Daily Google search queries - added value to national influenza surveillance
PHE ePoster Library. Owens K. 09/10/18; 221341; 161
Katie Owens
Katie Owens
Login now to access Regular content available to all registered users.

You may also access this content "anytime, anywhere" with the Free MULTILEARNING App for iOS and Android
Rate & Comment (0)
Abstract Current surveillance schemes monitoring influenza-like illness (ILI) are mostly run on data routinely provided through established healthcare systems. To complement existing surveillance and potentially help improve the timeliness and obtain community based estimates of ILI in the general population, the use of online user generated content, in the form of Google search queries, was assessed via daily estimates. Combining natural language processing and machine learning techniques, a non-linear Gaussian Process model was developed by i-sense to produce real-time ILI estimates. The supervised model, trained on historical Royal College of General Practitioners (RCGP) weekly ILI GP consultation rates, produced daily estimates. These were based on the proportion of ILI related search queries within a 10%-15% sample of all queries issued, extracted daily from Google's Health Trends Application Programming Interface (API).The underlying trend of daily ILI estimates for 2017/18 was comparable to those seen within established surveillance systems. An increase in daily estimated rates was observed from week 46, before peaking during week 2. This peak was observed one week earlier than that for RCGP data (week 3) and similar to daily ILI GP syndromic surveillance data.Throughout the season, daily estimates produced by the model provided more timely updates at a national level compared to traditional weekly sentinel surveillance, but similar to daily ILI syndromic surveillance data. Using the model as a surveillance method would be complementary to those already in place, providing an additional estimation of ILI cases in the general population in real-time. External funding details Funding by EPSRC through i-sense.
    This eLearning portal is powered by:
    This eLearning portal is powered by MULTIEPORTAL
Anonymous User Privacy Preferences

Strictly Necessary Cookies (Always Active)

MULTILEARNING platforms and tools hereinafter referred as “MLG SOFTWARE” are provided to you as pure educational platforms/services requiring cookies to operate. In the case of the MLG SOFTWARE, cookies are essential for the Platform to function properly for the provision of education. If these cookies are disabled, a large subset of the functionality provided by the Platform will either be unavailable or cease to work as expected. The MLG SOFTWARE do not capture non-essential activities such as menu items and listings you click on or pages viewed.

Performance Cookies

Performance cookies are used to analyse how visitors use a website in order to provide a better user experience.

Save Settings