DIABETES AND DIABETIC RETINOPATHY DETECTION

Abstract

Diabetes and diabetic retinopathy are major health burden worldwide in the 21st century. The information which is gathered by data analysis of hospitals is utilized by applying different blends of calculations and algorithms for the early-stage prediction of heart related ailments. Machine Learning is one of the slanting innovations utilized in numerous circles far and wide including the medicinal services application for predicting illnesses. In this project, we are focusing on predicting the possibility of diabetes and diabetic retinopathy related problems. We have used six different algorithms like logistic regression, support vector machine, k nearest neighbors, decision tree, random forest and gradient boosting for prediction of heart problems. We compared the accuracy of machine learning algorithms that could be used for predictive analysis of diabetes and predicting the overall risks. Feature extraction is also done during data preprocessing. Dataset are divided into training and testing sets. For diabetes detection, nine different input areas are created for the user based on which detection is done. Diabetic retinopathy (DR) is an eye disease caused by the complication of diabetes and we should detect it early for effective treatment. As diabetes progresses, the vision of a patient may start to deteriorate and lead to diabetic retinopathy. For diabetic retinopathy, convolutional neural network is used. User has to upload the image of retina for detection.