A Hybrid CNN–GRU–LSTM Algorithm with SHAP-Based Interpretability for EEG-Based ADHD Diagnosis

Baibulova M. Aitimov M. Burganova R. Abdykerimova L. Sabirova U. Seitakhmetova Z. Uvaliyeva G. Orynbassar M. Kassekeyeva A. Kassim M.
August 2025 Multidisciplinary Digital Publishing Institute (MDPI)

Algorithms
2025 #18 Issue 8

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–GRU–LSTM 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–RNN–transformer 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’s clinical relevance. This work advances the development of transparent and reliable EEG-based tools for pediatric ADHD screening.

ADHD , CNN-GRU-LSTM , EEG , hybrid deep learning , SHAP , transformer

Text of the article Перейти на текст статьи

Faculty of Information Technology, Department of Information Systems, L. N. Gumilyov, Eurasian National University, Astana, 010000, Kazakhstan
Educational Program of Informatics and Information and Communication Technologies, Korkyt Ata Kyzylorda University, Kyzylorda, 120000, Kazakhstan
Department of Social Work and Tourism, Esil University, Astana, 010000, Kazakhstan
Department of Information Systems, M. Kh. Dulaty Taraz University, Taraz, 080000, Kazakhstan
Department of Sociology, National University of Uzbekistan Named After Mirzo Ulugbek, Tashkent, 100174, Uzbekistan
Department of Computer Modeling and Information Technology, East Kazakhstan University Named After S. Amanzholov, Ust-Kamenogorsk, 070000, Kazakhstan
Department of Computer Science, Sh. Yessenov Caspian University of Technology and Engineering, Aktau, 130000, Kazakhstan
Computer Engineering, University Technology MARA, Selangor, Shah Alam, 40450, Malaysia

Faculty of Information Technology
Educational Program of Informatics and Information and Communication Technologies
Department of Social Work and Tourism
Department of Information Systems
Department of Sociology
Department of Computer Modeling and Information Technology
Department of Computer Science
Computer Engineering

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026