The Use of Artificial Intelligence in the Diagnosis of Eye Diseases - a Review

Abstract

Introduction:

This review article consolidates current knowledge on the application of artificial intelligence (AI) in the diagnostic and therapeutic processes of ocular diseases, focusing on glaucoma, diabetic retinopathy (DR), cataract, and age-related macular degeneration (AMD). It also discusses the limitations of AI algorithms and highlights potential areas for future clinical research.

Materials and methods:
A literature review was conducted using the PubMed and Google Scholar databases with the following keywords: "glaucoma," "cataract," "diabetic retinopathy," "age-related macular degeneration," "artificial intelligence," "machine learning," and "deep learning."

Summary:
Diseases such as glaucoma, cataract, DR, and AMD significantly impact patients' quality of life. Factors like the growing number of patients, limited access to specialists, and time-consuming diagnostics have increased interest in AI-based tools. In recent years, machine learning (ML) and deep learning (DL) have contributed to faster, more objective diagnostics. In ophthalmology, AI enables automatic analysis of fundus images, prediction of disease progression, and remote monitoring. These solutions support early detection, individualized treatment plans, and improved access to care. AI is particularly promising in screening programs for DR, analyzing optic nerve structures in glaucoma, and enhancing precision in cataract surgery and AMD progression monitoring.

Conclusions:
AI applications in ophthalmology have the potential to improve early diagnosis, optimize treatment, and ease the burden on clinicians. Despite this progress, challenges remain—such as the opaque decision-making of AI systems, ethical issues, and integration into routine clinical workflows. Addressing these barriers will be key to realizing the full benefits of AI and guiding future research in this rapidly evolving field.