Machine Learning Approach to Predict ADHD Types using EEG Signal Data

Early diagnosis and treatment of attention deficit hyperactivity disorder (ADHD) in children is essential for their overall wellbeing. A recent study introduced a method to classify ADHD as types. Machine Learning (ML) algorithms have revolutionized medical field, offering unprecedented potential in the diagnosis and categorization of complex conditions like ADHD and its subtypes. The proposed approach utilized supervised machine learning, specifically the K-Nearest Neighbour, Decision Tree and Random Forest using Conners data as input variables. EEG (Electroencephalography) signal data was employed to identify the specific type of ADHD. The proposed work introduces machine learning algorithms designed for ADHD classification, assessed using various statistical parameters including recall, precision, accuracy, and F1-score. Using Conners data, the results showed a 79.51% categorization accuracy. This outcome strongly underscores the significance of Conners data in effectively categorizing ADHD, highlighting its pivotal role in the process.