{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:57:52Z","timestamp":1773248272112,"version":"3.50.1"},"reference-count":20,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan","award":["AP26105045 \u201cDevelopment of artificial intelligence models and algorithms for analyzing social signals in children with autism\u201d"],"award-info":[{"award-number":["AP26105045 \u201cDevelopment of artificial intelligence models and algorithms for analyzing social signals in children with autism\u201d"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>This study proposes an interpretable hybrid deep learning framework for classifying attention deficit hyperactivity disorder (ADHD) using EEG signals recorded during cognitively demanding tasks. The core architecture integrates convolutional neural networks (CNNs), gated recurrent units (GRUs), and long short-term memory (LSTM) layers to jointly capture spatial and temporal dynamics. In addition to the final hybrid architecture, the CNN\u2013GRU\u2013LSTM model alone demonstrates excellent accuracy (99.63%) with minimal variance, making it a strong baseline for clinical applications. To evaluate the role of global attention mechanisms, transformer encoder models with two and three attention blocks, along with a spatiotemporal transformer employing 2D positional encoding, are benchmarked. A hybrid CNN\u2013RNN\u2013transformer model is introduced, combining convolutional, recurrent, and transformer-based modules into a unified architecture. To enhance interpretability, SHapley Additive exPlanations (SHAP) are employed to identify key EEG channels contributing to classification outcomes. Experimental evaluation using stratified five-fold cross-validation demonstrates that the proposed hybrid model achieves superior performance, with average accuracy exceeding 99.98%, F1-scores above 0.9999, and near-perfect AUC and Matthews correlation coefficients. In contrast, transformer-only models, despite high training accuracy, exhibit reduced generalization. SHAP-based analysis confirms the hybrid model\u2019s clinical relevance. This work advances the development of transparent and reliable EEG-based tools for pediatric ADHD screening.<\/jats:p>","DOI":"10.3390\/a18080453","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T08:45:18Z","timestamp":1753173918000},"page":"453","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Hybrid CNN\u2013GRU\u2013LSTM Algorithm with SHAP-Based Interpretability for EEG-Based ADHD Diagnosis"],"prefix":"10.3390","volume":"18","author":[{"given":"Makbal","family":"Baibulova","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Department of Information Systems, L. N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8397-8914","authenticated-orcid":false,"given":"Murat","family":"Aitimov","sequence":"additional","affiliation":[{"name":"Educational Program of Informatics and Information and Communication Technologies, Korkyt Ata Kyzylorda University, Kyzylorda 120000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roza","family":"Burganova","sequence":"additional","affiliation":[{"name":"Department of Social Work and Tourism, Esil University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lazzat","family":"Abdykerimova","sequence":"additional","affiliation":[{"name":"Department of Information Systems, M. Kh. Dulaty Taraz University, Taraz 080000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umida","family":"Sabirova","sequence":"additional","affiliation":[{"name":"Department of Sociology, National University of Uzbekistan Named After Mirzo Ulugbek, Tashkent 100174, Uzbekistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanat","family":"Seitakhmetova","sequence":"additional","affiliation":[{"name":"Department of Computer Modeling and Information Technology, East Kazakhstan University Named After S. Amanzholov, Ust-Kamenogorsk 070000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gulsiya","family":"Uvaliyeva","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Sh. Yessenov Caspian University of Technology and Engineering, Aktau 130000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maksym","family":"Orynbassar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Sh. Yessenov Caspian University of Technology and Engineering, Aktau 130000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aislu","family":"Kassekeyeva","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Department of Information Systems, L. N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murizah","family":"Kassim","sequence":"additional","affiliation":[{"name":"Computer Engineering, University Technology MARA, Shah Alam 40450, Selangor, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1111\/jcpp.12381","article-title":"Annual Research Review: A Meta-Analysis of the Worldwide Prevalence of Mental Disorders in Children and Adolescents","volume":"56","author":"Polanczyk","year":"2015","journal-title":"J. Child Psychol. Psychiatry"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/j.neubiorev.2021.01.022","article-title":"The World Federation of ADHD International Consensus Statement: 208 Evidence-Based Conclusions about the Disorder","volume":"128","author":"Faraone","year":"2021","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1007\/s00787-018-1256-3","article-title":"Barriers and Facilitators to Understanding of ADHD in Primary Care: A Mixed-Method Systematic Review","volume":"28","author":"French","year":"2019","journal-title":"Eur. Child Adolesc. Psychiatry"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1177\/1550059420946648","article-title":"Development of Frontal EEG Differences between Eyes-Closed and Eyes-Open Resting Conditions in Children: Data from a Single-Channel Dry-Sensor Portable Device","volume":"52","author":"Johnstone","year":"2021","journal-title":"Clin. EEG Neurosci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1177\/15500594221086195","article-title":"Phase-Amplitude Coupling Brain Networks in Children with Attention-Deficit\/Hyperactivity Disorder","volume":"53","author":"Liu","year":"2022","journal-title":"Clin. EEG Neurosci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e12891","DOI":"10.1111\/desc.12891","article-title":"Modeling Development of Frontal Electroencephalogram (EEG) Asymmetry: Sex Differences and Links with Temperament","volume":"23","author":"Gartstein","year":"2020","journal-title":"Dev. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Neurofeedback Collaborative Group (2023). Neurofeedback for Attention-Deficit\/Hyperactivity Disorder: 25-Month Follow-Up of Double-Blind Randomized Controlled Trial. J. Am. Acad. Child Adolesc. Psychiatry, 62, 435\u2013446.","DOI":"10.1016\/j.jaac.2022.07.862"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"051001","DOI":"10.1088\/1741-2552\/ab260c","article-title":"Deep Learning-Based Electroencephalography Analysis: A Systematic Review","volume":"16","author":"Roy","year":"2019","journal-title":"J. Neural Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"031001","DOI":"10.1088\/1741-2552\/ab0ab5","article-title":"Deep Learning for Electroencephalogram (EEG) Classification Tasks: A Review","volume":"16","author":"Craik","year":"2019","journal-title":"J. Neural Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1177\/15500594231193511","article-title":"The Hybrid Deep Learning Model for Identification of Attention-Deficit\/Hyperactivity Disorder Using EEG","volume":"55","author":"Chugh","year":"2024","journal-title":"Clin. EEG Neurosci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"33570","DOI":"10.1109\/ACCESS.2023.3264266","article-title":"Optimal channels and features selection based ADHD detection from EEG signal using statistical and machine learning techniques","volume":"11","author":"Maniruzzaman","year":"2023","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"715","DOI":"10.9758\/cpn.2022.20.4.715","article-title":"Automatic diagnosis of attention deficit hyperactivity disorder with continuous wavelet transform and convolutional neural network","volume":"20","author":"Altun","year":"2022","journal-title":"Clin. Psychopharmacol. Neurosci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2315","DOI":"10.1007\/s12559-024-10302-3","article-title":"Efficient deep learning approach for diagnosis of attention-deficit\/hyperactivity disorder in children based on EEG Signals","volume":"16","author":"Jahani","year":"2024","journal-title":"Cogn. Comput."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Khare, S.K., and Acharya, U.R. (2023). An explainable and interpretable model for attention deficit hyperactivity disorder in children using EEG signals. Comput. Biol. Med., 155.","DOI":"10.1016\/j.compbiomed.2023.106676"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Manjunatha, H., and Esfahani, E.T. (2021, January 4\u20136). Extracting interpretable EEG features from a deep learning model to assess the quality of human-robot co-manipulation. Proceedings of the 2021 10th International IEEE\/EMBS Conference on Neural Engineering (NER), Online.","DOI":"10.1109\/NER49283.2021.9441134"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"200062","DOI":"10.1016\/j.sasc.2023.200062","article-title":"A multi-dimensional hybrid CNN-BiLSTM framework for epileptic seizure detection using electroencephalogram signal scrutiny","volume":"5","author":"KR","year":"2023","journal-title":"Syst. Soft Comput."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yang, D., Liu, Y., Zhou, Z., Yu, Y., and Liang, X. (2020). Decoding visual motions from EEG using attention-based RNN. Appl. Sci., 10.","DOI":"10.3390\/app10165662"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e12827","DOI":"10.1002\/eng2.12827","article-title":"Enhancing EEG signals classification using LSTM-CNN architecture","volume":"6","author":"Omar","year":"2024","journal-title":"Eng. Rep."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1109\/JSAS.2025.3552546","article-title":"Electroencephalogram and Event-Related Potential in Mild Cognitive Impairment: Recent Developments in Signal Processing, Machine Learning, and Deep Learning","volume":"2","author":"Azami","year":"2025","journal-title":"IEEE J. Sel. Areas Sensors"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, Z., and Li, X. (2019, January 22\u201324). Use transfer learning to promote identification ADHD children with EEG recordings. Proceedings of the 2019 Chinese Automation Congress (CAC), Hangzhou, China.","DOI":"10.1109\/CAC48633.2019.8997426"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/8\/453\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:13:37Z","timestamp":1760033617000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/8\/453"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,22]]},"references-count":20,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["a18080453"],"URL":"https:\/\/doi.org\/10.3390\/a18080453","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,22]]}}}