Fast and accurate influenza forecasting in the United States with Inferno
Abstract
Infectious disease forecasting is an emerging field and has the potential to improve public health through anticipatory resource allocation, situational awareness, and mitigation planning. By way of exploring and operationalizing disease forecasting, the U.S. Centers for Disease Control and Prevention (CDC) has hosted FluSight since the 2013/14 flu season, an annual flu forecasting challenge. Since FluSight’s onset, forecasters have developed and improved forecasting models in an effort to provide more timely, reliable, and accurate information about the likely progression of the outbreak. While improving the predictive performance of these forecasting models is often the primary objective, it is also important for a forecasting model to run quickly, facilitating further model development and improvement while providing flexibility when deployed in a real-time setting. In this vein I introduce Inferno, a fast and accurate flu forecasting model inspired by Dante, the top performing model in the 2018/19 FluSight challenge. When pseudoprospectively compared to all models that participated in FluSight 2018/19, Inferno would have placed 2nd in the national and regional challenge as well as the state challenge, behind only Dante. Inferno, however, runs in minutes and is trivially parallelizable, while Dante takes hours to run, representing a significant operational improvement with minimalmore »
- Authors:
- Publication Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE Laboratory Directed Research and Development (LDRD) Program
- OSTI Identifier:
- 1844455
- Alternate Identifier(s):
- OSTI ID: 1842890; OSTI ID: 1868274
- Report Number(s):
- LA-UR-20-30384
Journal ID: ISSN 1553-7358; 10.1371/journal.pcbi.1008651
- Grant/Contract Number:
- 20190546ECR; 89233218CNA000001
- Resource Type:
- Published Article
- Journal Name:
- PLoS Computational Biology (Online)
- Additional Journal Information:
- Journal Name: PLoS Computational Biology (Online) Journal Volume: 18 Journal Issue: 1; Journal ID: ISSN 1553-7358
- Publisher:
- Public Library of Science (PLoS)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 59 BASIC BIOLOGICAL SCIENCES; 29 ENERGY PLANNING, POLICY, AND ECONOMY
Citation Formats
Osthus, Dave, and Funk, ed., Sebastian. Fast and accurate influenza forecasting in the United States with Inferno. United States: N. p., 2022.
Web. doi:10.1371/journal.pcbi.1008651.
Osthus, Dave, & Funk, ed., Sebastian. Fast and accurate influenza forecasting in the United States with Inferno. United States. https://doi.org/10.1371/journal.pcbi.1008651
Osthus, Dave, and Funk, ed., Sebastian. Mon .
"Fast and accurate influenza forecasting in the United States with Inferno". United States. https://doi.org/10.1371/journal.pcbi.1008651.
@article{osti_1844455,
title = {Fast and accurate influenza forecasting in the United States with Inferno},
author = {Osthus, Dave and Funk, ed., Sebastian},
abstractNote = {Infectious disease forecasting is an emerging field and has the potential to improve public health through anticipatory resource allocation, situational awareness, and mitigation planning. By way of exploring and operationalizing disease forecasting, the U.S. Centers for Disease Control and Prevention (CDC) has hosted FluSight since the 2013/14 flu season, an annual flu forecasting challenge. Since FluSight’s onset, forecasters have developed and improved forecasting models in an effort to provide more timely, reliable, and accurate information about the likely progression of the outbreak. While improving the predictive performance of these forecasting models is often the primary objective, it is also important for a forecasting model to run quickly, facilitating further model development and improvement while providing flexibility when deployed in a real-time setting. In this vein I introduce Inferno, a fast and accurate flu forecasting model inspired by Dante, the top performing model in the 2018/19 FluSight challenge. When pseudoprospectively compared to all models that participated in FluSight 2018/19, Inferno would have placed 2nd in the national and regional challenge as well as the state challenge, behind only Dante. Inferno, however, runs in minutes and is trivially parallelizable, while Dante takes hours to run, representing a significant operational improvement with minimal impact to performance. Forecasting challenges like FluSight should continue to monitor and evaluate how they can be modified and expanded to incentivize the development of forecasting models that benefit public health.},
doi = {10.1371/journal.pcbi.1008651},
journal = {PLoS Computational Biology (Online)},
number = 1,
volume = 18,
place = {United States},
year = {Mon Jan 31 00:00:00 EST 2022},
month = {Mon Jan 31 00:00:00 EST 2022}
}
https://doi.org/10.1371/journal.pcbi.1008651
Works referenced in this record:
Even a good influenza forecasting model can benefit from internet-based nowcasts, but those benefits are limited
journal, February 2019
- Osthus, Dave; Daughton, Ashlynn R.; Priedhorsky, Reid
- PLOS Computational Biology, Vol. 15, Issue 2
Summary results of the 2014-2015 DARPA Chikungunya challenge
journal, May 2018
- Del Valle, Sara Y.; McMahon, Benjamin H.; Asher, Jason
- BMC Infectious Diseases, Vol. 18, Issue 1
On the multibin logarithmic score used in the FluSight competitions
journal, September 2019
- Bracher, Johannes
- Proceedings of the National Academy of Sciences, Vol. 116, Issue 42
Nonmechanistic forecasts of seasonal influenza with iterative one-week-ahead distributions
journal, June 2018
- Brooks, Logan C.; Farrow, David C.; Hyun, Sangwon
- PLOS Computational Biology, Vol. 14, Issue 6
An open challenge to advance probabilistic forecasting for dengue epidemics
journal, November 2019
- Johansson, Michael A.; Apfeldorf, Karyn M.; Dobson, Scott
- Proceedings of the National Academy of Sciences, Vol. 116, Issue 48
Accurate estimation of influenza epidemics using Google search data via ARGO
journal, November 2015
- Yang, Shihao; Santillana, Mauricio; Kou, S. C.
- Proceedings of the National Academy of Sciences, Vol. 112, Issue 47
A collaborative multiyear, multimodel assessment of seasonal influenza forecasting in the United States
journal, January 2019
- Reich, Nicholas G.; Brooks, Logan C.; Fox, Spencer J.
- Proceedings of the National Academy of Sciences, Vol. 116, Issue 8
Results from the centers for disease control and prevention’s predict the 2013–2014 Influenza Season Challenge
journal, July 2016
- Biggerstaff, Matthew; Alper, David; Dredze, Mark
- BMC Infectious Diseases, Vol. 16, Issue 1
Multiscale influenza forecasting
journal, May 2021
- Osthus, Dave; Moran, Kelly R.
- Nature Communications, Vol. 12, Issue 1
Using data-driven agent-based models for forecasting emerging infectious diseases
journal, March 2018
- Venkatramanan, Srinivasan; Lewis, Bryan; Chen, Jiangzhuo
- Epidemics, Vol. 22
An interactive web-based dashboard to track COVID-19 in real time
journal, May 2020
- Dong, Ensheng; Du, Hongru; Gardner, Lauren
- The Lancet Infectious Diseases, Vol. 20, Issue 5
Strictly Proper Scoring Rules, Prediction, and Estimation
journal, March 2007
- Gneiting, Tilmann; Raftery, Adrian E.
- Journal of the American Statistical Association, Vol. 102, Issue 477
Dynamic Bayesian Influenza Forecasting in the United States with Hierarchical Discrepancy (with Discussion)
journal, March 2019
- Osthus, Dave; Gattiker, James; Priedhorsky, Reid
- Bayesian Analysis, Vol. 14, Issue 1
Prediction of infectious disease epidemics via weighted density ensembles
journal, February 2018
- Ray, Evan L.; Reich, Nicholas G.
- PLOS Computational Biology, Vol. 14, Issue 2
A New Approach to Linear Filtering and Prediction Problems
journal, March 1960
- Kalman, R. E.
- Journal of Basic Engineering, Vol. 82, Issue 1
Dynamic Bayesian Forecasting of Presidential Elections in the States
journal, March 2013
- Linzer, Drew A.
- Journal of the American Statistical Association, Vol. 108, Issue 501
Forecasting national and regional influenza-like illness for the USA
journal, May 2019
- Ben-Nun, Michal; Riley, Pete; Turtle, James
- PLOS Computational Biology, Vol. 15, Issue 5
Near-term forecasts of influenza-like illness
journal, June 2019
- Kandula, Sasikiran; Shaman, Jeffrey
- Epidemics, Vol. 27
Flexible Modeling of Epidemics with an Empirical Bayes Framework
journal, August 2015
- Brooks, Logan C.; Farrow, David C.; Hyun, Sangwon
- PLOS Computational Biology, Vol. 11, Issue 8
Collaborative efforts to forecast seasonal influenza in the United States, 2015–2016
journal, January 2019
- McGowan, Craig J.; Biggerstaff , Matthew; Johansson, Michael
- Scientific Reports, Vol. 9, Issue 1
Results from the second year of a collaborative effort to forecast influenza seasons in the United States
journal, September 2018
- Biggerstaff, Matthew; Johansson, Michael; Alper, David
- Epidemics, Vol. 24
Forecasting seasonal influenza with a state-space SIR model
journal, March 2017
- Osthus, Dave; Hickmann, Kyle S.; Caragea, Petruţa C.
- The Annals of Applied Statistics, Vol. 11, Issue 1
Forecasting the spatial transmission of influenza in the United States
journal, February 2018
- Pei, Sen; Kandula, Sasikiran; Yang, Wan
- Proceedings of the National Academy of Sciences, Vol. 115, Issue 11
Reply to Bracher: Scoring probabilistic forecasts to maximize public health interpretability
journal, September 2019
- Reich, Nicholas G.; Osthus, Dave; Ray, Evan L.
- Proceedings of the National Academy of Sciences, Vol. 116, Issue 42