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

ETV4 enhances glycolysis to suppress NK-cell cytotoxicity in the immune microenvironment of colon cancer.

Biochimica et biophysica acta. General subjects·2026
Same author

A Gradient-Guided Spatio-Temporal Graph Convolutional Network for Population-Level Major Depressive Disorder Classification.

IEEE journal of biomedical and health informatics·2026
Same author

The 2026 global roadmap for textile-integrated wearable technologies in health.

Physiological measurement·2026
Same author

Different modulation patterns of theta and gamma dual-site HD-tACS on cognitive impairment.

iScience·2026
Same author

Multiscale heterogeneity of atypical functional connectivity in autism.

Nature. Mental health·2026
Same author

Steric Hindrance Enhanced the Bowl-Shaped Curvature of Bridged Triphenylamine.

Organic letters·2026

Related Experiment Video

Updated: Sep 10, 2025

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method
07:12

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method

Published on: August 2, 2021

3.7K

Random Walk-Based Node Feature Learning for Major Depressive Disorder Identification Through Multi-Site rs-fMRI Data.

Wanting Xi1,2, Zijian Guo1,3, Ting Mei1

  • 1College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.

Human Brain Mapping
|August 21, 2025
PubMed
Summary

This study introduces a new method using brain network data to accurately identify major depressive disorder (MDD). The graph embedding approach improves diagnostic accuracy by analyzing functional connectivity features.

Keywords:
ensemble learningfunctional connectivitymajor depressive disordernode2vecrandom walk

More Related Videos

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity
10:43

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity

Published on: July 1, 2014

15.3K
MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder
08:20

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder

Published on: August 11, 2015

14.1K

Related Experiment Videos

Last Updated: Sep 10, 2025

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method
07:12

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method

Published on: August 2, 2021

3.7K
Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity
10:43

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity

Published on: July 1, 2014

15.3K
MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder
08:20

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder

Published on: August 11, 2015

14.1K

Area of Science:

  • Neuroscience
  • Psychiatry
  • Machine Learning

Background:

  • Major depressive disorder (MDD) is a widespread condition impacting quality of life and increasing suicide risk.
  • Accurate MDD identification is crucial for effective clinical diagnosis and treatment.
  • Current methods often overlook region of interest (ROI) features in functional brain networks and use limited datasets, hindering generalizability.

Purpose of the Study:

  • To develop and validate a novel graph embedding-based feature selection classification framework (GEF-FSC) for identifying MDD.
  • To leverage multi-site resting-state functional magnetic resonance imaging (rs-fMRI) data for robust MDD detection.
  • To explore the utility of higher-order structural information within functional brain networks for improved diagnostic accuracy.

Main Methods:

  • Utilized the node2vec algorithm for learning local and global functional connectivity (FC) features from ROIs in brain networks.
  • Employed flexible random walks to capture structural information within functional brain networks.
  • Applied Random Forest for feature selection and an ensemble classifier for MDD classification using multi-site rs-fMRI data.

Main Results:

  • The GEF-FSC framework achieved high classification accuracy: 81.65% (Dosenbach template) and 75.30% (AAL atlas) on the REST-meta-MDD dataset.
  • Demonstrated superior performance compared to eight benchmark methods and six state-of-the-art classifiers in accuracy, sensitivity, specificity, and F1-score.
  • Interpretability analysis identified key brain regions and networks associated with MDD, aligning with existing research.

Conclusions:

  • The GEF-FSC framework effectively classifies MDD using multi-site rs-fMRI data.
  • The study highlights the significance of higher-order structural information in functional brain networks for enhancing diagnostic accuracy.
  • The identified brain regions and networks provide insights into the neurobiological underpinnings of MDD.