Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 21, 2026

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Stability-Driven Selection of EEG Connectivity Features for Psychosis Classification: A Network-Based Machine

Mahdi Naeim¹, Mohammad Narimani¹

¹Department of Psychology, Faculty of Educational Sciences and Psychology, University of Mohaghegh Ardabili, Ardabil, Iran.

CNS Neuroscience & Therapeutics

|May 20, 2026

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

Explainable Temporal Deep Learning for EEG-Based Depression Detection Using Resting-State Brain Dynamics.

International journal of methods in psychiatric research·2026

Same author

Mapping research themes and collaborative networks in schizophrenia genetics and clinical psychological correlates: A bibliometric and scientometric study (1957-2025).

Medicine·2026

Same author

Mapping research trends and gaps in cognitive dysfunction in Parkinson's disease: A bibliometric and scientometric analysis.

Journal of health psychology·2026

Same author

A Comparative Study of Moral, Emotional, and Spiritual Intelligence in Parents of Aggressive and Non-Aggressive Children: A Developmental Psychology and Parenting Behavior Perspective.

Brain and behavior·2026

Same author

Mapping scientific trends in bipolar disorder and digital psychiatry (2000-2025): A bibliometric and visualized analysis of AI-driven diagnosis and digital interventions.

Digital health·2026

Same author

EEG-based biomarkers for psychosis: Comparative performance of support vector machines and deep neural networks.

Biological psychology·2026

This study developed a machine learning framework using electroencephalography (EEG) connectivity to classify psychosis, identifying stable theta-band features as reliable markers for potential clinical screening tools.

Area of Science:

Neuroscience
Computational Psychiatry
Biomedical Engineering

Background:

Psychosis classification remains challenging, necessitating novel biomarkers.
Electroencephalography (EEG) offers a non-invasive window into brain dynamics.
Network analysis of EEG connectivity shows promise for identifying neural correlates of psychiatric disorders.

Purpose of the Study:

To create a machine learning (ML) framework for psychosis classification using EEG connectivity.
To identify stable and reproducible EEG network features as candidate biomarkers.
To employ a stability-driven approach for robust marker discovery.

Main Methods:

Secondary analysis of a public EEG dataset (43 participants: 19 psychosis, 24 controls).
Extraction of functional connectivity (PLV, coherence) and graph-theoretical network features across frequency bands.

Keywords:

EEG connectivity SHAP interpretability network features psychosis classification stability‐driven feature selection

More Related Videos

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

Related Experiment Videos

Last Updated: May 21, 2026

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

Nested cross-validation with permutation importance, SHAP values, and stability scores for feature selection; SVM and Random Forest models used for classification.

Main Results:

Support Vector Machine (SVM) model achieved high accuracy (91.2%) and AUC (0.967).
Stable theta-band connectivity features, including fronto-parietal Phase-Lag Index (PLV) and global efficiency, were identified as key discriminators.
SHAP analysis confirmed the consistent importance of these features, though findings are exploratory due to sample size and dataset limitations.

Conclusions:

Network features derived from stable EEG connectivity offer interpretable and robust candidate markers for psychosis classification.
The developed framework enhances reproducibility in biomarker discovery.
EEG-based tools show potential for clinical screening, contingent upon external validation.