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: May 21, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

From EEG signals to quantitative assessment: predicting depression severity using a novel deep learning framework.

Shouqing Liu1, Yuhuan Cui2, Yanting Xu2

  • 1The Second Hospital of Jinhua, Jinhua, 321016, China.

Scientific Reports
|May 19, 2026
PubMed
Summary

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

A novel chimeric peptide binds MC3T3‑E1 cells to titanium and enhances their proliferation and differentiation.

Molecular medicine reports·2013
Same author

Fast trabecular bone strength predictions of HR-pQCT and individual trabeculae segmentation-based plate and rod finite element model discriminate postmenopausal vertebral fractures.

Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research·2013
Same author

Biological activities and corresponding SARs of andrographolide and its derivatives.

Mini reviews in medicinal chemistry·2013
Same author

The prognostic value of MGMT promoter methylation in Glioblastoma multiforme: a meta-analysis.

Familial cancer·2013
Same author

Understanding the structure and mechanism of formation of a new magnetic microbubble formulation.

Theranostics·2013
Same author

Analysis of IL-17 gene polymorphisms in Chinese patients with dilated cardiomyopathy.

Human immunology·2013

This study introduces a deep learning model using electroencephalography (EEG) to objectively predict depression severity. The novel approach accurately quantifies depressive disorder (DD) levels, offering a potential biomarker.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Depression severity assessment currently lacks objective biomarkers, relying on subjective scales.
  • There is a need for quantitative, automated methods to predict depressive disorder (DD) severity.
  • Resting-state electroencephalography (EEG) offers a non-invasive window into brain activity relevant to neurological conditions.

Purpose of the Study:

  • To develop and validate a deep learning model for automated, quantitative prediction of depression severity using resting-state EEG.
  • To integrate phase lag index (PLI), graph embedding (GE), and gated multilayer perceptron (gMLP) for enhanced feature extraction.
  • To assess the model's performance against traditional machine learning and deep learning approaches.

Main Methods:

Keywords:
Deep learningDepressionElectroencephalographyFunctional connectivitySeverity assessment

Related Experiment Videos

Last Updated: May 21, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

  • Collected resting-state EEG data from 70 patients with DD and 30 healthy controls (HC).
  • Developed a novel deep learning framework, PLI_GE_gMLP, integrating PLI, GE, and gMLP.
  • Utilized SHAP (Shapley Additive Explanations) for model interpretability analysis.

Main Results:

  • The PLI_GE_gMLP model achieved a mean absolute error (MAE) of 4.30 in predicting depression severity.
  • The proposed model significantly outperformed established machine learning and deep learning methods.
  • SHAP analysis identified frontal and temporal lobe functional connectivity (Beta and Theta bands) as key predictive features.

Conclusions:

  • The PLI_GE_gMLP model provides an accurate and interpretable method for quantitative depression severity prediction.
  • The findings highlight the potential of EEG-based biomarkers for objective assessment of DD.
  • The integration of GE and gMLP effectively captures spatiotemporal and functional connectivity features crucial for predicting depression severity.