Abstract
Since 2013, the Centers for Disease Control and Prevention (CDC) has hosted an annual influenza season forecasting challenge. The 2015–2016 challenge consisted of weekly probabilistic forecasts of multiple targets, including fourteen models submitted by eleven teams. Forecast skill was evaluated using a modified logarithmic score. We averaged submitted forecasts into a mean ensemble model and compared them against predictions based on historical trends. Forecast skill was highest for seasonal peak intensity and short-term forecasts, while forecast skill for timing of season onset and peak week was generally low. Higher forecast skill was associated with team participation in previous influenza forecasting challenges and utilization of ensemble forecasting techniques. The mean ensemble consistently performed well and outperformed historical trend predictions. CDC and contributing teams will continue to advance influenza forecasting and work to improve the accuracy and reliability of forecasts to facilitate increased incorporation into public health response efforts.
Highlights
Seasonal influenza epidemics result in substantial human health and financial burdens in the United States, with an estimated 140,000–710,000 hospitalizations and 12,000–56,000 deaths annually depending on the severity of the season[1,2]
Accurate and timely forecasts of influenza activity could assist in the public health response to both seasonal epidemics and future pandemics
The evaluation methodology was modified to allow for a pre-specified number of preceding and proceeding values to be considered correct to reduce the effect of revisions to Illness Surveillance Network (ILINet) on forecast scores
Summary
Seasonal influenza epidemics result in substantial human health and financial burdens in the United States, with an estimated 140,000–710,000 hospitalizations and 12,000–56,000 deaths annually depending on the severity of the season[1,2]. For influenza-like illness (ILI), hospitalizations, and mortality[5] While these systems collect valuable data, they are intrinsically describing activity that occurred in the past and require data processing time, limiting their utility for real-time public health decision making. Accurate and timely forecasts of influenza activity could assist in the public health response to both seasonal epidemics and future pandemics. Since the 2013–2014 influenza season, CDC has hosted collaborative challenges to forecast the timing, intensity, and short-term trajectory of ILI activity in the United States using data from the US Outpatient Influenza-like Illness Surveillance Network (ILINet), a robust and geographically broad surveillance system, as its benchmark[6,7]. To help communicate forecasts in real-time, a public webpage to host predictions was created[10]
Sign-in/Register to view highlights & summary 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 callDisclaimer: 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.
