Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Even a good influenza forecasting model can benefit from internet-based nowcasts, but those benefits are limited

Journal Article · · PLoS Computational Biology (Online)
 [1];  [1];  [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
+ Show Author Affiliations
The ability to produce timely and accurate flu forecasts in the United States can significantly impact public health. Augmenting forecasts with internet data has shown promise for improving forecast accuracy and timeliness in controlled settings, but results in practice are less convincing, as models augmented with internet data have not consistently outperformed models without internet data. In this paper, we perform a controlled experiment, taking into account data backfill, to improve clarity on the benefits and limitations of augmenting an already good flu forecasting model with internet-based nowcasts. Here, our results show that a good flu forecasting model can benefit from the augmentation of internet-based nowcasts in practice for all considered public health-relevant forecasting targets. The degree of forecast improvement due to nowcasting, however, is uneven across forecasting targets, with short-term forecasting targets seeing the largest improvements and seasonal targets such as the peak timing and intensity seeing relatively marginal improvements. The uneven forecasting improvements across targets hold even when “perfect” nowcasts are used. These findings suggest that further improvements to flu forecasting, particularly seasonal targets, will need to derive from other, non-nowcasting approaches.
Research Organization:
Los Alamos National Laboratory (LANL)
Sponsoring Organization:
USDOE Laboratory Directed Research and Development (LDRD) Program
Grant/Contract Number:
89233218CNA000001
OSTI ID:
1495153
Report Number(s):
LA-UR-18-24343
Journal Information:
PLoS Computational Biology (Online), Journal Name: PLoS Computational Biology (Online) Journal Issue: 2 Vol. 15; ISSN 1553-7358
Publisher:
Public Library of ScienceCopyright Statement
Country of Publication:
United States
Language:
English

References (27)

Results from the second year of a collaborative effort to forecast influenza seasons in the United States journal September 2018
Detecting influenza epidemics using search engine query data journal February 2009
Real-time influenza forecasts during the 2012–2013 season journal December 2013
Adaptive nowcasting of influenza outbreaks using  Google searches journal October 2014
The Parable of Google Flu: Traps in Big Data Analysis journal March 2014
Twitter Improves Influenza Forecasting journal January 2014
Forecasting Peaks of Seasonal Influenza Epidemics journal January 2013
Forecasting the 2013–2014 Influenza Season Using Wikipedia journal May 2015
Nonmechanistic forecasts of seasonal influenza with iterative one-week-ahead distributions journal June 2018
The Use of Twitter to Track Levels of Disease Activity and Public Concern in the U.S. during the Influenza A H1N1 Pandemic journal May 2011
Forecasting influenza-like illness dynamics for military populations using neural networks and social media journal December 2017
Regularization Paths for Generalized Linear Models via Coordinate Descent journal January 2010
Subregional Nowcasts of Seasonal Influenza Using Search Trends journal January 2017
Global Disease Monitoring and Forecasting with Wikipedia journal March 2016
Evaluation of mechanistic and statistical methods in forecasting influenza-like illness text January 2018
Advances in nowcasting influenza-like illness rates using search query logs journal August 2015
Evaluation of mechanistic and statistical methods in forecasting influenza-like illness journal July 2018
Measuring Global Disease with Wikipedia: Success, Failure, and a Research Agenda
  • Priedhorsky, Reid; Osthus, Dave; Daughton, Ashlynn R.
  • Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing - CSCW '17 https://doi.org/10.1145/2998181.2998183
conference January 2017
Global Disease Monitoring and Forecasting with Wikipedia journal November 2014
Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance journal October 2015
Estimating influenza incidence using search query deceptiveness and generalized ridge regression journal October 2019
Circulating Proteomic Signature of Early Death in Heart Failure Patients with Reduced Ejection Fraction journal January 2019
Forecasting the 2013--2014 Influenza Season using Wikipedia text January 2014
Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance text January 2015
Measuring global disease with Wikipedia: Success failure, and a research agenda (Supplemental data) dataset January 2016
Measuring global disease with Wikipedia: Success failure, and a research agenda (Supplemental data) dataset January 2016
Subregional Nowcasts of Seasonal Influenza Using Search Trends text January 2017

Cited By (3)

Forecasting dengue and influenza incidences using a sparse representation of Google trends, electronic health records, and time series data journal November 2019
Google Health Trends performance reflecting dengue incidence for the Brazilian states journal March 2020
Improving probabilistic infectious disease forecasting through coherence journal January 2021

Figures / Tables (11)

Fig 1(p. 5)figure Fig 1
Fig 2(p. 6)figure Fig 2
Fig 3(p. 7)figure Fig 3
Fig 4(p. 7)figure Fig 4
Fig 5(p. 9)figure Fig 5
Table 1(p. 10)table Table 1
Fig 6(p. 11)figure Fig 6
Fig 7(p. 14)figure Fig 7
Fig 9(p. 15)figure Fig 9
Figure-8(p. 15)figure Figure-8
Fig 10(p. 16)figure Fig 10

Similar Records

Multiscale influenza forecasting
Journal Article · Wed May 19 20:00:00 EDT 2021 · Nature Communications · OSTI ID:1833720
Nowcasting influenza outbreaks using open-source media report.
Technical Report · Thu Jan 31 23:00:00 EST 2013 · OSTI ID:1093696

Related Subjects

60 APPLIED LIFE SCIENCES