Kim Jun Won, Kim Bung-Nyun, Kim Johanna Inhyang, Yang Chan-Mo, Kwon Jaehyung
Department of Psychiatry, Daegu Catholic University School of Medicine, Daegu, Republic of Korea.
Division of Child and Adolescent Psychiatry, Department of Psychiatry, Seoul National University Hospital, Seoul, Republic of Korea.
Neuropsychiatr Dis Treat. 2025 Feb 13;21:271-279. doi: 10.2147/NDT.S509094. eCollection 2025.
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.
注意缺陷多动障碍（ADHD）是一种神经发育疾病，在及时准确诊断方面存在挑战。本研究评估将脑电图（EEG）数据与机器学习技术相结合以提高ADHD诊断准确性的有效性。
共有168名参与者，包括107名ADHD患者和61名神经典型（NT）个体，使用《儿童情感障碍和精神分裂症现患与终生版韩国版》（K-SADS-PL-K）进行评估。对来自19个通道的EEG数据在五个频段进行分析：δ波（1 - 4赫兹）、θ波（4 - 8赫兹）、α波（8 - 12赫兹）、β波（12 - 30赫兹）和γ波（30 - 51赫兹）。采用极端梯度提升（XGBoost）分类器进行分类，并使用留一法交叉验证（LOSO）来确保模型的稳健性。
通过30秒分段进行的数据增强为ADHD生成了2434个EEG片段，为NT生成了1060个。XGBoost模型的测试准确率达到90.81%，F1分数为0.9347。使用SHAP（SHapley值相加解释）值进行的特征重要性分析确定，中β频率特征，特别是来自O1电极部位的特征，是分类的重要贡献因素。
基于EEG的机器学习模型，如XGBoost分类器，显示出作为ADHD诊断的非侵入性工具的潜力，具有高准确性和可解释性。这种方法的新颖之处在于将SHAP分析与数据增强技术和LOSO交叉验证相结合，确保了可解释性和稳健的泛化能力。建议未来使用更大的数据集和多样化的人群进行研究，以验证研究结果并探索临床应用。
