Análise do sinal de EEG para auxílio clínico na detecção de TDAH em crianças

Abstract

Attention Deficit Hyperactivity Disorder (ADHD) is one of the most commonly diagnosed psychiatric disorders in childhood, significantly affecting children’s behavior and development. If ADHD is not identified and treated appropriately, it can result in serious consequences in adulthood, ranging from poor academic and professional performance to substance abuse. Despite advances in research on the topic, ADHD diagnosis still has limitations, as it relies primarily on the observation of behavioral symptoms. The electroencephalogram (EEG) has proven to be a promising alternative for identifying mental disorders, as it allows for the monitoring of brain waves, providing direct information about an individual’s cognitive activity. In this context, this work aims to analyze the feasibility of using EEG to identify ADHD in children. To this end, robust preprocessing techniques were applied and tested using SVM, KNN, and Random Forest machine learning models. Following the proposed methodology, this study concludes the superiority of the KNN model with 98.91classifying EEG waves of children with ADHD.