AN EFFICIENT DIABETES MELLITUS PREDICTION WITH GRID BASED RANDOM FOREST CLASSIFIER

Human body turns the food consumed into energy, but when insulin doesn't act in its way to convert the blood glucose into energy, then the glucose remains in the bloodstream and causes a life-threatening health issue called Diabetes Mellitus or Diabetes. According to the growing morbidity in recent years, in 2040, the world's diabetic patients will reach 642 million, which means that one of the ten adults in the future is suffering from diabetes. There is no doubt that this alarming figure needs great attention. With the rapid development of machine learning, machine learning has been applied to many aspects of medical health. So, for efficiently and effectively diagnosing the Diabetes Mellitus, a method is proposed using the ML Grid Search algorithm. In this method, a database called Pima Indian Diabetic Dataset is used. This system has two phases: the training phase and the test phase. In training phase, preprocessing, feature selection and instance evaluation is done. In test phase, preprocessing, instance evaluation and disease prediction is done. For feature selection, the random forest feature selection is used and for classification, support vector regression, logistic regression and grid based random forest classifier is used. The proposed method of predicting the diabetes, the accuracy is almost 95.7% which is higher when compared to previous methods.