Providing diagnosis on diabetes using cloud computing environment to the people living in rural areas of India

Diabetes is one of the major diseases prevalent today affecting around 400 million people worldwide. Approximately one in ten adult people worldwide have diabetes. Unfortunately, about half of them live in rural areas and are not aware about the severity of the disease. Treatment of diabetes is feasible, but also challenging and expensive. Our contribution is to develop a reference model in assisting rural people suffering from diabetes. It helps the rural people of India in characterizing the victims of diabetes 2 at the earlier stages. This model improves the communication and interaction between patients and doctors. The target of analysis made in the present research is to list the risks factors and correlation that exist among those risk factors. In this work, logistic regression, support vector machine, random forest, decision tree, Naive Bayes, K nearest neighbor classifiers are used for prediction, and their accuracy is compared to choose the better machine learning model. SVM provides higher accuracy (96.0) among the choosen algorithms.