Apple has been working on eventually bringing health sensors to AirPods for years now as presented below.

• 01: Apple Invents a new Health feature for AirPods that will provide diagnosis & monitoring of Bruxism (2022)
• 02: Apple Invents a next-generation AirPods Sensor System that could measure Biosignals and Electrical Activity of a user's Brain (2023)
• 03 AirPods Trademark Update covering Health (2024)

On the rumor front, Bloomberg has pointed to Apple reportedly exploring ways to make AirPods more than just audio devices, aiming to leverage them as tools for health and fitness tracking, potentially reducing the need for users to rely solely on an Apple Watch for certain health data.

On Thursday (Mar 20, 2025) the U.S. Patent Office published a patent application of Apple's that relates to possible future health features for AirPods.

In their patent background, Apple notes that individuals move their bodies and limbs in highly unique and repeatable patterns based on, for example, pelvic rotation, pelvic tilt, knee and hip flexion, knee and ankle interaction, and lateral pelvic displacement. Changes to these determinants can indicate health issues, such as injury or disease.

Changes due to a progressive disease or aging occur slowly over many months or years, making such changes difficult for the individual or their doctor to observe during semi-annual or annual checkups. It is desirable, however, to detect such biomechanical aging or disease processes over the long term before they are observable in a clinical setting, so that preventative treatments can be prescribed and evaluated for effectiveness by the individual or doctor before they develop into more serious health problems.

Detecting Biomechanical Impairment using AirPods

Apple's patent application covers detecting biomechanical impairment using wearable devices (AirPods). In some embodiments, a method comprises: obtaining a first set of sensor data, a location of the AirPods and a timestamp; determining a first set of fitness metrics based on the sensor data; predicting a baseline health profile based on the first set of fitness metrics; storing the baseline health profile, location and timestamp; at a second time after the timestamp: detecting that the wearable device is at the location; obtaining a second set of sensor data from the sensors of the AirPods; determining a second set of fitness metrics based on the second set of sensor data; predicting a current health profile for the user based on the second set of fitness metrics; comparing the current health profile with the baseline health profile; and responsive to a result of the comparing, performing an action.

In some embodiments, the sensors include inertial sensors, a heart rate sensor and at least one in-ear device.

In some embodiments, predicting the baseline and current health profiles include providing the first and second sets of fitness metrics as inputs to a machine learning model that is trained to predict an overall fitness score for the user.

In some embodiments, the machine learning model is trained using health profiles of other individuals at the location that have a similar health profile as the user.

In some embodiments, the machine learning model is trained on augmented historical health profiles of the user.

In some embodiments, the first and second sets of fitness metrics include at least one of gait analysis, walking steadiness or cardiorespiratory fitness.

In some embodiments, the action includes sending an alert notification to the user.

Other embodiments are directed to an apparatus, system and computer-readable medium.

Particular embodiments described in Apple's patent provide one or more of the following advantages. This disclosed system and method uses machine learning to generate a baseline user health profile over time (e.g., one month) based on sensor measurements output by various sensors of a wearable devices (e.g., AirPods, Apple Watch, fitness devices, head mounted devices, chest mounted devices).

The user baseline health profile can be associated with a particular geographic location and/or time. The detection of sudden or long-term changes to the user's baseline health profile can trigger notification to the user (e.g., visual, audio or haptic notification) indicating that the user's current health profile deviated (e.g., deteriorated) from the user's baseline health profile, and the particular metrics that caused the deviation (e.g., uneven gait, change in walking speed, breathing pattern, bone vibration, inner sound, Bruxism, joint cracking).

Apple's patent that was published on Thursday March 20, 2025 lists Senior Automation and Tools Development Engineer as the sole inventor.

The Difference Between Machine Learning and AI