Apple researchers have discovered that wearable devices like AirPods can be used to estimate a user’s respiratory rate. The discovery could provide a potential avenue in biometric sensor usage.
In a paper highlighted on the Apple Machine Learning Research website and originally shared by MyHealthyApple, researchers found that “wearable headphones” have the ability to register audible inhalations and exhalations during exertion using the device’s on-board microphones.
The paper says that RR offers a cost-effective method of tracking disease progression and cardio-respiratory fitness over time using “accessible, aesthetically acceptable,” non-invasive wearable devices.
Data was collected from 21 individuals using microphone-enabled, near-field headphones before, during, and after strenuous exercise. RR was manually annotated by counting audibly perceived inhalations and exhalations.
A multi-level convolutional neural network was used to achieve signal clarity among other things and the results observed show that RR can be estimated with a concordance correlation coefficient (CCC) of 0.76 and a mean squared error (MSE) of 0.2, demonstrating that audio can be a viable signal for passively estimating RR.
Results presented validate that RR can be estimated from audio captured using wearable microphones, enabling the detection of heavy breathing conditions and the monitoring of RR changes, a measure of cardio-respiratory fitness, over time. The findings show promise for further development of a respiratory health tool with a larger study cohort.
The paper does not specifically mention AirPods. However, Apple is known to have explored the potential of health monitoring features on its wireless earphones.
Rumors in the past have suggested that health sensors may be included in AirPods in the near future, and Apple executives have previously discussed building health features into the AirPods to provide users with additional health data.