METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR DETECTING HEART RATE

• US 20110022199A1
• Filed: 02/26/2009
• Published: 01/27/2011
• Est. Priority Date: 02/26/2008
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Finsor Oy
• Inventors: Paalasmaa, Joonas
• Granted Patent: US 9,072,437 B2
• Time in Patent Office: Days
• US Class Current: 700/89
• 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 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/1102 Ballistocardiography
• CPC Class Codes: A61B 5/113 occurring during breathing
• CPC Class Codes: A61B 5/6887 mounted on external non-worn devices, e.g. non-medical devices
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• 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: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 7/02 Stethoscopes acoustic details thereof G10K11/00

Abstract

A method includes retrieving a signal that measures an activity of a cardiac system. A heart beat model is created based on the retrieved signal, and heart beats are detected using the heart beat model. The model can be trained using a machine learning technique and also respiratory cycle phase information can be used in training the model. A related algorithm, apparatus and computer program are also included.

Claims

1. A method, comprising:

retrieving a signal that measures an activity of a cardiac system

creating a heart beat model based on the retrieved signal; and

detecting heart beats using the heart beat model.

2. The method of claim 1, wherein the signal measures mechanical activity of a cardiac system.

3. The method of claim 1, further comprising utilizing information about the respiratory cycle in the heart beat detection.

4. The method of claim 1, wherein the signal that measures an activity of a cardiac system is a ballistocardiography signal.

5. The method of claim 1, wherein the signal that measures an activity of a cardiac system is a signal from a force sensor.

6. The method of claim 1, comprising outputting data directly or indirectly indicative of heart beat rate.

8. The method of claim 1, wherein the heart beat model is a supervised learning classifier.

9. The method of claim 1, wherein the method comprises:

using a heart beat shape information in training the model.

10. The method of claim 1, wherein the method comprises:

using a heart beat interval information in training the model.

11. The method of claim 1, wherein the method comprises:

using a respiratory cycle phase information in training the model.

12. The method of claim 1, wherein the method comprises:

providing an estimation of an expected heart beat shape based on the model.

13. The method of claim 1, comprising:

calculating an estimation of heart beat onset times; and

using the estimation in the detection of heart beats.

14. The method of claim 1, comprising:

creating an inverse model of an original heart beat shape that gives as a result the shape of the heart beat before it has been mixed with adjacent beats; and

solving the inverse model and using the recovered heart beat shape in heart beat model creation and heart beat detection.

28. Computer readable medium having stored thereon a computer program executable in an apparatus, and when executed configured to implement the method claims 1.

7. The method of 1, further comprising:

updating the heart beat model by training the model using a machine learning technique, such as supervised learning.

15. An apparatus, comprising:

a processing unit configured to retrieve a signal that measures an activity of a cardiac system, the processing unit being further configured to create a heart beat model based on the retrieved signal; and

the processing unit being further configured to detect heart beats using the heart beat model.

16. The apparatus of claim 15, wherein said model is indicative of an actual shape of a heart beat impulse.

17. The apparatus of claim 15, wherein the apparatus is configured to output data directly or indirectly indicative of heart beat rate.

18. The apparatus of claim 15, wherein the apparatus is configured to update the heart beat model by training the model using a machine learning technique, such as supervised learning.

19. The apparatus of claim 15, wherein the model is a supervised learning classifier.

20. The apparatus of claim 15, wherein the apparatus is configured to provide an estimation of an expected heart beat shape based on the model.

21. The apparatus of claim 15, wherein the apparatus is configured to use information about a respiratory cycle phase in training the heart beat model.

22. The apparatus of claim 15, wherein

the processing unit is configured to calculate an estimation of heart beat onset times, and wherein

the processing unit is further configured to use the estimation in the detection of heart beats.

23. The apparatus of claim 15, wherein the processing unit is configured to implement an algorithm to cancel the interference of overlapping heart beat impulses.

24. The apparatus of claim 15, wherein the apparatus is configured to create an inverse model of an original heart beat shape that gives as a result the shape of the heart beat before it has been mixed with adjacent beats, and to solve the inverse model and to use the recovered heart beat shape in heart beat model creation and heart beat detection.

25. The apparatus of claim 15, wherein the signal measures mechanical activity of a cardiac system.

26. The apparatus of claim 15, wherein the signal that measures an activity of a cardiac system is a ballistocardiography signal.

27. Computer readable medium having stored thereon a computer program executable in an apparatus, the computer program comprising:

program code for implementing an algorithm that controls the apparatus to retrieve a signal that measures an activity of a cardiac system, further controls the apparatus to create a heart beat model based on the retrieved signal, and further controls the apparatus to detect heart beats using the heart beat model.