Using healthcare analytics to determine an effective diagnostic model for ADHD in students

Attention Deficit Hyperactivity Disorder (ADHD) is a mental health disorder. People diagnosed with ADHD are often inattentive (have difficulty focusing on a task for a considerable period of time), overly impulsive (make rash decisions), and are hyperactive (moving excessively, often at inappropriate times). ADHD is often diagnosed through psychiatric assessments with additional input from physical/neurological evaluations. Current tools designed for ADHD screening collect data manually and do not interoperate with each other. This paper will first review the effectiveness of common screening tools in relation to the Diagnostic and Statistical Manual of Mental Disorders (DSM) for ADHD classifier. This paper will also introduce the concept of using written performance data as a method of screening, since previous research has linked written language disorder (WLD) to ADHD as well. The current phase of this research proposes that an integrated computational model that combines outcomes from these screening tools will have a more effective diagnosis of ADHD in adult students than from the diagnosis of any individual screening tool. The integrated computational model, based on neural networks, will be built and tested in a future phase with each of the datasets (physical, behavior and learning performance) being collected from students.