Researchers Develop FeverPhone App: Transforming Smartphones into Accurate Thermometers

Revolutionizing Temperature Measurement: Introducing FeverPhone - Turning Smartphones into Accurate Thermometers

Image Credit: The Engineer

Researchers at the University of Washington claim to have developed a solution, called FeverPhone, that addresses the challenge device manufacturers face in integrating temperature sensors into smartphones and smartwatches for precise medical-grade body temperature measurements. They propose that a simple app can transform an ordinary smartphone into a reliable thermometer.

While some smart wearables like the Apple Watch Series 8 and Apple Watch Ultra now include temperature sensors, Apple emphasizes that the current technology is not yet accurate enough for medical purposes. Instead, these devices employ temperature measurements to enhance users' understanding of their sleep patterns, rather than providing real-time, accurate temperature readings like a dedicated digital thermometer.

During the height of the Covid-19 pandemic, the demand for non-contact digital thermometers surged, leading to shortages. To provide an easily accessible alternative, researchers at the University of Washington focused on utilizing smartphones. What sets their solution apart is that it doesn't require any additional attachments or hardware upgrades.

Smartphones already incorporate thermistors, which are components used to measure the device's internal temperature, such as the battery, to prevent overheating. This is why iPhones sometimes display a warning message when they need to cool down before further use.

Although thermistors in smartphones cannot directly measure a user's body temperature, they can track the heat energy exchanged between the user and the mobile device they are in contact with. To simulate a test subject with a fever, the researchers used a sous-vide machine to heat a bag of water and pressed the touchscreens of various smartphones, including those with protective cases and screen protectors, against it.

The built-in thermistor measured the rate at which the device heated up during this interaction. The collected data was then used to train a machine learning model that powers the FeverPhone app, enabling it to estimate the user's body temperature.

To use the FeverPhone app, users need to hold their device by its corners and press the touchscreen against their forehead for approximately 90 seconds. This duration was determined as the optimal time for sufficient transfer of body heat to the device. The touchscreen detects the interaction with the forehead, signaling the device and the app to initiate a deliberate measurement.

A clinical trial conducted at the University of Washington's School of Medicine's Emergency Department involved 37 participants, including 16 individuals with a mild fever. The results obtained from the FeverPhone app were compared to readings from an oral thermometer. The app demonstrated the ability to predict the user's core body temperature with an average error of approximately 0.41 degrees Fahrenheit (0.23 degrees Celsius). This level of accuracy is comparable to that of home-use thermometers, including non-contact options.

A clinical trial conducted at the University of Washington's School of Medicine's Emergency Department involved 37 participants, including 16 individuals with a mild fever. The results obtained from the FeverPhone app were compared to readings from an oral thermometer.

The app demonstrated the ability to predict the user's core body temperature with an average error of approximately 0.41 degrees Fahrenheit (0.23 degrees Celsius). This level of accuracy is comparable to that of home-use thermometers, including non-contact options.