Comprehensive Analysis for Diagnosing Attention Deficit Hyperactivity Disorder Using Support Vector Machine and Multilayer Perceptron

ADHD or Attention Deficit Hyperactivity Disorder, is a nervous system disorder that primarily creates problems for youngsters. It is associated with behavioral disorders, which are mostly typified by inattention and hyperactivity. This study's primary goals are to (i) identify and detect individuals with ADHD based on risk variables and (ii) provide a suitable machine-learning method for ADHD prediction and detection. Using logistic regression, the characteristics of people with ADHD are extracted. Numerous machine learning methods, including Random Forest (RF), Naïve Bayes (NB), Support Vector Machines (SVM), and K-Nearest Neighbours (KNN), can be used to predict ADHD. To predict ADHD, current techniques have used neuroimaging and behavioral analysis. According to the study, MLP offers great accuracy in ADHD classification and prediction. According to the study, a genetic component is crucial in identifying ADHD. Different parameters received from functional magnetic resonance imaging(fMRI), electroencephalography (EEG), medical notes, video, and speech, can be used in investigation for prediction and detection of ADHD.