Graph Neural Networks with Transformer Fusion of Brain Connectivity Dynamics and Tabular Data for Forecasting Future Tobacco Use

2025/12/29 by Runzhi Zhou, Xi Luo, Zhou, Runzhi +1
Computer Science · Neuroscience · Psychology · #Artificial neural network #Deep learning #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Feature learning #Functional Brain Connectivity Studies #Graph #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Machine Learning in Healthcare #Mental Health Research Topics #Modalities #Neuroimaging #Neurons and Cognition (q-bio.NC) #Sensor fusion #Transformer #electronic engineering #information engineering

paper · open access · doi:10.48550/arxiv.2512.23137

published in PubMed Central (National Institutes of Health)

openalex publication_date 2025/12/29 · openalex created_date 2025/12/31 · openalex updated_date 2026/07/28

Abstract

Integrating non-Euclidean brain imaging data with Euclidean tabular data, such as clinical and demographic information, poses a substantial challenge for medical imaging analysis, particularly in forecasting future outcomes. While machine learning and deep learning techniques have been applied successfully to cross-sectional classification and prediction tasks, effectively forecasting outcomes in longitudinal imaging studies remains challenging. To address this challenge, we introduce a time-aware graph neural network model with transformer fusion (GNN-TF). This model flexibly integrates both tabular data and dynamic brain connectivity data, leveraging the temporal order of these variables within a coherent framework. By incorporating non-Euclidean and Euclidean sources of information from a longitudinal resting-state fMRI dataset from the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA), the GNN-TF enables a comprehensive analysis that captures critical aspects of longitudinal imaging data. Comparative analyses against a variety of established machine learning and deep learning models demonstrate that GNN-TF outperforms these state-of-the-art methods, delivering superior predictive accuracy for predicting future tobacco usage. The end-to-end, time-aware transformer fusion structure of the proposed GNN-TF model successfully integrates multiple data modalities and leverages temporal dynamics, making it a valuable analytic tool for functional brain imaging studies focused on clinical outcome prediction.

Citations

• A Survey on Evaluation of Large Language Models
• Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
• Joint Graph Convolution for Analyzing Brain Structural and Functional Connectome
• Graph Neural Networks in Network Neuroscience
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Spatio-Temporal Graph Convolution for Resting-State fMRI Analysis
• GNNExplainer: Generating Explanations for Graph Neural Networks
• Machine learning in resting-state fMRI analysis
• GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction
• How Powerful are Graph Neural Networks?
• Graph Attention Networks
• Attention Is All You Need
• Self-Normalizing Neural Networks
• Geometric deep learning on graphs and manifolds using mixture model CNNs
• Semi-Supervised Classification with Graph Convolutional Networks
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• Predicting Cognition from fMRI:A Comparative Study of Graph, Transformer, and Kernel Models Across Task and Rest Conditions
• Multimodal Graph Neural Networks for Prognostic Modeling of Brain Network Reorganization
• Generative forecasting of brain activity enhances Alzheimer's classification and interpretation
• FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generation
• Forecasting Future Anatomies: Longitudinal Brain Mri-to-Mri Prediction