Conference Details

Abstract :

Attention deficit and hyperactivity disorder (ADHD) is the most concerning developmental disorder which is affecting kids and adolescents both around the world. The main symptoms of ADHD comprises of absent mindedness, fidgeting, poor cognitive skills, impulsive tendencies, hyperactivity etc. Genetic and neural abnormalities are considered as significant contributor to ADHD; however, the main etiology of ADHD is still not known. At present, ADHD diagnosis is primarily done by clinical review of the kid by the specialist using some rating scales, making the diagnosis process quite subjective. There is crucial need for an accurate and reliable diagnostic standard for ADHD for timely and effective treatment. This paper reviews various machine learning and deep learning methods proposed for ADHD diagnosis in recent times. In 2nd part, it highlights the motivation behind use of machine learning for ADHD detection. The next sections describe various brain imaging modalities and novel execution strategies employed by machine learning models for ADHD detection. In the conclusion, this paper discusses about future scope of machine learning in ADHD diagnosis.