Method and apparatus for identifying potentially misclassified arrhythmic episodes

• US 20080065165A1
• Filed: 12/21/2006
• Published: 03/13/2008
• Est. Priority Date: 09/13/2006
• Status: Active Grant

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Cazares, Shelley, Johnson, Christopher Dale, Sathaye, Alok
• Granted Patent: US 7,738,950 B2
• Time in Patent Office: Days
• US Class Current: 607/27
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/0245 by using sensing means generating electric signals, i.e. ECG signals
• CPC Class Codes: A61B 5/24 Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
• CPC Class Codes: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• CPC Class Codes: A61B 5/6846 specially adapted to be brought in contact with an internal body part, i.e. invasive
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• 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: A61N 1/37247 User interfaces, e.g. input or presentation means
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture

Abstract

An implantable cardiac device is configured to classify cardiac arrhythmias using a plurality of arrhythmia discrimination algorithms. Data is provided that is associated with a plurality of cardiac arrhythmic episodes for which a cardiac electrical therapy was delivered or withheld by the implantable medical device based on the plurality of arrhythmia discrimination algorithms. A metric for each of the arrhythmic episodes is computed. The metric defines a measure by which the implantable cardiac device properly classified the arrhythmia. Potentially misclassified arrhythmic episodes of the plurality of cardiac arrhythmic episodes for which cardiac electrical therapy was inappropriately delivered or withheld are algorithmically identified using the metric.

Claims

1. A method for identifying cardiac arrhythmias that are potentially misclassified by a cardiac device implanted in a patient, the implantable cardiac device configured to classify cardiac arrhythmias using a plurality of arrhythmia discrimination algorithms, the method comprising:

providing data associated with a plurality of cardiac arrhythmic episodes for which a cardiac electrical therapy was delivered or withheld by the implantable cardiac device based on the plurality of arrhythmia discrimination algorithms;

computing a metric for each of the arrhythmic episodes, the metric defining a measure by which the implantable cardiac device properly classified the arrhythmia; and

algorithmically identifying potentially misclassified arrhythmic episodes of the plurality of cardiac arrhythmic episodes for which cardiac electrical therapy was inappropriately delivered or withheld using the metric.

2. The method of claim 1, wherein the metric defines a probability of incorrectly classifying a cardiac arrhythmic episode.

3. The method of claim 1, wherein the metric defines a probability of incorrectly classifying a ventricular tachycardia episode.

4. The method of claim 1, wherein the metric is reflective of the accuracy by which each arrhythmia discrimination algorithm implemented by the implantable cardiac device properly classified an arrhythmic episode.

5. The method of claim 1, wherein the metric is based on a product of the probabilities of the arrhythmia discrimination algorithms implemented by the implantable cardiac device to incorrectly classify an arrhythmic episode.

6. The method of claim 1, wherein algorithmically identifying potentially misclassified arrhythmic episodes comprises comparing metric values of the plurality of cardiac arrhythmic episodes to a threshold or a threshold range.

7. The method of claim 1, wherein the data and metrics associated with the plurality of cardiac arrhythmic episodes are arranged in a logbook format, the method further comprising displaying the potentially misclassified arrhythmic episodes for clinician review.

8. The method of claim 7, further comprising varying the manner in which the data and metrics associated with the potentially misclassified arrhythmic episodes are displayed in accordance with a degree of potential misclassification.

9. The method of claim 1, wherein the data and metrics associated with the plurality of cardiac arrhythmic episodes are arranged in a logbook format, the method further comprising sorting the data based on the metrics, and displaying the sorted data and metrics for clinician review.

10. The method of claim 1, wherein computing the metric and algorithmically identifying potentially misclassified arrhythmic episodes are respectively performed by a device external to the patient.

11. The method of claim 1, further comprising adjusting a parameter of one or more of the arrhythmia discrimination algorithms.

12. The method of claim 1, wherein:

the data is provided to a processor external to the patient;

the external processor implements one or more arrhythmia discrimination algorithms to classify the cardiac arrhythmias based on the data; and

the metric represents a measure of certainty that the cardiac arrhythmia classification of arrhythmic episodes respectively made by the implantable cardiac device and the external processor are in agreement.

13. The method of claim 12, further comprising adjusting the metric in response to clinician input.

14. The method of claim 12, further comprising flagging arrhythmic episodes for clinician review in response to the metric failing to exceed a certainty threshold.

15. The method of claim 12, further comprising modifying one or more of the plurality of arrhythmia discrimination algorithms of the implantable cardiac device in response to the metric failing to exceed a certainty threshold.

16. The method of claim 12, wherein the plurality of arrhythmia discrimination algorithms comprises an algorithm that compares a morphology of a cardiac signal to a supraventricular tachycardia (SVT) template, the method further comprising automatically generating an SVT template for arrhythmic episodes for which the cardiac arrhythmia classifications respectively made by the implantable cardiac device and the external processor are in disagreement but the metric meets or exceeds a certainty threshold.

17. The method of claim 12, wherein the plurality of arrhythmia discrimination algorithms comprises an algorithm that compares a morphology of a cardiac signal to a supraventricular tachycardia (SVT) template, the method further comprising:

flagging arrhythmic episodes for clinician review in response to the metric failing to meet or exceed a certainty threshold; and

generating an SVT template for selected ones of the flagged arrhythmic episodes in response to a clinician input.

18. A system for identifying cardiac arrhythmias that are potentially misclassified, comprising:

an implantable cardiac device configured to classify cardiac arrhythmias using a plurality of arrhythmia discrimination algorithms;

a memory that stores data associated with a plurality of cardiac arrhythmic episodes for which a cardiac electrical therapy was delivered or withheld by the implantable cardiac device based on the plurality of arrhythmia discrimination algorithms; and

a processor configured to compute a metric for each of the arrhythmic episodes, the metric defining a measure by which the implantable cardiac device properly classified the arrhythmia, the processor configured to identify potentially misclassified arrhythmic episodes of the plurality of cardiac arrhythmic episodes for which cardiac electrical therapy was inappropriately delivered or withheld using the metric.

19. The system of claim 18, wherein at least one of the memory and the processor is provided in the implantable cardiac device.

20. The system of claim 18, wherein at least one of the memory and the processor is provided in a patient-external device.

21. The system of claim 18, wherein the metric defines a probability of incorrectly classifying a cardiac arrhythmic episode.

22. The system of claim 18, wherein the metric is reflective of the accuracy by which each arrhythmia discrimination algorithm implemented by the implantable cardiac device properly classified an arrhythmic episode.

23. The system of claim 18, wherein the metric is based on a product of the probabilities of the arrhythmia discrimination algorithms implemented by the implantable cardiac device to incorrectly classify an arrhythmic episode.

24. The system of claim 18, wherein the processor is configured to identify potentially misclassified arrhythmic episodes by comparing metric values of the plurality of cardiac arrhythmic episodes to a threshold or a threshold range.

25. The system of claim 18, wherein the data and metrics associated with the plurality of cardiac arrhythmic episodes are organized in a logbook format in the memory, the system further comprising a display configured to display the potentially misclassified arrhythmic episodes for clinician review.

26. The system of claim 18, wherein a parameter of one or more of the arrhythmia discrimination algorithm is adjusted in the implantable cardiac device based on the metric.

27. The system of claim 18, wherein the memory and the processor are disposed in a patient-external device, the processor configured to implement one or more arrhythmia discrimination algorithms to classify the cardiac arrhythmias based on the data, wherein the metric represents a measure of certainty that the cardiac arrhythmia classification of arrhythmic episodes respectively made by the implantable cardiac device and the processor are in agreement.

28. The system of claim 27, wherein the metric is adjusted by the processor in response to clinician input.

29. The system of claim 27, wherein the processor is configured to flag arrhythmic episodes for clinician review in response to the metric failing to exceed a certainty threshold.

30. The system of claim 27, wherein one or more of the plurality of arrhythmia discrimination algorithms of the implantable cardiac device is modified at least in part by the processor in response to the metric failing to exceed a certainty threshold.

31. The system of claim 27, wherein the plurality of arrhythmia discrimination algorithms comprises an algorithm that compares a morphology of a cardiac signal to a supraventricular tachycardia (SVT) template, the processor configured to automatically generate an SVT template for arrhythmic episodes for which the cardiac arrhythmia classifications respectively made by the implantable cardiac device and the processor are in disagreement but the metric meets or exceeds a certainty threshold.

32. The system of claim 27, wherein the plurality of arrhythmia discrimination algorithms comprises an algorithm that compares a morphology of a cardiac signal to a supraventricular tachycardia (SVT) template, the processor configured to flag arrhythmic episodes for clinician review in response to the metric failing to meet or exceed a certainty threshold and to generate an SVT template for selected ones of the flagged arrhythmic episodes in response to a clinician input.