Through a partnership with Cornell University, Apple has published a new research paper outlining how its AirPods can estimate wearer’s respiratory rates through their microphones.
The paper details how respiratory rate is a clinical metric used to evaluate overall health and fitness. It says that it can be linked to several factors, including exercise and chronic acute illness.
In the research paper, Apple and Cornell outline how they used model-driven technology to estimate a wearer’s respiratory rate using short audio clips picked up by the AirPods and AirPods Pro. Data was collected from 21 people using Apple’s AirPods and AirPods Pro.
Below is an excerpt from the study:
“RR was manually annotated by counting audibly perceived inhalations and exhalations. A multi-task Long-Short Term Memory (LSTM) network with convolutional layers was implemented to process mel-filterbank energies, estimate RR in varying background noise conditions, and predict heavy breathing (greater than 25 breaths per minute). The multi-task model performs both classification and regression tasks and leverages a mixture of loss functions. It was observed 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.”
This paper arrives amid rumours that Apple could have plans to bring new health-monitoring and fitness tracking features to the next iteration of the AirPods Pro.
You can find the full study here.