Optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms

Abstract

In recent years, diabetes has become a global public health problem, and it is reported that the migrant Indians have more prevalence rate of Type-II diabetes. Also, the type-II diabetes in Indians are increased to a large extent due to modern lifestyle, food habits etc. In this work, an ElectroGastroGram (EGG) based non-invasive assessment for early prediction of type-II diabetes is proposed. Furthermore, the EGG signals are acquired from normal individuals and people with an age group between 50 and 65 who are suffering from Type-II diabetes using three electrode EGG acquisition devices. Also, the Explainable Artificial Intelligence (XAI) especially SHapley Additive exPlanations (SHAP) and Meta-Heuristics based feature selection methods are utilized to determine the prominent EGG signal features. A framework is devised using Meta-Heuristic based Hybrid Extreme Gradient (MH-XGB) Boost Classifier for an efficient classification of normal EGG signals and diabetic EGG signals. The proposed MH-XGB classifier is compared with the benchmark models namely Random Forest (RF) classifier and conventional Extreme Gradient Boosting (XGBoost) classifier by using performance metrics. Results demonstrate that the proposed MH-XGB classifier exhibits accuracy, sensitivity, specificity of 95.8%, 100%, and 92.3% respectively which is superior to other benchmark models. Additionally, it is demonstrated that the AUC, F1 Score and False Positive Rate (FPR) of the proposed MH-XGB classifier is 0.9545, 0.96 and 0.077 respectively. The proposed method is highly useful for early prediction of real-time societal disease (diabetes-Type-II) in an effective manner.