Detection of Diabetic Retinopathy Using Machine Learning: A Comprehensive Review

Diabetic retinopathy (DR) is a leading cause of vision loss and blindness, particularly among diabetic individuals. Early detection is vital to prevent severe complications, yet manual screening remains labor-intensive and error-prone. This study reviews advancements in DR detection through machine learning (ML), focusing on support vector machines (SVM), convolutional neural networks (CNN), and deep learning frame-works. Examining research from the past decade, we explore methodologies, datasets, and feature extraction techniques for automated DR identification. A comparative evaluation highlights model strengths, limitations, and potential enhancements. Our objective is to advance ML-based diagnostic tools for clinical implementation, improving efficiency and accuracy in DR screening. Ultimately, this can enhance patient outcomes and reduce blindness risks, contributing to more effective diabetic retinopathy management.