Diabetes Prediction using Machine Learning Techniques

Machine learning is one of the most inspired zones of experimentation that is flatter progressively accepted in a health institution. This research work distributes with planned machine learning techniques strategy for speculating diabetes patients on the basis of their medical records. Nowadays it is a very ordinary disease in all age categories. It may also lead to different type of diseases like heart and kidney disease, nerve damage, blood vessel damage and blindness. Here we consider Pima Indian Diabetes Dataset (PIDD), which collects the information about the patient's test result that may be negative or positive. The objective is to predict whether a person is diabetic or not, using different classifiers such as Support Vector Machine(SVM), Naive Bayes(NB), Decision Tree(DT), K-Nearest Neighbor(KNN), Artificial Neural Network(ANN) and Random Forest(RF). Basically, the work addresses different features associated with diabetes risk in addition to incorporating methods that advance the practice of epidemiology. Moreover, this exploration is improved to the correctness in diabetes prediction using medical data with various machine learning algorithms and methods.