Earbuds may soon be able to detect common ear infections and other ailments, according to a new study.
The “EarHealth” system pairs Bluetooth earbuds with a smartphone that’s equipped with a deep learning platform.
Deep learning is a type of machine learning, which itself is a form of artificial intelligence.
EarHealth works by sending a chirp through the earbuds of a healthy user. It records how the chirp reverberates throughout the ear canals, creating a profile of each user’s unique inner ear geometry.
Subsequent chirps—for example, a user might set the system for once daily testing—monitor each ear for three conditions—ear wax blockage, ruptured ear drums, and otitis media, a common ear infection—that alter the ear canal’s geometry.
Each condition has a unique audio signature that the deep learning system can detect with fairly accurate results.
The researchers report EarHealth achieved an accuracy of 82.6% in 92 users, including 27 healthy subjects, 22 patients with a ruptured eardrum, 25 patients with otitis media, and 18 patients with ear wax blockage.
“With people worldwide are living longer, and the prevalence of headphones, it is more important than ever to monitor one’s ear health,” says lead author Zhanpeng Jin, associate professor in the computer science and engineering department in the University at Buffalo School of Engineering and Applied Sciences.
“With EarHealth, we have developed what we believe is the first-ever earbud-based system that monitors ear health conditions in an effective, affordable, and user-friendly way,” he adds. “Because it has the potential to detect these conditions very early, it could greatly improve health outcomes for many people.”
The researchers presented the work at the ACM’s International Conference on Mobile Systems, Applications, and Services (MobiSys) in Portland, Oregon. The National Science Foundation provided funding.
Additional coauthors are from Northwestern University; the First Affiliated Hospital of USTC in China; the University of Colorado Denver; Harvard Medical School; and the University at Buffalo.
The team is planning additional studies to refine the system, including testing how ear hair, a history of eardrum inflammation, and other factors might affect EarHealth’s performance.
Written by Cory Nealon.
