This study provided an extensive overview of the use of artificial intelligence (AI) in the categorization of different eye conditions. The paper discussed several approaches and models, such as Support Vector Machines (SVMs) and Convolutional Neural Networks (CNNs), that are used to analyze medical pictures, such as optical coherence tomography (OCT) images and fundus photos. The application of AI to identify common eye conditions such as cataracts, glaucoma, age-related macular degeneration, and diabetic retinopathy is covered in the study. This review also contrasted fundus photos and OCT images for disease detection effectiveness. Because fundus photography is so accessible and user-friendly, it is frequently employed to get 2D photographs of the retina. It cannot, however, provide fine-grained cross-sectional images of the retinal layers. However, OCT imaging provides high resolution, cross-sectional pictures that make it possible to comprehend retinal disease and structure in greater depth. This study summarized the findings of around twenty-five research publications and offered a thorough picture of the state of artificial intelligence applications in ophthalmology today. It assessed several AI models’ performance criteria, including sensitivity, specificity, accuracy, F1-score, precision, recall, and kappa values. The study highlighted the need for more research and development to improve the effectiveness and dependability of AI-based diagnostic tools and also indicated obstacles and future prospects in the area. Overall, the discipline of ophthalmology stands to gain much from the integration of AI with fundus and OCT imaging, not to mention improved patient outcomes.