There are few tasks that your smartphone cannot perform. But, have you ever envisioned your smartphone as a substitute for a medical device, such as a thermometer? Now, this is certainly feasible.
The FeverPhone app, developed by a group of researchers at the University of Washington, can transform smartphones into thermometers without the need for additional hardware.
According to the developers, the app utilises the touchscreen and repurposes the existing battery temperature sensors to collect data that is used by a machine learning model to estimate people’s inner body temperatures.
Ashok Nair joins the healthtech platform WatchYourHealth as Co-Founder and Global Executive Director.
“When researchers tested FeverPhone on 37 patients in an emergency department, the app estimated central body temperatures with accuracy comparable to that of some consumer thermometers,” according to a statement from the University.
The group published their findings in the Proceedings of the ACM on Interactive, Mobile, Wearable, and Ubiquitous Technologies on March 28.
“As an undergraduate, I conducted research in a laboratory to demonstrate that a smartphone’s temperature sensor could be used to measure ambient temperature. When I arrived at the University of Washington, my advisor and I pondered how we could apply a similar method to health. We decided to measure fever in a straightforward manner. Joseph Breda, a doctoral student at the Paul G. Allen School of Computer Science & Engineering at the University of Washington and the study’s lead author, said in a statement, “The primary concern with temperature is not that it is a difficult signal to measure, but that people do not have thermometers.”
According to the scientists, the app is the first to estimate whether individuals have fevers using existing phone sensors.
Breda also maintained that the app requires additional training data before it can be broadly adopted, but the potential of such technology is exciting for physicians.
People frequently visit the emergency room claiming they had a fever. And this is very distinct from saying, “I had a fever.” People rushing to the emergency room during an outbreak of influenza, for instance, can take five days or even a week. So, if people shared 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,” said Dr. Mastafa Springston, co-author of the study and UW clinical instructor in the Department of Emergency Medicine at the UW School of Medicine.
According to the scientists, clinical-grade thermometers estimate body temperature using minuscule sensors known as thermistors. Smartphones on the market contain thermistors, which are primarily used to monitor the temperature of the battery. However, the UW researchers realised that they could use these sensors to monitor heat transfer between a person and a mobile device. The touchscreen of the phone could detect skin-to-phone contact, and the thermistors could measure the ambient temperature and the increase in heat when the phone was in contact with a body, according to the report.
In a clinical trial at the UW School of Medicine’s Emergency Department, the researchers compared FeverPhone’s temperature estimates to an oral thermometer reading. 16 of the 37 participants recruited had at least a moderate fever.
“Overall, FeverPhone estimated patient core body temperatures with an average error of approximately 0.41 degrees Fahrenheit (0.23 degrees Celsius), which is within the clinically acceptable range of 0.5 C,” the authors explained.
The researchers have identified several areas for further study. According to the team, participants with severe fevers above 101.5 F (38.6 C) were excluded from the study because these temperatures are simple to diagnose and sweaty skin tends to confound other skin-contact thermometers.
Additionally, FeverPhone was only evaluated on three phone models. According to the team, training it to operate on other smartphones and devices such as smartwatches would increase its potential for public health applications.
“We began with smartphones because they are pervasive and simple to obtain data from. I am already examining whether a smartwatch can receive an analogous signal. Because watches are so much smaller, their temperatures can alter more rapidly. “You could envision a user placing a Fitbit on their cranium and determining in 10 seconds whether or not they have a fever,” Breda said.
