Researchers from the University of Iowa have developed a “smart thermometer” capable of predicting influenza activity in both large populations and individuals. Findings were published in Clinical Infectious Diseases.
"Being able to track the duration of fevers and the return of fevers could help us learn more about an influenza season as it is emerging and possibly provide information about other infections, including new emerging infectious diseases," said senior study author Philip Polgreen, MD, an associate professor of internal medicine and epidemiology.
Current methods in tracking flu outbreaks rely on data from the Centers for Disease Control and Prevention (CDC), but this data are often two weeks behind real-time flu activity. In response, researchers developed a smart thermometer connected to a mobile phone application to track flu activity.
"Our findings suggest that data from smart thermometers are a new source of information for accurately tracking influenza in advance of standard approaches," Polgreen says. "More advanced information regarding influenza activity can help alert health care professionals that influenza is circulating, help coordinate response efforts, and help anticipate clinic and hospital staffing needs and increases in visits associated with high levels of influenza activity."
To evaluate the accuracy of the thermometer, researchers collected influenza-like illness (ILI) activity data from providers and compared that data from the smart thermometer. Findings showed the smart thermometers data were highly correlated with ILI data at a regional level. Additionally, researchers found they could improve flu predictions by adding forecasting models to thermometer data improved predictions of flu activity by three weeks in advance.
"We found the smart thermometer data are highly correlated with information obtained from traditional public health surveillance systems and can be used to improve forecasting of influenza-like illness activity, possibly giving warnings of changes in disease activity weeks in advance," said lead study author Aaron Miller, PhD, a University of Iowa postdoctoral scholar in computer science. "Using simple forecasting models, we showed that thermometer data could be effectively used to predict influenza levels up to two to three weeks into the future. Given that traditional surveillance systems provide data with a lag time of one to two weeks, this means that estimates of future flu activity may actually be improved up to four or five weeks earlier."