Background: This study elucidates the intricate relationship between stressful life events and the development of ADHD symptoms in children, acknowledging the considerable variability in individual responses. By examining these differences, we aim to uncover the unique combinations of factors contributing to varying levels of vulnerability and resilience among children. Methods: Utilizing longitudinal data from the Adolescent Brain Cognitive Development study (baseline: N = 6,303, age = 9.9), we applied Generalized Random Forest (GRF) to model the nonlinear relationships among genetic predispositions, brain features, and environmental factors. Results: Significant individual variability was observed in children's ADHD symptoms post‐stress, particularly at the 1‐year and 2‐year follow‐ups. At the 1‐year follow‐up, increased vulnerability was indicated by heightened parental mental health problems and a lower polygenic risk score for smoking. By the 2‐year follow‐up, escalated parental mental health disorders, higher ADHD polygenic risk scores (PRS), and altered structural connectivity in the cognitive control network were significant contributors to individual differences. Conclusions: These findings underscore the importance of integrating environmental, genetic, and neural variables to identify children vulnerable or resilient to developing ADHD symptoms following early‐life stress. This study demonstrates how multimodal data combined with nonparametric machine learning can advance precision psychology and psychiatry, aiding targeted support for affected children.
Analyzing individual differences in treatment or exposure effects is a central challenge in psychology and behavioral sciences. Conventional statistical models have focused on average treatment effects, overlooking individual variability, and struggling to identify key moderators. Generalized Random Forest (GRF) can predict individualized treatment effects, but current implementations suffer from two critical limitations: (1) prediction performances vary substantially across random initializations, and (2) identification of key moderator is limited in high-dimensional settings. Here, we introduce two methodological advances to address these issues. First, a seed ensemble strategy stabilizes predictions by aggregating models trained under different random initializations. Second, a backward elimination procedure systematically identifies key moderators from high-dimensional inputs. Simulation analyses across diverse scenarios demonstrate that our approach achieves reliable and valid predictions across random seeds, improved performance in moderator identification, and robust generalization to independent data. To facilitate adoption and interpretation, we provide step-by-step guidance using large-scale neuroimaging dataset ( N = 8,778) with reusable code. These enhancements make GRF more reliable for modeling individual differences in treatment effects, supporting data-driven hypothesis generation, and identification of responsive subgroups.
Early detection of youth depression is crucial, given its rising prevalence and long-term consequences. Although genetic factors contribute significantly to youth depression, their integration with neuroimaging remains limited. We present a deep learning framework using polygenic scores (PGS) to pretrain a 3D convolutional neural network on diffusion MRI (track-weighted fractional anisotropy), capturing gene–brain associations from a multi-ethnic cohort in the Adolescent Brain Cognitive Development Study (N=4,741). Fine-tuned for predicting depression, the model improved cross-sectional (N=266; AUC=0.62) and two-year predictions of depression and suicidality (AUC=0.61–0.66). It outperformed unimodal models, increasing accuracy by up to 24% over PGS-only and 5.8% over brain-only models. Explainable artificial intelligence identified key white matter tracts—superior longitudinal fasciculus, cingulum and corpus callosum—as predictive features. Decision curve analysis showed greater clinical utility. The model generalized to an independent Korean youth sample (N=108; AUC=0.67), supporting the cross-ethnic scalability of PGS-informed diffusion MRI for precision psychiatry
Background: This study elucidates the intricate relationship between stressful life events and the development of ADHD symptoms in children, acknowledging the considerable variability in individual responses. By examining these differences, we aim to uncover the unique combinations of factors contributing to varying levels of vulnerability and resilience among children. Methods: Utilizing longitudinal data from the Adolescent Brain Cognitive Development study (baseline: N=6303, age=9.9), we applied Generalized Random Forest to model the non-linear relationships among genetic predispositions, brain features, and environmental factors. Results: Significant individual variability was observed in children’s ADHD symptoms post-stress, particularly at the 1-year and 2-year follow-ups. At the 1-year follow-up, increased vulnerability was indicated by heightened parental mental health problems and a lower polygenic risk score for smoking. By the 2-year follow-up, escalated parental mental health disorders, higher ADHD polygenic risk scores, and altered structural connectivity in the cognitive control network were significant contributors to individual differences. Conclusions: These findings underscore the importance of integrating environmental, genetic, and neural variables to identify children vulnerable or resilient to developing ADHD symptoms following early-life stress. This study demonstrates how multimodal data combined with non-parametric machine-learning can advance precision psychology and psychiatry, aiding targeted support for affected children.