Combining digital data streams and epidemic networks for real time outbreak detection

TL;DR

LRTrend is an interpretable machine learning framework that combines diverse digital data streams and epidemic networks to detect disease outbreaks in real time, effectively identifying COVID-19 waves shortly after they begin.

Contribution

The paper introduces LRTrend, a novel framework that integrates multiple data sources and learns epidemic networks for early outbreak detection in epidemiology.

Findings

Successfully detected COVID-19 Delta and Omicron waves within 2 weeks of outbreak start.

Revealed diverse epidemic clusters not explained by mobility networks.

Demonstrated effectiveness using 2 years of data across 305 regions.

Abstract

Responding to disease outbreaks requires close surveillance of their trajectories, but outbreak detection is hindered by the high noise in epidemic time series. Aggregating information across data sources has shown great denoising ability in other fields, but remains underexplored in epidemiology. Here, we present LRTrend, an interpretable machine learning framework to identify outbreaks in real time. LRTrend effectively aggregates diverse health and behavioral data streams within one region and learns disease-specific epidemic networks to aggregate information across regions. We reveal diverse epidemic clusters and connections across the United States that are not well explained by commonly used human mobility networks and may be informative for future public health coordination. We apply LRTrend to 2 years of COVID-19 data in 305 hospital referral regions and frequently detect regional Delta and Omicron waves within 2 weeks of the outbreak's start, when case counts are a small fraction of the wave's resulting peak.