Format

Send to

Choose Destination
Sci Rep. 2019 Jan 24;9(1):683. doi: 10.1038/s41598-018-36361-9.

Collaborative efforts to forecast seasonal influenza in the United States, 2015-2016.

Author information

1
Epidemiology and Prevention Branch, Influenza Division, Centers for Disease Control and Prevention, Atlanta, Georgia, USA.
2
Epidemiology and Prevention Branch, Influenza Division, Centers for Disease Control and Prevention, Atlanta, Georgia, USA. mbiggerstaff@cdc.gov.
3
Dengue Branch, Division of Vector-Borne Diseases, Centers for Disease Control and Prevention, Atlanta, Georgia, USA.
4
Arete Associates, Northridge, California, USA.
5
Predictive Science, Inc., San Diego, California, USA.
6
Computer Science Department, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA.
7
Division of Media and Network Technologies and Division of Frontier Science, Graduate School of Information Science and Technology, Gi-CoRE Station for Big Data & Cybersecurity, Hokkaido University, Sapporo, Japan.
8
Division of Environmental Health Sciences, School of Public Health, University of Minnesota, Minneapolis, Minnesota, USA.
9
Knowledge Based Systems, Inc., College Station, Texas, USA.
10
Computational Biology Department, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA.
11
Discovery Analytics Center, Virginia Tech University, Arlington, Virginia, USA.
12
Department of Statistics and Data Science, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA.
13
Department of Environmental Health Sciences, Mailman School of Public Health, Columbia University, New York, New York, USA.
14
Department of Mathematics, University of Arizona, Tucson, Arizona, USA.
15
Department of Statistics, University of California, Berkeley, Berkeley, California, USA.
16
Department of Statistics, Iowa State University, Ames, Iowa, USA.
17
Department of Mathematics and Statistics, Mount Holyoke College, South Hadley, Massachusetts, USA.
18
Department of Biostatistics and Epidemiology, School of Public Health and Health Sciences, University of Massachusetts, Amherst, Amherst, Massachusetts, USA.
19
Department of Statistics and Data Science, Machine Learning Department, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA.
20
Northeastern University, Boston, Massachusetts, USA.

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.

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center