EEG-Based Machine Learning Techniques for ADHD Detection: A Review of Datasets, Feature Extraction Methods, and Classification Algorithms

Author

Dr. V. Maria Antoniate Martin, Sri Ramanaa Balaaji B

Abstract

 Attention-Deficit/Hyperactivity Disorder (ADHD) is a common neurodevelopmental condition that disrupts attention, impulse control and executive function, yet it is still diagnosed largely through subjective behavioral assessment. Pairing electroencephalography (EEG) with machine learning has become a popular route toward more objective markers. In this review we compare fifteen EEG-based ADHD studies published between 2020 and 2025 on three points: the datasets they used, how they pulled useful features out of the EEG signal, and which classifiers they trained to separate ADHD from control participants. Feature extraction turns out to be very varied, running from handcrafted statistical and nonlinear measures to representations learned automatically by deep networks, and the classifiers range from support vector machines to graph-based neural networks. Two structural problems stand out, though. More than half of the studies draw on one and the same public dataset, and their validation strategies differ so much that the reported accuracies, several of them above 99%, cannot be lined up fairly against each other. We set out these problems and suggest where future work should head: larger and more varied datasets, standardized subject-level validation, and closer attention to interpretability. All three are needed before EEG-based ADHD detection can be trusted in clinical practice.

Keywords

Attention-Deficit/Hyperactivity Disorder (ADHD); Electroencephalography (EEG); Machine Learning; Feature Extraction; EEG Datasets; Classification Algorithms

Full Text:

Download Paper PDF

References

[1] Ahire, N. K. (2025). Attention-driven deep learning framework for EEG analysis in ADHD detection. Applied Neuropsychology: Child. Advance online publication. https://doi.org/10.1080/21622965.2025.2512919

[2] Alim, A., & Imtiaz, M. H. (2023). Automatic identification of children with ADHD from EEG brain waves. Signals, 4(1), 193–205. https://doi.org/10.3390/signals4010010

[3] Bakhtyari, M., & Mirzaei, S. (2022). ADHD detection using dynamic connectivity patterns of EEG data and ConvLSTM with attention framework. Biomedical Signal Processing and Control, 76, 103708. https://doi.org/10.1016/j.bspc.2022.103708

[4] Bansal, J., Gangwar, G., Aljaidi, M., Alkoradees, A., & Singh, G. (2025). EEG-based ADHD classification using autoencoder feature extraction and ResNet with double augmented attention mechanism. Brain Sciences, 15(1), 95. https://doi.org/10.3390/brainsci15010095

[5] Dubreuil-Vall, L., Ruffini, G., & Camprodon, J. A. (2020). Deep learning convolutional neural networks discriminate adult ADHD from healthy individuals on the basis of event-related spectral EEG. Frontiers in Neuroscience, 14, 251. https://doi.org/10.3389/fnins.2020.00251

[6] Ekhlasi, A., Nasrabadi, A. M., & Mohammadi, M. R. (2021). Classification of the children with ADHD and healthy children based on the directed phase transfer entropy of EEG signals. Frontiers in Biomedical Technologies, 8(2), 115–122. https://doi.org/10.18502/fbt.v8i2.6515

[7] Karabiber Cura, Ö., Akan, A., & Kocaaslan Atlı, S. (2024). Detection of attention deficit hyperactivity disorder based on EEG feature maps and deep learning. Biocybernetics and Biomedical Engineering, 44(3), 596–613. https://doi.org/10.1016/j.bbe.2024.07.003

[8] Kim, J., & Yang, S. (2025). Electroencephalogram (EEG) based prediction of attention deficit hyperactivity disorder (ADHD) using machine learning [Conference abstract, EPV0351]. European Psychiatry, 68(Suppl. 1). https://doi.org/10.1192/j.eurpsy.2025.1155

[9] Latifi, B., Amini, A., & Nasrabadi, A. M. (2024). Siamese based deep neural network for ADHD detection using EEG signal. Computers in Biology and Medicine, 182, 109092. https://doi.org/10.1016/j.compbiomed.2024.109092

[10] Li, L., Guo, X., Yang, Z., Zhao, Y., Liu, X., Yang, J., Chen, Y., Peng, X., & Han, L. (2025). ADHD detection from EEG signals using GCN based on multi-domain features. Frontiers in Neuroscience, 19, 1561994. https://doi.org/10.3389/fnins.2025.1561994

[11] Maniruzzaman, M., Shin, J., Hasan, M. A. M., & Yasumura, A. (2022). Efficient feature selection and machine learning based ADHD detection using EEG signal. Computers, Materials & Continua, 72(3), 5179–5195. https://doi.org/10.32604/cmc.2022.028339

[12] Moghaddari, M., Lighvan, M. Z., & Danishvar, S. (2020). Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG. Computer Methods and Programs in Biomedicine, 197, 105738. https://doi.org/10.1016/j.cmpb.2020.105738

[13] Sathiya, E., Rao, T. D., & Kumar, T. S. (2024). Gabor filter-based statistical features for ADHD detection. Frontiers in Human Neuroscience, 18, 1369862. https://doi.org/10.3389/fnhum.2024.1369862

[14] Sharma, Y., & Singh, B. K. (2023). Attention deficit hyperactivity disorder detection in children using multivariate empirical EEG decomposition approaches: A comprehensive analytical study. Expert Systems with Applications, 213, 119219. https://doi.org/10.1016/j.eswa.2022.119219

[15] TaghiBeyglou, B., Shahbazi, A., Bagheri, F., Akbarian, S., & Jahed, M. (2022). Detection of ADHD cases using CNN and classical classifiers of raw EEG. Computer Methods and Programs in Biomedicine Update, 2, 100080. https://doi.org/10.1016/j.cmpbup.2022.100080