Task-Related and Resting-State EEG Classification of Adult Patients with ADHD Using Machine Learning

Attention-deficit hyperactivity disorder (ADHD) is a prevalent psychological disorder characterized by attention deficits and high impulsivity, impacting both adults and children. This study aims to assess the effectiveness of task-related electroencephalography (EEG) and resting-state EEG in distinguishing adult patients with ADHD from healthy controls. Machine learning techniques are employed to classify the patients’ status based on EEG features. The primary objective of this investigation is to determine whether the classification performance of task-based EEG data recorded during a stop-signal task recruiting inhibitory processes outperforms that of resting-state EEG data. We hypothesize that task-based EEG data contains valuable biomarkers related to inhibitory control that can be utilized to detect ADHD, whereas resting-state EEG data does not possess such useful biomarkers.