October 31, 2012

Cellular Data Bites Back at Malaria

Ian Armas Foster

Despite the immense complexity in predicting the spread of disease, mathematicians have developed models and formulas that predict how many people will succumb to a certain disease over time—the  same formulas that constitute Newton’s Law of Cooling and Population Growth. But in order to really get a handle on a disease, the location and trajectory of an outbreak are paramount, as demonstrated by new research in public health.

A group of researchers from the Harvard School of Public Health sought to gain insight on the spread of disease by combining big data from cell phone usage with malaria prevalence maps in order to track the movement of the disease in their paper, “Quantifying the impact of human mobility on malaria.”

Said author Caroline Buckee, an assistant professor of epidemiology at HSPH, “This is the first time that such a massive amount of cell phone data—from millions of individuals over the course of a year—has been used, together with detailed infectious disease data, to measure human mobility and understand how a disease is spreading.”

The team analyzed the movement of nearly 15 million Kenyan cell phone subscribers over the course of a year (from June 2008 to June 2009) and compared it to the instances of malaria found in the country using a map provided by the Kenya Medical Research Institute and the Malaria Altlas Project. The goal was to identify both source and sink points, or where the disease originates and where the disease primarily ends up.

Not surprisingly, they found that one of the primary sources was the area near Lake Victoria, as lakes are prime breeding grounds for mosquitoes. However, according to the study, a surprisingly large portion of non-native infections ended up in Nairobi, Kenya’s capitol.

The researchers, using text and call information, figured out that Nairobi was a sink by mapping every journey taken by each of the nearly 15 million cell phone subscribers. 15 million people journeying over the course of a year produces quite a large dataset, even before comparing it to the malaria prevalence map. Through that data it was discovered that many people who travel to mosquito hotspots like Lake Victoria or the shore originate in Nairobi and end up bringing the disease back with them.

 Malaria kills one million people per year, the vast majority of which are children under the age of 5 in Sub-Saharan Africa. The disease has received worldwide attention, with organizations like Nothing But Nets raising millions of dollars for mosquito bednets to prevent carriers from infecting people during the night. This research could aid that cause by pointing to locations where nets would be more effective, and possibly even sending text alerts to people who are moving into a highly infected area.

 

Related Articles

Can Hype Spell Hope for Predictive Healthcare Analytics?

Adding Autonomy to Personalized Medicine

Taking the Shock out of Sepsis with Big Data Analytics