Mapping multimodal risk factors to mental health outcomes

A key challenge in predicting a person’s state of mind is that a wide range of contributing factors each has a subtle, yet meaningful, influence on mental health. Here we applied data mining techniques to identify the most important risk factors for predicting current symptoms and longitudinal outcomes from the Adolescent Brain Cognitive Developmental study (n = 11,552). Our results consistently revealed that social conflicts were the strongest predictors of psychopathology, especially family fighting and reputational damage between peers. Sex differences also emerged as a critical factor for predicting long-term mental health outcomes. Neuroimaging-derived metrics were consistently the least informative. Although these findings provide novel insight into the developmental origins of psychopathology, our best-performing models could explain only up to 40% of the variation between individuals. Future research is needed to obtain a more complete understanding of all the factors that meaningfully contribute to mental health.