Smartphone app can sense ear infections in children

17 May 2019 (Last Updated December 23rd, 2019 10:16)

A research team at University of Washington in the US has developed software that leverages a small paper funnel and a smartphone’s microphone and speaker to detect ear infections in children.

Smartphone app can sense ear infections in children
University of Washington School of Medicine assistant professor uses the app and funnel to check the ear. Credit: Dennis Wise/University of Washington.

A research team at University of Washington in the US has developed software that leverages a small paper funnel and a smartphone’s microphone and speaker to detect ear infections in children.

The smartphone sends a series of soft audible chirps into the ear via the paper funnel and senses any fluid build-up behind the eardrum based on how the chirps are reflected back to the device.

In the event of no fluid, the eardrum vibrates and sends back a variety of sound waves that generate a broad, shallow dip in the overall signal.

When fluid is present, the eardrum doesn’t vibrate and the reflected sound waves create a narrow, deep dip in the signal.

This app is claimed to have a detection probability of 85%, which is comparable to existing diagnostics that involve instruments using acoustics or puffs of air.

University of Washington Paul G Allen School of Computer Science & Engineering associate professor Shyam Gollakota said: “Designing an accurate screening tool on something as ubiquitous as a smartphone can be game-changing for parents as well as healthcare providers in resource limited regions.

“A key advantage of our technology is that it does not require any additional hardware other than a piece of paper and a software app running on the smartphone.”

The researchers examined 53 children aged 18 months to 17 years for training an algorithm that identifies changes in the sound signals reflected back from the eardrum.

Approximately 50% of the children were set to undergo surgery for ear tube placement to relieve chronic or recurrent ear fluid bouts, while the remaining children were scheduled to receive a different surgery not related to ears.

When tested, the algorithm was able to correctly identify the likelihood of fluid in 85% of the cases.

“The algorithm was able to correctly identify the likelihood of fluid in 85% of the cases.”

In addition, testing in younger children aged 9-18 months showed that the algorithm identified all positive cases and 90% of the negative cases.

Upon assessment with different smartphones and various types of paper to make the funnel, the results were observed to be consistent.

The team intends to commercialise the technology through Edus Health, a spinout company.