Detecting sleep intention
A wearable physiological monitoring device is configured to determine a wearer's sleep intention. In particular, the device evaluates activity that might be objectively associated with awaking from sleep in order to distinguish between a wearer's intention to end sleep and transitory stirring or other intermittent activity occurring in the context of a longer sleep interval. By evaluating sleep intention more accurately in this manner, the device can advantageously request sleep analysis from a remote server in those instances where a user intends to end a period of sleep (so that this data can be available to the user more quickly), while avoiding unnecessary or redundant server-side processing of sleep data in those instances where a user intends to continue sleeping.
1 . A method comprising:
acquiring sensor data from a physiological monitor worn by a user during a sleep interval;
transmitting the sensor data from the physiological monitor to a remote server, the remote server configured to perform a sleep analysis based on the sensor data from the physiological monitor;
detecting, with a processor, a waking event based on the sensor data, the waking event objectively indicative of the user waking from the sleep interval;
in response to the waking event, evaluating the sensor data with the processor to determine whether an intention of the user is to stay awake or return to sleep;
determining that the intention of the user is to return to sleep;
in response to determining the intention to return to sleep, deferring the sleep analysis with the remote server and continuing to monitor sensor data from the physiological monitor for a subsequent waking event;
detecting the subsequent waking event;
determining that the intention of the user is to stay awake;
in response to determining the intention of the user is to stay awake, initiating the sleep analysis with the remote server, the sleep analysis including a calculation of one or more sleep metrics that evaluate the sleep interval based on the sensor data from the physiological monitor; and
providing a result of the sleep analysis to the user.
2 . The method of claim 1 , wherein detecting the waking event includes detecting physical movement inconsistent with sleep.
3 . The method of claim 1 , wherein detecting the waking event includes detecting heart rate activity inconsistent with sleep.
4 . The method of claim 1 , wherein detecting the waking event includes detecting a body temperature inconsistent with sleep.
5 . The method of claim 1 , wherein evaluating the sensor data with the processor includes evaluating the sensor data using a probabilistic analysis of historical sleep data to determine a probability of the intention of the user to stay awake or return to sleep according to one or more variables.
6 . The method of claim 5 , wherein the historical sleep data includes data for the user.
7 . The method of claim 5 , wherein the historical sleep data includes data for other users.
8 . The method of claim 5 , wherein the one or more variables include a categorical variable.
9 . The method of claim 8 , wherein the categorical variable includes at least one of a time of day, a day, and a time of year.
10 . The method of claim 5 , wherein the one or more variables include at least one of a duration of the waking event, a duration of the sleep interval, an amount of time away from a typical waking time, a duration of physical movement, and an amount of physical movement.
11 . The method of claim 1 , wherein the sensor data includes at least one of photoplethysmography data, accelerometer data, and temperature data.
12 . The method of claim 1 , further comprising detecting an onset of the sleep interval based on the sensor data.
13 . The method of claim 1 , wherein evaluating whether the intention of the user is to stay awake or return to sleep includes training a machine-learning algorithm to estimate a likelihood of the intention based on one or more characteristics of the sleep interval.
14 . The method of claim 1 , wherein evaluating whether the intention of the user is to stay awake includes processing the sensor data with at least one of the physiological monitor, a mobile device coupled in a communicating relationship with the physiological monitor, and a remote server coupled in a communicating relationship with the physiological monitor.
15 . The method of claim 1 , wherein initiating the sleep analysis includes requesting an update to the sensor data with the remote server, and performing the sleep analysis with the remote server based on the sensor data and the update to the sensor data.
16 . The method of claim 1 , wherein providing the result of the sleep analysis includes transmitting the result from the remote server to a mobile device associated with the user.
17 . The method of claim 16 , further comprising displaying the result of the sleep analysis to the user on the mobile device.
18 . The method of claim 1 , wherein initiating the sleep analysis with the remote server when the intention of the user is to stay awake includes initiating the sleep analysis in a manner to provide a timely analysis shortly after waking.
19 . The method of claim 18 , further comprising calculating an intensity score for the user at least in part based on a heart rate variability calculated for the user during the sleep interval.
20 . The method of claim 18 , further comprising calculating a recovery score for the user at least in part based on a heart rate variability calculated for the user during the sleep interval.