DIABETIC RETINOPATHY DETECTION USING MACHINE LEARNING

Diabetic retinopathy (DR) is a prominent cause of vision loss and disability in people around the world. This progressive condition, due to long diabetes at requires early detection and intervention to protect viewing. Traditional diagnostic techniques rely primarily on the retina and manual. To address these issues, this project aims to create an intelligent system for recognizing diabetic retinopathy, excluding direct image processing, using the methodology of dataset control for machine learning. The system uses structured tabular patient information including retinal studies results, including demographic data, clinical indicators (such as blood glucose levels), duration of diabetes, and lifestyle factors. The advanced -preliminal processing method is used to process these data records, such as normalization, coding of categorical variables, missing data, and functional scaling. Processed data is used to train and evaluate various algorithms of machine learning, including Support Vector Machines (SVM), Random Forest, Decision Trees, K-Nearest-Neighbors (KNN), and Logistics Regression.