Discriminating polymorphic and monomorphic cardiac rhythms using template generation

• US 8,532,762 B2
• Filed: 12/20/2005
• Issued: 09/10/2013
• Est. Priority Date: 12/20/2005
• Status: Active Grant

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Cazares, Shelley, Ricci, Carlos, Li, Dan, Lin, Yayun, Zhang, Yi, Kim, Jaeho, Bocek, Joseph
• Primary Examiner(s): Patel, Niketa
• Assistant Examiner(s): EL-KAISSI, HIBA CARINE
• Application Number:
  US11/312,279
• Publication Number:
  US 20070142736A1
• Time in Patent Office: 2,821 Days
• Field of Search: 607 4- 5, 607/9, 607 14- 15, 600508-510, 600515-523
• US Class Current: 607/4
• CPC Class Codes: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/361 Detecting fibrillation
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• CPC Class Codes: A61B 5/366 Detecting abnormal QRS complex, e.g. widening
• 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 1/3622 comprising two or more electrodes co-operating with different heart regions
• CPC Class Codes: A61N 1/3702 Physiological parameters A61N1/365 takes precedence; evoked response A61N1/371
• CPC Class Codes: A61N 1/39622 Pacing therapy
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Cardiac arrhythmias are classified based on the morphology of the arrhythmia episode beats. Templates are formed using morphological features of the cardiac beats of the episode. The arrhythmia episode is classified as a monomorphic tachyarrhythmia or polymorphic tachyarrhythmia based on the one or more templates. The arrhythmia episode may be classified based on a number templates formed from the arrhythmia episode. The templates are formed by determining a measure of similarity between morphological features of a cardiac beat to a template. The similarities can be determined based on a pairing rule that determines which beat morphologies are compared. Selection of therapy for treating the arrhythmia episode may depend on the historical success of a therapy at mitigating previous arrhythmias of the same type as the arrhythmia episode.

Claims

1. A method of arrhythmia discrimination for implementation by an implantable cardiac rhythm management device, comprising:

detecting cardiac beats associated with an arrhythmia episode;

forming a plurality of templates of the arrhythmia episode using morphological features of the cardiac beats of the arrhythmia episode, wherein forming the plurality of templates includes;

forming at least one template of the arrhythmia episode;

measuring similarity between morphological features of a cardiac beat of the arrhythmia episode and each previously formed template of the arrhythmia episode;

using the cardiac beat to modify a previously formed template of the arrhythmia episode in response to a measure of similarity between the cardiac beat and the previously formed template being greater than a similarity threshold; and

forming an additional template of the arrhythmia episode in response to measures of similarity between the cardiac beat and each previously formed template being less than a similarity threshold;

determining the number of templates formed from the arrhythmia episode; and

discriminating between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia based on the number of templates determined to be formed using the cardiac beats of the arrhythmia episode.

2. The method of claim 1, wherein measuring the similarity between the morphological features of the cardiac beat and each previously formed template comprises:

extracting a fiducial point from a rate channel signal of the cardiac beat;

extracting a plurality of features from a shock channel signal of the cardiac beat; and

determining a correlation coefficient between the shock channel features and each previously formed template.

3. The method of claim 1, further comprises using the discrimination between monomorphic and polymorphic tachyarrhythmia to reclassify a previously made ventricular tachyarrhythmia (VT) or supraventricular tachyarrhythmia (SVT) classification.

4. The method of claim 1, wherein using the cardiac beat to modify a previously formed template of the arrhythmia episode comprises averaging features of the cardiac beat and the previously formed template.

5. The method of claim 1, wherein forming the plurality of templates further comprises forming an additional template of the arrhythmia episode in response to measures of similarity between the cardiac beat and at least two previously formed template templates being greater than a similarity threshold.

6. The method of claim 5, further comprising erasing the at least two previously formed templates.

7. The method of claim 1, wherein discriminating between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia comprises determining if the number of templates is greater then a predetermined fraction multiplied by the number of beats of the arrhythmia episode for which similarity was measured.

8. The method of claim 1, wherein at least one of forming the one or more templates and discriminating between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia is performed during the arrhythmia episode.

9. The method of claim 1, further comprising:

storing a particular template of the one or more templates, the particular template representative of the arrhythmia episode; and

classifying a subsequent monomorphic tachyarrhythmia episode according to monomorphic arrhythmia type using the particular template.

10. The method of claim 1, further comprising confirming a determination of supraventricular tachyarrhythmia if the arrhythmia episode is determined to be monomorphic tachyarrhythmia based on the discrimination between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia.

11. The method of claim 1, further comprising:

classifying the arrhythmia episode according to monomorphic arrhythmia type if the arrhythmia episode is determined to be monomorphic tachyarrhythmia based on the discrimination between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia; and

selecting a therapy based on at least one of the discrimination between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia and the classification of the arrhythmia episode type, wherein selecting the therapy includes selecting the therapy based on a history of success of the therapy at terminating the arrhythmia.

12. The method of claim 1, further comprising selecting a therapy to treat the arrhythmia episode based on a history of satisfactory treatment, wherein the history of satisfactory treatment is based on effectiveness of the selected therapy and at least one additional factor.

13. An implantable medical device, comprising:

sensor circuitry comprising electrodes for electrically coupling to a heart, the sensor circuitry configured to detect cardiac beats associated with an cardiac arrhythmia episode;

a template generator coupled to the sensor circuitry and configured to form a plurality of templates of the arrhythmia episode using the detected cardiac beats, wherein the template generator includes;

circuitry configured to form at least one template of the arrhythmia episode;

circuitry configured to measure a similarity between morphological features of a cardiac beat of the arrhythmia episode and each previously formed template of the arrhythmia episode;

circuitry configured to use the cardiac beat to modify a previously formed template of the arrhythmia episode in response to a measure of similarity between the cardiac beat and the previously formed template being greater than a similarity threshold; and

circuitry configured to form an additional template of the arrhythmia episode in response to measures of similarity between the cardiac beat and each previously formed template being less than a similarity threshold; and

an arrhythmia processor coupled to the template generator, the arrhythmia processor configured to determine the number of templates formed from the arrhythmia episode and discriminate between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia based on the number of templates determined to be formed using the cardiac beats of the arrhythmia episode.

14. The device of claim 13, wherein the similarity of the one or more templates is determined by calculating a correlation coefficient comparing a template and a cardiac beat.

15. The device of claim 13, wherein the circuitry configured to form the plurality of templates further comprises circuitry configured to combine at least two previously formed templates of the plurality of templates and the cardiac beat to form an additional template and to erase the at least two previously formed templates in response to the similarity measure between the cardiac beat and the at least two previously formed templates being greater than a similarity threshold.

16. The device of claim 13, further comprising a memory for storing particular templates of the one or more templates, wherein the arrhythmia processor is configured to classify subsequently detected monomorphic arrhythmia episodes according to monomorphic arrhythmia type using the one or more of the particular templates.

17. The device of claim 16, further comprising:

a control system configured to select an electrical stimulation therapy to treat a subsequently detected monomorphic arrhythmia episode based on the classification according to monomorphic arrhythmia type; and

therapy circuitry configured to deliver the selected therapy.

18. The device of claim 13, further comprising:

a control system configured to select an electrical stimulation therapy based on the discrimination between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia; and

therapy circuitry configured to deliver the selected therapy.

19. A system for arrhythmia discrimination, comprising:

means for detecting cardiac beats associated with an arrhythmia episode;

means for forming a plurality of templates of the arrhythmia episode using morphological features of the cardiac beats of the arrhythmia episode, wherein forming the plurality of templates includes;

means for forming at least one template of the arrhythmia episode;

means for measuring similarity between morphological features of a cardiac beat of the arrhythmia episode and each previously formed template of the arrhythmia episode;

means for using the cardiac beat to modify a previously formed template of the arrhythmia episode in response to a measure of similarity between the cardiac beat and the previously formed template being greater than a similarity threshold; and

means for forming an additional template of the arrhythmia episode in response to measures of similarity between the cardiac beat and each previously formed template being less than a similarity threshold;

means for determining the number of templates formed from the arrhythmia episode; and

means for discriminating between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia based on the number of templates determined to be formed using the cardiac beats of the arrhythmia episode.

20. The system of claim 19, wherein the means for forming the plurality of templates further comprises means for forming an additional template of the arrhythmia episode in response to measures of similarity between the cardiac beat and at least two previously formed templates being greater than a similarity threshold.

21. The system of claim 19, further comprising means for classifying the arrhythmia episode according to monomorphic arrhythmia type if the arrhythmia episode is determined to be monomorphic tachyarrhythmia based on the discrimination between monomorphic tachyarrhythmia and polymorphic tachyarrhythmia.

22. The system of claim 21, further comprising means for selecting a therapy based on a history of satisfaction with the selected therapy, wherein the history of satisfaction is based on whether the therapy is effective and at least one additional factor.