PREDICTIVE STUDY AND CLASSIFICATION OF DIABETES USING MACHINE LEARNING TECHNIQUES

Abstract

Diabetes mellitus (DM) is a common but deadly disease in humans. It is caused by having excessive sugar levels existing for a long time. It causes around 30 to 40 lakh deaths worldwide each year. Technology plays a consequential role in the medical industry to assess diabetes prediction research studies. In this research, we trained four machine learning techniques so as to make predictions on whether a person is diabetic or not, on the basis of some health details of the individual. The Pima Indian Diabetes dataset is used, which consists of 768 samples, and each sample contains 8 attributes and one target class attribute. Data pre-processing techniques are used to get the raw dataset cleaned, to remove the inconsistencies, anomalies and missing values present in the data which are not suitable for the machine learning models. K-Nearest Neighbour (KNN), Logistic Regression (LR), Support Vector Machine (SVM) and Artificial Neural Networks (ANN) are the techniques used for prediction of diabetes in this research. As a result, K-Nearest Neighbour which is a classification machine learning technique, performed the best, with an accuracy of 76.17% , while support vector machine, logistic regression and Artificial Neural Network gave 75.8%, 73.04% and 73.82% respectively.