FeverPhone: This App Will Transform Your Smartphone Into a Thermometer Without Invasive Hardware

For individuals in need of a quick temperature check but lacking a thermometer, help may soon be at hand.

A group of researchers from the University of Washington came up with FeverPhone, a special app that requires no extra hardware just to transform your simple smartphone into a clinically accurate thermometer.

Your Smartphone Can Accurately Measure Body Temperature

In the face of viral infections like COVID-19, the ability to measure body temperature accurately is crucial for early detection and containment.

However, traditional thermometers can be expensive and may not be readily available, particularly in under-resourced areas. This has led to the development of FeverPhone, an app designed to leverage existing smartphone hardware to transform smartphones into thermometers without the need for additional devices.

How FeverPhone Works

According to Gizmodo, FeverPhone harnesses the touchscreens and battery temperature sensors of smartphones to collect data. Through machine learning algorithms, this data is used to estimate core body temperatures.

In laboratory tests, the app demonstrated comparable accuracy to some consumer-grade thermometers. The potential of this technology has excited doctors, as it could enable individuals to share their fever results with public health agencies, facilitating early interventions and faster responses during outbreaks.

Smartphones commonly contain thermistors, tiny sensors that monitor battery temperature. The researchers realized that these sensors could be repurposed to measure heat transfer between the phone and a person's body.

By assessing the heat rise when the phone comes into contact with a person and utilizing touchscreen data, FeverPhone can estimate body temperature.

Is FeverPhone Really Effective?

To validate the efficacy of FeverPhone, the researchers conducted tests using various scenarios and phone models. They gathered data by simulating a warm forehead using a plastic bag of water heated with a sous-vide machine. The app was then calibrated using machine learning models to account for variations in phone models, accessories, and pressure on the phone.

The researchers conducted a clinical trial which involved 37 participants. They use the app to measure the temperature of each individual. Upon testing, they discovered that the average error in the measurement is only 0.41 degrees Fahrenheit (0.23 degrees Celsius).

Limitations and the Future of Study

While the initial results are promising, the researchers acknowledge the need for further investigation. The study did not include individuals with severe fevers or test a wide range of phone models.

"We started with smartphones since they're ubiquitous and easy to get data from. 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 study's lead author Joseph Breda said.

Expanding FeverPhone's compatibility with various smartphones and smartwatches would enhance its potential for widespread public health applications. Additionally, researchers envision exploring the use of smartwatches for temperature monitoring, as their smaller size enables quicker temperature changes and ease of use.