The increasing trend for international travel and population mobility have led to increased global interconnectivity and along with that global pandemics. The 2014-2016 West Africa Ebola outbreak – the largest recorded in history – illustrated how these features along with a community unprepared for a sudden outbreak can turn a situation into a crisis, one that costs thousands of lives.
UNICEF Innovation is using technology to tackle this threat. In recent years, the availability of detailed data on human behaviour combined with environmental measurements have led to great advances in the computational modeling of these epidemics.
The work we do.
UNICEF is developing an open-source platform to collect, combine, analyze, and display real-time information based on contributions from academic, private sector and open source data. Data sources include, among others: high-resolution population estimates, air travel from Amadeus, regional mobility estimated using aggregated anonymized mobile phone records and geotagged social media traces, temperature data from IBM, and case data from WHO reports, such as Zika, Dengue, and Ebola.
This data is used as input for epidemiological models running on the platform in real-time and generating forecast scenarios about the spatio-temporal spread of a given disease. Our vision is to integrate several open sources models being developed by the research community.
Our research aims to answer the following questions. Where is the disease under investigation more likely to spread next? Therefore, where should the response efforts be mostly focused to prevent the spread? This information will inform UNICEF country offices and other stakeholders to take faster data-driven decisions about epidemic prevention and containment.
Nevertheless, these datasets are passively built through the use of technology and it is precisely the most vulnerable populations, and children in particular, the demographics with less access to technology, and therefore the less represented in any of these newly available datasets. Hence, we are also developing methodologies to quantify the bias of mobility, as computed from different technologies, as well as to build models that are able to combine data from different sources to produce a more accurate view of the aggregated mobility patterns, one that does not leave behind precisely those populations most in need of support and assistance.
A practical example: Risk of dengue spread in Colombia
In Colombia, UNICEF Innovation is working on a project to push forward inter-institutional efforts for the exploration and development of uses of Big Data for the Colombian health sector. The project brings together UNICEF Colombia, the Ministry of Health, the National Health Institute, Telefonica and academic collaborators from the University of Notre Dame and Boston Children’s Hospital. By means of computer simulations that use real-time data on reported cases and human mobility measured from mobile phone records, we will generate real-time forecasts on the risk of vector-borne disease incidence and spread in Colombian municipalities. This information will be used by the government to take faster decisions for their epidemic preparedness and response activities.