aiqbench analysis
This study applies advanced machine learning techniques, including Temporal Graph Convolutional Networks (T-GCNs) and recurrent neural networks, to predict adolescent substance use onset using longitudinal ABCD Study data. While tree-based models like temporal XGBoost currently lead in standalone performance, the research highlights that integrating graph-derived relational context provides valuable complementary risk signals through score-level stacking. The findings underscore the utility of combining time-series modeling with network analysis for early intervention strategies in public health applications.
Longitudinal and Graph-Augmented Prediction of Adolescent Substance Use Onset in the ABCD Study
arXiv:2608.14578v1 Announce Type: cross Abstract: Early identification of adolescent substance-use risk is an important prevention challenge, yet the relative value of baseline characteristics, longitudinal trajectories, and relational context remains unclear. Using data from approximately 11,860 participants in the Adolescent Brain Cognitive Development (ABCD) Study, we compare cross-sectional, longitudinal, and graph-based approaches for predicting alcohol sipping, alcohol use, marijuana use, and alcohol/marijuana use. We evaluate tree-based models, recurrent neural networks, and Temporal Graph Convolutional Networks (T-GCNs) constructed from family, school, and feature-similarity graphs. Longitudinal models consistently outperform baseline models, with temporal XGBoost achieving the strongest standalone performance. Although T-GCNs generally do not surpass temporal XGBoost, graph-derived risk scores provide complementary information. Combining temporal XGBoost and T-GCN predictions through score-level stacking yields the best performance across all outcomes, achieving AUC-ROC values above 0.79. Feature analyses identify peer deviance, age, externalizing symptoms, parental monitoring, cultural norms, and neighborhood context as important predictors of substance use onset. These findings demonstrate the value of longitudinal modeling for substance-use prediction and suggest that graph-based representations can provide effective auxiliary risk signals.
Abstract:Early identification of adolescent substance-use risk is an important prevention challenge, yet the relative value of baseline characteristics, longitudinal trajectories, and relational context remains unclear. Using data from approximately 11,860 participants in the Adolescent Brain Cognitive Development (ABCD) Study, we compare cross-sectional, longitudinal, and graph-based approaches for predicting alcohol sipping, alcohol use, marijuana use, and alcohol/marijuana use. We evaluate tree-based models, recurrent neural networks, and Temporal Graph Convolutional Networks (T-GCNs) constructed from family, school, and feature-similarity graphs. Longitudinal models consistently outperform baseline models, with temporal XGBoost achieving the strongest standalone performance. Although T-GCNs generally do not surpass temporal XGBoost, graph-derived risk scores provide complementary information. Combining temporal XGBoost and T-GCN predictions through score-level stacking yields the best performance across all outcomes, achieving AUC-ROC values above 0.79. Feature analyses identify peer deviance, age, externalizing symptoms, parental monitoring, cultural norms, and neighborhood context as important predictors of substance use onset. These findings demonstrate the value of longitudinal modeling for substance-use prediction and suggest that graph-based representations can provide effective auxiliary risk signals.
Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG); Applications (stat.AP)
arXiv:2608.14578 [cs.AI]
(or arXiv:2608.14578v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.14578 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 271 words
Related coverage
Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge
arXiv · Sep 3, 2026
Graph Data Augmentation via Contrastive Generator Inversion ($\texttt{DCBA}$)
arXiv · Oct 6, 2026
Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction
arXiv · Jun 9, 2026
Continuous Cross-Domain Traffic State Prediction via Memory-Augmented Graph Liquid Time-Constant Networks
arXiv · Jun 16, 2026