Malaria can have severe socio-economic impacts on populations. It’s a cause of household poverty as it results in absenteeism from daily activities of productive living and earning an income. It also prevents many children from attending school, diminishing their capacity to realise their full potential.
Malaria is preventable and curable. Increased efforts are dramatically reducing the malaria burden in many countries.
Zambia has undertaken an ambitious campaign to eliminate malaria by 2020. To support its efforts EXASOL, an in-memory analytic database developer, and PATH, an international nonprofit organisation and global leader in health and innovation, have announced a partnership to support the Zambian government’s campaign says, an article in IT News Africa.
“Data analytics is often discussed as a way for business to derive value from the data they hold, whether that is to increase profitability or serve customers better,” said Aaron Auld, CEO, EXASOL. “But data can also unlock important information that can help organizations such as PATH improve the way they address Malaria. This ultimately shows the value of data in saving lives.” EXASOL joins Visualize No Malaria, a partnership between Zambia’s Ministry of Health, PATH, Tableau, and several technical partners including Alteryx, Mapbox, DataBlick, Twilio, DigitalGlobe, and Slalom.
EXASOL‘s contribution includes providing access to its database in the cloud on Amazon Web Services. It’ll enable the Visualize No Malaria team to perform complex, real-time analysis and queries of Big Data.
Allan Walker, a volunteer with expertise in data analytics and visualisation, is helping PATH’s Visualize No Malaria team to create analyses that estimate where malaria cases are more likely to occur and find relationships between mosquito vectors and human carriers of the disease.
The team’s project involves loading complex geospatial data into EXASOL’s database to model geological features in Zambia’s Southern Province, such as elevation, slope and hydrological features such as topographic wetness and stream power. It shows if land is dry or wet, and if water is still or moving.
The team also uses time-series regression models of population density and mobility, and meteorological models of precipitation and temperature to establish relationships with epidemiological data. The analyses can then be used by Zambian decision-makers to focus on probable malaria outbreak areas then respond quickly to new cases. This data can be life-saving for many communities. Other African countries battling malaria can benefit too.