How AirPods could help you spot a health problem

What is the respiratory rate?

The respiratory rate or rhythm is the number of times a person breathes per minute. You can say that it is like the heart rate transferred to the respiratory system. This is a value that is used in medicine to be able to evaluate the general health of a specific patient. Currently, to perform this measurement, the patient must be seated, I want to, and as calm as possible. With a clock in front, the number of breaths that is given should be counted. For an adult it is established that the respiratory rate is 8 to 16 breaths per minute and in babies it can reach up to 44.

In the case of tachypnea, the fact of having a very fast breathing, can be related to numerous diseases. This is what Apple wants to detect, since for a person it can be an invaluable value in the day to day, blaming the fact of breathing more to a generalized fatigue. But the truth is that detecting tachypnea quickly is vital as it is a clinical sign of diseases as serious as heart failure, pneumonia and even pulmonary thrombosis. It is also related to diseases that do not have a high mortality rate, such as anxiety.

Apple is aware of these facts and wants to integrate sensors that are capable of measuring the respiratory rate. It will undoubtedly be a very complement to the health functions of the Apple Watch and the taking of oxygen saturation and heart rate. In general, this measurement can be carried out through the headset microphone wireless that can capture the inhalations and exhalations that the user makes during an effort.

How Apple did the study

This study has been published on the Apple Machine Learning Research website and, as we have mentioned previously, the microphone of a device is used. Although AirPods are not named directly, it is known to all that numerous patents have come out showing how AirPods can include health-related sensors.

This particular study has been carried out with 21 people who used field headphones with microphones before, during and after a training. The breaths that could be heard were recorded manually. In addition, a neural network was used to be able to know the correlation that exists between the manual capture and the data obtained by the microphones. It could be seen that there was a very good agreement with these data, making the results very promising.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *