Researchers identified search terms from 2011 to 2012 and compared them with the U.S. Centers for Disease Control and Prevention’s data on the prevalence of risk factors in certain states, including exercise, tobacco use, diabetes and cardiovascular disease, according to a Reuters report on the study.
Researchers generated predictive algorithms to measure the correlation between risk factor and disease presence. The web search model predicted 11.2 percent of people in Alabama had diabetes, and the actual values from the CDC indicated 11.8 percent had diabetes. Additionally the model predicted 9.4 percent of people in New Jersey and 8.1 percent of people in Nevada had diabetes, and the actual values show 8.8 percent of people in New Jersey and 10.3 percent of people in Nevada had diabetes.
“The high predictive validity of web search activity for non-communicable disease risk has potential to provide real-time information on population risk during policy implementation and other population-level NCD prevention efforts,” the authors concluded.
More articles on health IT:
MEDITECH, Merge, Kareo join CommonWell
New Mexico Health Information Collaborative launches HIE
Former Cleveland Clinic executive Fred DeGrandis named chief administrative officer of the Global Center for Health Innovation
