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

Imaging Studies for Cardiovascular System IV: CMRI01:21

Imaging Studies for Cardiovascular System IV: CMRI

529
Cardiovascular magnetic resonance imaging, or CMRI, is a non-invasive diagnostic test that employs a magnetic field and radiofrequency waves to create precise images of the heart and arteries. It provides comprehensive information about cardiac anatomy, function, perfusion, and tissue characterization without ionizing radiation.IndicationsCMRI diagnoses various heart conditions, including tissue damage from heart attacks, ischemic heart disease, myocarditis, aortic issues (tears, aneurysms,...
529

You might also read

Related Articles

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

Sort by
Same author

Cardiac autonomic modulation in response to a glucose stimulus.

Medical & biological engineering & computing·2018
Same author

A 3D Hermite-based multiscale local active contour method with elliptical shape constraints for segmentation of cardiac MR and CT volumes.

Medical & biological engineering & computing·2017
See all related articles

Related Experiment Video

Updated: Apr 25, 2026

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

3.4K

Fusion of RR Interval Dynamics and HRV Multidomain Signatures Using Multimodal Neural Models for Metabolic Syndrome

Miguel A Mejia1,2, Oscar J Suarez3, Gilberto Perpiñan1

  • 1Faculty of Electronic Engineering, Popular University of Cesar, Valledupar 200001, Cesar, Colombia.

Medical Sciences (Basel, Switzerland)
|April 24, 2026
PubMed
Summary

This study developed an automated framework using electrocardiogram (ECG) data and heart rate variability (HRV) to identify metabolic syndrome (MetS). The system accurately detects MetS by analyzing cardiac autonomic control during an oral glucose tolerance test (OGTT).

Keywords:
RR interval dynamicsconvolutional neural network (CNN)heart rate variability (HRV)long short-term memory (LSTM)metabolic syndromeoral glucose tolerance test (OGTT)support vector machine (SVM)

More Related Videos

Author Spotlight: Exploring Dynamic Neural Changes Associated with Religious Chanting
05:05

Author Spotlight: Exploring Dynamic Neural Changes Associated with Religious Chanting

Published on: May 31, 2024

1.6K

Related Experiment Videos

Last Updated: Apr 25, 2026

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

3.4K
Author Spotlight: Exploring Dynamic Neural Changes Associated with Religious Chanting
05:05

Author Spotlight: Exploring Dynamic Neural Changes Associated with Religious Chanting

Published on: May 31, 2024

1.6K

Area of Science:

  • Cardiovascular Physiology
  • Autonomic Nervous System
  • Metabolic Health
  • Machine Learning in Medicine

Background:

  • Metabolic syndrome (MetS) is associated with impaired cardiac autonomic control.
  • Electrocardiogram (ECG)-derived markers, especially during physiological stress like an oral glucose tolerance test (OGTT), can reveal these autonomic alterations.
  • Understanding these changes is crucial for early detection and management of cardiometabolic risk.

Purpose of the Study:

  • To develop and validate an automated framework for identifying Metabolic Syndrome (MetS) using ECG and heart rate variability (HRV) features.
  • To assess the capability of machine learning models in distinguishing between individuals with MetS, healthy controls, and endurance athletes based on autonomic profiles.
  • To explore the utility of ECG-derived autonomic markers for non-invasive cardiometabolic risk screening.

Main Methods:

  • Extracted RR intervals and HRV features (time-domain, spectral, nonlinear) from 12-lead ECG recordings during a five-stage OGTT in 40 male participants (MetS, controls, marathon runners).
  • Employed a multilead Pan-Tompkins approach for RR interval detection and fusion-based validation.
  • Trained and evaluated three multimodal classifiers (CNN-MLP, CNN-MLP with SVM head, CNN + LSTM-MLP + SVM) using RR sequences and HRV descriptors.

Main Results:

  • Conventional HRV analysis showed distinct autonomic profiles: MetS subjects had reduced parasympathetic activity, while marathoners exhibited enhanced vagal modulation and complexity.
  • All developed machine learning models demonstrated strong discriminative performance, achieving accuracies between 0.92-0.95, F1-macro scores of 0.92-0.95, and macro-AUC values of 0.96-0.97.
  • The CNN-MLP model yielded the best overall performance, with the CNN + LSTM-MLP + SVM architecture showing superior discrimination for athletes and competitive recall for MetS.

Conclusions:

  • ECG-based autonomic assessment during OGTT is a feasible and non-invasive method for identifying metabolic syndrome.
  • The developed automated framework shows significant potential for early metabolic risk detection in clinical and preventive settings.
  • This approach offers a complementary tool for cardiometabolic screening, enhancing early diagnosis and intervention strategies.