Prediction of Diabetes Using Machine Learning Classifiers

Diabetes is the most prevalent chronic disease and a number of people are suffering from it all over the world. Diabetes could be due to hereditary reasons, obesity, etc. Diabetes can cause other complications like heart disease, so prediction and prevention of diabetes is of utmost importance. In this paper, five machine learning algorithms that are Logistic Regression, Decision Tree, Random Forest, Support Vector Machine and K-Nearest Neighbor have been used for the prediction of diabetes. It was found that Logistic Regression performed the best amongst the five classifiers and obtained highest accuracy of 0.7359, precision of 0.7312, recall of 0.7359 and f1-score of 0.7329.