Method and apparatus for identifying potentially misclassified arrhythmic episodes

• US 8,948,858 B2
• Filed: 04/29/2010
• Issued: 02/03/2015
• 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: Sathaye, Alok, Cazares, Shelley, Johnson, Christopher Dale
• Primary Examiner(s): Koharski, Christopher D
• Assistant Examiner(s): So, Elizabeth K
• Application Number:
  US12/769,851
• Publication Number:
  US 20100211125A1
• Time in Patent Office: 1,741 Days
• Field of Search: 600508-528, 607 1- 5, 607 7- 18, 607/25, 607/62, 607/115, 607/119, 607/122, 607/123, 128897-899
• US Class Current: 600/515
• 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 system, comprising:

an implantable cardiac device (ICD), comprising;

sensing circuitry configured to sense cardiac electrical activity;

energy delivery circuitry configured to deliver cardiac electrical therapy to treat cardiac tachyarrhythmias;

a local processor coupled to the sensing circuitry and the energy delivery circuitry;

a local memory coupled to the local processor and configured to store a plurality of cardiac tachyarrhythmia discrimination algorithms and LCD data produced by the local processor, the ICD data comprising data associated with a plurality of cardiac tacharrhythmic episodes classified by the ICD based on the plurality of tachyarrhythmia discrimination algorithms; and

communications circuitry coupled to the local processor; and

an external device, comprising;

a communications interface configured to receive the LCD data;

an external memory configured to store the LCD data and an external discrimination algorithm (EDA) different from the cardiac tachyarrhythmia discrimination algorithms stored in the ICD , the EDA comprising one or more cardiac tachyarrhythmia discrimination algorithms requiring computational resources exceeding those offered by the ICD; and

an external processor coupled to the communications interface and the external memory, the external processor configured to apply the EDA to the ICD data stored in the external memory to automatically classify the plurality of cardiac tacharrhythmic episodes classified by the ICD without requiring user intervention, the external processor configured to generate a validation metric based on a comparison between the ICD and external device classifications of each of the plurality of cardiac tacharrhythmic episodes, the validation metric indicative of a level of confidence of the ICD properly classifying the plurality of cardiac tacharrhythmic episodes.

2. The system of claim 1, wherein the external processor is configured to determine a discrepancy or agreement between the ICD and external device episode classifications of each of the cardiac tacharrhythmic episodes.

3. The system of claim 1, wherein the external processor is configured to determine a discrepancy or agreement between the ICD and external device episode classifications of each of the cardiac tacharrhythmic episodes relative to a predetermined certainty threshold.

4. The system of claim 1 wherein the external processor is configured to determine to a first specified degree of certainty whether each of the cardiac tacharrhythmic episodes was correctly classified by the ICD.

5. The system of claim 1, wherein the external processor is configured to determine to a second specified degree of certainty whether each of the cardiac tacharrhythmic episodes was incorrectly classified by the ICD.

6. The system of claim 1, wherein the external processor is configured to:

determine to a first specified degree of certainty whether each of the cardiac tacharrhythmic episodes was correctly classified by the ICD; and

determine to a second specified degree of certainty whether each of the cardiac tacharrhythmic episodes was incorrectly classified by the ICD;

wherein the first and second specified degrees of certainty are adjustable

7. The system of claim 1, wherein the external processor is configured to:

determine to a second specified degree of certainty whether each of the cardiac tacharrhythmic episodes was incorrectly classified by the ICD; and

flag the cardiac tacharrhythmic episodes that were incorrectly classified by the ICD and failed to exceed the second specified degree of certainty.

8. The system of claim 1, wherein the external processor is configured to:

determine to a second specified degree of certainty whether each of the cardiac tacharrhythmic episodes was incorrectly classified by the ICD;

flag the cardiac tacharrhythmic episodes that were incorrectly classified by the ICD and failed to exceed the second specified degree of certainty;

receive a physician authorized update for one or more of the ICD cardiac tachyarrhythmia discrimination algorithms associated with the flagged cardiac tacharrhythrnic episodes confirmed as incorrectly classified by the ICD; and

transmit the update to the ICD for incorporation in the local memory of the ICD.

9. The system of claim 1, wherein the external processor is configured to:

determine to a second specified degree of certainty whether each of the cardiac tacharrhythmic episodes was incorrectly classified by the ICD;

algorithmically generate an update for one or more of the ICD cardiac tachyarrhythmia discrimination algorithms associated with the cardiac tacharrhythmic episodes incorrectly classified by the ICD and exceeding the second specified degree of certainty; and

transmit the update to the ICD for incorporation in the local memory of the ICD.

10. A system, comprising:

an implantable cardiac device (ICD), comprising;

sensing circuitry configured to sense cardiac electrical activity;

energy delivery circuitry configured to deliver cardiac electrical therapy to treat cardiac tachyarrhythmias;

a local processor coupled to the sensing circuitry and the energy delivery circuitry;

a local memory coupled to the local processor and configured to store one or more cardiac signal templates, a plurality of cardiac tachyarrhythmia discrimination algorithms, and ICD data produced by the local processor, the ICD data comprising data associated with a plurality of cardiac tacharrhythmic episodes classified by the ICD using the plurality of tachyarrhythmia discrimination algorithms and the one or more cardiac signal templates; and

communications circuitry coupled to the local processor; and

an external device, comprising;

a communications interface configured to receive the ICD data;

an external memory configured to store the ICD data, an external discrimination algorithm (EDA) different from the cardiac tachyarrhythmia discrimination algorithms stored in the ICD, and one or more supraventricular tachycardia (SVT) templates, the EDA comprising one or more cardiac tachyarrhythmia discrimination algorithms requiring computational resources exceeding those offered by the ICD; and

an external processor coupled to the communications interface and the external memory, the external processor configured to apply the EDA to the ICD data stored in the external memory to automatically classify the plurality of cardiac tacharrhythmic episodes classified by the ICD relative to the one or more SVT templates without requiring user intervention, the external processor configured to generate a validation metric based on a misclassification of one or more of the plurality of cardiac tacharrhythmic episodes by the ICD, the validation metric indicative of a level of confidence of the ICD properly classifying the plurality of cardiac tacharrhythmic episodes.

11. The system of claim 10, wherein the external processor is configured to generate a modification to one or more of the ICD cardiac tachyarrhythmia discrimination algorithms or cardiac signal templates based on the one or more cardiac tacharrhythmic episodes misclassified by the ICD, and transmit the modification to the ICD for incorporation in the local memory.

12. The system of claim 10, wherein the external processor is configured to generate an updated SVT template based on the one or more cardiac tacharrhythmic episodes misclassified by the ICD, and transmit the updated SVT template to the ICD for incorporation in the local memory.

13. The system of claim 10, wherein the external processor is configured to generate an updated SVT template based on a cardiac tachyarrhythmic episode misclassified as a ventricular tachyarrhythmic episode by the ICD, and transmit the updated SVT template to the ICD for incorporation in the local memory.

14. The system of claim 13, wherein the external processor is configured to generate a physician alert in response to transmission of the updated SVT template to the ICD.

15. The system of claim 10, wherein the external processor is configured to automatically generate an SVT template for tachyarrhythmic episodes for which the cardiac tachyarrhythrnia episode classifications respectively made by the EDA and the ICD are in disagreement and a comparison of the respective classifications exceeds a specified degree of certainty.

16. The system of claim 10, wherein the external processor is configured to:

compare the cardiac tachyarrhythmia episode classifications respectively made by the EDA and the ICD and determine if disagreement between the respective classifications exceeds a specified degree of certainty;

flag tachyarrhythmic episodes for clinician review in response to disagreement between the respective classifications failing to exceed the specified degree of certainty;

generate an SVT template for selected ones of the flagged arrhythmic episodes in response to a clinician input; and

transmit the generated SVT template or templates to the ICD for incorporation in the local memory.

17. The system of claim 10, wherein the output generated by the external processor comprises a physician alert or notification.

18. A method, comprising:

storing a plurality of cardiac tachyarrhythmia discrimination algorithms in an implantable cardiac device (ICD);

classifying a plurality of cardiac tacharrhythmic episodes by the ICD using the plurality of tachyarrhythmia discrimination algorithms;

producing ICD data associated with the plurality of cardiac tacharrhythmic episodes including ICD classification data;

receiving the ICD data by an external system;

applying an external discrimination algorithm (EDA) to the received ICD data by the external system, the EDA different from the cardiac tachyarrhythmia discrimination algorithms stored in the ICD, the EDA comprising one or more cardiac tachyarrhythmia discrimination algorithms requiring computational resources exceeding those offered by the ICD;

automatically classifying the plurality of cardiac tacharrhythmic episodes classified by the ICD using the EDA without requiring user intervention; and

generating, by the external system, a validation metric based on a comparison between the ICD and external device classifications of each of the plurality of cardiac tacharrhythmic episodes, the validation metric indicative of level of confidence of the ICD properly classifying the plurality of cardiac tacharrhythmic episodes.

19. The method of claim 18, wherein generating the output comprises:

generating, by the external system, a modification to one or more of the ICD cardiac tachyarrhythmia discrimination algorithms based on one or more cardiac tacharrhythtnic episodes misclassified by the ICD; and

transmitting the modification from the external system to the ICD for incorporation therein.

20. The method of claim 18, comprising:

determining to a first specified degree of certainty whether each of the cardiac tacharrhythmic episodes was correctly classified by the ICD;

determining to a second specified degree of certainty whether each of the cardiac tacharrhythmic episodes was incorrectly classified by the ICD; and

adjusting one or both of the first and second specified degrees of certainty;

wherein each of the respective determining and adjusting processes is implemented at least in part by the external system.