A street scene in an unknown village in Angola, where outbreaks of Cholera occurred in 2006 and 2007. Researchers from the Technion and Microsoft developed software that can predict such outbreaks. Photo: Paulo César Santos Via Wikimedia Commons.

Technion-Israel Institute of Technology doctoral student Kira Radinsky and Microsoft researcher Eric Horvitz have developed a program that can predict future disease and violence outbreaks with 70 to 90 percent accuracy. The researchers combined archives accumulated over 20 years by the New York Times and other websites like Wikipedia, and used the data to make the predictions.

“I truly view this as a foreshadowing of what’s to come… eventually this kind of work will start to have an influence on how things go for people,” Horvitz told Technology Review, according to Israel Hayom.

Radinsky and Horvitz’s software correctly predicted Cholera outbreaks in 2006 and 2007 in Angola by using the data to determine that prolonged years of drought tend to be followed by outbreaks of the disease.

“A cholera outbreak warning can be given a year in advance,” said Radinsky.