Google Technology in the Surveillance of Hand Foot Mouth Disease in Asia

Abstract

Background: Hand foot Mouth Disease (HFMD) is a worldwide Enteroviral infection; severe outbreaks have occurred recently in the US and Asia. Google technology has been shown to predict influenza epidemics and is a potential resource to track epidemics in developed countries where the use of Web-based searches is prevalent.Methods: Google Trends and Google Correlate were used to enumerate Web based search queries related to HFMD in three Asian regions and were compared to known seasonal variations and standard surveillance data to investigate for strong correlation. We also test whether a mathematical model, constructed using Google Correlate, would have been able to predict, in retrospect, an outbreak of HFMD in Singapore.Results: HFMD-related search queries strongly correlated to known HFMD seasonal variation and standard surveillance data. Our mathematical model of Singaporean HFMD did predict the magnitude and chronology of the summer 2012 outbreak.Conclusions: Given the correlation of Google technology with known HFMD seasonal patterns and surveillance data in select Asian regions, this technology shows enormous potential for HFMD surveillance. Further prospective studies are needed to validate the utility of Google technology in HFMD surveillance.

Towards Identifying and Reducing the Bias of Disease Information Extracted from Search Engine Data

“…This result is not only better than the error level generated when strictly using historical HFMD cases, the composite index, and the revised index but rather it is also 11.19% lower than the error level generated when combining the composite index with lagged CCDC data. While Cayce et al [8] found Google Trends to serve as a suitable tool for tracking HFMD trends in developed countries in Asia (e.g., Singapore and Japan), they also found that Google Trends is not strongly correlated with surveillance data in Hong Kong. This phenomenon may be more pronounced for developing countries where regional differences are significant.…”

“…The Baidu Index provides data on three spatial scales: country-, province-and city-wide. To date, the Baidu Index has been used to track influenza [6] and H7N9 [8] trends in China. However, previous studies have primarily focused on a single spatial scale [1,[11][12][13].…”

“…Despite these biases and problems, as a new and alternative data source, we cannot deny the advantages of search engine data for monitoring diseases. To date, search engine data have been used to track the flu [1,5], dengue fever [6,7], Hand, Foot and Mouth Disease (HFMD) [8,9] and several other diseases. Lazer et al [3] have argued that search engine data, such as those used in Google Flu Trends and in other major data sets, should not be used alone but should instead be used as a supplement to traditional data.…”