Longitudinal and Graph-Augmented Prediction of Adolescent Substance Use Onset in the ABCD Study
Summary
The study compares longitudinal, cross-sectional, and graph-based models for predicting adolescent substance use onset using ABCD Study data, showing that combined approaches achieve better accuracy with AUC-ROC values above 0.79.
View Cached Full Text
Cached at: 08/18/26, 09:46 AM
# Longitudinal and Graph-Augmented Prediction of Adolescent Substance Use Onset in the ABCD Study Source: [https://arxiv.org/abs/2608.14578](https://arxiv.org/abs/2608.14578) [View PDF](https://arxiv.org/pdf/2608.14578) > 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\. ## Submission history From: Yixuan He \[[view email](https://arxiv.org/show-email/f313ce22/2608.14578)\] **\[v1\]**Fri, 12 Jun 2026 05:00:30 UTC \(276 KB\)
Similar Articles
Trajectory-Aware Clinical Risk Prediction via Severity-Grounded Knowledge Graphs and Retrieval-Augmented Generation
Proposes TRACER, a framework that integrates severity-grounded knowledge graphs and retrieval-augmented generation for trajectory-aware clinical risk prediction, achieving large gains in mortality and readmission prediction on MIMIC-III and MIMIC-IV datasets.
Uncertainty-Aware Longitudinal Forecasting of Alzheimer's Disease Progression Using Deep Learning
This paper proposes a probabilistic framework for Alzheimer's disease progression forecasting that combines ordinal diagnosis prediction, multi-horizon trajectory generation, and decomposed uncertainty estimation using a Temporal Fusion Transformer encoder and an autoregressive Mixture Density Network. The model outperforms baselines on ADNI data, achieving near-nominal 90% credible interval coverage with clinically meaningful uncertainty signals.
Probabilistic Contrastive Pretraining for Multi-task ADME Property Prediction
This paper proposes a probabilistic contrastive pretraining framework for molecular graph transformers to improve multi-task ADME property prediction in drug discovery, achieving significant gains on three benchmarks.
Forecasting Medium-Horizon Alzheimer's Disease Progression: Residual Gap-Aware Transformers for 24-Month CDR-SB Change from ADNI Clinical and Biomarker Histories
This paper proposes a residual gap-aware transformer that combines a mixed-effects statistical reference with transformer-based residual learning to forecast 24-month CDR-SB change from ADNI clinical and biomarker histories, achieving reduced MSE and improved correlation over baselines.
GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation
GraphDiffMed is a medication recommendation framework that uses dual-scale differential attention and pharmacological graph priors to improve recommendation quality and safety on EHR data. Experiments on MIMIC-III show consistent improvements over baselines.