TY - JOUR
T1 - Using web search queries to monitor influenza-like illness
T2 - an exploratory retrospective analysis, Netherlands, 2017/18 influenza season
AU - Schneider, Paul P
AU - van Gool, C.J.
AU - Spreeuwenberg, Peter
AU - Hooiveld, Mariëtte
AU - Donker, Gé A
AU - Barnett, David J
AU - Paget, John
N1 - Funding Information:
Funding statement: This work was supported by funding from Wellcome [108903/B/15/Z] and the University of Sheffield.
Publisher Copyright:
© 2020 European Centre for Disease Prevention and Control (ECDC). All rights reserved.
PY - 2020/5/28
Y1 - 2020/5/28
N2 - BackgroundDespite the early development of Google Flu Trends in 2009, standards for digital epidemiology methods have not been established and research from European countries is scarce.AimIn this article, we study the use of web search queries to monitor influenza-like illness (ILI) rates in the Netherlands in real time.MethodsIn this retrospective analysis, we simulated the weekly use of a prediction model for estimating the then-current ILI incidence across the 2017/18 influenza season solely based on Google search query data. We used weekly ILI data as reported to The European Surveillance System (TESSY) each week, and we removed the then-last 4 weeks from our dataset. We then fitted a prediction model based on the then-most-recent search query data from Google Trends to fill the 4-week gap ('Nowcasting'). Lasso regression, in combination with cross-validation, was applied to select predictors and to fit the 52 models, one for each week of the season.ResultsThe models provided accurate predictions with a mean and maximum absolute error of 1.40 (95% confidence interval: 1.09-1.75) and 6.36 per 10,000 population. The onset, peak and end of the epidemic were predicted with an error of 1, 3 and 2 weeks, respectively. The number of search terms retained as predictors ranged from three to five, with one keyword, 'griep' ('flu'), having the most weight in all models.DiscussionThis study demonstrates the feasibility of accurate, real-time ILI incidence predictions in the Netherlands using Google search query data.
AB - BackgroundDespite the early development of Google Flu Trends in 2009, standards for digital epidemiology methods have not been established and research from European countries is scarce.AimIn this article, we study the use of web search queries to monitor influenza-like illness (ILI) rates in the Netherlands in real time.MethodsIn this retrospective analysis, we simulated the weekly use of a prediction model for estimating the then-current ILI incidence across the 2017/18 influenza season solely based on Google search query data. We used weekly ILI data as reported to The European Surveillance System (TESSY) each week, and we removed the then-last 4 weeks from our dataset. We then fitted a prediction model based on the then-most-recent search query data from Google Trends to fill the 4-week gap ('Nowcasting'). Lasso regression, in combination with cross-validation, was applied to select predictors and to fit the 52 models, one for each week of the season.ResultsThe models provided accurate predictions with a mean and maximum absolute error of 1.40 (95% confidence interval: 1.09-1.75) and 6.36 per 10,000 population. The onset, peak and end of the epidemic were predicted with an error of 1, 3 and 2 weeks, respectively. The number of search terms retained as predictors ranged from three to five, with one keyword, 'griep' ('flu'), having the most weight in all models.DiscussionThis study demonstrates the feasibility of accurate, real-time ILI incidence predictions in the Netherlands using Google search query data.
KW - DIGITAL DISEASE DETECTION
KW - SURVEILLANCE
U2 - 10.2807/1560-7917.ES.2020.25.21.1900221
DO - 10.2807/1560-7917.ES.2020.25.21.1900221
M3 - Article
C2 - 32489174
SN - 1560-7917
VL - 25
SP - 13
EP - 22
JO - Eurosurveillance
JF - Eurosurveillance
IS - 21
ER -