Siamese based deep neural network for ADHD detection using EEG signal

Abstract

Background: Detecting Attention-Deficit/Hyperactivity Disorder (ADHD) in children is crucial for timely intervention and personalized treatment.

Objective: This study aims to utilize deep learning techniques to analyze brain maps derived from Power Spectral Density (PSD) of Electroencephalography (EEG) signals in pediatric subjects for ADHD detection.

Methods: We employed a Siamese-based Convolutional Neural Network (CNN) to analyze EEG-based brain maps. Gradient-weighted class activation mapping (Grad-CAM) was used as an explainable AI (XAI) visualization method to identify significant features.

Results: The CNN model achieved a high classification accuracy of 99.17 %. Grad-CAM analysis revealed that PSD features from the theta band of the frontal and occipital lobes are effective discriminators for distinguishing children with ADHD from healthy controls.

Conclusion: This study demonstrates the effectiveness of deep learning in ADHD detection and highlights the importance of regional PSD metrics in accurate classification. By utilizing Grad-CAM, we elucidate the discriminative power of specific brain regions and frequency bands, thereby enhancing the understanding of ADHD neurobiology for improved diagnostic precision in pediatric populations.

Keywords: ADHD detection; EEG brain maps; Explainable AI; Gradient-weighted class activation mapping; Power spectral density; Siamese CNN.