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 Experiment Video

Updated: Jul 9, 2026

Closed-Loop Neurostimulation for Biomarker-Driven, Personalized Treatment of Major Depressive Disorder
05:19

Closed-Loop Neurostimulation for Biomarker-Driven, Personalized Treatment of Major Depressive Disorder

Published on: July 7, 2023

Cognition-Modulated EEG Signatures and Clinical Features in Major Depressive Disorder: A Machine Learning-Based

Cheng-Ta Li1,2,3, Chih-An Lai4, Jia-Shyun Jeng1,2

  • 1Precision Depression Intervention Center (PreDIC), Department of Psychiatry, Taipei Veterans General Hospital, 112 Taipei, Taiwan.

Alpha Psychiatry
|July 8, 2026
PubMed
Summary

Related Concept Videos

Depressive Disorders: Etiology01:27

Depressive Disorders: Etiology

Depressive disorders result from a complex interplay of biological, psychological, and sociocultural factors, each contributing uniquely to the development and persistence of the condition. Understanding these factors provides critical insight into the multifaceted nature of depression.
Biological Factors in Depression
Biological predispositions significantly influence the risk of developing depressive disorders. Genetic studies highlight the role of variations in the serotonin transporter...

You might also read

Related Articles

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

Sort by
Same author

Risks and Familial Coaggregation of Autism Spectrum Disorder Among First-Degree Relatives of Individuals With Colorectal Cancer.

Psychiatry investigation·2026
Same author

Abnormal left prefrontal N100 and its relationship with fronto-limbic metabolism in major depressive disorder.

Translational psychiatry·2026
Same author

Distinct therapeutic profiles of ketamine in treatment-resistant depression: an exploratory analysis.

The international journal of neuropsychopharmacology·2026
Same author

Global cognitive dysfunction and <i>β</i>-amyloid neuropathology in late-life and treatment-resistant major depression.

Psychological medicine·2026
Same author

Eukaryotic initiation factor 4E: a key factor of traumatic stress-induced depression-related cognitive decline at different age.

Translational psychiatry·2026
Same author

Pharmacological management of agitation in dementia: An evidence-based review with expert consensus.

Journal of the Chinese Medical Association : JCMA·2026

Machine learning analysis of electroencephalography (EEG) data shows promise for objectively characterizing major depressive disorder (MDD) heterogeneity. This approach accurately predicts depression severity and treatment refractoriness using frontal EEG features.

Area of Science:

  • Neuroscience
  • Computational Psychiatry
  • Biomedical Engineering

Background:

  • Major Depressive Disorder (MDD) presents with diverse clinical features like symptom severity, treatment resistance, and suicidality.
  • Current assessments rely on subjective scales and clinical history, necessitating objective biomarkers.
  • Frontal and anterior cingulate cortex (ACC) network dysfunction is implicated in MDD pathophysiology.

Purpose of the Study:

  • To explore the utility of electroencephalography (EEG) and machine learning (ML) for objective characterization of MDD clinical heterogeneity.
  • To classify suicidality, depressive symptom severity, and treatment refractoriness using EEG-derived features.
  • To investigate the role of frontal-ACC circuitry in MDD through a cognitive task.

Main Methods:

Keywords:
electroencephalographymachine learningmajor depressive disordersuicidal ideationtreatment-resistant depression

Related Experiment Videos

Last Updated: Jul 9, 2026

Closed-Loop Neurostimulation for Biomarker-Driven, Personalized Treatment of Major Depressive Disorder
05:19

Closed-Loop Neurostimulation for Biomarker-Driven, Personalized Treatment of Major Depressive Disorder

Published on: July 7, 2023

  • Analysis of resting-state and cognition-modulated EEG data from 209 MDD patients.
  • Utilized a rostral ACC-engaging cognitive task (RECT) to probe frontal-ACC networks.
  • Extracted linear and non-linear EEG features from frontal electrodes across frequency bands, integrated with ML classifiers (Random Forest, SVM).
  • Addressed class imbalance for suicidality using synthetic oversampling.

Main Results:

  • Random Forest (RF) models outperformed Support Vector Machines (SVM) for all outcomes.
  • RF achieved high classification accuracies: ~83% for depression severity (AUC=0.83) and ~87% for treatment refractoriness (AUC=0.87).
  • Feature importance revealed frontal electrodes and nonlinear EEG complexity as key predictors across outcomes.
  • Data balancing improved suicidality classification performance.

Conclusions:

  • A unified EEG-based approach combining cognitive modulation and ensemble ML is feasible for identifying MDD characteristics.
  • Findings underscore the significance of frontal network dysfunction in MDD across its spectrum.
  • Further validation in larger, longitudinal cohorts is warranted to confirm these objective biomarkers.