Compact Deep Learning for Major Depressive Disorder Classification from Resting-State EEG: Independent Cohort Validation and Channel-Level Explainability
The Journal of Neurobehavioral Sciences · 2026
DOI: 10.32739/jnbs.13.2.289 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Neurobehavioral Sciences, 2026. Verfasst von Çağlar Uyulan.
Abstract (Originalsprache)
Aims:Major depressive disorder (MDD) is a common psychiatric disorder, and objective measures that can support clinical assessment are increasingly being investigated. Electroencephalography (EEG) provides a non-invasive and relatively low-cost approach for examining brain activity and has shown potential for EEG-based MDD classification. This study investigated whether short resting-state EEG segments could distinguish individuals with MDD from healthy controls (HC) using two compact deep learning architectures: a Lightweight 1D Convolutional Neural Network (Light 1D-CNN) and a CNN-MiniTransformer. Materials and Methods: The study included 112 resting-state EEG recordings from 56 individuals with MDD and 56 HC. Ninety-two recordings were used for model development and internal evaluation, while 20 independent recordings were reserved for external validation. Nineteen-channel eyes-closed EEG recordings were standardized to 125 Hz and divided into non-overlapping 1-s segments. Channel-ablation analysis was performed to examine spatial EEG importance.
Results
On the internal test set, the Light 1D-CNN achieved 96.43% accuracy, a 96.39% F1-score, and an AUROC of 0.9941, while the CNN-MiniTransformer achieved 95.26%, 95.31%, and 0.9906, respectively. On external validation, the Light 1D-CNN achieved 93.72% accuracy and an AUROC of 0.9785, whereas the CNN-MiniTransformer achieved 94.65% accuracy and an AUROC of 0.9872. P4 was the most influential channel in both global and MDD-specific analyses, with Fz and F4 also showing strong contributions. The parietal region showed the highest importance, followed by the frontal region.
Conclusion
Both compact deep learning models showed strong performance for MDD–HC classification using short resting-state EEG segments and maintained high performance on independently held-out recordings. Similar channel-importance patterns across the two architectures also provide an interpretable basis for further investigation of spatial EEG characteristics associated with MDD.
Zitieren
APA
Uyulan, Ç. (2026). Compact Deep Learning for Major Depressive Disorder Classification from Resting-State EEG: Independent Cohort Validation and Channel-Level Explainability. The Journal of Neurobehavioral Sciences. https://doi.org/10.32739/jnbs.13.2.289
Vancouver
Uyulan Ç. Compact Deep Learning for Major Depressive Disorder Classification from Resting-State EEG: Independent Cohort Validation and Channel-Level Explainability. The Journal of Neurobehavioral Sciences. 2026. doi:10.32739/jnbs.13.2.289
BibTeX
@article{Uyulan2026,
author = {Uyulan, Çağlar},
title = {Compact Deep Learning for Major Depressive Disorder Classification from Resting-State EEG: Independent Cohort Validation and Channel-Level Explainability},
journal = {The Journal of Neurobehavioral Sciences},
year = {2026},
doi = {10.32739/jnbs.13.2.289}
}
EUVIMED