Diabetic Type II Prediction Using Fused Machine Learning

In medicine, early illness prediction is crucial for disease prevention. Diabetes is one of the world's worst illnesses. Due to the prevalence of sugar and fat in contemporary society, diabetes risk has grown. It is essential to comprehend the symptoms of the disease in order to forecast it. The use of machine learning (ML) algorithms for disease diagnosis is increasing. This article offers a prediction model for type II diabetes using fused machine learning (FML). Three kinds of models comprise the conceptual framework: Support Vector Machine (SVM) models, decision tree models (DT), and Gaussian naive bayes models (GNB). The feature vector has extracted using DT and GNB algorithm. The feature vector has classified by using SVM algorithm. These algorithms analyze the data to evaluate the positivity or negativity of a diabetes diagnosis.