Federated Epidemic Surveillance

TL;DR

This study proposes a hypothesis testing framework to identify surges in epidemic-related data streams and conducts experiments to assess the power of different p-value combination methods to detect surges without needing to combine or share the underlying counts.

Abstract

Epidemic surveillance is a challenging task, especially when crucial data is fragmented across institutions and data custodians are unable or unwilling to share it. This study aims to explore the feasibility of a simple federated surveillance approach. The idea is to conduct hypothesis tests for a rise in counts behind each custodian's firewall and then combine p-values from these tests using techniques from meta-analysis. We propose a hypothesis testing framework to identify surges in epidemic-related data streams and conduct experiments on real and semi-synthetic data to assess the power of different p-value combination methods to detect surges without needing to combine the underlying counts. Our findings show that relatively simple combination methods achieve a high degree of fidelity and suggest that infectious disease outbreaks can be detected without needing to share even aggregate data across institutions.

Figures (6)

• Figure 1: Adult patients hospitalized with confirmed COVID (7 day sum) of total and four largest facilities that together account for 95.12% of the market share in Seattle.
• Figure 2: Power analysis of federated surveillance methods.
• Figure 3: Real data analysis of federated surveillance methods.
• Figure 4: Federated surveillance methods on semi-synthetic data, varying site-level data generating process.
• Figure 5: Semi-synthetic analysis of the weighted methods.