Comparative Analysis of Machine Learning Models for the Detection of Diabetic Retinopathy: A Performance Evaluation

Diabetic retinopathy (DR) is a common complication of diabetes and a leading cause of blindness worldwide. Early detection and timely intervention are critical for preventing vision loss in affected individuals. In this research paper, we explore applying four machine-learning algorithms to detect diabetic retinopathy. Specifically, we investigate the effectiveness of convolutional neural networks (CNNs), transfer learning, and MobileNetV2 in analyzing retinal images to identify signs of diabetic retinopathy. Through comprehensive experimentation and evaluation on the same dataset, we compare the performance of these algorithms in terms of accuracy, sensitivity, specificity, and computational efficiency. Our findings provide insights into the potential of machine learning techniques for assisting clinicians in the early diagnosis and management of diabetic retinopathy, thereby contributing to improved healthcare outcomes for diabetic patients.