Risk assessment for metabolic syndrome

A computer-implemented method comprising:

• receiving, at a device from a sensor, during a time interval, a first set of sensor data values at a first frequency and a second set of data values at a second frequency different than the first frequency;
• generating one or more first processed sensor data values based at least in part on the first set of sensor data values and one or more second processed sensor data values based at least in part on the second set of sensor data values, wherein the one or more first processed sensor data values includes a same total number of data values as the one or more second processed sensor data values;
• generating, using a machine-learning model, a risk score for the time interval based at least in part on the one or more first processed sensor data values and the one or more second processed sensor data values;
• and
• outputting, in response to the risk score being greater than a predetermined threshold score, a notification to the device associated with a user, wherein the notification includes:
• an indication of a health risk that is associated with the user of the device, wherein the health risk includes a metabolic syndrome risk;
• and
• a recommendation corresponding to the health risk, wherein the recommendation includes at least one of a first recommendation for the user to change a behavior to lower the risk of the user developing the metabolic syndrome risk or a second recommendation to undergo a medical screening to screen for the metabolic syndrome risk.

One or more non-transitory computer-readable media comprising computer-executable instructions that, when executed by one or more processors of a device, cause the device to perform operations comprising:

• receiving, at the device from a sensor, during a time interval, a first set of sensor data values at a first frequency and a second set of data values at a second frequency different than the first frequency;
• generating one or more first processed sensor data values based at least in part on the first set of sensor data values and one or more second processed sensor data values based at least in part on the second set of sensor data values, wherein the one or more first processed sensor data values includes a same total number of data values as the one or more second processed sensor data values;
• generating, using a machine-learning model, a risk score for the time interval based at least in part on the one or more first processed sensor data values and the one or more second processed sensor data values;
• and
• outputting, in response to the risk score being greater than a predetermined threshold score, a notification to the device associated with a user, wherein the notification includes:
• an indication of a health risk that is associated with the user of the device, wherein the health risk includes a metabolic syndrome risk;
• and
• a recommendation corresponding to the health risk, wherein the recommendation includes at least one of a first recommendation for the user to change a behavior to lower the risk of the user developing the metabolic syndrome risk or a second recommendation to undergo a medical screening to screen for the metabolic syndrome risk.

A system comprising:

• a memory comprising computer-executable instructions;
• and
• a processor configured to access the memory and execute the computer-executable instructions to perform operations comprising:
• receiving, at the system from a sensor, during a time interval, a first set of sensor data values at a first frequency and a second set of data values at a second frequency different than the first frequency;
• generating one or more first processed sensor data values based at least in part on the first set of sensor data values and one or more second processed sensor data values based at least in part on the second set of sensor data values, wherein the one or more first processed sensor data values includes a same total number of data values as the one or more second processed sensor data values;
• generating, using a machine-learning model, a risk score for the time interval based at least in part on the one or more first processed sensor data values and the one or more second processed sensor data values;
• and
• outputting, in response to the risk score being greater than a predetermined threshold score, a notification to the system associated with a user, wherein the notification includes:
• an indication of a health risk that is associated with the user of the system, wherein the health risk includes a metabolic syndrome risk;
• and
• a recommendation corresponding to the health risk, wherein the recommendation includes at least one of a first recommendation for the user to change a behavior to lower the risk of the user developing the metabolic syndrome risk or a second recommendation to undergo a medical screening to screen for the metabolic syndrome risk.