Next Article in Journal
TAM 4 for Enterprise System Adoption: A PCA-Based Multi-Theory Framework and Scenario-Based PLS-SEM Validation
Previous Article in Journal
DFSel-FT: A Differentiable Feature Selection and FT-Transformer Framework for Interpretable Thyroid Disease Classification Using Tabular Data
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Computers
Volume 15
Issue 6
10.3390/computers15060333
computers-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Hybrid Spatio-Temporal Graph Transformer for EEG-Based ADHD Detection via Network Index Modeling

by
Makbal Baibulova
1,
Ayagoz Mukhanova
1,*,
Aliya Abdukarimova
2,*,
Lazzat Abdykerimova
3,
Bulat Serimbetov
2,
Madi Akhmetzhanov
4,
Zhanat Seitakhmetova
5,
Elmira Yeshtayeva
6,
Murizah Kassim
7 and
Aizat Amirbay
1
1
Faculty of Information Technology, Department of Information Systems, L. N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan
2
Department of Information Technology, K. Kulazhanov Kazakh University of Technology and Business, Astana 010000, Kazakhstan
3
Department of Information Systems, M. Kh. Dulaty Taraz University, Taraz 080000, Kazakhstan
4
Department of Applied Informatics and Programming, M. Kh. Dulaty Taraz University, Taraz 080000, Kazakhstan
5
Department of Computer Modeling and Information Technology, East Kazakhstan University Named After S.Amanzholov, Ust-Kamenogorsk 070000, Kazakhstan
6
Foreign Languages Department of the Faculty of Philology, L. N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan
7
Institute for Big Data Analytics and Artificial Intelligence (IBDAAI), Universiti Teknologi MARA, Shah Alam 40450, Selangor, Malaysia
*
Authors to whom correspondence should be addressed.
Computers 2026, 15(6), 333; https://doi.org/10.3390/computers15060333 (registering DOI)
Submission received: 17 April 2026 / Revised: 20 May 2026 / Accepted: 21 May 2026 / Published: 23 May 2026
Versions Notes

Abstract

Objective and reproducible diagnosis of attention-deficit/hyperactivity disorder (ADHD) remains challenging because of the limited availability of reliable electroencephalography (EEG) biomarkers and the high variability of neural signals. This study proposes a computational framework for ADHD detection based on dynamic functional connectivity and network-index modeling. Multichannel EEG recordings were transformed into temporal connectivity graphs using sliding-window correlations of band-limited amplitude envelopes. Several network-index models were evaluated, including linear, graph-based, recurrent, and hybrid spatio-temporal approaches. The proposed Hybrid Spatio-Temporal Graph Transformer demonstrated moderate, yet reproducible, subject-level classification performance. On the independent test set, the model achieved an accuracy of 63.16%, a balanced accuracy of 62.22%, a sensitivity of 80.00%, a specificity of 44.44%, an F1-score of 69.57%, and an AUC-ROC of 0.7444. Additional analysis of the derived network index demonstrated moderate intergroup separability, with a mean index shift of 1.16, Cohen’s d = 0.73, Pearson’s r = 0.36, and distribution overlap = 0.72. These findings suggest that the proposed framework captures informative spatio-temporal EEG connectivity patterns associated with ADHD; however, the model’s diagnostic applicability should be considered preliminary and requires validation in larger independent cohorts.
Keywords: ADHD; EEG; dynamic functional connectivity; graph neural networks; spatio-temporal modeling; attention mechanisms; decision support systems ADHD; EEG; dynamic functional connectivity; graph neural networks; spatio-temporal modeling; attention mechanisms; decision support systems

Share and Cite

MDPI and ACS Style

Baibulova, M.; Mukhanova, A.; Abdukarimova, A.; Abdykerimova, L.; Serimbetov, B.; Akhmetzhanov, M.; Seitakhmetova, Z.; Yeshtayeva, E.; Kassim, M.; Amirbay, A. A Hybrid Spatio-Temporal Graph Transformer for EEG-Based ADHD Detection via Network Index Modeling. Computers 2026, 15, 333. https://doi.org/10.3390/computers15060333

AMA Style

Baibulova M, Mukhanova A, Abdukarimova A, Abdykerimova L, Serimbetov B, Akhmetzhanov M, Seitakhmetova Z, Yeshtayeva E, Kassim M, Amirbay A. A Hybrid Spatio-Temporal Graph Transformer for EEG-Based ADHD Detection via Network Index Modeling. Computers. 2026; 15(6):333. https://doi.org/10.3390/computers15060333

Chicago/Turabian Style

Baibulova, Makbal, Ayagoz Mukhanova, Aliya Abdukarimova, Lazzat Abdykerimova, Bulat Serimbetov, Madi Akhmetzhanov, Zhanat Seitakhmetova, Elmira Yeshtayeva, Murizah Kassim, and Aizat Amirbay. 2026. "A Hybrid Spatio-Temporal Graph Transformer for EEG-Based ADHD Detection via Network Index Modeling" Computers 15, no. 6: 333. https://doi.org/10.3390/computers15060333

APA Style

Baibulova, M., Mukhanova, A., Abdukarimova, A., Abdykerimova, L., Serimbetov, B., Akhmetzhanov, M., Seitakhmetova, Z., Yeshtayeva, E., Kassim, M., & Amirbay, A. (2026). A Hybrid Spatio-Temporal Graph Transformer for EEG-Based ADHD Detection via Network Index Modeling. Computers, 15(6), 333. https://doi.org/10.3390/computers15060333

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop