Data from cell phones can be obtained to identify people who are likely to contract the flu, giving epidemiologists a potentially game-changing new tool in the fight against a disease that kills thousands of Americans every year, according to a new research.
"We believe this serves as a window into the future of epidemiological data collection," said Dr Allison Aiello of the University of North Carolina.
"I think that the development of these kinds of models for medical data, where we can now collect data more frequently or in a more personalized manner, using cell phones, is extremely important," said Duke statistician Katherine Heller, a co-author of the paper.
For the study, 103 undergraduates living in 6 University of Michigan dorms were loaded with an app in their cell phones that used Bluetooth to record when came into contact with one another. The undergraduates were also made to fill outa weekly online survey to report health-related behaviors, social interactions and flu symptoms. Anyone who reported flu symptoms was then tested for the flu virus.
This enabled the researchers to identify who contracted the flu after coming in contact with someone else in the cohort with the flu- and what differentiated those people from others who did not contact the flu after such contact. Also they monitored how long it took for people infected with the flu to recover.
An algorithm was developed with the help of statistical analysis that predicts an individual's chance of becoming sick after exposure to the virus, based on behaviors such as sleep, drinking and smoking and personal traits such as sex, age and vaccination status. They then found out that people who drink and smoke were more susceptible to the flu and take longer time to recover than those who had good sleep and exercise habits. The unique aspect of this tool is that it takes into account all the factors at once to figure out each individual's likelihood of getting sick on any particular day.