ADHD is one of the developmental disorders (neurodevelopmental disorders) noticed by behavioral symptoms such as inattention and hyperactivity-impulsivity.While it is easy to be misunderstood by a selfish child and the surroundings because it shows various symptoms, the feeling of trouble (feeling of trouble) in multiple situations such as school and workplace increases and it strongly hinders activities of daily living.However, because there are no definitive biomarkers to index illness or disability, diagnosis relies on subjective behavioral observations by experienced professionals.

　Previous studies have suggested that ADHD has impaired inhibitory function headed by the prefrontal cortex of the cerebrum.This study is machine learning based on data on changes in the activity state of cerebral blood flow in the prefrontal area and the behavior of children when performing a task (suppression task) to investigate the suppressive function called "reverse stroop task". We have developed a method that can predict the diagnosis of children with ADHD with high sensitivity using an algorithm.

　Since developmental disorders such as ADHD are often accompanied by comorbidities such as mental illness with aging, early detection, early intervention and support, and medical treatment are desired.The method established by this study has made it possible to make unprecedented simple, objective, and highly sensitive diagnostic predictions for children with ADHD.It is expected that this result will greatly contribute to the screening for early detection in the school field as the effect judgment of diagnostic assistance and treatment in the clinical field.

Paper information:[Journal of Attention Disorders] Applied machine learning method to predict children with ADHD using prefrontal cortex activity: A multicenter study in Japan