Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Retraction Note: Prediction of malnutrition in kids by integrating ResNet-50-based deep learning technique using facial images.

Scientific reports·2026
Same author

Glycemic trajectory after face-to-face diabetes self-management education: a dose-response meta-analysis.

Diabetes research and clinical practice·2026
Same author

Self-defending 6G networks through AI-driven adaptive decoy generation at the edge.

Scientific reports·2026
Same author

Deep-learning based adaptive fusion of CC and MLO views for improved mammographic cancer diagnosis.

MethodsX·2026
Same author

Effective deep convolutional neural network with attention mechanism for Alzheimer disease classification.

Frontiers in radiology·2026
Same author

Iterative multiblock framework for high frequency EEG based neurological disorder detection.

Scientific reports·2026

Related Experiment Video

Updated: May 22, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.2K

Optimized hybrid machine learning framework for early diabetes prediction using electrogastrograms.

Paramasivam Alagumariappan1, Malathy Sathyamoorthy2, Rajesh Kumar Dhanaraj3

  • 1Department of Biomedical Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, India.

Scientific Reports
|March 15, 2025
PubMed
Summary

A new non-invasive method using ElectroGastroGram (EGG) signals and Explainable Artificial Intelligence (XAI) accurately predicts Type-II diabetes. This approach offers a promising tool for early disease detection in at-risk populations.

Keywords:
Artificial intelligenceDiagnosisDigestive healthElectrogastrogramsExplainable artificial intelligenceType II diabetes

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

933

Related Experiment Videos

Last Updated: May 22, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

933

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence in Healthcare
  • Diabetes Research

Background:

  • Type-II diabetes is a growing global health concern, particularly prevalent among migrant Indians due to lifestyle changes.
  • Early prediction of Type-II diabetes is crucial for effective management and prevention of complications.
  • Existing diagnostic methods may be invasive or lack early predictive capabilities.

Purpose of the Study:

  • To propose a novel, non-invasive method for the early prediction of Type-II diabetes using ElectroGastroGram (EGG) signals.
  • To leverage Explainable Artificial Intelligence (XAI) and meta-heuristics for accurate feature selection from EGG signals.
  • To develop and validate a robust classification framework for distinguishing between normal and diabetic EGG signals.

Main Methods:

  • Acquisition of EGG signals from individuals aged 50-65, including healthy controls and Type-II diabetes patients.
  • Application of SHapley Additive exPlanations (SHAP) and meta-heuristics for identifying significant EGG signal features.
  • Development of a Meta-Heuristic based Hybrid Extreme Gradient (MH-XGB) Boost Classifier for signal classification.

Main Results:

  • The proposed MH-XGB classifier achieved high performance metrics: 95.8% accuracy, 100% sensitivity, and 92.3% specificity.
  • The classifier demonstrated superior performance compared to benchmark models like Random Forest (RF) and conventional Extreme Gradient Boosting (XGBoost).
  • Excellent Area Under the Curve (AUC) of 0.9545, F1 Score of 0.96, and a low False Positive Rate (FPR) of 0.077 were recorded.

Conclusions:

  • The EGG-based non-invasive assessment combined with XAI and MH-XGB classification is highly effective for early Type-II diabetes prediction.
  • This method offers a valuable tool for real-time, non-invasive disease detection, addressing a significant public health challenge.
  • The findings support the potential of advanced AI techniques in revolutionizing diabetes diagnostics and management.