Generalizable prediction of childhood ADHD symptoms from neurocognitive testing and youth characteristics.
Alexander Weigard, Katherine L McCurry, Zvi Shapiro, Meghan E Martz, Mike Angstadt, Mary M Heitzeg, Ivo D Dinov, Chandra Sripada
Author Information
Alexander Weigard: Department of Psychiatry, University of Michigan, Ann Arbor, USA. asweigar@med.umich.edu. ORCID
Katherine L McCurry: Department of Psychiatry, University of Michigan, Ann Arbor, USA. ORCID
Zvi Shapiro: Department of Psychology, Emory University, Atlanta, USA.
Meghan E Martz: Department of Psychiatry, University of Michigan, Ann Arbor, USA.
Mike Angstadt: Department of Psychiatry, University of Michigan, Ann Arbor, USA.
Mary M Heitzeg: Department of Psychiatry, University of Michigan, Ann Arbor, USA.
Ivo D Dinov: Departments of Computational Medicine and Bioinformatics, and Health Behavior and Biological Sciences, University of Michigan, Ann Arbor, USA. ORCID
Chandra Sripada: Department of Psychiatry, University of Michigan, Ann Arbor, USA. ORCID
Childhood attention-deficit/hyperactivity disorder (ADHD) symptoms are believed to result from disrupted neurocognitive development. However, evidence for the clinical and predictive value of neurocognitive assessments in this context has been mixed, and there have been no large-scale efforts to quantify their potential for use in generalizable models that predict individuals' ADHD symptoms in new data. Using data drawn from the Adolescent Brain Cognitive Development Study (ABCD), a consortium that recruited a diverse sample of over 10,000 youth (ages 9-10 at baseline) across 21 U.S. sites, we develop and test cross-validated machine learning models for predicting youths' ADHD symptoms using neurocognitive abilities, demographics, and child and family characteristics. Models used baseline demographic and biometric measures, geocoded neighborhood data, youth reports of child and family characteristics, and neurocognitive tests to predict parent- and teacher-reported ADHD symptoms at the 1-year and 2-year follow-up time points. Predictive models explained 15-20% of the variance in 1-year ADHD symptoms for ABCD Study sites that were left out of the model-fitting process and 12-13% of the variance in 2-year ADHD symptoms. Models displayed high generalizability across study sites and trivial loss of predictive power when transferred from training data to left-out data. Features from multiple domains contributed meaningfully to prediction, including neurocognition, sex, self-reported impulsivity, parental monitoring, and screen time. This work quantifies the information value of neurocognitive abilities and other child characteristics for predicting ADHD symptoms and provides a foundational method for predicting individual youths' symptoms in new data across contexts.
