Illness Detection Based on Modifiable Behavior Predictors
Methods, systems, and devices for illness detection are described. A method may include identifying physical activity data, sleep data, or both, associated with a user based on physiological data for the user collected via a wearable device throughout a first and second time interval. The method may include inputting the physical activity data, the sleep data, or both, into a classifier, and identifying, using the classifier, a satisfaction of deviation criteria between a subsets of the physical activity data, the sleep data, or both, collected throughout the first and second intervals. The method may further include causing a graphical user interface (GUI) of a user device to display an illness rick metric associated with the user based at least in part on the satisfaction of the deviation criteria, the illness risk metric associated with a probability that the user will transition from a healthy state to an unhealthy state.
1 . A method for automatically detecting illness, comprising:
receiving physiological data associated with a user from a wearable device, the physiological data collected via the wearable device throughout a first time interval and a second time interval subsequent to the first time interval;
identifying, based at least in part on the received physiological data, physical activity data, sleep data, or both, associated with the user throughout at least a portion of the first time interval and at least a portion of the second time interval;
inputting the physical activity data, the sleep data, or both, into a classifier;
identifying, using the classifier, a satisfaction of one or more deviation criteria between a first subset of the physical activity data, a first subset of the sleep data, or both, collected throughout the first time interval and a respective second subset of the physical activity data, a respective second subset of the sleep data, or both, collected throughout the second time interval; and
causing a graphical user interface of a user device to display an illness rick metric associated with the user based at least in part on the satisfaction of the one or more deviation criteria, the illness risk metric associated with a probability that the user will transition from a healthy state to an unhealthy state.
2 . The method of claim 1 , further comprising:
identifying a decrease in physical activity associated with the user between the first time interval and the second time interval based at least in part on the physical activity data, a decrease in energy expenditure associated with the user between the first time interval and the second time interval, or both, wherein identifying the satisfaction of the one or more deviation criteria is based at least in part on the decrease in physical activity, the decrease in energy expenditure, or both.
3 . The method of claim 1 , further comprising:
identifying a decrease in a duration of physical activity associated with the user between the first time interval and the second time interval based at least in part on the physical activity data, a decrease in a consistency of physical activity associated with the user between the first time interval and the second time interval, or both, wherein identifying the satisfaction of the one or more deviation criteria is based at least in part on the decrease in the duration of physical activity, the decrease in the consistency of physical activity, or both.
4 . The method of claim 1 , further comprising:
receiving additional physiological data associated with the user from the wearable device, the additional physiological data collected via the wearable device throughout a third time interval which precedes at least a portion of the first time interval;
identifying a user activeness metric associated with the user based at least in part on the additional physiological data; and
identifying one or more predictive weights associated with the physical activity data, the sleep data, or both, based on the user activeness metric, the one or more predictive weights associated with a relative predictive accuracy for detecting illness, wherein identifying satisfaction of the one or more deviation criteria is based at least in part on the one or more predictive weights.
5 . The method of claim 1 , further comprising:
identifying a pattern adjustment model associated with an activity pattern for the user, a sleeping pattern for the user, or both; and
inputting the pattern adjustment model into the classifier, wherein identifying the satisfaction of the one or more deviation criteria is based at least in part on the pattern adjustment model.
6 . The method of claim 5 , wherein the pattern adjustment model comprises a weekly pattern adjust model, a seasonal pattern adjustment model, a yearly pattern adjustment model, or any combination thereof.
7 . The method of claim 5 , wherein identifying the pattern adjustment model comprises:
receiving additional physiological data associated with the user from the wearable device, the additional physiological data collected via the wearable device throughout a third time interval which precedes at least a portion of the first time interval; and
generating the pattern adjustment model based at least in part on the additional physiological data.
8 . The method of claim 5 , further comprising:
identifying one or more predictive weights associated with the physical activity data, the sleep data, or both, based on the activity pattern and the sleeping pattern, respectively, the one or more predictive weights associated with a relative predictive accuracy for detecting illness, wherein identifying satisfaction of the one or more deviation criteria is based at least in part on the one or more predictive weights.
9 . The method of claim 1 , further comprising:
identifying that one or more changes between a first portion of the sleep data collected during the first time interval and a second portion of sleep data collected during the second time interval satisfy one or more thresholds, wherein identifying the satisfaction of the one or more deviation criteria is based at least in part on the one or more changes.
10 . The method of claim 1 , wherein the one or more changes comprise a change in a bed time for the user, a change in a wake-up time for the user, a change in a sleep duration for the user, a change in a sleep latency for the user, a change in a consistency in bed times for the user, a change in a consistency in wake times for the user, or any combination thereof.
11 . The method of claim 1 , further comprising:
identifying adherence data associated with the user, the adherence data associated with a frequency that the user wears the wearable device; and
identifying a change in the adherence data, wherein identifying the satisfaction of the one or more deviation criteria, causing the graphical user interface of the user device to display the illness rick metric, or both, is based at least in part on identifying the change in the adherence data.
12 . The method of claim 1 , wherein the wearable device comprises a wearable ring device.
13 . The method of claim 1 , wherein the wearable device collects the physiological data from the user based on arterial blood flow.
14 . The method of claim 1 , wherein the user device comprises a user device associated with the user, a user device associated with an administrator associated with a group of users including the user, or both.
15 . The method of claim 1 , wherein the physiological data is associated with a plurality of users including the user, the physiological data collected via a plurality of wearable devices associated with the plurality of users, the method further comprising:
identifying, based at least in part on the received physiological data, physical activity data, sleep data, or both, associated with each user of the plurality of users;
inputting the physical activity data, the sleep data, or both, for each user of the plurality of users into the classifier;
identifying, using the classifier, an illness risk metric associated with each user of the plurality of users based at least in part on the physical activity data, the sleep data, or both, for each user of the plurality of users; and
causing a graphical user interface of an administrator user device to display at least one illness risk metric associated with at least one user of the plurality of users.
16 . An apparatus for automatically detecting illness, comprising:
a processor;
memory coupled with the processor; and
instructions stored in the memory and executable by the processor to cause the apparatus to:
receive physiological data associated with a user from a wearable device, the physiological data collected via the wearable device throughout a first time interval and a second time interval subsequent to the first time interval;
identify, based at least in part on the received physiological data, physical activity data, sleep data, or both, associated with the user throughout at least a portion of the first time interval and at least a portion of the second time interval;
input the physical activity data, the sleep data, or both, into a classifier;
identify, using the classifier, a satisfaction of one or more deviation criteria between a first subset of the physical activity data, a first subset of the sleep data, or both, collected throughout the first time interval and a respective second subset of the physical activity data, a respective second subset of the sleep data, or both, collected throughout the second time interval; and
cause a graphical user interface of a user device to display an illness rick metric associated with the user based at least in part on the satisfaction of the one or more deviation criteria, the illness risk metric associated with a probability that the user will transition from a healthy state to an unhealthy state.
17 . The apparatus of claim 16 , wherein the instructions are further executable by the processor to cause the apparatus to:
identify a decrease in physical activity associated with the user between the first time interval and the second time interval based at least in part on the physical activity data, a decrease in energy expenditure associated with the user between the first time interval and the second time interval, or both, wherein identifying the satisfaction of the one or more deviation criteria is based at least in part on the decrease in physical activity, the decrease in energy expenditure, or both.
18 . The apparatus of claim 16 , wherein the instructions are further executable by the processor to cause the apparatus to:
identify a decrease in a duration of physical activity associated with the user between the first time interval and the second time interval based at least in part on the physical activity data, a decrease in a consistency of physical activity associated with the user between the first time interval and the second time interval, or both, wherein identifying the satisfaction of the one or more deviation criteria is based at least in part on the decrease in the duration of physical activity, the decrease in the consistency of physical activity, or both.
19 . The apparatus of claim 16 , wherein the instructions are further executable by the processor to cause the apparatus to:
receive additional physiological data associated with the user from the wearable device, the additional physiological data collected via the wearable device throughout a third time interval which precedes at least a portion of the first time interval;
identify a user activeness metric associated with the user based at least in part on the additional physiological data; and
identify one or more predictive weights associated with the physical activity data, the sleep data, or both, based on the user activeness metric, the one or more predictive weights associated with a relative predictive accuracy for detecting illness, wherein identifying satisfaction of the one or more deviation criteria is based at least in part on the one or more predictive weights.
20 . The apparatus of claim 16 , wherein the instructions are further executable by the processor to cause the apparatus to:
identify a pattern adjustment model associated with an activity pattern for the user, a sleeping pattern for the user, or both; and
input the pattern adjustment model into the classifier, wherein identifying the satisfaction of the one or more deviation criteria is based at least in part on the pattern adjustment model.