Statistical heart rate monitoring for estimating calorie expenditure

• US 10,244,948 B2
• Filed: 03/04/2016
• Issued: 04/02/2019
• Est. Priority Date: 03/06/2015
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Pham, Hung A., Mermel, Craig, Moore, III, Richard Channing, Raghuram, Karthik Jayaraman, Ullal, Adeeti, Singh Alvarado, Alexander, Tan, Xing
• Primary Examiner(s): Bertram, Eric D.
• Application Number:
  US15/061,653
• Publication Number:
  US 20160256058A1
• Time in Patent Office: 1,124 Days
• CPC Class Codes: A61B 2560/0223 of calibration, e.g. protocols for calibrating sensors
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/4866 Evaluating metabolism A61B5/083 takes precedence

Abstract

Systems and methods are disclosed for tracking physiological states and parameters for calorie estimation. A start of an exercise session associated with a user of a wearable computing device is determined. Heart rate data is measured for a first period of time. An onset heart rate value of the user is determined based on the measured heart rate data, the onset heart rate value associated with a lowest valid heart rate measured during the first period of time. A resting heart rate parameter (RHR) of a calorimetry model is associated with at least one of the onset heart rate value, a preset RHR, and an RHR based on user biometric data. Energy expenditure of the user during a second period of time is estimated based on the calorimetry model and a plurality of heart rate measurements obtained by the wearable computing device during the second period of time.

Claims

1. A method of calibrating a fitness tracking device for calorie estimation for a specific exercise session, the method comprising:

determining, by a wearable computing device, a start of an exercise session associated with a user of the wearable computing device, the wearable computing device including a processor, a memory, a heart rate sensor, and at least one of a motion sensing module, a display module, and an interface module;

in response to determining the start of the exercise session, measuring, by the heart rate sensor of the wearable computing device, heart rate data (HR) for a first period of time, the first period of time following the start of the exercise session;

determining, by the processor of the wearable computing device, an onset heart rate value of the user based on the measured heart rate data, the onset heart rate value associated with a lowest valid heart rate measured during the first period of time, the onset heart rate value being different from a calibrated resting heart rate (RHR) for the user stored in the memory;

associating, by the processor of the wearable computing device, an RHR parameter of a calorimetry model to the onset heart rate value to calibrate the wearable computing device for the exercise session; and

estimating, by the processor of the wearable computing device, energy expenditure of the user during a second period of time based on the calorimetry model and a plurality of heart rate measurements (HR) obtained by the wearable computing device during the second period of time, the second period of time associated with a portion of time after the first period of time and prior to an end of the exercise session.

2. The method of claim 1, wherein estimating the energy expenditure further comprises calculating a fraction of heart rate reserve (FHR) based on maximum heart rate (HR_max), wherein:

FHR=(HR_max−

HR)/(HR_max−

RHR).

3. The method of claim 2, wherein the energy expenditure is proportional to a function ƒ

(FHR), wherein ƒ

(FHR) is approximately a sigmoidal nonlinearity.

4. The method of claim 3, wherein ƒ

(0)=1 and ƒ

(1)=0.

5. The method of claim 2, wherein HR_max is based on at least one of:

an age of the user; and

at least one of a previously measured heart rate.

6. The method of claim 1, wherein the RHR for the user stored in the memory data comprises a heart rate value based on a maximum oxygen exchange rate of the user (VO₂max) and a maximum heart rate of the user (HR_max), and VO₂max comprises one of a default value or a value previously calibrated by the user.

7. The method of claim 6, wherein the (HR_max) comprises at least one of:

a maximum heart rate value of the at least one of a previously measured heart rate;

a percentile of the at least one of a previously measured heart rate;

a percentile of the at least one of a previously measured heart rate above a first threshold heart rate value;

a percentile of the at least one of a previously measured heart rate above a HR_max based on the age of the user; and

a maximum heart rate value being less than a percentage of the HR_max based on an age of the user.

8. The method of claim 7, wherein:

the percentile of the at least one of a previously measured heart rate is approximately a 98^th percentile;

the percentile of the at least one of a previously measured heart rate above a first threshold heart rate value is approximately a 98^th percentile;

the percentile of the at least one of a previously measured heart rate above a HR_max based on the age of the user is approximately a 98^th percentile; and

the percentage of the HR_max based on the age of the user is approximately 110%.

9. The method of claim 1, wherein the calibrated RHR includes at least one of:

a preset value; and

a RHR based on user biometric data.

10. The method of claim 9, wherein the preset RHR comprises at least one of:

a minimum value of a list of RHR values from prior exercise sessions;

a percentile of the list of RHR values from prior exercise sessions; and

a percentile of RHR values in the list below a second threshold heart rate value.

11. The method of claim 10, wherein:

the second threshold heart rate value comprises 90 beats per minute.

12. The method of claim 9, wherein:

the preset value comprises 72 beats per minute; and

the RHR based on user biometric data comprises a heart rate value based on a maximum oxygen exchange rate of the user (VO₂max) and a maximum heart rate of the user (HR_max).

13. The method of claim 1, wherein the first period of time comprises 10 seconds to 1 minute.

14. The method of claim 1, wherein the first period of time is associated with a timer, wherein the timer activates at least one of a low-power mode of heart rate sensing and a high-power mode of heart rate sensing.

15. A system for tracking physiological states and parameters for calorie estimation and configured to be calibrated for a specific exercise session, the system comprising:

a wearable computing device, the wearable computing device including a processor, a memory, a heart rate sensor, and at least one of a motion sensing module, a display module, and an interface module, the wearable computing device configured to;

determine a start of an exercise session associated with a user of the wearable computing device;

in response to determining the start of the exercise session, measure heart rate data (HR) for a first period of time, the first period of time following the start of the exercise session;

determine an onset heart rate value of the user based on the measured heart rate data, the onset heart rate value associated with a lowest valid heart rate measured during the first period of time, the onset heart rate value being different from a calibrated resting heart rate (RHR) for the user stored in the memory;

associate an RHR parameter of a calorimetry model to the onset heart rate value to calibrate the wearable computing device for the exercise session; and

estimate energy expenditure of the user during a second period of time based on the calorimetry model and a plurality of heart rate measurements (HR) obtained by the wearable computing device during the second period of time, the second period of time associated with a portion of time after the first period of time and prior to an end of the exercise session.

16. The system of claim 15, wherein estimating the energy expenditure further comprises calculating a fraction of heart rate reserve (FHR) based on maximum heart rate (HR_max), wherein:

FHR=(HR_max−

HR)/(HR_max−

RHR).

17. The system of claim 16, wherein HR_max is based on at least one of:

an age of the user; and

at least one of a previously measured heart rate.

18. The system of claim 17, wherein the at least one of a previously measured heart rate comprises at least one of:

a maximum heart rate value of the at least one of a previously measured heart rate;

a percentile of the at least one of a previously measured heart rate;

a percentile of the at least one of a previously measured heart rate above a first threshold heart rate value;

a percentile of the at least one of a previously measured heart rate above a HR_max based on the age of the user; and

a maximum heart rate value being less than a percentage of the HR_max based on the age of the user.

19. The system of claim 15, wherein the calibrated RHR includes at least one of:

a preset value; and

a RHR based on user biometric data.

20. The system of claim 19, wherein the preset RHR comprises at least one of:

a minimum value of a list of RHR values from prior exercise sessions;

a percentile of the list of RHR values from prior exercise sessions; and

a percentile of RHR values in the list below a second threshold heart rate value.