Theoretical Framework for Early Mental Disorder Prediction Using Deep Learning
Early detection of mental disorders such as Attention Deficit Hyperactivity Disorder (ADHD), Depression, Post Traumatic Stress Disorder (PTSD) and Anxiety in Adolescents is a major public health concern. This paper represents a theoretical deep learning model to identify discriminative Electroencephalography (EEG) features associated with mental disorders. EEG signals contain rich neurophysiological information that can support early diagnosis of mental disorders. This framework addresses the need for clinical interpretable machine learning models by providing accurate predictions and transparent explanations.