System and method for estimating cardiovascular fitness of a person

• US 10,470,704 B2
• Filed: 09/03/2014
• Issued: 11/12/2019
• Est. Priority Date: 09/16/2013
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Sartor, Francesco, Bonomi, Alberto Giovanni
• Primary Examiner(s): Weare, Meredith
• Application Number:
  US14/915,914
• Publication Number:
  US 20160206248A1
• Time in Patent Office: 1,896 Days
• CPC Class Codes: A61B 2505/09 Rehabilitation or training
• 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 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• 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 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A61B 5/14542 for measuring blood gases A61B5/14551 takes precedence
• CPC Class Codes: A61B 5/4866 Evaluating metabolism A61B5/083 takes precedence
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The present invention relates to a system (1) for estimating cardiovascular fitness of a person, comprising a heart rate monitor (10) for acquiring a heart rate signal including information about the heart rate of the person, an activity monitor (20) for acquiring an activity signal indicative of physical activity of the person, a classifier (30) for classifying the activity of the person based on the acquired activity signal, a selector (40) for selecting one or more heart rate features obtained from the acquired heart rate signal based on the acquired heart rate signal and the classification of the activity for use in an estimation of the cardiovascular fitness of the person, and an estimator (50) for estimating the cardiovascular fitness of the person based on the one or more selected heart rate features.

Claims

1. A device for estimating a maximal oxygen uptake (VO₂max) of a person, the device comprising:

a heart rate monitor that acquires a heart rate signal including information about the heart rate of the person;

an activity monitor that acquires an activity signal indicative of physical activity of the person; and

a processor operably coupled with memory, the heart rate monitor, and the activity monitory, the processor being configured to cause instructions to execute to;

classify an activity of the person based on the activity signal into cycling, walking, running, steady recovery, or no activity;

identify one or more heart rate features that are available from the heart rate signal;

select, based on the classification of the activity and the identified heart rate features, one or more VO₂max estimation models from a plurality of heart rate feature-based VO₂max estimation models stored in the memory;

select, for each selected VO₂max estimation model of the one or more selected VO₂max estimation models, an available heart rate feature that is based on the acquired heart rate signal;

estimate the VO₂max of the person based on one or more selected available heart rate features and the one or more selected VO₂max estimation models; and

output, on a display, information indicative of the estimated VO₂max.

2. The device as claimed in claim 1,

wherein selecting the available heart rate feature obtained from the acquired heart rate signal comprises selecting the available heart rate feature from the group of heart rate features comprising heart rate recovery, peak heart rate, heart rate variability, heart rate rise, resting heart rate.

3. The device as claimed in claim 1,

wherein selecting the available heart rate feature obtained from the acquired heart rate signal comprises selecting the available heart rate feature based on which heart rate phase is currently present.

4. The device as claimed in claim 1,

wherein estimating the VO₂max comprises estimating the VO₂max of the person based on the one or more selected available heart rate features and user information about the person including one or more of age, gender, weight, height, body mass index of the person received via an interface.

5. The device as claimed in claim 1,

wherein selecting the available heart rate feature is based on a root mean square error associated with at least one model of the one or more selected VO₂max estimation models.

6. The device of claim 1,

wherein said activity monitor includes an accelerometer for acquiring an acceleration signal indicative of acceleration of at least part of the body of the person as activity signal.

7. The device of claim 1,

wherein said heart rate monitor includes a photo-plethysmography or optical sensor.

8. A method for estimating a maximal oxygen uptake (VO₂max) of a person using one or more processors, the method comprising:

acquiring, by one or more of the processors from a heart rate monitor worn on the person'"'"'s body, a heart rate signal that includes information indicative of physical activity of the person;

acquiring, by one or more of the processors from an accelerometer worn on the person'"'"'s body, an activity signal indicative of physical activity of the person;

classifying an activity of the person based on the acquired activity signal into cycling, walking, running, steady recovery, or no activity;

identifying one or more heart rate features that are available from the heart rate signal;

selecting, based on the classification of the activity and the identified heart rate features, one or more VO₂max estimation models from a plurality of heart rate feature-based VO₂max estimation models stored in the memory;

selecting, for each selected VO₂max estimation model of the one or more selected VO₂max estimation models, an available heart rate feature that is based on the acquired heart rate signal;

estimating the VO₂max of the person based on one or more selected available heart rate features and the one or more selected VO₂max estimation models; and

outputting, on an output component, information indicative of the estimated VO₂max.

9. The method of claim 8, wherein selecting the available heart rate feature is based on a root mean square error associated with at least one model of the one or more selected VO₂max estimation models.

10. The method of claim 8, wherein selecting the available heart rate feature obtained from the acquired heart rate signal comprises selecting the available heart rate feature from the group of heart rate features comprising heart rate recovery, peak heart rate, heart rate variability, heart rate rise, resting heart rate.

11. The method of claim 8, wherein said heart rate monitor includes a photo-plethysmography.

12. The method of claim 8, wherein estimating the VO₂max comprises estimating the VO₂max of the person based on the one or more selected available heart rate features and user information about the person including one or more of age, gender, weight, height, body mass index of the person received via an interface.

13. The method of claim 8, wherein selecting the available heart rate feature obtained from the acquired heart rate signal comprises selecting the available heart rate feature based on which heart rate phase is currently present.

14. The method of claim 8, wherein said heart rate monitor includes an optical sensor.

15. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to estimate a maximal oxygen uptake (VO₂max) of a person by performing the following operations:

acquiring, by one or more of the processors from a heart rate monitor worn on the person'"'"'s body, a heart rate signal that includes information indicative of physical activity of the person;

acquiring, by one or more of the processors from an accelerometer worn on the person'"'"'s body, an activity signal indicative of physical activity of the person;

classifying an activity of the person based on the acquired activity signal into cycling, walking, running, steady recovery, or no activity;

identifying one or more heart rate features that are available from the heart rate signal;

selecting, based on the classification of the activity and the identified heart rate features, one or more VO₂max estimation models from a plurality of heart rate feature-based VO₂max estimation models stored in the memory;

selecting, for each selected VO₂max estimation model of the one or more selected VO₂max estimation models, an available heart rate feature that is based on the acquired heart rate signal;

estimating the VO₂max of the person based on one or more selected available heart rate features and the one or more selected VO₂max estimation models; and

outputting, on an output component, information indicative of the estimated VO₂max.

16. The at least one non-transitory computer-readable medium of claim 15, wherein selecting the available heart rate feature is based on a root mean square error associated with at least one model of the one or more selected VO₂max estimation models.

17. The at least one non-transitory computer-readable medium of claim 15, wherein selecting the available heart rate feature obtained from the acquired heart rate signal comprises selecting the available heart rate feature from the group of heart rate features comprising heart rate recovery, peak heart rate, heart rate variability, heart rate rise, resting heart rate.

18. The at least one non-transitory computer-readable medium of claim 15, wherein said heart rate monitor includes a photo-plethysmography or optical sensor.

19. The at least one non-transitory computer-readable medium of claim 15, wherein estimating the VO₂max comprises estimating the VO₂max of the person based on the one or more selected available heart rate features and user information about the person including one or more of age, gender, weight, height, body mass index of the person received via an interface.

20. The at least one non-transitory computer-readable medium of claim 15, wherein selecting the available heart rate feature obtained from the acquired heart rate signal comprises selecting the available heart rate feature based on which heart rate phase is currently present.