Detecting influenza epidemics using search engine query data

Abstract

Seasonal influenza epidemics are a major public health concern, causing tens of millions of respiratory illnesses and 250,000 to 500,000 deaths worldwide each year. In addition to seasonal influenza, a new strain of influenza virus against which no previous immunity exists and that demonstrates human-to-human transmission could result in a pandemic with millions of fatalities. Early detection of disease activity, when followed by a rapid response, can reduce the impact of both seasonal and pandemic influenza. One way to improve early detection is to monitor health-seeking behaviour in the form of queries to online search engines, which are submitted by millions of users around the world each day. Here we present a method of analysing large numbers of Google search queries to track influenza-like illness in a population. Because the relative frequency of certain queries is highly correlated with the percentage of physician visits in which a patient presents with influenza-like symptoms, we can accurately estimate the current level of weekly influenza activity in each region of the United States, with a reporting lag of about one day. This approach may make it possible to use search queries to detect influenza epidemics in areas with a large population of web search users.

Forecasting influenza outbreak dynamics in Melbourne from Internet search query surveillance data

“…As the algorithm is based on Internet searches,9 differences in Internet penetration and/or utilisation between populations presumably influence the quality of the data,26 which highlights the importance of evaluating these forecasting techniques in an Australian context. Moreover, this lack of transparency renders it difficult to decide when and how the observation model should be adjusted to account for changes to the Google Flu Trends algorithm.…”

Prevention and Management of Non-Communicable Disease: The IOC Consensus Statement, Lausanne 2013

“…For example, traditional retailers analyze buying habits of their customers and run algorithms to better predict their needs and customize their product suggestions based on unique preferences of the individual [59]. In Public Health, Google is able to predict the spread of an influenza pandemic more accurately and several weeks earlier than the traditional surveillance systems of the US Centers for Disease Control (CDC) [60]. Comprehensive data analytics have long been used in sports such as baseball and soccer to determine success factors and adjust the tactics accordingly [61].…”

Beyond Regulation: Risk Pricing and Responsible Innovation

“…To give one recent example, by analyzing real time searches on terms related to "influenza-like illness", Google Trends has shown the ability to accurately predict by up to several weeks where influenza outbreaks are most likely to occur on a geographical basis, validated through data sets provided by the Centers for Disease Control in the United States (22). Such approaches can be immensely powerful for supporting risk assessment and decision makingsGoogle's Flu Trends supports public health planning to target response to seasonal epidemics.…”