Status: Funded - Open
Katherine Lawrence, PhD
BACKGROUND: Children with ADHD are at increased risk for poor outcomes. Many children with ADHD have changes in the severity of their ADHD or depressive symptoms during adolescence, and youth with both ADHD and depression are at risk for even worse outcomes. GAP: It is not currently possible to predict future ADHD or depressive symptom severity for a child who has ADHD. However, such predictions would improve clinical care for children with ADHD. HYPOTHESIS: We hypothesize that brain activity to rewards will let us predict future ADHD and depressive severity more accurately. We also expect that using brain-based subgroups will let us predict future ADHD and depressive symptom severity even more accurately. METHODS: This study will leverage existing longitudinal data available from children with ADHD. We will use this data to develop and validate machine learning models that will predict future ADHD and depressive severity among children with ADHD. RESULTS: Pending. IMPACT: This study will improve our understanding of how we can best predict future ADHD and depressive symptom severity in children with ADHD. Being able to accurately predict future ADHD and depressive severity would directly improve clinical monitoring and treatment planning for children with ADHD.