Leveraging Random Forests explainability for predictive modeling of children's conduct problems: insights from individual and family factors.

Conduct problems are among the most complex, impairing, and prevalent challenges affecting the mental health of children and adolescents. Due to their multifaceted nature, it is important to develop predictive models that capture the intricate interactions among contributing factors. This longitudinal study aims to: (1) evaluate the utility and effectiveness of Random Forest models for classifying children with varying levels of conduct problems, (2) analyze the interactions between individual and family variables in predicting high levels of conduct problems, and (3) determine the most relevant factors or combinations for accurate child classification. The sample was drawn from the ELISA study, and consisted of 1,352 children assessed twice within a 1-year frame. The use of Random Forest and its inherent structure allowed to identify subsets of variables with the capability of predicting Conduct Problems in children. This research demonstrates the effectiveness of integrating psychological insights with advanced computational techniques to address critical concerns in children's mental health, emphasizing the need for enhanced screening and tailored interventions.