In:
PLOS ONE, Public Library of Science (PLoS), Vol. 16, No. 5 ( 2021-5-19), p. e0250890-
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.
Type of Medium:
Online Resource
ISSN:
1932-6203
DOI:
10.1371/journal.pone.0250890
DOI:
10.1371/journal.pone.0250890.g001
DOI:
10.1371/journal.pone.0250890.g002
DOI:
10.1371/journal.pone.0250890.g003
DOI:
10.1371/journal.pone.0250890.g004
DOI:
10.1371/journal.pone.0250890.g005
DOI:
10.1371/journal.pone.0250890.g006
DOI:
10.1371/journal.pone.0250890.g007
DOI:
10.1371/journal.pone.0250890.g008
DOI:
10.1371/journal.pone.0250890.g009
DOI:
10.1371/journal.pone.0250890.g010
DOI:
10.1371/journal.pone.0250890.g011
DOI:
10.1371/journal.pone.0250890.g012
DOI:
10.1371/journal.pone.0250890.g013
DOI:
10.1371/journal.pone.0250890.g014
DOI:
10.1371/journal.pone.0250890.g015
DOI:
10.1371/journal.pone.0250890.t001
DOI:
10.1371/journal.pone.0250890.t002
DOI:
10.1371/journal.pone.0250890.t003
DOI:
10.1371/journal.pone.0250890.t004
DOI:
10.1371/journal.pone.0250890.t005
DOI:
10.1371/journal.pone.0250890.t006
DOI:
10.1371/journal.pone.0250890.t007
DOI:
10.1371/journal.pone.0250890.t008
DOI:
10.1371/journal.pone.0250890.t009
DOI:
10.1371/journal.pone.0250890.t010
DOI:
10.1371/journal.pone.0250890.t011
DOI:
10.1371/journal.pone.0250890.t012
DOI:
10.1371/journal.pone.0250890.t013
DOI:
10.1371/journal.pone.0250890.t014
DOI:
10.1371/journal.pone.0250890.t015
DOI:
10.1371/journal.pone.0250890.s001
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2021
detail.hit.zdb_id:
2267670-3
Bookmarklink