Nonlinear Feature Modeling Using Kolmogorov-Arnold Networks in Electroencephalography for Depression Classification: Deep Learning Study.
- 1Henan University of Urban Construction, No. 207, Longxiang Avenue, Xincheng District, Pingdingshan, Henan, 467000, China, 86 13837588771.
Abstract
Background
Depression is a common mental disorder that seriously affects mental health and quality of life. Traditional depression diagnosis mainly relies on clinical interviews and subjective assessments, which may lead to variability in diagnostic outcomes. Electroencephalogram (EEG)-based computer-aided diagnosis has emerged as a promising, objective approach for depression recognition. However, effectively modeling the complex nonlinear characteristics of EEG signals remains a major challenge for existing deep learning methods.Objective
This study aimed to investigate the applicability of Kolmogorov-Arnold Networks (KANs) for EEG-based depression recognition and to evaluate the effectiveness of KAN-based nonlinear modeling frameworks on frequency-domain EEG features.Methods
KAN was introduced into EEG-based depression recognition to enhance nonlinear feature representation of brain electrical signals. Two representative KAN-based convolutional architectures, ConvKAN and its efficiency-optimized variant ConvKAN Efficient, were systematically investigated for EEG classification tasks. These architectures incorporated KANLinear layers together with dynamic grid updating, enhanced weight initialization, and regularization strategies to improve nonlinear modeling capability while maintaining computational efficiency. Extensive experiments were conducted on the EDRA dataset, and the proposed framework was compared with conventional convolutional neural network-based methods and traditional machine learning approaches. Model performance was evaluated using accuracy, precision, recall, and F₁-score metrics.Results
Experimental results demonstrated that the KAN-based frameworks achieved superior EEG classification performance compared with conventional convolutional neural network-based methods and traditional machine learning approaches. Among the evaluated models, ConvKAN Efficient achieved the best overall performance, with accuracy, precision, recall, and F₁-score all exceeding 94% on the EDRA dataset. The results indicate that KAN-based architectures can effectively capture the complex nonlinear characteristics of EEG signals while preserving high computational efficiency.Conclusions
This study systematically demonstrates the applicability of KAN-based nonlinear modeling frameworks to EEG-based depression recognition. The proposed framework provides a scalable and effective approach for EEG signal analysis and offers valuable technical support for both theoretical research and clinical applications in computer-aided depression recognition.
Related
- Evolution of deep learning for structural magnetic resonance imaging analysis in Alzheimer’s disease: from slice-level classification to brain structure modeling
- Functional connectivity of anterior cingulate cortex subregions in suicidal ideation in major depression: circuit mechanisms, exploratory classification, and treatment-related changes.
- Altered Inhibitory Control Across Subclinical Depression and Major Depressive Disorder: Evidence From Stroop Tasks and Diffusion Modeling.
- Multiscale Topology-Regulated Nonlinear Dynamics for Protein B-Factor Prediction and Single-Cell Type Classification
- Estimating latent neuronal nonlinear dynamics by sequential Monte Carlo method and sparse modeling
BibTeX
@article{yang2026nonlinear,
title = {{Nonlinear Feature Modeling Using Kolmogorov-Arnold Networks in Electroencephalography for Depression Classification: Deep Learning Study.}},
author = {Bin Yang and Yongfeng Fan and Xinhong Wei and Chunlei Shi},
journal = {JMIR AI},
year = {2026},
month = oct,
doi = {10.2196/101076},
url = {https://europepmc.org/article/MED/42896101},
note = {CC BY},
}
RIS
TY - JOUR
TI - Nonlinear Feature Modeling Using Kolmogorov-Arnold Networks in Electroencephalography for Depression Classification: Deep Learning Study.
AU - Bin Yang
AU - Yongfeng Fan
AU - Xinhong Wei
AU - Chunlei Shi
PY - 2026
DA - 2026/10/19
JO - JMIR AI
DO - 10.2196/101076
UR - https://europepmc.org/article/MED/42896101
AB - Background Depression is a common mental disorder that seriously affects mental health and quality of life. Traditional depression diagnosis mainly relies on clinical interviews and subjective assessments, which may lead to variability in diagnostic outcomes. Electroencephalogram (EEG)-based computer-aided diagnosis has emerged as a promising, objective approach for depression recognition. However, effectively modeling the complex nonlinear characteristics of EEG signals remains a major challenge for existing deep learning methods.Objective This study aimed to investigate the applicability of Kolmogorov-Arnold Networks (KANs) for EEG-based depression recognition and to evaluate the effectiveness of KAN-based nonlinear modeling frameworks on frequency-domain EEG features.Methods KAN was introduced into EEG-based depression recognition to enhance nonlinear feature representation of brain electrical signals. Two representative KAN-based convolutional architectures, ConvKAN and its efficiency-optimized variant ConvKAN Efficient, were systematically investigated for EEG classification tasks. These architectures incorporated KANLinear layers together with dynamic grid updating, enhanced weight initialization, and regularization strategies to improve nonlinear modeling capability while maintaining computational efficiency. Extensive experiments were conducted on the EDRA dataset, and the proposed framework was compared with conventional convolutional neural network-based methods and traditional machine learning approaches. Model performance was evaluated using accuracy, precision, recall, and F₁-score metrics.Results Experimental results demonstrated that the KAN-based frameworks achieved superior EEG classification performance compared with conventional convolutional neural network-based methods and traditional machine learning approaches. Among the evaluated models, ConvKAN Efficient achieved the best overall performance, with accuracy, precision, recall, and F₁-score all exceeding 94% on the EDRA dataset. The results indicate that KAN-based architectures can effectively capture the complex nonlinear characteristics of EEG signals while preserving high computational efficiency.Conclusions This study systematically demonstrates the applicability of KAN-based nonlinear modeling frameworks to EEG-based depression recognition. The proposed framework provides a scalable and effective approach for EEG signal analysis and offers valuable technical support for both theoretical research and clinical applications in computer-aided depression recognition.
SN - 2817-1705
ER -