New Studies Find That Mobile Phone Data Can Be Used to Track Spread of Infectious Diseases

Between 2006 and 2012, the amount of cell phone users has increased from about 2 billion to 6 billion, which has created an amazing opportunity for health professionals.

Using mobile phone data, a team of scientists were able to quantitatively demonstrate that the data from mobile phones could predict seasonal disease patterns, thus proving that it may be possible to track the spread of infectious disease each season.

Princeton University and Harvard University researchers used anonymous mobile phone records of more than 15 million people to track the spread of rubella — a contagious viral infection — throughout Kenya.

“One of the unique opportunities of mobile phone data is the ability to understand how travel patterns change over time,” said C. Jessica Metcalf, co-author of the study, which was published in the Proceedings of the National Academy of Sciences. “And rubella is a well-known seasonal disease that has been hypothesized to be driven by human population dynamics, making it a good system for us to test.”

A separate study, which was published in the Proceedings of the 21st ACMSIGKDD Conference on Knowledge Discovery and Data Mining, used mobile health technology to track the spread of influenza. The conference is held annually by the Association for Computing Machinery’s Special Interest Group on Knowledge Discovery and Data Mining, or ACMSIGKDD.

Researchers from the University of North Carolina, Duke University, and the University of Michigan gave 103 undergraduates living in six of the University of Michigan’s dorms mobile phones, which had an app that could record contact between participants via Bluetooth. Participants were also asked to do a weekly survey of social interactions, health-related behaviors, and flu symptoms. If participants reported flu symptoms, they were tested for the virus.

The study tracked flu transmission rates and recovery times. Using that data, researchers were able to create an algorithm that would determine the likelihood of an individual getting sick on a particular day.

“The potential of mobile phone data for quantifying mobility patterns has only been appreciated in the last few years, with methods pioneered by authors on this paper,” said Amy Wesolowski, lead author of the study published in the Proceedings of the National Academy of Sciences. “It is a natural extension to look at seasonal travel using these data.”