the ENIGMA-ADHD working group,

bioRxiv2019

Subcortical brain volume, regional cortical thickness and cortical surface area across attention-deficit/hyperactivity disorder (ADHD), autism spectrum disorder (ASD), and obsessive-compulsive disorder (OCD): findings from the ENIGMA-ADHD, -ASD, and -OCD working groups

ObjectiveAttention-deficit/hyperactivity disorder (ADHD), autism spectrum disorder (ASD), and obsessive-compulsive disorder (OCD) are common neurodevelopmental disorders that frequently co-occur. We aimed to directly compare all three disorders. The ENIGMA consortium is ideally positioned to investigate structural brain alterations across these disorders.\n\nMethodsStructural T1-weighted whole-brain MRI of controls (n=5,827) and patients with ADHD (n=2,271), ASD (n=1,777), and OCD (n=2,323) from 151 cohorts worldwide were analyzed using standardized processing protocols. We examined subcortical volume, cortical thickness and surface area differences within a mega-analytical framework, pooling measures extracted from each cohort. Analyses were performed separately for children, adolescents, and adults using linear mixed-effects models adjusting for age, sex and site (and ICV for subcortical and surface area measures).\n\nResultsWe found no shared alterations among all three disorders, while shared alterations between any two disorders did not survive multiple comparisons correction. Children with ADHD compared to those with OCD had smaller hippocampal volumes, possibly influenced by IQ. Children and adolescents with ADHD also had smaller ICV than controls and those with OCD or ASD. Adults with ASD showed thicker frontal cortices compared to adult controls and other clinical groups. No OCD-specific alterations across different age-groups and surface area alterations among all disorders in childhood and adulthood were observed.\n\nConclusionOur findings suggest robust but subtle alterations across different age-groups among ADHD, ASD, and OCD. ADHD-specific ICV and hippocampal alterations in children and adolescents, and ASD-specific cortical thickness alterations in the frontal cortex in adults support previous work emphasizing neurodevelopmental alterations in these disorders.

neuroscience↗

bioRxiv2019

Machine Learning Classification of Attention-Deficit/Hyperactivity Disorder Using Structural MRI Data

ADHD affects 5% of children world-wide. Of these, two-thirds continue to have impairing symptoms of ADHD into adulthood. Although a large literature implicates structural brain differences in the pathophysiology of the disorder, it is not clear if adults with ADHD have similar neuroanatomical impairments as those seen in children with recent reports from the large ENIGMA-ADHD consortium finding structural abnormalities for children but not for adults. This paper uses deep learning neural network classification models to determine if there are neuroanatomical changes in the brains of children with ADHD that are also observed for adult ADHD, and vice versa. We found that structural MRI data can significantly separate ADHD from control participants for both children and adults. Consistent with the prior reports from ENIGMA-ADHD, prediction performance and effect sizes were better for the child than the adult samples. The model trained on adult samples significantly predicted ADHD in the child sample, suggesting that our model learned anatomical features that common to ADHD in childhood and adulthood. These results support the continuity of ADHDs pathophysiology from childhood to adulthood. In addition, our work demonstrates a novel use of neural network classification models to test hypotheses about developmental continuity.

bioinformatics↗