Abstract
Accurate prediction of flu activity enables health officials to plan disease prevention and allocate treatment resources. A promising forecasting approach is to adapt the well-established endemic-epidemic modeling framework to time series of infectious disease proportions. Using U.S. influenza-like illness surveillance data over 18 seasons, we assessed probabilistic forecasts of this new beta autoregressive model with proper scoring rules. Other readily available forecasting tools were used for comparison, including Prophet, (S)ARIMA and kernel conditional density estimation (KCDE). Short-term flu activity was equally well predicted up to four weeks ahead by the beta model with four autoregressive lags and by KCDE; however, the beta model runs much faster. Non-dynamic Prophet scored worst. Relative performance differed for seasonal peak prediction. Prophet produced the best peak intensity forecasts in seasons with standard epidemic curves; otherwise, KCDE outperformed all other methods. Peak timing was best predicted by SARIMA, KCDE or the beta model, depending on the season. The best overall performance when predicting peak timing and intensity was achieved by KCDE. Only KCDE and naive historical forecasts consistently outperformed the equal-bin reference approach for all test seasons. We conclude that the endemic-epidemic beta model is a performant and easy-to-implement tool to forecast flu activity a few weeks ahead. Real-time forecasting of the seasonal peak, however, should consider outputs of multiple models simultaneously, weighing their usefulness as the season progresses.
Highlights
Influenza is a contagious respiratory illness caused by different types of influenza viruses.The outcomes of flu infections vary widely, and serious infections can cause hospitalization or death.The Centers for Disease Control and Prevention (CDC) in the U.S estimated that around 8% of theU.S population becomes infected with influenza during an average season [1]
The national weighted influenza-like illness index is calculated as the proportion of outpatient visits with ILI reported through Illness Surveillance Network (ILINet), weighted by state population [21]
A peak or secondary peak occurred in season week 22, which corresponds to Morbidity and Mortality Weekly Report [21] (MMWR) week 52 (Figure 2)
Summary
The Centers for Disease Control and Prevention (CDC) in the U.S estimated that around 8% of the. U.S population becomes infected with influenza during an average season [1]. Accurate prediction of flu activity provides health officials with valuable information to plan disease prevention and allocate treatment resources. Since 2013, CDC organizes the “Predict the Influenza Season Challenge”. (https://predict.cdc.gov/, known as the CDC FluSight challenge) for every flu season, to encourage academic and private industry researchers to forecast national and regional flu activity. Some of the most common approaches in influenza forecasting can be grouped into the following categories [4,5,6]: compartmental models [7,8], agent-based models, direct regression models [9,10] and time series models [11,12,13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Environmental Research and Public Health
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
