Automated detection of breathing disturbances

Abstract

Approaches to determining a sleep fitness score for a user are provided, such as may be based upon monitored breathing disturbances of a user. The system receives user state data generated over a time period by a combination of sensors provided via a wearable tracker associated with the user. A system can use this information to calculate a sleep fitness score, breathing disturbance score, or other such value. The system can classify every minute within the time period as either normal or atypical, for example, and may provide such information for presentation to the user.

What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 receiving photoplethysmographic (PPG) data for a user wearing a wearable device, the PPG data captured using one or more PPG sensors of the wearable device;   analyzing, for a sleep period of the user, the PPG data to determine a breathing disturbance score for the sleep period, the sleep period determined in part using motion data captured by a motion sensor of the wearable computing device;   calculating a sleep fitness score for the user over the sleep period, the sleep fitness score calculated based at least in part upon the breathing disturbance score and the motion data; and   providing for display at least one of the sleep fitness score or the breathing disturbance score.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising:
 calculating the sleep fitness score based at least in part upon (1) a difference between the breathing disturbance score and a historical baseline breathing disturbance score for the user and (2) an amount of motion determined for the sleep period using the motion data captured by the motion sensor.   
     
     
         3 . The computer-implemented method of  claim 2 , further comprising:
 receiving respiration rate data for the user over the sleep period, the respiration rate data captured using a bed sensor; and   calculating the sleep fitness score further based upon the respiration rate data for the user.   
     
     
         4 . The computer-implemented method of  claim 1 , further comprising:
 updating a baseline breathing score for the user using the breathing disturbance score for portions of the sleep period; and   providing the updated baseline breathing score for display.   
     
     
         5 . The computer-implemented method of  claim 1 , wherein the PPG data includes data captured using a green PPG sensor, a red PPG sensor, and an infrared PPG sensor on the wearable device. 
     
     
         6 . The computer-implemented of  claim 1 , further comprising:
 determining a percentage of temporal windows, out of a plurality of temporal windows for the sleep period, classified as representing disturbed breathing for the user; and   generating the breathing disturbance score based at least in part on the percentage.   
     
     
         7 . The computer-implemented of  claim 6 , further comprising:
 receiving additional sensor data generated by at least one additional sensor of the wearable device, the additional sensor data generated during a second period outside the sleep period;   determining a baseline physiological metric associated with the user based on the additional sensor data; and   classifying respective temporal windows based at least in part upon the baseline physiological metric associated with the user.   
     
     
         8 . A computer-implemented method, comprising:
 receiving breathing pattern data and motion data for a user, the breathing pattern data and motion data captured using one or more sensors of a device proximate the user;   determining, using the motion data, a sleep period for the user;   analyzing the breathing pattern data, captured during the sleep period, to determine a sleep fitness score for the user; and   providing, for presentation, the sleep fitness score for the user.   
     
     
         9 . The computer-implemented method of  claim 8 , further comprising:
 determining the sleep period in part by determining at least a threshold period of time wherein an amount of motion represented by the motion data is less than a determined motion threshold.   
     
     
         10 . The computer-implemented method of  claim 8 , further comprising:
 calculating a breathing disturbance score using the breathing pattern data, the breathing pattern data including PPG data captured using a set of PPG sensors of the device.   
     
     
         11 . The computer-implemented method of  claim 10 , further comprising:
 calculating the sleep fitness score based further upon the breathing disturbance score and the motion data.   
     
     
         12 . The computer-implemented method of  claim 10 , further comprising:
 calculating the sleep fitness score further based upon respiration rate data captured for the user over the sleep period.   
     
     
         13 . The computer-implemented method of  claim 10 , wherein the device proximate the user is a wearable tracker worn on a wrist of the user. 
     
     
         14 . A system, comprising:
 at least one processor; and   non-transitory computer-readable memory including instructions that, when executed by the at least one processor, cause the system to:
 receive breathing pattern data and motion data for a user, the breathing pattern data and motion data captured using one or more sensors of a device proximate the user; 
 determine, using the motion data, a sleep period for the user; 
 analyze the breathing pattern data, captured during the sleep period, to determine a sleep fitness score for the user; and 
 provide, for presentation, the sleep fitness score for the user. 
   
     
     
         15 . The system of  claim 14 , wherein the instructions when executed further cause the system to:
 determine the sleep period in part by determining at least a threshold period of time wherein an amount of motion represented by the motion data is less than a determined motion threshold.   
     
     
         16 . The system of  claim 14 , wherein the instructions when executed further cause the system to:
 calculate a breathing disturbance score using the breathing pattern data, the breathing pattern data including PPG data captured using a set of PPG sensors of the device.   
     
     
         17 . The system of  claim 16 , wherein the instructions when executed further cause the system to:
 calculate the sleep fitness score based further upon the breathing disturbance score and the motion data.   
     
     
         18 . The system of  claim 16 , wherein the instructions when executed further cause the system to:
 calculate the sleep fitness score further based upon respiration rate data captured for the user over the sleep period.   
     
     
         19 . The system of  claim 14 , wherein the device proximate the user is a wearable tracker worn on a wrist of the user. 
     
     
         20 . The system of  claim 14 , wherein the instructions when executed further cause the system to:
 extract a low-frequency component of first sensor data, generated by a red PPG sensor, and a low-frequency component of second sensor data, generated by an infrared PPG sensor;   determine processed sensor data based on dividing the low-frequency component of the first sensor data by the low-frequency component of the second sensor data; and   classifying at least one of a plurality of temporal windows for the sleep period using the processed sensor data.