Classification of ADHD with the Functional Connectivity by Usage of Different Atlases in Lahore, Pakistan

Abstract

Attention Deficit-Hyperactivity Disorder (ADHD) is a psychiatric condition that affects children's abilities. Nowadays computational diagnosis strategies of neuropsychiatric disorders are gaining more attention. Diagnosing this disorder based on fMRI is critical to determine the brain's Functional Connectivity (FC). Millions of children have the symptoms of this disease.The brain is notoriously unreliable for diagnosing neurological conditions. This condition is referred to as a chronic disease.A great number of youngsters exhibit signs of this disease. As a result, the study endeavored to come up with a model and design that is both reliable and accurate for diagnosing ADHD.A variety of techniques used in this present study, such as the local binary encoding method (LBEM) is utilized for future extraction, and the hierarchical extreme learning machine (HELM)is used to extract information on the connectivity functionalities of the brain.To validate our approach, the data of One hundred fifty-three children serve as a sample for the diagnosis, from which one hundred children are ultimately determined to have ADHD.These affected ADHD children are used for our experimental purpose. According to the findings of the research, the results are based on comparing various Atlases given as AAL, CC200, and CC400. Our model gainssuperior performance with CC400 when comparedwith other Atlases.