Professional Documents
Culture Documents
Role of Big Data in Detection
Role of Big Data in Detection
Role of big data in the Intelligence Network, a news-feed information on their condition on the
aggregator developed by the Public internet and an estimate of disease in
early detection of Ebola Health Agency of Canada, provided the community can be produced by Published Online
and other emerging the first alert of SARS (more than monitoring the frequency of specific December 3, 2014
http://dx.doi.org/10.1016/
infectious diseases 2 months before publication by searches. Overall, results for this S2214-109X(14)70356-0
WHO) and prompted the confirm- approach have been promising; the
The lack of adequate disease surveil- ation of an emerging disease event scope of research has, however, been
lance systems in Ebola-affected areas by the Chinese Government. 2 A limited to a small number of diseases,
has both reduced the ability to respond more recently devel oped system, particularly influenza, and has mainly For HealthMap see
locally and has increased global risk. HealthMap,3 is currently applying a focused on industrialised countries. http://healthmap.org/ebola/
There is a need to improve disease similar data-aggregation approach to We used Google Trends to assess For Google Trends see
surveillance in vulnerable regions, and monitor the evolving Ebola outbreak; the volume and location of Google http://www.google.com/trends
digital surveillance could present a HealthMap identified news stories searches for “ebola” between Jan 1,
viable approach. reporting a strange fever in Guinea 2014, and Oct 27, 2014. Search volume
Digital surveillance seeks to gain on March 14, 2014—9 days before the data were downloaded from Google
knowledge of public health issues release of official case information for Trends on Oct 28, 2014. Internet
through the analysis of data in the the ongoing Ebola outbreak. search volume increased markedly
digital domain (such as internet Currently, the most comprehensively from affected regions over the course
search metrics, Twitter posts, or investigated digital surveillance of the epidemic, and most Google
online news stories), the distribution approach is based on monitoring of searches during 2014 for “ebola”
of these data, and patterns of access. internet search metrics.4 These systems originated from the regions most
It has already shown some promise.1 work on the premise that people who affected (Liberia, Guinea, and Sierra
In 2002, the Global Public Health contract a disease are likely to seek Leone; figure). Furthermore, search
Tunisia
Algeria
Libya
Mauritania
Cape Verde
Mali
1 case
1 case Niger
Senegal
The Gambia
Chad
Guinea-Bissau Burkina Faso
Guinea
1553 cases
Benin
Google search index Sierra Ghana
No data 6–7 15–21 3896 cases Leone Togo Nigeria
Côte
1 8–9 22–32
Liberia d’Ivoire
2–3 10–11 >32
4–5 12–14 4665 cases
20 cases Cameroon
0 250 500 1000 1500 2000
Kilometres