Implementation of Diabetic Retinopathy Prediction System using Data Mining

Diabetic retinopathy (DR) is the most common cause of newly diagnosed blindness every year. Annual eye checking for diabetic patients are suggested in order to find and treat DR in a timely manner, since blindness from this condition is preventable with early identification. DR detection is solely based on existing patient records. Now a day's medical data growing tremendously and we need to process that data for detection. But it is time consuming hence data mining techniques helps to get rid from this issue. We use neural network (NN) and naïve bayes for classification. According to comparison results NN gives better accuracy than naïve bayes and time and memory required for NN is less as compared to naïve bayes.