Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 May 19;16(5):e0250890.
doi: 10.1371/journal.pone.0250890. eCollection 2021.

Influenza forecasting for French regions combining EHR, web and climatic data sources with a machine learning ensemble approach

Canelle Poirier  1   2   3   4 , Yulin Hswen  5   6 , Guillaume Bouzillé  1   2   7 , Marc Cuggia  1   2   7 , Audrey Lavenu  8   9   10 , John S Brownstein  6   3 , Thomas Brewer  6 , Mauricio Santillana  3   4
Affiliations

Influenza forecasting for French regions combining EHR, web and climatic data sources with a machine learning ensemble approach

Canelle Poirier et al. PLoS One. .

Abstract

Effective and timely disease surveillance systems have the potential to help public health officials design interventions to mitigate the effects of disease outbreaks. Currently, healthcare-based disease monitoring systems in France offer influenza activity information that lags real-time by one to three weeks. This temporal data gap introduces uncertainty that prevents public health officials from having a timely perspective on the population-level disease activity. Here, we present a machine-learning modeling approach that produces real-time estimates and short-term forecasts of influenza activity for the twelve continental regions of France by leveraging multiple disparate data sources that include, Google search activity, real-time and local weather information, flu-related Twitter micro-blogs, electronic health records data, and historical disease activity synchronicities across regions. Our results show that all data sources contribute to improving influenza surveillance and that machine-learning ensembles that combine all data sources lead to accurate and timely predictions.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Ranks obtained by each model over the 12 French regions for PCC and RMSE.
Fig 2
Fig 2. Visualization of correlation and errors obtained for real-time estimate with each model.
Fig 3
Fig 3. One-week ahead estimate obtained with ARGONet and AR(52) models from January 2015 to March 2017.
Fig 4
Fig 4. Two-week ahead estimate obtained with ARGONet and AR(52) models from January 2015 to March 2017.
Fig 5
Fig 5. Error distribution.
Fig 6
Fig 6. Correlation distribution.
Fig 7
Fig 7. Real-time estimate obtained with ARGONet and AR(52) models from January 2015 to March 2017.
Fig 8
Fig 8. Nouvelle-Aquitaine real time estimate.
Fig 9
Fig 9. Coefficients Nouvelle-Aquitaine real-time estimate.
Fig 10
Fig 10. Visualization of correlation and errors obtained for one-week ahead estimate with each model.
Fig 11
Fig 11. Nouvelle-Aquitaine one-week ahead estimate.
Fig 12
Fig 12. Coefficients Nouvelle-Aquitaine one-week ahead estimate.
Fig 13
Fig 13. Visualization of correlation and errors obtained for two-week ahead estimate with each model.
Fig 14
Fig 14. Nouvelle-Aquitaine two-week ahead estimate.
Fig 15
Fig 15. Coefficients Nouvelle-Aquitaine two-week ahead estimate.
See this image and copyright information in PMC

References

    1. Ferguson N. M. et al. Strategies for mitigating an influenza pandemic. Nature 442, 448–452, (2006). 10.1038/nature04795 - DOI - PMC - PubMed
    1. Yang S., Santillana M. & Kou S. C. Accurate estimation of influenza epidemics using google search data via ARGO. Proc. Natl. Acad. Sci. United States Am. 112, 14473–14478, (2015). 10.1073/pnas.1515373112 - DOI - PMC - PubMed
    1. Yang W., Lipsitch M. & Shaman J. Inference of seasonal and pandemic influenza transmission dynamics. Proc. Natl. Acad. Sci. United States Am. 112, 2723–2728, (2015). 10.1073/pnas.1415012112 - DOI - PMC - PubMed
    1. Kalimeri K. et al. Unsupervised extraction of epidemic syndromes from participatory influenza surveillance self-reported symptoms. PLOS Comput. Biol. 15, e1006173, (2019). 10.1371/journal.pcbi.1006173 - DOI - PMC - PubMed
    1. Fleming D.M., P. W., van der Velden J. The evolution of influenza surveillance in europe and prospects for the next 10 years. Vaccine 21, 1749–1753 (2003). 10.1016/S0264-410X(03)00066-5 - DOI - PubMed

Publication types