Stability‐Driven Selection of EEG Connectivity Features for Psychosis Classification: A Network‐Based Machine Learning Approach
Top Cited Papers
Open Access
- 20 May 2026
- journal article
- Published by Wiley in CNS Neuroscience & Therapeutics
- Vol. 32 (5) , e70943
Abstract
Objectives: To develop a network‐based machine learning framework for classifying psychosis using EEG connectivity features and to identify stable, reproducible candidate markers through a stability‐driven approach. Methods: This study was designed as a cross‐sectional analytical secondary data analysis using a publicly available EEG dataset comprising 43 participants (19 psychosis, 24 controls). Functional connectivity measures (PLV and coherence) and graph‐theoretical network features were extracted across frequency bands. A nested cross‐validation framework with subject‐wise splitting was applied. Feature importance was evaluated using permutation importance and SHAP, and stability scores were computed across folds to identify robust features. Classification was performed using support vector machine (SVM) and random forest (RF) models. Results: The SVM model achieved superior performance (accuracy: 91.2%, AUC: 0.967). Stability analysis identified theta‐band connectivity features, particularly fronto‐parietal PLV and global efficiency, as the most reliable and discriminative. SHAP analysis confirmed their consistent contribution across subjects. However, these findings should be interpreted as exploratory given the relatively small sample size and the use of a single dataset. Conclusion: Stable connectivity‐derived network features provide interpretable and robust candidate EEG markers for psychosis classification. The proposed framework enhances reproducibility and supports the potential of EEG‐based tools for clinical screening, while emphasizing the need for external validation.Keywords
This publication has 15 references indexed in Scilit:
- How EEG preprocessing shapes decoding performanceCommunications Biology, 2025
- EEG-based Signatures of Schizophrenia, Depression, and Aberrant Aging: A Supervised Machine Learning InvestigationSchizophrenia Bulletin, 2024
- A systematic review of EEG based automated schizophrenia classification through machine learning and deep learningFrontiers in Human Neuroscience, 2024
- Optimizing feature subset for schizophrenia detection using multichannel EEG signals and rough set theoryCognitive Neurodynamics, 2024
- The EEG multiverse of schizophreniaCerebral Cortex, 2022
- Anticipatory deficits in psychosis during social cognition task revealed by task-based EEG dynamic functional connectivity analysisPsyArXiv, 2022
- Automatic classification of schizophrenia patients using resting-state EEG signalsPhysical and Engineering Sciences in Medicine, 2021
- EEG Frequency Bands in Psychiatric Disorders: A Review of Resting State StudiesFrontiers in Human Neuroscience, 2019
- Brain oscillations in neuropsychiatric diseaseDialogues in clinical neuroscience, 2013
- Towards the utilization of EEG as a brain imaging toolNeuroImage, 2012