Detecting and estimating sleep stages

• US 9,968,293 B1
• Filed: 05/16/2014
• Issued: 05/15/2018
• Est. Priority Date: 05/16/2014
• Status: Active Grant

• Current Assignee: DP Technologies, Inc.
• Original Assignee: DP Technologies, Inc.
• Inventors: Kahn, Philippe, Kinsolving, Arthur
• Primary Examiner(s): McCrosky, David J
• Application Number:
  US14/280,548
• Time in Patent Office: 1,460 Days
• Field of Search: 600300, 600301, 600595, 705 2, 705 3, 3405731, 340575
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/4812 Detecting sleep stages or cycles
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: Y10S 128/923 by comparison of patient data to other data

Abstract

Exemplary methods, apparatuses, and systems receive a plurality of user characteristics. The characteristics are transmitted to a server. A sleep profile selected by the server based upon the characteristics is received. The sleep profile includes an estimated sleep cycle having a plurality of stages representing aggregated sleep data from a plurality of persons. The sleep profile is selected in response to determining that the plurality of persons is associated with characteristics similar to the received user characteristics. A shift from a first stage in a current sleep cycle to a second stage in a current sleep cycle is detected. The detection of the shift is based upon a set of data from a sensor measuring physical indications of the user'"'"'s sleep. An estimate of an additional portion of the current sleep cycle is generated by matching the detected shift to a corresponding shift between stages in the estimated sleep cycle.

Claims

1. A computer-implemented method comprising:

receiving a plurality of user characteristics of a user;

transmitting the plurality of user characteristics to a server;

receiving a sleep profile selected by the server based upon the received user characteristics, wherein the selected sleep profile includes an estimated sleep cycle having a plurality of stages generated from aggregated sleep data from a plurality of persons, and wherein the sleep profile is selected in response to determining that the plurality of persons is associated with characteristics similar to the received user characteristics;

detecting a shift from a first stage in a current sleep cycle of the user to a second stage in a current sleep cycle of the user, the detection of the shift based upon a first set of data from a sensor measuring physical indications of sleep from the user;

generating a prediction of an additional portion of the current sleep cycle by matching the detected shift to a corresponding shift between stages in the estimated sleep cycle; and

modifying a sampling rate of the sensor based on the prediction of the additional portion of the current sleep cycle.

2. The computer-implemented method of claim 1, wherein the first stage is a non-rapid eye movement (NREM) stage of sleep and the second stage is a rapid eye movement (REM) stage of sleep.

3. The computer-implemented method of claim 1, wherein the received user characteristics include one or more biometric traits of the user.

4. The computer-implemented method of claim 1, wherein the received user characteristics include one or more environmental factors prior to or during the current sleep cycle.

5. The computer-implemented method of claim 1, wherein the received user characteristics include a time the user begins a period of sleep.

6. The computer-implemented method of claim 1, wherein the received user characteristics include an amount of user activity prior to a time the user begins period of sleep.

7. The computer-implemented method of claim 1, wherein modifying a sampling rate of the sensor based on the prediction of the additional portion of the current sleep cycle further comprises:

determining that the user has begun a period of sleep based upon a second set of data from the sensor measuring physical indications of sleep from the user;

reducing the sampling rate of the sensor in response to determining that the user has begun the period of sleep;

determining, based upon selected sleep profile, an estimated amount of time that will pass between the beginning of the period of sleep and the shift from the first stage in the current sleep cycle to the second stage in a current sleep cycle; and

increasing the sampling rate prior to passing of the estimated amount of time following the beginning of the period of sleep.

8. The computer-implemented method of claim 1, wherein modifying a sampling rate of the sensor based on the prediction of the additional portion of the current sleep cycle further comprises:

reducing the sampling rate of the sensor;

determining, based upon selected sleep profile, an estimated amount of time that will pass between the second stage in the current sleep cycle and a third stage in the current sleep cycle; and

increasing the sampling rate prior to passing of the estimated amount of time following the detected shift to the second stage.

9. The computer-implemented method of claim 1, wherein the sensor is implemented within a wristband worn by the user during sleep and wherein the indications of sleep include physical motion of a wrist.

10. The computer-implemented method of claim 1, wherein generating the estimate of the additional portion of the current sleep cycle by matching the detected shift to the corresponding shift between stages in the estimated sleep cycle comprises:

determining an amount of time between the detected shift and a detected second shift in the current sleep cycle;

determining a time difference between the determined amount of the time and an estimated amount of time between the corresponding shift and a corresponding second shift in the estimated sleep cycle; and

modifying a duration of time of one or more intermediate sleep stages in the estimated sleep cycle based on the determined time difference.

11. A non-transitory computer-readable medium storing instructions, which when executed by a processing device, cause the processing device to perform a method comprising:

receiving a plurality of user characteristics of a user;

transmitting the plurality of user characteristics to a server;

receiving a sleep profile selected by the server based upon the received user characteristics, wherein the selected sleep profile includes an estimated sleep cycle having a plurality of stages generated from aggregated sleep data from a plurality of persons, and wherein the sleep profile is selected in response to determining that the plurality of persons is associated with characteristics similar to the received user characteristics;

detecting a shift from a first stage in a current sleep cycle of the user to a second stage in a current sleep cycle of the user, the detection of the shift based upon a first set of data from a sensor measuring physical indications of sleep from the user;

generating a prediction of an additional portion of the current sleep cycle by matching the detected shift to a corresponding shift between stages in the estimated sleep cycle; and

modifying a sampling rate of the sensor based on the prediction of the additional portion of the current sleep cycle.

12. The non-transitory computer-readable medium of claim 11, wherein the first stage is a non-rapid eye movement (NREM) stage of sleep and the second stage is a rapid eye movement (REM) stage of sleep.

13. The non-transitory computer-readable medium of claim 11, wherein the received user characteristics include one or more biometric traits of the user.

14. The non-transitory computer-readable medium of claim 11, wherein the received user characteristics include one or more environmental factors prior to or during the current sleep cycle.

15. The non-transitory computer-readable medium of claim 11, wherein the received user characteristics include a time the user begins a period of sleep.

16. The non-transitory computer-readable medium of claim 11, wherein the received user characteristics include an amount of user activity prior to a time the user begins period of sleep.

17. The non-transitory computer-readable medium of claim 11, wherein modifying a sampling rate of the sensor based on the prediction of the additional portion of the current sleep cycle further comprises:

determining that the user has begun a period of sleep based upon a second set of data from the sensor measuring indications of sleep from movement of the user;

reducing the sampling rate of the sensor in response to determining that the user has begun the period of sleep;

determining, based upon selected sleep profile, an estimated amount of time that will pass between the beginning of the period of sleep and the shift from the first stage in the current sleep cycle to the second stage in a current sleep cycle; and

increasing the sampling rate prior to passing of the estimated amount of time following the beginning of the period of sleep.

18. The non-transitory computer-readable medium of claim 11, wherein modifying a sampling rate of the sensor based on the prediction of the additional portion of the current sleep cycle further comprises:

reducing the sampling rate of the sensor;

determining, based upon selected sleep profile, an estimated amount of time that will pass between the second stage in the current sleep cycle and a third stage in the current sleep cycle; and

increasing the sampling rate prior to passing of the estimated amount of time following the detected shift to the second stage.

19. The non-transitory computer-readable medium of claim 11, wherein the sensor is implemented within a wristband worn by the user during sleep and wherein the indications of sleep include physical motion of a wrist.

20. An apparatus comprising:

a processing device; and

a memory coupled to the processing device, the memory storing instructions which, when executed by the processing device, cause the apparatus to;

receive a plurality of user characteristics of a user;

transmit the plurality of user characteristics to a server;

receive a sleep profile selected by the server based upon the received user characteristics, wherein the selected sleep profile includes an estimated sleep cycle having a plurality of stages generated from aggregated sleep data from a plurality of persons, and wherein the sleep profile is selected in response to determining that the plurality of persons is associated with characteristics similar to the received user characteristics;

detect a shift from a first stage in a current sleep cycle of the user to a second stage in a current sleep cycle of the user, the detection of the shift based upon a first set of data from a sensor measuring physical indications of sleep from the user;

generate a prediction of an additional portion of the current sleep cycle by matching the detected shift to a corresponding shift between stages in the estimated sleep cycle; and

modify a sampling rate of the sensor based on the prediction of the additional portion of the current sleep cycle.

21. The apparatus of claim 20, wherein the first stage is a non-rapid eye movement (NREM) stage of sleep and the second stage is a rapid eye movement (REM) stage of sleep.