Early prediction of ADHD symptoms from perinatal characteristics: A machine learning study

Early identification of risk for attention-deficit hyperactivity disorder (ADHD) symptoms can enable more timely interventions and improve long-term outcomes. While previous research has linked various maternal and perinatal factors to ADHD, few studies have examined these predictors collectively in a single comprehensive analysis. This study aimed to assess whether later ADHD symptoms can be predicted from information available at birth, specifically ethnicity, maternal metabolic markers, mental health, and socioeconomic status. It additionally aimed to identify the most influential predictors. Using data from the Born in Bradford (BiB) study, we applied multiple linear regression (LR) and machine learning techniques to predict ADHD symptoms as measured by the Hyperactivity/Inattention subscale of the Strengths and Difficulties Questionnaire (SDQ). A 10-fold cross-validated LR model explained 6.97% of the variance in SDQ scores. In the random forest model, infant male sex and maternal smoking during pregnancy emerged as the top predictors. These findings provide proof of principle for early identification of children at risk of ADHD. Future models may benefit from incorporating additional perinatal data to improve predictive accuracy.