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 El...

Full description

Saved in:
Bibliographic Details
Main Authors: Paramasivam Alagumariappan, Malathy Sathyamoorthy, Rajesh Kumar Dhanaraj, K. Kamalanand, C. Emmanuel, Sarah Allabun, Manal Othman, Masresha Getahun, Ben Othman Soufiene
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-93495-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850039611349270528
author Paramasivam Alagumariappan
Malathy Sathyamoorthy
Rajesh Kumar Dhanaraj
K. Kamalanand
C. Emmanuel
Sarah Allabun
Manal Othman
Masresha Getahun
Ben Othman Soufiene
author_facet Paramasivam Alagumariappan
Malathy Sathyamoorthy
Rajesh Kumar Dhanaraj
K. Kamalanand
C. Emmanuel
Sarah Allabun
Manal Othman
Masresha Getahun
Ben Othman Soufiene
author_sort Paramasivam Alagumariappan
collection DOAJ
description 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.
format Article
id doaj-art-f6a747ab3f9c46df98a1d3d13d1d973a
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-f6a747ab3f9c46df98a1d3d13d1d973a2025-08-20T02:56:19ZengNature PortfolioScientific Reports2045-23222025-03-0115111610.1038/s41598-025-93495-3Optimized hybrid machine learning framework for early diabetes prediction using electrogastrogramsParamasivam Alagumariappan0Malathy Sathyamoorthy1Rajesh Kumar Dhanaraj2K. Kamalanand3C. Emmanuel4Sarah Allabun5Manal Othman6Masresha Getahun7Ben Othman Soufiene8Department of Biomedical Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and TechnologyDepartment of Information Technology, KPR Institute of Engineering and TechnologySymbiosis Institute of Computer Studies and Research (SICSR), Symbiosis International (Deemed University)Department of Instrumentation Engineering, MIT Campus, Anna UniversityAcademics and Research, Gleneagles Global Health CityDepartment of Medical Education, College of Medicine, Princess Nourah bint Abdulrahman UniversityDepartment of Medical Education, College of Medicine, Princess Nourah bint Abdulrahman UniversityDepartment of Computer Science and Information Technology, College of Engineering and Technology, Kebri Dehar UniversityPRINCE Laboratory Research, ISITcom, Hammam Sousse, University of SousseAbstract 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.https://doi.org/10.1038/s41598-025-93495-3Artificial intelligenceDigestive healthDiagnosisElectrogastrogramsExplainable artificial intelligenceType II diabetes
spellingShingle Paramasivam Alagumariappan
Malathy Sathyamoorthy
Rajesh Kumar Dhanaraj
K. Kamalanand
C. Emmanuel
Sarah Allabun
Manal Othman
Masresha Getahun
Ben Othman Soufiene
Optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms
Scientific Reports
Artificial intelligence
Digestive health
Diagnosis
Electrogastrograms
Explainable artificial intelligence
Type II diabetes
title Optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms
title_full Optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms
title_fullStr Optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms
title_full_unstemmed Optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms
title_short Optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms
title_sort optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms
topic Artificial intelligence
Digestive health
Diagnosis
Electrogastrograms
Explainable artificial intelligence
Type II diabetes
url https://doi.org/10.1038/s41598-025-93495-3
work_keys_str_mv AT paramasivamalagumariappan optimizedhybridmachinelearningframeworkforearlydiabetespredictionusingelectrogastrograms
AT malathysathyamoorthy optimizedhybridmachinelearningframeworkforearlydiabetespredictionusingelectrogastrograms
AT rajeshkumardhanaraj optimizedhybridmachinelearningframeworkforearlydiabetespredictionusingelectrogastrograms
AT kkamalanand optimizedhybridmachinelearningframeworkforearlydiabetespredictionusingelectrogastrograms
AT cemmanuel optimizedhybridmachinelearningframeworkforearlydiabetespredictionusingelectrogastrograms
AT sarahallabun optimizedhybridmachinelearningframeworkforearlydiabetespredictionusingelectrogastrograms
AT manalothman optimizedhybridmachinelearningframeworkforearlydiabetespredictionusingelectrogastrograms
AT masreshagetahun optimizedhybridmachinelearningframeworkforearlydiabetespredictionusingelectrogastrograms
AT benothmansoufiene optimizedhybridmachinelearningframeworkforearlydiabetespredictionusingelectrogastrograms