Integrating Slow Neural Oscillations and Physiological Burden for Trait Anxiety Prediction

Jungyoun Janice Min, Jiong Chen, Jingxuan Bao, Shu Yang, Yize Zhao, Li Shen, Duy Duong-Tran

Keywords: Temporal Feature Extraction, Resting-State fMRI, Multimodal, Allostatic Load markers, Trait Anxiety, Graph Attention Network

TL;DR: Preserving slow-4/slow-5 temporal dynamics with multimodal graph attention yields stable and interpretable brain–body markers for trait anxiety

Abstract: Effective modeling of health outcomes from biomedical time series requires methods that capture both temporal and frequency dynamics. Trait anxiety, a transdiagnostic risk factor, manifests in neural activity and systemic physiology. We present a multimodal graph-attention framework that integrates resting-state fMRI time series with structural connectivity and allostatic-load biomarkers via cross-modal attention. Using 120 participants from the LEMON dataset, the model achieved modest but stable predictive accuracy. Within the brain branch, we systematically compared feature extraction strategies and found that preserving temporal order in slow-4/slow-5 oscillations was essential for prediction, while approaches discarding temporal structure consistently underperformed. Interpretability analyses highlighted limbic–visual circuits and metabolic–immune markers as reproducible contributors. These findings demonstrate that capturing temporal dynamics is critical in health time-series modeling, and show how multimodal graph-attention can provide both predictive value and interpretable digital biomarkers for anxiety vulnerability.

Submission Number: 64