Prediction of Diabetes Mellitus Type-2 Using Machine Learning

Around 400 million people suffer from diabetes around the world. Diabetes prediction is challenging as it involves complex interactions or inter-dependencies between various human organs like eye, kidney, heart, etc. The machine learning (ML) algorithms provide an efficient way of predicting the diabetes. The objective of this work is to build a system using ML techniques for the accurate forecast of diabetes in a patient. The decision tree (DT) algorithms are well suited for this. In this work, we have applied the DT algorithm to forecast type 2 diabetes mellitus (T2DM). Extensive experiments were performed on the Pima Indian Diabetes Dataset (PIDD) obtained from the UCI machine learning repository. Based on the results, we observed that the decision tree was able to forecast accurately when compared to the SVM algorithm on the diabetes data.