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

Transfer learning from 2D natural images to 4D fMRI brain images via geometric mapping.

Medical image analysis·2026
Same author

Structural brain differences in major depressive disorder patients with suicidal risk: Evidence from the DIRECT consortium.

Journal of affective disorders·2026
Same author

The altered representation of interoceptive sensations in individuals with alexithymia: A mouse-tracking and EEG co-registration study.

Neuroscience·2026
Same author

Controllability of morphometric network colocalize with underlying neurobiology in major depression.

Psychological medicine·2026
Same author

Retraction notice to "Multi-feature concatenation and multi-classifier stacking: An interpretable and generalizable machine learning method for MDD discrimination with rsfMRI" [NeuroImage 285 (2024) 120497].

NeuroImage·2025
Same author

Beyond screen-time: Exploring how appearance-related social media consciousness shapes Chinese adolescents' subjective well-being through individual differences in age, gender, and functionality appreciation.

Body image·2025

Related Experiment Video

Updated: Jul 7, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.5K

Multi-feature concatenation and multi-classifier stacking: An interpretable and generalizable machine learning method

Yunsong Luo1, Wenyu Chen1, Ling Zhan1

  • 1College of Computer and Information Science, Southwest University, Chongqing, 400715, PR China.

Neuroimage
|December 24, 2023
PubMed
Summary

A new machine learning method (MFMC) accurately distinguishes major depressive disorder (MDD) patients using resting-state functional MRI (rsfMRI) data. This approach improves diagnostic accuracy and identifies key brain regions for potential biomarkers.

Keywords:
GeneralizabilityInterpretable machine learningMajor depressive disorderMulti-siteNeuroimage biomarker of MDDResting-state fMRI data

More Related Videos

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

16.9K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

761

Related Experiment Videos

Last Updated: Jul 7, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.5K
Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

16.9K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

761

Area of Science:

  • Neuroimaging
  • Psychiatric Disorders
  • Machine Learning

Background:

  • Major Depressive Disorder (MDD) is a complex psychiatric condition requiring precise diagnostic tools.
  • Resting-state functional MRI (rsfMRI) offers valuable insights into brain structure, function, and connectivity for MDD research.
  • Current machine learning methods for MDD discrimination using rsfMRI show promise but require enhanced accuracy, generalizability, and interpretability.

Purpose of the Study:

  • To develop and validate an advanced machine learning method (MFMC) for improved discrimination of MDD patients from healthy controls.
  • To enhance the generalizability and interpretability of machine learning-based diagnostic approaches for MDD.
  • To identify potential neuroimaging biomarkers for MDD diagnosis and prognosis.

Main Methods:

  • Proposed a novel machine learning method (MFMC) integrating multiple features and stacked classifiers.
  • Tested MFMC on the large-scale REST-meta-MDD dataset comprising 2428 subjects from 25 diverse sites.
  • Utilized XGBoost as a meta-classifier to enable probing of the decision-making process and feature importance.

Main Results:

  • MFMC achieved a high MDD discrimination accuracy of 96.9%, surpassing existing methods.
  • Demonstrated robust generalizability by maintaining performance on independent training and testing datasets from different sites.
  • Identified 13 critical feature values from 9 brain regions (e.g., posterior cingulate gyrus, superior frontal gyrus orbital part, angular gyrus) that significantly contribute to classification.

Conclusions:

  • The proposed MFMC method offers a significant advancement in the accuracy and generalizability of MDD diagnosis using rsfMRI.
  • The identified brain features and regions show potential as reliable diagnostic and prognostic biomarkers for MDD.
  • The interpretability of MFMC facilitates understanding the neurobiological underpinnings of MDD and supports clinical application.