University of Washington Professor Shwetak Patel and other researchers have built an app that turns smartphones into thermometers without adding new hardware.
The app, FeverPhone uses the phone’s touchscreen, battery temperature sensors and a machine-learning model to estimate people’s core body temperatures. When the researchers tested FeverPhone on 37 patients in an emergency department, the app estimated core body temperatures with accuracy comparable to some consumer thermometers. The study, however, did not include people with severe fevers above 101.5°F.
The researchers used the data from different test cases to train a machine learning model that used the complex interactions to estimate body temperature. As more test cases were added, they were able to calibrate the model to account for the variations in things such as phone accessories. Then the team was ready to test the app on people.
To use FeverPhone, the participants held the phones like point-and-shoot cameras — with forefingers and thumbs touching the corner edges to reduce heat from the hands being sensed. They then pressed the touchscreen against their foreheads for about 90 seconds, which the researchers found to be the ideal time to sense body heat transferring to the phone. The app estimated patient core body temperatures with an average error of about 0.23 degrees Celsius, which is in the clinically acceptable range.
The study has been published in the journal Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies.
