Is there any incremental benefit to conducting neuroimaging and neurocognitive assessments in the diagnosis of ADHD in young children? A machine learning investigation.

Given the negative trajectories of early behavior problems associated with Attention-Deficit/Hyperactivity Disorder (ADHD), early diagnosis of ADHD is considered critical to enable early intervention and treatment. To this end, the current investigation employed machine learning to evaluate the relative predictive value of parent/teacher ratings, as well as behavioral and neural measures of executive function in predicting ADHD diagnostic category in a sample consisting of 162 young children (53.7% ADHD, ages 4 to 7, mean age 5.55, 67.9% male, 82.6% Hispanic/Latino). Among all the target measures assessed in the study, teacher ratings of executive function were identified as by far the most important measure in predicting ADHD diagnostic category. While a more extensive evaluation of neural measures, such as diffusion-weighted imaging, may provide more information as they relate to the underlying cognitive deficits associated with ADHD, the current study indicates that commonly used structural imaging measures of cortical thickness, as well as widely used cognitive measures of executive function, have little incremental value in differentiating typically developing children from those diagnosed with ADHD. Future research evaluating the importance of such measures in predicting childrens functional impairment in academic and social areas would provide additional insight into their contributing role in ADHD.