Predict the Severity of Diabetes Cases, Using K-Means and Decision Tree Approach

Abstract

In recent years, diabetes has emerged as one of the most prevalent infections, and its prevalence is rapidly increasing globally. Type 2 diabetes is common throughout the world. For the management and prophylaxis of diabetes, early detection is crucial. Machine Learning (ML) approaches are rapidly gaining importance in the field of diagnostic purposes due to their ability to classify data. In this article, a mixed recommended technique is presented to assist in the diagnosis of Type 2 diabetes. The suggested model-based minimization uses K-means, and the proposed classifier is a J48 decision tree. To get the experiment's results, we used the Pima Indians Diabetic Database from the UCI ML Repository. The outcome demonstrates that, in comparison to other earlier research that is described in the literature, the proposed model has achieved more reliability. These findings demonstrate that the proposed methodology might be useful for diagnosing Type 2 diabetes.