CRII: HCC: A multimodal approach for the assessment of hyperactivity behaviors in ADHD

Chapman University, Orange CA

Investigators

Abstract

This research focuses on the impacts of misdiagnosing Attention Deficit Hyperactivity Disorder (ADHD). This project provides decision support to clinicians to improve the diagnosis of ADHD. The goal is to enhance the accuracy and reliability of ADHD assessments. This project also will add to the generalized understanding of human activity recognition. It is typical for people with ADHD to express inattention, impulsivity, and hyperactivity. Hyperactivity symptoms include fidgeting, restlessness, talking too much or at the wrong time. These symptoms are first noticed by parents and teachers. This often results in an evaluation for ADHD. Assessing these behaviors is challenging. It may rely on information provided through interviews, observations, and surveys. The gathering of this information is from parents, teachers, and clinicians. Various factors may influence the ability to receive an accurate diagnosis of ADHD. These factors may include parental income or a child's gender, race, or symptom severity. The project aims to develop computational approaches to collect and analyze ADHD data. The project will use a combination of human expertise and computational ADHD data collected. The project expectation is this will allow improved understanding of ADHD behaviors. The approach will provide quality and reliable information to improve ADHD assessment. Early diagnosis and targeted interventions can improve and empower people with ADHD, which will help them to reach their full potential. Current technology offers promising opportunities to support professionals in the assessment of ADHD. These advancements include inertial movement units (IMU), touch-sensitive screens, and high precision cameras. These technologies provide access to health-related behavioral information. These may include movement levels, physical activity, and speech. This data could offer valuable insights into hyperactivity behaviors. It is not clear which current sensors will improve the assessment of hyperactivity. This research will focus on designing applications to improve and support this process. The applications will gather sensor data and contextual data gathered from children. There will be a mix of children with and without an ADHD diagnosis. The research team will conduct interviews to understand the needs of experts. This will lead to the creation of an application to improve data collection for ADHD. An evaluation of the created application will show its feasibility and acceptability. This evaluation will provide meaningful information about ADHD hyperactivity behaviors. It will augment the capabilities of experts in the assessment process. The result will be a decision support system to aid in the assessment of neuro-diverse behaviors. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.