Heartbeat detection and categorization

• US 9,078,572 B2
• Filed: 10/30/2013
• Issued: 07/14/2015
• Est. Priority Date: 10/30/2013
• Status: Active Grant

• Current Assignee: APN Health, LLC
• Original Assignee: APN Health, LLC
• Inventors: Brodnick, Donald
• Primary Examiner(s): EVANISKO, GEORGE ROBERT
• Application Number:
  US14/067,561
• Publication Number:
  US 20150119736A1
• Time in Patent Office: 622 Days
• US Class Current: 1/1
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/7239 using differentiation including higher order derivatives
• 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

An automatic method for detecting heartbeats of a patient from two or more selected ECG signals, the method comprising: (a) determining a velocity for each of the selected signals; (b) summing together absolute values of each of the velocities; (c) comparing the sum with a threshold T having a value about one-half of an expected maximum value of the sum; and (d) if the sum is greater than the threshold T and if elapsed time since an immediately-previous heartbeat detection is greater than a preset refractory period t_R, a heartbeat has been detected at a time t_D of the velocity determinations. The method also further includes steps by which the detected heartbeats are categorized based on the velocities at the time of detection.

Claims

1. An automatic method for detecting heartbeats of a patient, the method comprising:

sensing two or more selected ECG signals; and

automatically processing the ECG signals with a programmable processor configured to;

determine a velocity for each of the selected signals;

sum together absolute values of each of the velocities;

compare the sum with a threshold T having a value about one-half of an expected maximum value of the sum; and

detect a heartbeat at a time t_D of the velocity determinations when the sum is greater than the threshold T and when elapsed time since an immediately-previous heartbeat detection is greater than a preset refractory period t_R.

2. The automatic heartbeat detection method of claim 1 further including, when a heartbeat has been detected, the steps of:

forming a vector F(t_D) the components of which are the velocities of each of the selected signals at the time t_D;

determining the angle between the vector F(t_D) and a previously-stored template vector;

comparing the angle with a threshold angle; and

when the angle is less than the threshold angle, categorizing the heartbeat as similar to a heartbeat which corresponds to the template vector.

3. The automatic heartbeat detection method of claim 2 wherein the angle determination and comparison include the steps of:

computing a squared vector magnitude SVM_D as the dot product F(t_D)·

F(t_D);

computing the dot product DP_q of F(t_D) with a template vector F_q;

computing a squared vector magnitude SVM_q as the dot product F_q·

F_q;

computing a signed squared cosine difference angle SCDA_q as

SCDA_q=sgn(DP_q)*DP_q*DP_q/(SVM_D*SVM_q); and

comparing SCDA_q with a squared cosine threshold SC_L.

4. The automatic heartbeat detection method of claim 3 further including comparing the vector F(t_D) with each of a plurality of template vectors to determine if the vector F(t_D) is within the threshold angle of any of the plurality of template vectors.

5. The automatic heartbeat detection method of claim 4 wherein when the angle between the vector F(t_D) and more than one of the plurality of template vectors is less than the threshold angle, categorizing the heartbeat as similar to a heartbeat which corresponds to the template vector having the smallest angle between itself and the vector F(t_D).

6. The automatic heartbeat detection method of claim 5 wherein when the angle between the vector F(t_D) and each of the plurality of template vectors is greater than or equal to the threshold angle, adding a template vector equal to the vector F(t_D) to the plurality of template vectors.

7. The automatic heartbeat detection method of claim 5 wherein the patient is in a non-sedated state and further including the step of providing interventional treatment to the patient in a sedated state based on heartbeats categorized while the patient was in the non-sedated state.

8. The automatic heartbeat detection method of claim 2 further including comparing the vector F(t_D) with each of a plurality of template vectors to determine if the vector F(t_D) is within the threshold angle of any of the plurality of template vectors.

9. The automatic heartbeat detection method of claim 8 wherein when the angle between the vector F(t_D) and more than one of the plurality of template vectors is less than the threshold angle, categorizing the heartbeat as similar to a heartbeat which corresponds to the template vector having the smallest angle between itself and the vector F(t_D).

10. The automatic heartbeat detection method of claim 8 wherein when the angle between the vector F(t_D) and each of the plurality of template vectors is greater than or equal to the threshold angle, adding a template vector equal to the vector F(t_D) to the plurality of template vectors.

11. The automatic heartbeat detection method of claim 8 wherein the patient is in a non-sedated state and further including the step of providing interventional treatment to the patient in a sedated state based on heartbeats categorized while the patient was in the non-sedated state.

12. The automatic heartbeat detection method of claim 8 wherein each of the template vectors has a threshold angle associated therewith, not all of which have the same angle value.

13. The automatic heartbeat detection method of claim 8 wherein at least a portion of the plurality of template vectors are preset template vectors.

14. The automatic heartbeat detection method of claim 13 wherein each of the plurality of template vectors is a preset template vector.

15. The automatic heartbeat detection method of claim 2 further including a slot-plurality of template vector slots, the slot-plurality being greater than or equal to the plurality of template vectors and each template vector is in a corresponding template vector slot, wherein when the vector F(t_D) is not within the threshold angle of any of the plurality of template vectors and an empty template vector slot is available, adding a template vector equal to the vector F(t_D) to the plurality of template vectors.

16. The automatic heartbeat detection method of claim 15 wherein when no empty template vector slot is available, replacing one of the template vectors with a new template vector equal to the vector F(t_D).

17. The automatic heartbeat detection method of claim 2 further including storing the categorized heartbeat.

18. The automatic heartbeat detection method of claim 17 further including displaying information descriptive of one or more stored heartbeats.

19. The automatic heartbeat detection method of claim 1 wherein determining the velocity of each of the selected signals includes:

digitizing each of the selected signals; and

filtering each of the digitized signals to generate the velocity for each selected signal.

20. The automatic heartbeat detection method of claim 19 wherein the filter is a first-difference filter.

21. The automatic heartbeat detection method of claim 20 wherein the first-difference filter is a boxcar filter.

22. The automatic heartbeat detection method of claim 1 further including adjusting the threshold T based on the maximum velocity sum during a preset time period t_m.

23. The automatic heartbeat detection method of claim 22 wherein when the preset time period t_m has elapsed and when a preset detection failure time limit t_L has not elapsed since previous heartbeats were detected, determining the threshold T by computing T=T_p (G_max/2−

T_p)/4 where G_max is the maximum velocity sum during the elapsed preset time period t_m and T_p is the previous value of the threshold T.

24. The automatic heartbeat detection method of claim 23 wherein when preset time period t_m has elapsed and when a preset detection failure time limit t_L has elapsed since previous heartbeats were detected, setting the threshold T to G_max/2.

25. The automatic heartbeat detection method of claim 24 wherein t_R is about 120 milliseconds, t_m is about 2 seconds, and t_L is about 5 seconds.

26. The automatic heartbeat detection method of claim 1 wherein three ECG signals are selected, and the signals form a quasi-orthogonal set.

27. The automatic heartbeat detection method of claim 1 wherein the ECG signals further include one or more ECG signals in addition to the selected ECG signals, and the method includes storing one or more of the additional ECG signals.

28. The automatic heartbeat method of claim 27 further including displaying information descriptive of a detected heartbeat.

29. The automatic heartbeat detection method of claim 1 further including, when a heartbeat has been detected, the steps of:

forming a vector F(t_D) the components of which are the velocities of each of the selected signals at the time t_D and the velocities of each of the selected signals at time t_D δ

;

determining the angle between the vector F(t_D) and a previously-stored template vector;

comparing the angle with a threshold angle; and

when the angle is less than the threshold angle, categorizing the heartbeat as similar to a heartbeat which corresponds to the template vector.

30. The automatic heartbeat detection method of claim 29 wherein the angle determination and comparison include the steps of:

computing a squared vector magnitude SVM_D as the dot product F(t_D)·

F(t_D);

computing the dot product DP_q of F(t_D) with a template vector F_q;

computing a squared vector magnitude SVM_q as the dot product F_q·

F_q;

computing a signed squared cosine difference angle SCDA_q as

SCDA_q=sgn(DP_q)*DP_q*DP_q/(SVM_D*SVM_q); and

comparing SCDA_q with a squared cosine threshold SC_L.

31. The automatic heartbeat detection method of claim 30 further including comparing the vector F(t_D) with each of a plurality of template vectors to determine if the vector F(t_D) is within the threshold angle of any of the plurality of template vectors.

32. The automatic heartbeat detection method of claim 31 wherein when the angle between the vector F(t_D) and more than one of the plurality of template vectors is less than the threshold angle, categorizing the heartbeat as similar to a heartbeat which corresponds to the template vector having the smallest angle between itself and the vector F(t_D).

33. The automatic heartbeat detection method of claim 32 wherein when the angle between the vector F(t_D) and each of the plurality of template vectors is greater than or equal to the threshold angle, adding a template vector equal to the vector F(t_D) to the plurality of template vectors.

34. The automatic heartbeat detection method of claim 32 wherein the patient is in a non-sedated state and further including the step of providing interventional treatment to the patient in a sedated state based on heartbeats categorized while the patient was in the non-sedated state.

35. The automatic heartbeat detection method of claim 29 further including comparing the vector F(t_D) with each of a plurality of template vectors to determine if the vector F(t_D) is within the threshold angle of any of the plurality of template vectors.

36. The automatic heartbeat detection method of claim 35 wherein when the angle between the vector F(t_D) and more than one of the plurality of template vectors is less than the threshold angle, categorizing the heartbeat as similar to a heartbeat which corresponds to the template vector having the smallest angle between itself and the vector F(t_D).

37. The automatic heartbeat detection method of claim 35 wherein when the angle between the vector F(t_D) and each of the plurality of template vectors is greater than or equal to the threshold angle, adding a template vector equal to the vector F(t_D) to the plurality of template vectors.

38. The automatic heartbeat detection method of claim 35 wherein the patient is in a non-sedated state and further including the step of providing interventional treatment to the patient in a sedated state based on heartbeats categorized while the patient was in the non-sedated state.

39. The automatic heartbeat detection method of claim 35 wherein each of the template vectors has a threshold angle associated therewith, not all of which have the same angle value.

40. The automatic heartbeat detection method of claim 35 wherein at least a portion of the plurality of template vectors are preset template vectors.

41. The automatic heartbeat detection method of claim 40 wherein each of the plurality of template vectors is a preset template vector.

42. The automatic heartbeat detection method of claim 29 further including a slot-plurality of template vector slots, the slot-plurality being greater than or equal to the plurality of template vectors and each template vector is in a corresponding template vector slot, wherein when the vector F(t_D) is not within the threshold angle of any of the plurality of template vectors and an empty template vector slot is available, adding a template vector equal to the vector F(t_D) to the plurality of template vectors.

43. The automatic heartbeat detection method of claim 42 wherein when no empty template vector slot is available, replacing one of the template vectors with a new template vector equal to the vector F(t_D).

44. The automatic heartbeat detection method of claim 29 further including storing the categorized heartbeat.

45. The automatic heartbeat detection method of claim 44 further including displaying information descriptive of one or more stored heartbeats.