A Diabetes Mellitus Detection Using Fusion of IoMT, Generative AI, and eXplainable AI: Diabetes Classification Using IoMT

Abstract

Diabetes Mellitus (DM) is a metabolic disorder when the sugar level in the blood is elevated consistently. The presence of Diabetes Mellitus is one of the global health challenges, several research works focusing on the early detection and management of innovative machine learning technologies were developed in recent years. In this book chapter, we introduce a novel approach to classify diabetes mellitus by leveraging the Internet of Medical Things (IoMT) and generative AI models. IoT devices continuously monitor critical health data and transmit them to a central machine learning model for analysis and preprocessing is done. The preprocessed data act as the input for the machine learning models to predict diabetes. The imbalanced dataset is converted into a balanced one using two generative AI models called VAE and GAN. We used five ML classification models kNN, SVM, DT, LR and RF with boosting. Hard voting is performed to determine the final class. Our experiment result shows that the proposed ensemble model produces an accuracy of 81% which outperformed other model's accuracy