Automatic identification of ADHD children during visual attention task using variable length EEG

Abstract

neuropsychiatric disorders affect millions of people of all ages worldwide. Attention deficit/Hyperactivity Disorder (ADHD), a typical neurodevelopmental disorder, deteriorates the performance of children in family and school settings thereby, hindering typical brain development. ADHD children, in most cases, are predominantly inattentive. In this research, automatic identification of neuronal patterns in ADHD children undergoing visual continuous performance tasks (CPT) is used to successfully differentiate between ADHD and typically developing children. The proposed methodology utilizes wavelet packet decomposition to extract relative energy from different EEG sub-bands, namely-delta (0.5- 4 Hz) theta (4-8 Hz), alpha (8-13 Hz), beta1 (13-20 Hz), beta2 (20-30 Hz) and gamma (>30 Hz). The obtained feature from all bands is then passed to the Support Vector Machine (SVM) for the classification of children as normal and those with ADHD. The performance of the algorithm is assessed by following performance parameters, accuracy, sensitivity, specificity, and area under the receiver operating characteristic (AUROC) curve. While testing the classification performance keeping the relative energy of individual bands in feature space, it is observed that between groups difference in normal and ADHD is much higher in high-frequency bands i.e., beta and gamma compared to low-frequency bands. However, all other bands are interacting features that performed well along with the relevant features (beta and gamma energy bands, here). The area under the curve obtained with a subject-independent approach and combined EEG sub-band's relative energy in feature space is found to be 0.99.