{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:21:36Z","timestamp":1790742096048,"version":"4.1.0"},"reference-count":63,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100020912","name":"King Faisal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020912","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Schizophrenia (SZ) presents significant diagnostic challenges in clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, we explore novel deep learning approaches for the automated detection of this severe psychiatric disorder through electroencephalography (EEG) analysis. Using a publicly available dataset of EEG recordings from 14 SZ patients and 14 healthy controls, we developed a robust processing pipeline that includes bandpass filtering (0.5\u201345 Hz), artifact removal through Independent Component Analysis, and signal enhancement via wavelet transformation. Our feature extraction approach captured both temporal characteristics, including statistical measures such as mean, standard deviation, skewness, and kurtosis, as well as spectral properties, including power distributions across the delta, theta, alpha, beta, and gamma bands. By combining the F-score method, based on Analysis of Variance (ANOVA), Mutual Information assessment, and random forest techniques, we identified 27 highly discriminative features from the original set of 171 extracted features. We developed and evaluated two novel architectures: an LSTM-based model and a Transformer-based model. Both incorporated attention mechanisms and multi-scale temporal convolutional networks to effectively capture the complex patterns in EEG signals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>While the LSTM model performed strongly with 95.65% accuracy (\u00b1 0.16%), 96.28% sensitivity (\u00b1 0.59%), and 95.26% specificity (3.84%), our Transformer-based model achieved even more impressive results: 98.20% accuracy (\u00b1 0.20%), 98.11% sensitivity (\u00b1 0.28%), and 98.12% specificity (\u00b1 0.40%) by using k-fold cross-validation. The Transformer-based was achieved 76.95% in Leave-One-Subject-Out (LOSO) cross-validation. These findings highlight the potential of transformer architectures to detect the subtle neurophysiological markers of schizophrenia in EEG recordings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Our approach could eventually provide clinicians with an objective tool to support earlier and more accurate diagnosis of schizophrenia, potentially improving treatment outcomes through timely intervention.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2026.1663906","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T04:43:14Z","timestamp":1782880994000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Transformer architecture for diagnosing schizophrenia disabilities through EEG analysis"],"prefix":"10.3389","volume":"17","author":[{"given":"Nizar","family":"Alsharif","sequence":"first","affiliation":[{"name":"Department of Computer Science, Al-baha University","place":["Albaha, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nadhem","family":"Ebrahim","sequence":"additional","affiliation":[{"name":"Department of Computer Science College of Engineering, University of Akron","place":["Akron, OH, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdullah H.","family":"Al-Nefaie","sequence":"additional","affiliation":[{"name":"Department of Quantitative Methods, School of Business, King Faisal University","place":["Al-Ahsa, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyad A. T.","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Faculty of Data Science and Information Technology, INTI International University","place":["Nilai, Negeri Sembilan, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theyazn H. H.","family":"Aldhyani","sequence":"additional","affiliation":[{"name":"Applied College, King Faisal University","place":["Al-Ahsa, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130353","article-title":"Deep neurocomputational fusion for ASD diagnosis using multi-domain EEG analysis","volume":"641","author":"Abdur Rasool","year":"2025","journal-title":"Neurocomputing"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2023.103949","article-title":"Fusion of pattern-based and statistical features for schizophrenia detection from EEG signals","volume":"112","author":"Agarwal","year":"2023","journal-title":"Med. Eng. Phys."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102917","article-title":"Schizophrenia recognition based on the phase space dynamic of EEG signals and graphical features","volume":"69","author":"Akbari","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"B4","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/s0165-0327(98)00142-6","article-title":"The emerging epidemiology of hypomania and bipolar II disorder","volume":"50","author":"Angst","year":"1998","journal-title":"J. Affect. Disord."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2026.110049","article-title":"HAMD-Net: A biologically informed hybrid attention model for EEG classification of multiple neurological disorders","volume":"120","author":"Aslam","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"B6","first-page":"69","article-title":"Cross-subject and cross-session continual adaptation of EEG signals using temporal context encoding","author":"Aslam","year":"2025"},{"key":"B7","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s13246-021-01083-2","article-title":"A deep learning approach in automated detection of schizophrenia using scalogram images of EEG signals","volume":"45","author":"Aslan","year":"2022","journal-title":"Phys. Eng. Sci. Med."},{"key":"B8","doi-asserted-by":"crossref","DOI":"10.4018\/978-1-5225-7598-6.ch037","article-title":"Data mining and knowledge discovery in databases","volume-title":"Advanced Methodologies and Technologies in Network Architecture, Mobile Computing, and Data Analytics","author":"Azevedo","year":"2019"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105570","article-title":"Detection of schizophrenia using hybrid of deep learning and brain effective connectivity image from electroencephalogram signal","volume":"146","author":"Bagherzadeh","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102039","article-title":"Advanced EEG-based learning approaches to predict schizophrenia: Promises and pitfalls","volume":"114","author":"Barros","year":"2021","journal-title":"Artif. Intell. Med."},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1109\/HealthCom46333.2019.9009437","article-title":"High-performance exclusion of schizophrenia using a novel machine learning method on EEG data","author":"Buettner","year":"2019"},{"key":"B12","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/978-981-15-5243-4_19","article-title":"EEG-based automated detection of schizophrenia using long short-term memory (LSTM) network","volume-title":"Advances in Machine Learning and Computational Intelligence","author":"Chandran","year":"2021"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1784","DOI":"10.1109\/tnsre.2021.3105669","article-title":"Classification of first-episode schizophrenia, chronic schizophrenia and healthy control based on brain network of mismatch negativity by graph neural network","volume":"29","author":"Chang","year":"2021","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B14","doi-asserted-by":"publisher","first-page":"13858","DOI":"10.1038\/s41598-018-32290-9","article-title":"Recognition of schizophrenia with regularized support vector machine and sequential region of interest selection using structural magneticresonance imaging","volume":"8","author":"Chin","year":"2018","journal-title":"Sci. Rep."},{"key":"B15","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1016\/j.schres.2021.05.018","article-title":"Going deep into schizophrenia with artificial intelligence","volume":"245","author":"Cortes-Briones","year":"2022","journal-title":"Schizophr. Res."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.1042814","article-title":"Neuroimaging in schizophrenia: A review article","volume":"16","author":"Dabiri","year":"2022","journal-title":"Front. Neurosci."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102525","article-title":"Schizophrenia detection technique using multivariate iterative filtering and multichannel EEG signals","volume":"67","author":"Das","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"B18","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.medengphy.2021.06.008","article-title":"Targeted muscle effort distribution with exercise robots: Trajectory and resistance effects","volume":"94","author":"De las Casas","year":"2021","journal-title":"Med. Eng. Phys."},{"key":"B19","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.medengphy.2021.05.017","article-title":"Discrimination capability of linear and nonlinear gait features in group classification","volume":"93","author":"de Mendon\u00e7a Mesquita","year":"2021","journal-title":"Med. Eng. Phys."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1038\/s41537-022-00231-1","article-title":"Machine learning algorithm unveils glutamatergic alterations in the post-mortem schizophrenia brain","volume":"8","author":"De Rosa","year":"2022","journal-title":"Schizophrenia"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1109\/TNSRE.2019.2913799","article-title":"EEG classification during scene free-viewing for schizophrenia detection","volume":"27","author":"Devia","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B22","unstructured":"EEG in schizophrenia"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104811","article-title":"Wavelet transforms for feature engineering in EEG data processing: an application on schizophrenia","volume":"85","author":"Gosala","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B24","volume-title":"Data Mining: Concepts and Techniques","author":"Han","year":"2016"},{"key":"B25","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1016\/j.inffus.2022.12.019","article-title":"Fusion of multivariate EEG signals for schizophrenia detection using CNN and machine learning techniques","volume":"92","author":"Hassan","year":"2023","journal-title":"Inf. Fusion"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11030285","article-title":"A review of machine learning and deep learning approaches on mental health diagnosis","volume":"11","author":"Iyortsuun","year":"2023","journal-title":"Healthcare (Basel)"},{"key":"B27","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/tpami.2017.2785313","article-title":"CROification: Accurate kernel classification with the efficiency of sparse linear SVM","volume":"41","author":"Kafai","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B28","doi-asserted-by":"publisher","first-page":"035005","DOI":"10.1088\/1361-6579\/acbc06","article-title":"SchizoNET: a robust and accurate Margenau-Hill timefrequency distribution based deep neural network model for schizophrenia detection using EEG signals","volume":"44","author":"Khare","year":"2023","journal-title":"Physiol. Meas."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0251842","article-title":"EEG microstate features for schizophrenia classification","volume":"16","author":"Kim","year":"2021","journal-title":"PloS One"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11142265","article-title":"EEG-based schizophrenia diagnosis through time series image conversion and deep learning","volume":"11","author":"Ko","year":"2022","journal-title":"Electronics"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.1016\/j.bbe.2020.05.008","article-title":"Schizophrenia detection using multivariate empirical mode decomposition and entropy measures from multichannel EEG signal","volume":"40","author":"Krishnan","year":"2020","journal-title":"Biocybern. Biomed. Eng."},{"key":"B32","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1007\/s00034-019-01212-z","article-title":"Comparative analysis of the fuzzy C-means and neuro-fuzzy systems for detecting retinal disease","volume":"39","author":"Kumar","year":"2020","journal-title":"Circuits Syst. Signal Process."},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18116099","article-title":"Schizophrenia: A survey of artificial intelligence techniques applied to detection and classification","volume":"18","author":"Lai","year":"2021","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"B34","doi-asserted-by":"publisher","first-page":"3037","DOI":"10.3390\/electronics10233037","article-title":"A survey on EEG signal processing techniques and machine learning: Applications to the neurofeedback of autobiographical memory deficits in schizophrenia","volume":"10","author":"Luj\u00e1n","year":"2021","journal-title":"Electronics"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.23959","article-title":"Neurobiology of schizophrenia: A comprehensive review","volume":"14","author":"Luvsannyam","year":"2022","journal-title":"Cureus"},{"key":"B36","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s10916-019-1400-8","article-title":"Detection of skin cancer using SVM, random forest and kNN classifiers","volume":"43","author":"Murugan","year":"2019","journal-title":"J. Med. Syst."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3390\/app9142870","article-title":"Deep convolutional neural network model for automated diagnosis of schizophrenia using EEG signals","volume":"9","author":"Oh","year":"2019","journal-title":"Appl. Sci."},{"key":"B38","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.schres.2020.09.009","article-title":"Differentiating patients with schizophrenia from healthy controls by hippocampal subfields using radiomics","volume":"223","author":"Park","year":"2020","journal-title":"Schizophr. Res."},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2021.645952","article-title":"Data augmentation: Using channel-level recombination to improve classification performance for motor imagery EEG","volume":"15","author":"Pei","year":"2021","journal-title":"Front. Hum. Neurosci."},{"key":"B40","first-page":"511","article-title":"Communications in Computer and Information Science","volume-title":"Cognitive Systems and Information Processing, ICCSIP 2021","author":"Pei","year":"2022"},{"key":"B41","doi-asserted-by":"publisher","first-page":"026038","DOI":"10.1088\/1741-2552\/adbfc0","article-title":"Toward the enhancement of affective brain\u2013computer interfaces using dependence within EEG series","volume":"22","author":"Pei","year":"2025","journal-title":"J. Neural Eng."},{"key":"B42","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1109\/JBHI.2019.2941222","article-title":"A multi-domain connectome convolutional neural network for identifying schizophrenia from EEG connectivity patterns","volume":"24","author":"Phang","year":"2019","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2026.106417","article-title":"Challenges in translating AI-driven ASD\/ADHD diagnosis: A methodological systematic review","volume":"214","author":"Rasool","year":"2026","journal-title":"Int. J. Med. Inf."},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105554","article-title":"An overview of artificial intelligence techniques for diagnosis of schizophrenia based on magnetic resonance imaging modalities: Methods, challenges, and future works","volume":"146","author":"Sadeghi","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105206","article-title":"SCZ-SCAN: An automated schizophrenia detection system from electroencephalogram signals","volume":"86","author":"Sahu","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116230","article-title":"Automatic identification of schizophrenia using EEG signals based on discrete wavelet transform and RLNDiP technique with ANN","volume":"192","author":"Sairamya","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2022.893788","article-title":"Machine learning techniques for the diagnosis of schizophrenia based on event-related potentials","volume":"16","author":"Santos Febles","year":"2022","journal-title":"Front. Neuroinform."},{"key":"B48","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s11571-020-09655-w","article-title":"Automated detection of schizophrenia using optimal wavelet-based l 1 norm features extracted from single-channel EEG","volume":"15","author":"Sharma","year":"2021","journal-title":"Cognit. Neurodyn."},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2111.11298","article-title":"Novel EEG based schizophrenia detection with IoMT framework for smart healthcare","author":"Sharma","year":"2021","journal-title":"arXiv"},{"key":"B50","doi-asserted-by":"publisher","first-page":"03TR01","DOI":"10.1088\/1361-6579\/acb24d","article-title":"Automated detection of schizophrenia using deep learning: A review for the last decade","volume":"44","author":"Sharma","year":"2023","journal-title":"Physiol. Meas."},{"key":"B51","first-page":"139","article-title":"Early diagnosis of schizophrenia in EEG signals using one dimensional transformer model","author":"Shoeibi","year":"2024"},{"key":"B52","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.inffus.2022.12.010","article-title":"Diagnosis of brain diseases in fusion of neuroimaging modalities using deep learning: A review","volume":"93","author":"Shoeibi","year":"2023","journal-title":"Inf. Fusion"},{"key":"B53","article-title":"Automatic diagnosis of schizophrenia using EEG signals and CNN-LSTM models","author":"Shoeibi","year":"2021","journal-title":"arXiv"},{"key":"B54","first-page":"874","article-title":"Deep learning-based diagnosis of schizophrenia","volume":"12","author":"Sridhar","year":"2021","journal-title":"Turk. J. Comput. Math. Educ. (TURCOMAT)"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106225","article-title":"A deep learning based model using RNN-LSTM for the detection of schizophrenia from EEG data","volume":"151","author":"Supakar","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10040493","article-title":"A narrative review of speech and EEG features for schizophrenia detection: Progress and challenges","volume":"10","author":"Teixeira","year":"2023","journal-title":"Bioengineering"},{"key":"B57","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1080\/078538902321117733","article-title":"Genetic influences on brain structure","volume":"4","author":"Thompson","year":"2001","journal-title":"Nat. Neurosci."},{"key":"B58","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1016\/j.neuroimage.2012.02.018","article-title":"The Human Connectome Project: A data acquisition perspective","volume":"62","author":"Van Essen","year":"2012","journal-title":"Neuroimage"},{"key":"B59","doi-asserted-by":"publisher","first-page":"45094","DOI":"10.4088\/jcp.ms21078com5","article-title":"The epidemiology and global burden of schizophrenia","volume":"84","author":"Velligan","year":"2023","journal-title":"J. Clin. Psychiatry"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.31083\/j.jin2301018","article-title":"Fusion of multi-domain EEG signatures improves emotion recognition","volume":"23","author":"Wang","year":"2024","journal-title":"J. Integr. Neurosci."},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12957","article-title":"Application of local configuration pattern Alazzaw\u0131 et\u00a0al. (2024)","volume":"41","author":"WeiKoh","year":"2022","journal-title":"Expert Syst."},{"key":"B62","first-page":"68","article-title":"EEG signals feature extraction and artificial neural networks classification for the diagnosis of schizophrenia","author":"Zhang","year":"2020"},{"key":"B63","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1109\/TAFFC.2017.2712143","article-title":"Identifying stable patterns over time for emotion recognition from EEG","volume":"10","author":"Zheng","year":"2019","journal-title":"IEEE Trans. Affect. Comput."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1663906\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T04:43:38Z","timestamp":1782881018000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1663906\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":63,"alternative-id":["10.3389\/fphys.2026.1663906"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1663906","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,1]]},"article-number":"1663906"}}