Computational Decision Support System for ADHD Identification

• Published in: International journal of automation and computing Vol. 18; no. 2; pp. 233 - 255
• Main Authors: De Silva, Senuri, Dayarathna, Sanuwani, Ariyarathne, Gangani, Meedeniya, Dulani, Jayarathna, Sampath, Michalek, Anne M. P.
• Format: Journal Article
• Language: English
• Published: Beijing Institute of Automation, Chinese Academy of Sciences 01.04.2021; Springer Nature B.V
• Subjects: Accuracy; Adults; Age groups; Artificial neural networks; Attention deficit hyperactivity disorder; Automation; CAE) and Design; Classification; Computer Applications; Computer science; Computer-Aided Engineering (CAD; Control; Decision making; Decision support systems; Engineering; Eye movements; Feature extraction; Feature selection; Health informatics; Hyperactivity; Identification; Magnetic resonance imaging; Mechatronics; Mental disorders; Model accuracy; Neural networks; Neurosciences; Physiology; Research Article; Robotics; System effectiveness; ADHD-Care decision support system (DDS); Attention deficit/hyperactivity disorder (ADHD); ensembled model; convolutional neural network (CNN); seed-based correlation; fixations; functional magnetic resonance imaging (fMRI); saccades; eye movement data; default mode network (DMN)
• ISSN: 1476-8186; 2153-182X; 1751-8520; 2153-1838
• DOI: 10.1007/s11633-020-1252-1

Attention deficit/hyperactivity disorder (ADHD) is a common disorder among children. ADHD often prevails into adulthood, unless proper treatments are facilitated to engage self-regulatory systems. Thus, there is a need for effective and reliable mechanisms for the early identification of ADHD. This paper presents a decision support system for the ADHD identification process. The proposed system uses both functional magnetic resonance imaging (fMRI) data and eye movement data. The classification processes contain enhanced pipelines, and consist of pre-processing, feature extraction, and feature selection mechanisms. fMRI data are processed by extracting seed-based correlation features in default mode network (DMN) and eye movement data using aggregated features of fixations and saccades. For the classification using eye movement data, an ensemble model is obtained with 81% overall accuracy. For the fMRI classification, a convolutional neural network (CNN) is used with 82% accuracy for the ADHD identification. Both ensemble models are proved for overfitting avoidance.