3 March 2024

Trendy Texts

Business, World, Economy, Tech, Sports News

FeverPhone: This app will turn your smartphone into a thermometer to detect fever!

FeverPhone: This app will turn your smartphone into a thermometer

Device makers have struggled to incorporate temperature sensors into smartphones and smartwatches in order to turn them into medically accurate body thermometers, but researchers at the University of Washington claim they’ve found a way to do so with nothing more than a new app. It’s named the FeverPhone.

Although smart wearables such as the Apple Watch Series 8 and Apple Watch Ultra can now detect a user’s body temperature using newly additional sensors, Apple cautions that the feature is not yet accurate enough to be utilised for medical diagnosis or treatment. Rather, both of those gadgets use temperature monitoring to provide customers a better knowledge of their sleep patterns throughout the night. Unlike heart rate readings, the Apple Watch is still not a digital thermometer capable of providing accurate temperature readings on demand.

Non-contact digital thermometers aren’t particularly costly, as many of us discovered during the wilder days of the Covid-19 outbreak, but they can swiftly sell out when demand for them skyrockets. Smartphones were used as a readily available alternative by researchers at the University of Washington. One significant difference is that their method does not require any additional attachments or hardware modifications. Smartphones already use thermistors to monitor the temperature of the device’s internals, including the battery, in order to trigger safety mechanisms to prevent overheating. This is why your iPhone will occasionally display a warning that it has to cool down before you can use it again.


Thermistors, which are also used in medical-grade thermometers, cannot directly monitor a user’s body temperature while within a smartphone, but they can trace the amount of heat energy transmitted between a person and the mobile device with which they are in touch. To imitate a feverish test subject, the researchers heated a plastic bag full of water with a sous-vide machine and pressed the touchscreens of various different cellphones against it, including handsets in protective cases and those with screen protectors. The device’s built-in thermistor was used to measure how rapidly it warmed up during this interaction, and the data was used to train a machine-learning model that powers the FeverPhone app and can predict a user’s body temperature.

The FeverPhone application appears simple enough, but users must hold their device at its corners and press its touchscreen against their forehead for almost 90 seconds. This was determined to be the perfect amount of time for enough body heat to be delivered to the device, and because the forehead engagement is recognised by the touchscreen, the device, and app can tell when a measurement is being taken on purpose.

Also Read: Nasal drops show remarkable results in stroke recovery, research finds

FeverPhone Testing

The app was evaluated by 37 users, including 16 with a slight fever, during a clinical trial at the University of Washington’s School of Medicine’s Emergency Department, and the results were compared to readings from an oral thermometer. The FeverPhone predicted a user’s core body temperature with “an average error of about 0.41 degrees Fahrenheit (0.23 degrees Celsius),” which is comparable to the accuracy of home usage thermometers, including non-contact choices.

FeverPhone App Performance

The researchers are currently attempting to increase the app’s performance by increasing the number of smartphone models used to train its machine learning model, which was initially limited to three smartphones. However, they are hopeful that it can be trained to work with smartwatches as well, which would work much better because their tiny size would allow them to heat up faster and allow for measurements that are considerably shorter than 90 seconds. FeverPhone may never be authorised as a medical grade thermometer, but it appears to be accurate enough to alert users when they may be sick and should take appropriate precautions to protect themselves and others.