Multi-region infectious disease prediction modeling based on spatio-temporal graph neural network and the dynamic model

Human mobility between different regions is a major factor in large-scale outbreaks of infectious diseases. Deep learning models incorporating infectious disease transmission dynamics for predicting the spread of multi-regional outbreaks due to human mobility have become a hot research topic. In this study, we incorporate the Graph Transformer Neural Network and graph learning mechanisms into a metapopulation SIR model to build a hybrid framework, Metapopulation Graph Transformer Neural Network (M-Graphormer), for high-dimensional parameter estimation and multi-regional epidemic prediction. The framework effectively solves the problem that existing models may lose some hidden spatial dependencies in the data when dealing with the dynamic graph structure of the network due to human mobility. We performed multi-wave infectious disease prediction in multiple regions based on real epidemic data. The results show that the framework is capable of performing high-dimensional parameter estimation and accurately predicting epidemic transmission dynamics in multiple regions even with low data quality. In addition, we retrospectively extrapolate the temporal evolution patterns of contact rate under different interventions implemented in different regions, reflecting the dynamics of intervention intensity and the need for flexibility in adjusting interventions in different regions. To provide early warning of infectious disease transmission, we retrospectively predicted the arrival time of infectious diseases using data from the early stages of outbreaks.Author summary: In this study, we developed a new method to predict how infectious diseases spread across multiple regions by considering human movement patterns. Our approach combines advanced graph-based deep learning techniques with a classic disease model, creating a powerful framework called M-Graphormer. This framework helps estimate complex disease parameters and predict epidemic trends even when data is scarce or of low quality. By using real-world data from multiple regions, we show that our model can accurately forecast the spread of infectious diseases and adjust for interventions like social distancing or travel restrictions. Additionally, we use our model to understand how different intervention strategies impact the disease’s progression over time. This research is important because it provides tools for public health authorities to anticipate future outbreaks, make better-informed decisions, and implement timely interventions to control the spread of disease. Our findings have the potential to improve the management of global health crises and offer early warnings of epidemic risks.