Ang Yi Herng Universiti Teknologi PETRONAS
This project introduces an AI-powered diagnostic tool for Attention Deficit Hyperactivity Disorder (ADHD) using EEG-based brain connectivity analysis. It leverages a novel method called Efficient Effective Connectivity (EEC) in combination with Convolutional Neural Networks (CNN) to classify ADHD and control groups with improved accuracy. In comparison to traditional metrics such as Directed Transfer Function (DTF) and Partial Directed Coherence (PDC), the proposed EEC approach achieved the highest accuracy of 82.73% ± 1.46 in 10-fold cross-validation. This innovation provides a more objective, consistent, and data-driven solution to ADHD diagnosis, addressing the limitations of current subjective assessment methods and contributing to advancements in computational neuroscience and AI-assisted healthcare.
