Determining sleep-related breathing events using sensor data from a wearable device

1 . A computer-implemented method, comprising:

determining that a user is in a sleep state;

while the user is in the sleep state, receiving from a wearable device worn by the user, a plurality of sensor data collected by a plurality of sensors of the wearable device during a plurality of time series, wherein each time series of the plurality of time series includes a plurality of points in time that occur while the user is in the sleep state;

for a time series of the plurality of time series and based at least in part on sensor data collected during the time series, determining a feature value for each of a plurality of features;

combining two or more of the feature values to generate a combined feature value for the time series;

determining that the combined feature value is indicative of a sleep-related breathing event occurring while the user is in the sleep state; and

in response to determining that the combined feature value is indicative of the sleep-related breathing event,

providing a visible presentation of information regarding the sleep-related breathing event,

wherein the information comprises the combined feature value or at least one of the two or more of the feature values, and

wherein the visible presentation is provided on a display of at least one of:

the wearable device; or

a computer device in communication with the wearable device.

2 . The computer-implemented method of claim 1 , wherein the plurality of features include one or more of a fall in SpO2 by at least a first amount, a rise in SpO2 by at least a second amount, a sleep stage transition from a first sleep stage to a second sleep stage, a fall in SpO2 by at least a third amount followed within a first defined number of seconds by a rise in SpO2 by at least a fourth amount, a change in a heart rate, a sleep stage transition from a third sleep stage followed within a second defined number of seconds by a fall in SpO2 by at least a fifth defined amount, or an accelerometer activity.

3 . The computer-implemented method of claim 1 , wherein the sensor data includes one or more of a heart rate sensor data, an SpO2 sensor data, a sleep stage classification, a temperature sensor data, an accelerometer sensor data, or an audio data.

4 . The computer-implemented method of claim 1 , wherein the sleep-related breathing event is at least one of an apnea or a hypopnea.

5 . The method of claim 1 , wherein the wearable device is at least one of a wrist band, an armband, a neck band, a headband, a ring, a necklace, a sheet, a mattress, a box spring, a pillow, or a clothing.

6 . A computing system, comprising:

one or more processors; and

a memory storing program instructions that, when executed by the one or more processors, cause the one or more processors to at least:

receive, during a sleep session of a user, sensor data collected from a plurality of sensors of a wearable device of the user, wherein the sensor data comprises time-series data collected during a window of time;

process the sensor data to generate a plurality of feature values for each of a plurality of features during the window of time;

combine two or more of the feature values to generate a combined feature value;

determine, based at least in part on the combined feature value, that the user has experienced a sleep-related breathing event during the window of time; and

send, for presentation, an indication of the sleep-related breathing event.

7 . The computing system of claim 6 , wherein the sleep-related breathing event is at least one of an apnea or a hypopnea.

8 . The computing system of claim 6 , wherein the plurality of features include one or more of a fall in SpO2 by at least a first amount during the window of time, a rise in SpO2 by at least a second amount during the window of time, a sleep stage transition from a first sleep stage to a second sleep stage during the window of time, a fall in SpO2 by at least a third amount during the window of time followed within a first defined number of seconds by a rise in SpO2 by at least a fourth amount during the window of time, a change in a heart rate during the window of time, a sleep stage transition from a third sleep stage followed within a second defined number of seconds by a fall in SpO2 by at least a fifth defined amount during the window of time, or an accelerometer activity during the window of time.

9 . The computing system of claim 8 , wherein the presentation comprises a display of at least one of the two or more of the feature values by at least one of:

the computing system; or

the wearable device.

10 . The computing system of claim 6 , wherein the sensor data includes one or more of a heart rate sensor data, an SpO2 sensor data, a sleep stage classification, a temperature sensor data, or an accelerometer sensor data.

11 . The computing system of claim 6 , wherein a duration of the window of time is less than a duration of the sleep session.

12 . The computing system of claim 6 , wherein the program instructions, when executed by the one or more processors to determine that the user has experienced the sleep-related breathing event, further cause the one or more processors to at least:

apply a weighting value to at least one of the two or more of the feature values; and

wherein the combined feature value is generated, with the weighting value applied to the at least one of the two or more of the feature values.

13 . The computing system of claim 6 , wherein the program instructions that, when executed by the one or more processors to determine that the user has experienced the sleep-related breathing event, further cause the one or more processors to at least:

process the combined feature value using a detection model to determine that the user has experienced the sleep-related breathing event.

14 . The computing system of claim 13 , wherein the detection model is trained to consider feature values determined based on sensor data collected during a window of time and an arrangement of those feature values during the window of time to determine that the user has experienced the sleep-related breathing event.

15 . The computing system of claim 6 , wherein the wearable device is at least one of a wrist band, an armband, a neck band, a headband, a ring, a necklace, a sheet, a mattress, a box spring, a pillow, or a clothing.

16 . A method, comprising:

processing sensor data collected from a plurality of sensors of a wearable device worn by a user during a sleep session to determine a plurality of feature values, wherein each one of the plurality of feature values is determined for one of a plurality of features;

combining two or more of the plurality of feature values determined during a window of time of the sleep session to generate a combined feature value;

determining, based at least in part on the combined feature value, that the user has experienced a sleep-related breathing event during at least the window of time; and

sending, for presentation, an indication of the sleep-related breathing event during at least the window of time and at least one of the two or more of the plurality of feature values,

wherein the presentation includes a display of at least the indication and the at least one of the two or more of the feature values determined during the window of time by at least one of:

the wearable device; or

a computing system in communication with the wearable device.

17 . The method of claim 16 , further comprising:

determining, during the sleep session and based at least in part on the sensor data, a plurality of sleep-related breathing events experienced by the user during the sleep session,

wherein the presentation further includes a display of an indication of a severity of a sleep disorder by the at least one of the wearable device or the computer system in communication with the wearable device, and

wherein the severity is determined based at least in part on the plurality of sleep-related breathing events.

18 . The method of claim 17 , wherein the sleep disorder is at least one of an apnea or a hypopnea, and

wherein the severity is determined in accordance with an Apnea-Hypopnea Index (“AHI”).

19 . The method of claim 16 , wherein the plurality of features include one or more of a fall in SpO2 by at least a first amount during the window of time, a rise in SpO2 by at least a second amount during the window of time, a sleep stage transition from a first sleep stage to a second sleep stage during the window of time, a fall in SpO2 by at least a third amount during the window of time followed within a first defined number of seconds by a rise in SpO2 by at least a fourth amount during the window of time, a change in a heart rate during the window of time, a sleep stage transition from a third sleep stage followed within a second defined number of seconds by a fall in SpO2 by at least a fifth defined amount during the window of time, or an accelerometer activity during the window of time.

20 . The method of claim 16 , wherein the wearable device is at least one of a wrist band, an armband, a neck band, a headband, a ring, a necklace, a sheet, a mattress, a box spring, a pillow, or a clothing, and

wherein the sensor data includes one or more of a heart rate sensor data, an SpO2 sensor data, a sleep stage classification, a temperature sensor data, or an accelerometer sensor data.