MACHINE LEARNING APPLIED TO THE DETECTION OF DIABETIC RETINOPATHY

ABSTRACT

Diabetic retinopathy is one of the most common causes of vision loss. The process involved in detecting diabetic retinopathy using clinical methods can be very tedious and may require highly technical analysis and it is time consuming. Although diabetic retinopathy is preventable and curable at early stage, the majority of diabetic patients are diagnosed with diabetic retinopathy very late. Therefore, it is very important to detect diabetic retinopathy at an early stage to seek treatments and prevention measures. Machine Learning methods have been extensively used in the detection of diabetic retinopathy, which has helped in reducing the high rate of vision loss. The Convolutional Neural Network (CNN) and Random Forest are used to build the diabetic retinopathy detection model. The diabetic retinopathy dataset is applied to CNN and Random Forest algorithms. The performance accuracy between the training and test set are calculated, CNN has an accuracy of 93%, and Random Forest has an accuracy of 68.75%. A system was also built in which the model developed using CNN (since it outperforms Random Forest) was integrated.