Problem
Research questions and friction points this paper is trying to address.
substance use initiation
longitudinal functional connectome
dynamic brain networks
adolescent risk prediction
neurodevelopmental trajectories
NeuroBRIDGE: Behavior-Conditioned Koopman Dynamics with Riemannian Alignment for Early Substance Use Initiation Prediction from Longitudinal Functional Connectome
🤖 AI Summary
This study addresses the challenge of early identification of adolescent substance use initiation risk, which remains difficult due to prevailing approaches that treat brain functional connectivity as static and overlook its dynamic co-evolution with behavior. To overcome this limitation, the authors propose NeuroBRIDGE, a novel framework that, for the first time, integrates Riemannian manifold alignment with behavior-conditioned Koopman dynamics to model the temporal evolution of longitudinal functional connectomes. The framework further incorporates a dual-temporal attention mechanism to enhance interpretability. Evaluated on the ABCD dataset, NeuroBRIDGE significantly outperforms baseline models in predictive accuracy and uncovers interpretable brain network pathways associated with neurodevelopmental risk for substance use.
📝 Abstract
Early identification of adolescents at risk for substance use initiation (SUI) is vital yet difficult, as most predictors treat connectivity as static or cross-sectional and miss how brain networks change over time and with behavior. We proposed NeuroBRIDGE (Behavior conditioned RIemannian Koopman Dynamics on lonGitudinal connEctomes), a novel graph neural network-based framework that aligns longitudinal functional connectome in a Riemannian tangent space and couples dual-time attention with behavioral-conditioned Koopman dynamics to capture temporal change. Evaluated on ABCD, NeuroBRIDGE improved future SUI prediction over relevant baselines while offering interpretable insights into neural pathways, refining our understanding of neurodevelopmental risk and informing targeted prevention.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Koopman dynamics
Riemannian alignment
longitudinal functional connectome
behavior-conditioned modeling
graph neural network
🔎 Similar Papers
No similar papers found.
