Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.
World J Psychiatry. Oct 19, 2026; 16(10): 123156
Published online Oct 19, 2026. doi: 10.5498/wjp.123156
FusedNeXt-based anxiety detection from electroencephalography topographic maps: A comparative analysis of alpha, beta, and theta bands
Suheda Kaya, Gulay Tasci, İlknur Tuncer, Burak Tasci, Nursena Baygın, Irem Tasci, Mehmet Baygin, Sengul Dogan, Turker Tuncer
Suheda Kaya, Gulay Tasci, Department of Psychiatry, Elazig Fethi Sekin City Hospital, Elazig 23100, Türkiye
İlknur Tuncer, Elazig Governorship, Elazığ 23100, Türkiye
Burak Tasci, Vocational School of Technical Sciences, Firat University, Elazig 23119, Türkiye
Nursena Baygın, Faculty of Engineering, Erzurum Technical University, Elazığ 25000, Türkiye
Irem Tasci, Department of Neurology, School of Medicine, Firat University, Elazig 23100, Türkiye
Mehmet Baygin, Department of Computer Engineering, Erzurum Technical University, Erzurum 25030, Türkiye
Sengul Dogan, Turker Tuncer, Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig 23119, Türkiye
Co-first authors: Suheda Kaya and Gulay Tasci.
Author contributions: Kaya S and Tasci G contributed equally to this manuscript and are co-first authors. Kaya S, Tasci G, Tuncer İ, Tasci B, Tasci I, Dogan S, and Tuncer T contributed to conceptualization and investigation; Kaya S, Tasci G, Tuncer İ, Tasci B, Baygın N, Tasci I, Baygin M, Dogan S, and Tuncer T contributed to methodology, validation, data curation, writing - original draft preparation, and writing - review and editing; Tasci B, Baygın N, Baygin M, Dogan S, and Tuncer T contributed to software, formal analysis, and visualization; Kaya S, Tasci G, Tuncer İ, and Tasci I contributed to resources; Tasci B, Dogan S, and Tuncer T contributed to supervision; Tasci B contributed to project administration. All authors have read and approved the final version of the manuscript.
AI contribution statement: AI tools were used for language editing and figure preparation. All AI-assisted outputs were reviewed and verified by the authors.
Institutional review board statement: This study was conducted in accordance with the Declaration of Helsinki and approved by the Institutional Review Board (Non-Invasive Ethics Committee) of Firat University (protocol code 2022/07-33 26.05.2022).
Informed consent statement: This study was conducted as a retrospective secondary computational analysis of a previously collected and de-identified hospital electroencephalography dataset. The participants were not prospectively recruited for the present computational study, and no additional clinical procedure, intervention, contact, or data collection was performed specifically for this research. The dataset was de-identified before being made available for analysis, and the researchers had no access to direct personal identifiers. The use of de-identified retrospective data was approved by the Institutional Review Board in accordance with institutional policies and applicable ethical regulations.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Data sharing statement: The authors are committed to making the data available if requested by the journal.
Corresponding author: Burak Tasci, Vocational School of Technical Sciences, Firat University, Cahit Arf Street, Elazig 23119, Türkiye.
btasci@firat.edu.tr
Received: May 11, 2026
Revised: July 23, 2026
Accepted: September 4, 2026
Published online: October 19, 2026
Processing time: 154 Days and 1.8 Hours
BACKGROUND
Electroencephalography (EEG) topographic maps preserve the spatial arrangement of scalp electrodes, but their apparent classification performance is sensitive to clinical phenotyping, preprocessing, and data partitioning.
AIM
To evaluate whether alpha-, beta-, and theta-band topographic maps provide different classification profiles under a controlled FusedNeXt framework.
METHODS
A lightweight FusedNeXt architecture was evaluated using band-specific topographic maps generated from a retrospective, de-identified hospital EEG dataset. Each 15-second EEG segment was divided into five non-overlapping 3-second windows. The same architecture, training settings, and band-specific input construction were used across all experiments. The dataset comprised 44 participants labelled anxiety and 44 labelled control. Group labels were obtained from the available hospital clinical records and clinical assessment. Uniform individual DSM/ICD codes, the specific diagnostic-manual version, structured diagnostic interview records, validated anxiety-scale scores and cut-off values, and anxiety-subtype information were not retained in the de-identified dataset. An approximately 80:20 stratified split was applied at the 15-second segment level, so different segments from the same participant could occur in both partitions. Generalization to unseen participants was additionally evaluated with participant-grouped five-fold cross-validation and participant-level mean-probability aggregation.
RESULTS
Under the fixed segment-level split, theta achieved the numerically highest window-level accuracy (85.24%), balanced accuracy (84.93%), macro F1-score (84.49%), and area under the curve (AUC) (0.9297); beta achieved 84.58% accuracy and an AUC of 0.9296, and alpha achieved 81.24% accuracy and an AUC of 0.8958. Under participant-grouped five-fold cross-validation, participant-level accuracy was 79.10% for theta, 77.84% for beta, and 74.66% for alpha. Beta and theta significantly outperformed alpha for balanced accuracy, macro F1-score, and AUC after Holm correction, whereas theta and beta did not differ significantly. Same-dataset baseline and ablation analyses provided additional evidence on model performance and component contribution. FusedNeXt contained approximately 7.17 million trainable parameters, required approximately 1.95 GFLOPs per forward pass, and classified one image in approximately 3 milliseconds.
CONCLUSION
The participant-grouped analysis provides an internal estimate of generalization to unseen participants within the same source dataset. The findings support band-specific discrimination within this cohort but do not establish diagnostic utility, a validated EEG biomarker, or external clinical validity. Independent external validation and more complete clinical phenotyping remain necessary.
Core Tip: This study presents a lightweight FusedNeXt-based framework for anxiety detection using electroencephalography (EEG) topographic map images. Instead of relying on handcrafted numerical features, alpha, beta, and theta frequency bands were converted into spatial scalp maps and evaluated under the same architecture, data split, and test protocol. The theta band achieved the best overall performance, while the beta band reduced false anxiety predictions in control samples. The proposed model provides competitive accuracy with low computational cost, supporting its potential use in fast EEG-based decision-support systems.
