Prematurity is known to be associated with smaller grey matter volumes in cortical and subcortical structures. These children are also at high risk for ADHD. Furthermore, studies focusing on understanding the neural mechanism associated with preterm birth and ADHD diagnosis are limited, particularly focusing on extremely preterm births. This knowledge is crucial so that children at risk for subsequent neurodevelopmental disability can receive extended developmental follow-up and earlier assessments and interventions. We will use a deep learning approach to determine the predictive ability of neonatal brain measures (sMRI) from TEA at risk for ADHD symptoms assessed at multiple time points (~6 years and ~10 years) in children born extremely preterm. We will use a prediction approach by training with ADHD-1000 datasets and applying the resulting model to an independent set of children born extremely preterm scanned at term-age-equivalent.