Global Prediction of COVID-19 Variant Emergence Using Dynamics-Informed Graph Neural Networks

2024-01-07

arXiv.org

AI Summary

To address the challenge of early cross-border transmission prediction for SARS-CoV-2 variants, this study proposes a dynamics-guided Dynamic Graph Neural Network (DGNN). First, it derives an analytical law governing the ratio of variant prevalence from epidemiological dynamics, yielding interpretable ratio-based features. Second, it constructs a heterogeneous spatiotemporal graph encompassing 87 countries and 36 variants, and designs a dynamics-aware GNN architecture that intrinsically embeds the derived dynamical规律 into the network structure—rather than merely incorporating it as a weighted loss term—thereby advancing beyond conventional physics-informed neural networks (PINNs). In standardized retrospective experiments, the method significantly outperforms pure mechanistic models, state-of-the-art machine learning approaches, and PINNs, achieving high-accuracy early warnings for both variant arrival times and epidemic inflection points.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

During the COVID-19 pandemic, a major driver of new surges has been the emergence of new variants. When a new variant emerges in one or more countries, other nations monitor its spread in preparation for its potential arrival. The impact of the variant and the timing of epidemic peaks in a country highly depend on when the variant arrives. The current methods for predicting the spread of new variants rely on statistical modeling, however, these methods work only when the new variant has already arrived in the region of interest and has a significant prevalence. The question arises: Can we predict when (and if) a variant that exists elsewhere will arrive in a given country and reach a certain prevalence? We propose a variant-dynamics-informed Graph Neural Network (GNN) approach. First, We derive the dynamics of variant prevalence across pairs of regions (countries) that applies to a large class of epidemic models. The dynamics suggest that ratios of variant proportions lead to simpler patterns. Therefore, we use ratios of variant proportions along with some parameters estimated from the dynamics as features in a GNN. We develop a benchmarking tool to evaluate variant emergence prediction over 87 countries and 36 variants. We leverage this tool to compare our GNN-based approach against our dynamics-only model and a number of machine learning models. Results show that the proposed dynamics-informed GNN method retrospectively outperforms all the baselines, including the currently pervasive framework of Physics-Informed Neural Networks (PINNs) that incorporates the dynamics in the loss function.

Problem

• COVID-19 variants prediction
• pandemic resurgence preparedness
• mitigating epidemic severity

Innovation

• Mutation Propagation
• Graph Neural Network
• COVID-19 Variant Prediction