EpiFlow: A framework for improving the utility of wastewater signals for disease forecasting

2026-08-06

AI Summary

This study addresses the challenge of improving real-time forecasting accuracy for infectious diseases such as COVID-19 when traditional clinical surveillance is compromised by reporting delays or fatigue. The authors propose a dynamic prediction framework that, for the first time, systematically integrates information entropy analysis, Granger causality testing, and time-varying coefficient models to quantify the predictive value of wastewater viral load and uncover its temporal lead over clinical indicators. Applied to multi-region COVID-19 hospitalization forecasting in Virginia, the approach significantly outperforms baseline models, achieving approximately a 20-percentage-point increase in prediction coverage, with particularly strong performance during low-prevalence periods and critical phases of outbreaks.

Abstract

Wastewater-based surveillance is an effective tool for disease monitoring and can provide early warning of outbreaks. Although wastewater viral loads (WVL) correlate with disease burden, their utility for improving real-time forecasting remains under investigation. During the early phases of an epidemic, many indicators can effectively monitor disease spread, but their reliability may decline because of reporting fatigue and low prevalence. Hospital burden can vary substantially even during low-prevalence periods, making accurate forecasting of burden indicators essential for minimizing disease impacts. In this paper, we present principled approaches for processing wastewater data, characterizing its relationship with burden indicators, and generating real-time forecasts. We assess the predictability of WVL using entropy measures. We analyze the relationship between WVL and burden indicators using causality tests that capture temporal dynamics and the leading-indicator behavior of WVL. We incorporate these insights into a time-varying forecasting model that accounts for the evolving relationship between the signals. We also evaluate the effects of delays in WVL reporting through simulations. We test the utility of our methods by forecasting COVID-19 hospital admissions across Virginia and its health regions during periods of varying disease prevalence. Incorporating WVL improves forecast accuracy relative to baseline models, particularly during critical epidemic phases, and results in a 20 percentage point improvement in forecast coverage. Our results demonstrate that WVL signals can improve infectious disease forecasting even under conditions of low prevalence or delayed reporting.

Problem

• wastewater-based surveillance
• disease forecasting
• viral load
• hospital burden
• predictability

Innovation

• wastewater-based surveillance
• disease forecasting
• causality analysis
• time-varying model
• entropy-based predictability