Early Detection of COVID-19 Hotspots Using Spatio-Temporal Data

TL;DR

This paper introduces a Bayesian spatio-temporal model utilizing neural network-enhanced kernels for early detection of COVID-19 hotspots at the county level in the US, improving interpretability and detection accuracy.

Contribution

It proposes a novel Gaussian process framework with deep neural network kernels for modeling COVID-19 spread, enabling early hotspot detection with enhanced interpretability.

Findings

Model outperforms baseline methods in hotspot detection accuracy

Deep neural network kernels improve model's representational capacity

Sparse variational inference makes the model scalable to large datasets

Abstract

Recently, the Centers for Disease Control and Prevention (CDC) has worked with other federal agencies to identify counties with increasing coronavirus disease 2019 (COVID-19) incidence (hotspots) and offers support to local health departments to limit the spread of the disease. Understanding the spatio-temporal dynamics of hotspot events is of great importance to support policy decisions and prevent large-scale outbreaks. This paper presents a spatio-temporal Bayesian framework for early detection of COVID-19 hotspots (at the county level) in the United States. We assume both the observed number of cases and hotspots depend on a class of latent random variables, which encode the underlying spatio-temporal dynamics of the transmission of COVID-19. Such latent variables follow a zero-mean Gaussian process, whose covariance is specified by a non-stationary kernel function. The most salient feature of our kernel function is that deep neural networks are introduced to enhance the model's representative power while still enjoying the interpretability of the kernel. We derive a sparse model and fit the model using a variational learning strategy to circumvent the computational intractability for large data sets. Our model demonstrates better interpretability and superior hotspot-detection performance compared to other baseline methods.