The FeverPhone App Turns an Off-the-Shelf Smartphone Into a Clinically-Accurate Thermometer

A team of researchers from the Universities of Washington and Toronto have developed an app which turns an off-the-shelf smartphone into a temperature sensor suitable for diagnosing a patient's fever — without needing any additional hardware: FeverPhone.

"In undergrad, I was doing research in a lab where we wanted to show that you could use the temperature sensor in a smartphone to measure air temperature," says lead author Joseph Breda of the inspiration behind the team's research. "When I came to the UW, my adviser and I wondered how we could apply a similar technique for health. We decided to measure fever in an accessible way. The primary concern with temperature isn't that it's a difficult signal to measure; it's just that people don’t have thermometers."

"People come to the ER all the time saying, 'I think I was running a fever.' And that's very different than saying 'I was running a fever,'" adds Mastafa Springston, PhD,co-author of the study into the app-based diagnostic approach. "In a wave of influenza, for instance, people running to the ER can take five days, or even a week sometimes. So if people were to share fever results with public health agencies through the app, similar to how we signed up for COVID exposure warnings, this earlier sign could help us intervene much sooner."

The trick is to use the temperature sensor already present in a smartphone for the purposes of checking on the health of the battery, but in an unusual manner. A patient holds the smartphone's display against their forehead for 90 seconds, and the rise in temperature is compared against the ambient temperature to determine their core body temperature — using a machine learning model trained on a number of test cases to calibrate the results.

While it may sound like a crazy approach, it works: in testing, the FeverPhone app was able to estimate the core body temperature of 37 patients in a real emergency department with an average error of 0.23°C (0.41°F) — around half the 0.5°C error range required for clinical use. "We started with smartphones since they’re ubiquitous and easy to get data from," Breda says. "I am already working on seeing if we can get a similar signal with a smartwatch. What’s nice, because watches are much smaller, is their temperature will change more quickly. So you could imagine having a user put a Fitbit to their forehead and measure in 10 seconds whether they have a fever or not."

The team has highlighted a range of avenues for future research, including expanding the number of smartphone models supported from its current three and expanding to wearables along with supporting measurement of severe fevers — excluded from initial testing due to how obvious the symptoms are to casual observation and interference between excessively sweaty skin and commercial skin-contact thermometers.

The team's work is available in the Proceedings of the ACM on Interactive, Mobile, Wearable, and Ubiquitous Technologies under open-access terms.

Main article image courtesy of Dennis Wise/University of Washington.