Classification of Diabetes Mellitus Using Machine Learning Techniques

Amit kumar Dewangan, Pragati Agrawal

Diabetes-Mellitus refers to the metabolic disorder that happens from misfunction in insulin secretion and action. It is characterized by hyperglycemia. The persistent hyperglycemia of diabetes leads to damage, malfunction and failure of different organs such as kidneys, eyes, nerves, blood vessels and heart. In the past decades several techniques have been implemented for the detection of diabetes. The diagnosis of diabetes is very important now a days using various types of techniques.  Here, there are various techniques, their classification and implementation using various types of software tools and techniques. The diagnosis of diabetes can be done using Artificial Neural Network, K-fold cross validation and classification, Vector support machine, K-nearest neighbor method, Data Mining Algorithm, etc. Using these techniques, we attempt to make an ensemble model by combining two techniques: Bayesian classification and Multilayer Perceptron for the accuracy, sensitivity and specificity measures of diagnosis of diabetes-mellitus.