Electroencephalogram (EEG) Based Prediction of Attention Deficit Hyperactivity Disorder (ADHD) Using Machine Learning

• Published in: Neuropsychiatric disease and treatment Vol. 21; pp. 271 - 279
• Main Authors: Kim, Jun Won, Kim, Bung-Nyun, Kim, Johanna Inhyang, Yang, Chan-Mo, Kwon, Jaehyung
• Format: Journal Article
• Language: English
• Published: New Zealand Taylor & Francis Ltd 01.01.2025; Dove; Dove Medical Press
• Subjects: Accuracy; Adults; Affective disorders; Algorithms; Attention deficit hyperactivity disorder; attention deficit hyperactivity disorder (adhd); Brain research; Classification; Diagnosis; EEG; Electroencephalography; Hyperactivity; Impulsivity; Learning algorithms; Machine learning; Mental disorders; Neurodevelopmental disorders; Original Research; Python; quantitative electroencephalography; Schizophrenia; Wavelet transforms; ADHD; diagnosis; quantitative electroencephalography; attention deficit hyperactivity disorder; machine learning
• ISSN: 1176-6328; 1178-2021
• DOI: 10.2147/NDT.S509094

Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental condition with challenges in timely and accurate diagnosis. This study evaluates the effectiveness of combining electroencephalogram (EEG) data with machine learning techniques to enhance ADHD diagnostic accuracy. A total of 168 participants, comprising 107 ADHD and 61 neurotypical (NT) individuals, were assessed using the Kiddie Schedule for Affective Disorders and Schizophrenia Present and Lifetime Version Korean Version (K-SADS-PL-K). EEG data from 19 channels were analyzed across five frequency bands: delta (1-4 hz), theta (4-8 hz), alpha (8-12 hz), beta (12-30 hz), and gamma (30-51 hz). The Extreme Gradient Boosting (XGBoost) classifier was employed for classification, and Leave-One-Subject-Out (LOSO) cross-validation was used to ensure model robustness. Data augmentation through 30-second segmentations generated 2434 EEG segments for ADHD and 1060 for NT. The XGBoost model achieved a test accuracy of 90.81% and an F1-score of 0.9347. Feature importance analysis using SHAP (SHapley Additive exPlanations) values identified middle beta frequency features, particularly from the O1 electrode site, as significant contributors to classification. EEG-based machine learning models, such as the XGBoost classifier, show potential as non-invasive tools for ADHD diagnosis, offering high accuracy and interpretability. The novelty of this approach lies in combining SHAP analysis with data augmentation techniques and LOSO cross-validation, ensuring both explainability and robust generalizability. Future research with larger datasets and diverse populations is recommended to validate findings and explore clinical applications.