodal learning systems, integration with large language models, and deployment in global eye-care networks to address disparities in access to care. A collaborative approach involving clinicians, data scientists, regulators, and industry will be essential to ensure safe, ethical, and effective adoption of AI technologies in ophthalmic practice.
Gurnani et al. (Thu,) studied this question.