Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190672,
        author = {Hanna Gafoor and IMA T S and MOHAMMED AFNAN K A and THWAYYIBA P A},
        title = {AI-Based Eye Disease Detection Systems: A Systematic Survey of Vision-Driven and Deep Learning Approaches},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {4928-4931},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190672},
        abstract = {Eye diseases such as diabetic retinopathy, glaucoma, cataract, and age-related macular degeneration are among the leading causes of vision impairment and irreversible blindness worldwide. Early diagnosis and timely intervention play a crucial role in preventing permanent vision loss. However, traditional screening methods rely heavily on manual examination by ophthalmologists, making them time-consuming, subjective, and inaccessible in resource-constrained regions.
This survey presents a comprehensive review of Artificial Intelligence (AI) and Deep Learning–based approaches for automated eye disease detection using retinal fundus images and ophthalmic datasets. The study systematically analyzes vision-based convolutional neural network models, transfer learning techniques, ensemble learning frameworks, and AI-assisted clinical decision support systems reported in recent literature.
Research articles published between 2015 and 2025 were collected from IEEE Xplore, SpringerLink, ScienceDirect, and Google Scholar. The survey findings indicate that CNN-based architectures and ensemble fusion strategies significantly improve diagnostic accuracy and robustness. Nevertheless, challenges such as limited dataset diversity, lack of model explainability, and insufficient real-time clinical deployment remain unresolved.
Future research should emphasize explainable, unified, and clinically deployable AI-driven frameworks to improve early detection and enhance global eye-care accessibility.},
        keywords = {Eye Disease Detection, Artificial Intelligence, Deep Learning, Fundus Images, Transfer Learning, Medical Image Analysis},
        month = {January},
        }