"App transforms smartphones into fever-detecting thermometers"

Researchers at the University of Washington have developed an app called FeverPhone that uses existing smartphone hardware to estimate core body temperature. The app uses the phone's touchscreen and battery temperature sensors to gather data that a machine learning model uses to estimate people's core body temperatures. In a clinical trial, the app estimated patient core body temperatures with an average error of about 0.23 degrees Celsius, which is in the clinically acceptable range of 0.5 C. The app has the potential to help doctors monitor fevers remotely and intervene sooner in cases of viral infections.