ADHD remains a serious public health concern particularly in relation to long-term outcome, with recent follow up data from other projects, such as the MTA study, suggesting that current assessment and sustained treatment practices do not much alter clinical course. In addition, societal and clinical concerns remain about mis-identification of children with ADHD who need care, because some children seem to improve developmentally, while others have poor outcomes. While a great deal is known about the correlates of developmental course, little of this knowledge has translated to clinical practice, and in particular to clinical prediction?essentially, deciding whether a child, presenting with ADHD, requires intervention or for whom a clinician can afford to wait and observed. We have previously made progress here by re-conceptualizing ADHD as a problem in self-regulation involving cognitive control as well as emotion regulation and emotionality. This has helped us find new and valid sub-profiles that are clinically predictive. We follow that up here and add new effort to use advanced computational tools to predict clinical course over a developmental period from 7-19 years of age, using a range of measures at different levels of analysis, and thus to develop algorithms that could point the way toward next-generation clinical translation from longitudinal studies.
ADHD continues to be a serious and impairing syndrome for millions of children, affecting families, schools, and life quality. While a great deal is known about the correlates of ADHD, this information has not translated sufficiently into more efficient clinical decision-making that recognizes the variety of children within this population. This project seeks to use advanced analytics and long-term follow up data to identify better ways to identify groups of children with ADHD with characteristic profiles to improve clinical care.
Showing the most recent 10 out of 49 publications
