Accepted Articles
Back to the articles list |
Back to browse issues page
1- Student Research Committee, Baqiyatallah University of Medical Sciences, Tehran, Iran
2- Department of Internal Medicine, University Hospital Zurich, Zurich, Switzerland
3- Neuroscience Research Center, Baqiyatallah University of Medical Sciences, Tehran, Iran
2- Department of Internal Medicine, University Hospital Zurich, Zurich, Switzerland
3- Neuroscience Research Center, Baqiyatallah University of Medical Sciences, Tehran, Iran
Abstract:
Purpose: The early diagnosis of schizophrenia (SZ) continues to be challenging due to the subjective nature of clinical assessments and the heterogeneity of symptoms. There is a pressing need for objective, scalable, and non-invasive diagnostic tools to complement traditional methods. This study proposes a machine learning (ML) framework that utilizes dynamic effective connectivity matrices (DCM) derived from event-related potentials (ERP) for SZ classification.
Methods: ERP data from 81 participants, including 49 SZ patients and 32 healthy controls, sourced from a publicly accessible and anonymized dataset. Granger causality was employed to compute 64×64 directional connectivity matrices, capturing inter-electrode information flow. Feature selection through t-tests identified 2,777 significant connectivity differences (p
< 0.05), which were subsequently used to train a Random Forest (RF) classifier. To address class imbalance, balanced training subsets were created. Additionally, the robustness of the model was evaluated under varying levels of white Gaussian noise (0% to 45%).
Results: The Random Forest classifier demonstrated high diagnostic accuracy (99.24%), sensitivity (98.34%), specificity (99.73%), and an F1-score of 98.91% across 100 iterations, effectively minimizing the risks of overfitting. Its performance remained robust under varying train-test splits and substantial noise levels, with an F1-score of 92% even with 45% white Gaussian noise. Feature selection significantly enhanced noise resilience and classification stability. Connectivity analysis revealed that central (Cz, FCz), occipito-parietal (PO3, Oz), and inferior (Iz) regions were key discriminators, indicating disrupted fronto-temporal and sensory integration networks in individuals with schizophrenia.
Conclusion: This study highlights the feasibility of ML-driven ERP connectivity analysis as a non-invasive tool for the early detection of SZ. Achieving near-perfect accuracy, the model demonstrates strong generalizability, interpretability, and clinical scalability, outperforming deep learning counterparts while relying on a minimal, targeted feature set. The findings underscore the diagnostic relevance of fronto-central and occipito-parietal connectivity patterns. While promising as a non-invasive diagnostic adjunct, future validation on larger, demographically diverse cohorts is essential.
Methods: ERP data from 81 participants, including 49 SZ patients and 32 healthy controls, sourced from a publicly accessible and anonymized dataset. Granger causality was employed to compute 64×64 directional connectivity matrices, capturing inter-electrode information flow. Feature selection through t-tests identified 2,777 significant connectivity differences (p
< 0.05), which were subsequently used to train a Random Forest (RF) classifier. To address class imbalance, balanced training subsets were created. Additionally, the robustness of the model was evaluated under varying levels of white Gaussian noise (0% to 45%).
Results: The Random Forest classifier demonstrated high diagnostic accuracy (99.24%), sensitivity (98.34%), specificity (99.73%), and an F1-score of 98.91% across 100 iterations, effectively minimizing the risks of overfitting. Its performance remained robust under varying train-test splits and substantial noise levels, with an F1-score of 92% even with 45% white Gaussian noise. Feature selection significantly enhanced noise resilience and classification stability. Connectivity analysis revealed that central (Cz, FCz), occipito-parietal (PO3, Oz), and inferior (Iz) regions were key discriminators, indicating disrupted fronto-temporal and sensory integration networks in individuals with schizophrenia.
Conclusion: This study highlights the feasibility of ML-driven ERP connectivity analysis as a non-invasive tool for the early detection of SZ. Achieving near-perfect accuracy, the model demonstrates strong generalizability, interpretability, and clinical scalability, outperforming deep learning counterparts while relying on a minimal, targeted feature set. The findings underscore the diagnostic relevance of fronto-central and occipito-parietal connectivity patterns. While promising as a non-invasive diagnostic adjunct, future validation on larger, demographically diverse cohorts is essential.
Type of Study: Original |
Subject:
Computational Neuroscience
Received: 2025/08/11 | Accepted: 2025/10/8
Received: 2025/08/11 | Accepted: 2025/10/8
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
Copyright © The Author(s);
This is an open access article distributed under the terms of the Creative Commons Attribution License (CC-By-NC), which permits use, distribution, and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
Contact Information
