Infections can be detected through headphones

Thanks to artificial intelligence, American researchers have turned helmets into a medical diagnostic tool. By analyzing the resonance of an audio signal, they can detect earplugs, ruptured eardrums, and ear infections.

You may also be interested

[EN VIDÉO] Deep Learning vs Machine Learning: What’s the Difference?
Both deep learning and machine learning use artificial intelligence.

L’appearance deep learning, or deep learning, over the past ten years has led to great advances in question artificial intelligence (AI). Thanks to neural networks, it can train algorithms for many tasks such as face recognition, machine translation, wrong wrong and even for the diagnosis of certain diseases. Indeed, researchers State University of New York at Buffalo have developed an AI that can check the health of the ears.

The system was named ear health (ear health) and works through in-ear headphones connected to a smartphone equipped with a platform deep learning. The headset emits a chirp or pulse with a linear frequency modulation. The AI ​​uses a built-in microphone to measure how this sound signal resonates in the ear canals and thus creates a profile of the unique geometry of the ear canal.inner ear owner.

Simple headphones to detect three diseases

The system will then beep regularly, for example once a day, to ensure that this profile has not changed. It is able to detect three conditions that change the geometry of the ear canals: sulfur capgap eardrum And one otitis.

The researchers tested their system on 92 volunteers, including 27 without hearing problems, 22 with tympanic membrane rupture25 people suffering from otitis and finally 18 people with cork earwax. The AI ​​was able to correctly identify states 82.6% of the time. The next step is to study the influence of other factors such as body hair or background. inflammation the eardrum may interfere with these results.

Interested in what you just read?

Back to top button

Adblock Detected

Please consider supporting us by disabling your ad blocker.