ObjectivesLeveraging a large population-level morphologic, microstructural, and functional neuroimaging dataset, we aimed to elucidate the underlying neurobiology of attention-deficit hyperactivity disorder (ADHD) in children. In addition, we evaluated the applicability of machine learning classifiers to predict ADHD diagnosis based on imaging and clinical information.MethodsFrom the Adolescents Behavior Cognitive Development (ABCD) database, we included 1,798 children with ADHD diagnosis and 6,007 without ADHD. In multivariate logistic regression adjusted for age and sex, we examined the association of ADHD with different neuroimaging metrics. The neuroimaging metrics included fractional anisotropy (FA), neurite density (ND), mean-(MD), radial-(RD), and axial diffusivity (AD) of white matter (WM) tracts, cortical region thickness and surface areas from T1-MPRAGE series, and functional network connectivity correlations from resting-state fMRI.ResultsChildren with ADHD showed markers of pervasive reduced microstructural integrity in white matter (WM) with diminished neural density and fiber-tracks volumes – most notable in the frontal and parietal lobes. In addition, ADHD diagnosis was associated with reduced cortical volume and surface area, especially in the temporal and frontal regions. In functional MRI studies, ADHD children had reduced connectivity among default-mode network and the central and dorsal attention networks, which are implicated in concentration and attention function. The best performing combination of feature selection and machine learning classifier could achieve a receiver operating characteristics area under curve of 0.613 (95% confidence interval = 0.580–0.645) to predict ADHD diagnosis in independent validation, using a combination of multimodal imaging metrics and clinical variables.ConclusionOur study highlights the neurobiological implication of frontal lobe cortex and associate WM tracts in pathogenesis of childhood ADHD. We also demonstrated possible potentials and limitations of machine learning models to assist with ADHD diagnosis in a general population cohort based on multimodal neuroimaging metrics.

ImportanceAside from widely known cardiovascular implications, higher weight in children may have negative associations with brain microstructure and neurodevelopment.ObjectiveTo evaluate the association of body mass index (BMI) and waist circumference with imaging metrics that approximate brain health.Design, Setting, and ParticipantsThis cross-sectional study used data from the Adolescent Brain Cognitive Development (ABCD) study to examine the association of BMI and waist circumference with multimodal neuroimaging metrics of brain health in cross-sectional and longitudinal analyses over 2 years. From 2016 to 2018, the multicenter ABCD study recruited more than 11 000 demographically representative children aged 9 to 10 years in the US. Children without any history of neurodevelopmental or psychiatric disorders were included in this study, and a subsample of children who completed 2-year follow-up (34%) was included for longitudinal analysis.ExposuresChildren’s weight, height, waist circumference, age, sex, race and ethnicity, socioeconomic status, handedness, puberty status, and magnetic resonance imaging scanner device were retrieved and included in the analysis.Main Outcomes and MeasuresAssociation of preadolescents’ BMI z scores and waist circumference with neuroimaging indicators of brain health: cortical morphometry, resting-state functional connectivity, and white matter microstructure and cytostructure.ResultsA total of 4576 children (2208 [48.3%] female) at a mean (SD) age of 10.0 years (7.6 months) were included in the baseline cross-sectional analysis. There were 609 (13.3%) Black, 925 (20.2%) Hispanic, and 2565 (56.1%) White participants. Of those, 1567 had complete 2-year clinical and imaging information at a mean (SD) age of 12.0 years (7.7 months). In cross-sectional analyses at both time points, higher BMI and waist circumference were associated with lower microstructural integrity and neurite density, most pronounced in the corpus callosum (fractional anisotropy for BMI and waist circumference at baseline and second year: P < .001; neurite density for BMI at baseline: P < .001; neurite density for waist circumference at baseline: P = .09; neurite density for BMI at second year: P = .002; neurite density for waist circumference at second year: P = .05), reduced functional connectivity in reward- and control-related networks (eg, within the salience network for BMI and waist circumference at baseline and second year: P < .002), and thinner brain cortex (eg, for the right rostral middle frontal for BMI and waist circumference at baseline and second year: P < .001). In longitudinal analysis, higher baseline BMI was most strongly associated with decelerated interval development of the prefrontal cortex (left rostral middle frontal: P = .003) and microstructure and cytostructure of the corpus callosum (fractional anisotropy: P = .01; neurite density: P = .02).Conclusions and RelevanceIn this cross-sectional study, higher BMI and waist circumference among children aged 9 to 10 years were associated with imaging metrics of poorer brain structure and connectivity as well as hindered interval development. Future follow-up data from the ABCD study can reveal long-term neurocognitive implications of excess childhood weight. Imaging metrics that had the strongest association with BMI and waist circumference in this population-level analysis may serve as target biomarkers of brain integrity in future treatment trials of childhood obesity.