Methods and apparatuses for cardiac arrhythmia classification using morphology stability

• US 7,430,446 B2
• Filed: 01/20/2005
• Issued: 09/30/2008
• Est. Priority Date: 01/20/2005
• Status: Expired due to Fees

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Li, Dan
• Primary Examiner(s): Layno; Carl H.
• Assistant Examiner(s): MALAMUD, DEBORAH LESLIE
• Application Number:
  US11/038,996
• Publication Number:
  US 20060161069A1
• Time in Patent Office: 1,349 Days
• Field of Search: 600/515, 600/518
• US Class Current: 600/515
• CPC Class Codes: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• 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 implantable cardioverter/defibrillator (ICD) includes a tachyarrhythmia detection and classification system that classifies tachyarrhythmias based on a morphological analysis of arrhythmic waveforms and a template waveform. Correlation coefficients each computed between morphological features of an arrhythmic waveform and morphological features of the template waveform provide for the basis for classifying the tachyarrhythmia. In one embodiment, morphological features are collected from a sensed arrhythmic waveform, and temporally corresponding morphological features are extracted a stored template waveform. In one embodiment, a correlation analysis takes into account the uncertainty associated with the production of the template waveform by using a template band that includes confidence intervals. In one embodiment, a correlation analysis produces Mahalanobis distance-based correlation coefficients for use in the classification of the tachyarrhythmia. In one embodiment, the stability of correlation coefficients are analyzed to classify the tachyarrhythmia.

Claims

1. A system for classifying tachyarrhythmias, the system comprising:

a correlation input to receive a plurality of feature correlation coefficient (Fcc) values each indicative of whether an arrhythmic heart beat of a 1;

1 tachyarrhythmia is morphologically correlated to a template heart beat of a known type cardiac rhythm;

a majority voting circuit coupled to the correlation input, the majority voting circuit adapted to classify the 1;

1 tachyarrhythmia as a first type tachyarrhythmia if a number of the arrhythmic heart beats that are correlated to the template heart beat equals or exceeds a predetermined threshold number, the majority voting circuit including;

a correlation comparator to receive each Fcc value of the plurality of Fcc values and indicate a correlated beat if the each Fcc value is greater than a predetermined detection threshold for the plurality of Fcc values;

a correlated beat counter circuit to count a number of the indicated correlated beats (N_CORR); and

a first type tachyarrhythmia classification circuit to classify the 1;

1 tachyarrhythmia as the first type tachyarrhythmia if the N_CORR equals or exceeds the predetermined threshold number; and

a morphology stability analysis circuit coupled to the majority voting circuit, the morphology stability analysis circuit adapted to further classify the 1;

1 tachyarrhythmia based on a stability associated with the Fcc values if the number of the arrhythmic heart beats that are correlated to the template heart beat is smaller than the predetermined threshold number.

2. The system of claim 1, wherein the morphology stability analysis circuit comprises:

a median Fcc computation circuit to compute a median Fcc (Fcc_MED) being a median value of the plurality of Fcc values; and

a spread Fcc counter circuit to count an Fcc spread number (Fcc_SPRD) being a number of Fcc values of the plurality of Fcc values that are within a window centered at the Fcc_MED,

and wherein the morphology stability analysis circuit is adapted to further classify the 1;

1 tachyarrhythmia based on the Fcc_SPRD, Fcc_MED, and N_CORR.

3. The system of claim 2, wherein the morphology stability analysis circuit further comprises a second type tachyarrhythmia classification circuit to classify the 1:

1 tachyarrhythmia as a second type tachyarrhythmia based on the Fcc_SPRD.

4. The system of claim 3, wherein the morphology stability analysis circuit further comprises a third type tachyarrhythmia classification circuit to classify the 1:

1 tachyarrhythmia as one of a third type tachyarrhythmia and the first type tachyarrhythmia based on the Fcc_MED and the N_CORR if the 1;

1 tachyarrhythmia is not classified as the second type tachyarrhythmia.

5. The system of claim 4, wherein the known cardiac rhythm is a normal sinus rhythm, the first type tachyarrhythmia is a supraventricular tachyarrhythmia (SVT), the second type tachyarrhythmia is a polymorphic ventricular tachyarrhythmia (PVT), and the third type tachyarrhythmia is a monomorphic ventricular tachyarrhythmia (MVT).

6. The system of claim 5, wherein the second type tachyarrhythmia classification circuit is adapted to classify the 1:

1 tachyarrhythmia as the PVT if the Fcc_SPRD is smaller than a predetermined threshold spread number.

7. The system of claim 6, wherein the third type tachyarrhythmia classification circuit is adapted to classify the 1:

1 tachyarrhythmia as the MVT if the Fcc_MED is equal to or smaller than a predetermined threshold median and the N_CORR is smaller than a predetermined threshold number and as the SVT if the Fcc_MED is greater than the predetermined threshold median and the N_CORR is equal to or greater than the predetermined threshold number.

8. A method for classifying tachyarrhythmias, the method comprising:

receiving a plurality of feature correlation coefficient (Fcc) values each indicative of whether an arrhythmic heart beat of a 1;

1 tachyarrhythmia is morphologically correlated to a template heart beat of a known type cardiac rhythm;

indicating a correlated beat if each Fcc value of the plurality of Fcc values is greater than a predetermined detection threshold;

counting a number of the indicated correlated beats (N_CORR);

classifying the 1;

1 tachyarrhythmia as the first type tachyarrhythmia if the N_CORR equals or exceeds the predetermined threshold number;

analyzing a stability of the Fcc values if the N_CORR is smaller than the predetermined threshold number; and

discriminating the 1;

1 tachyarrhythmia based on an outcome of the analyzing the stability of the Fcc values.

9. The method of claim 8, wherein discriminating the 1:

1 tachyarrhythmia comprises;

computing a median Fcc (Fcc_MED) being a median value of the plurality of Fcc values;

counting an Fcc spread number (Fcc_SPRD) being a number of Fcc values of the plurality of Fcc values that are within a window centered at the Fcc_MED; and

discriminating the 1;

1 tachyarrhythmia based on the Fcc_SPRD, Fcc_MED, and N_CORR.

10. The method of claim 9, wherein discriminating the 1:

1 tachyarrhythmia comprises classifying the 1;

1 tachyarrhythmia as a second type tachyarrhythmia based on the Fcc_SPRD.

11. The method of claim 10, wherein discriminating the 1:

1 tachyarrhythmia comprises classifying the 1;

1 tachyarrhythmia as one of a third type tachyarrhythmia and the first type tachyarrhythmia based on the Fcc_MED and the N_CORR if the 1;

1 tachyarrhythmia is not classified as the second type tachyarrhythmia.

12. The method of claim 11, wherein the known cardiac rhythm is a normal sinus rhythm, the first type tachyarrhythmia is a supraventricular tachyarrhythmia (SVT), the second type tachyarrhythmia is a polymorphic ventricular tachyarrhythmia (PVT), and the third type tachyarrhythmia is a monomorphic ventricular tachyarrhythmia (MVT).

13. The method of claim 12, wherein discriminating the 1:

1 tachyarrhythmia comprises classifying the 1;

1 tachyarrhythmia as the PVT if the Fcc_SPRD is smaller than a predetermined threshold spread number.

14. The method of claim 13, wherein discriminating the 1:

1 tachyarrhythmia comprises classifying the 1;

1 tachyarrhythmia as the MVT if the Fcc_MED is equal to or smaller than a predetermined threshold median and the N_CORR is smaller than a predetermined threshold number and as the SVT if the Fcc_MED is greater than the predetermined threshold median and the N_CORR is equal to or greater than the predetermined threshold number.

15. A system for classifying tachyarrhythmias, the system comprising:

means for producing a plurality of feature correlation coefficient (Fcc) values each indicative of whether an arrhythmic heart beat of a 1;

1 tachyarrhythmia is morphologically correlated to a template heart beat of a known type cardiac rhythm;

means for classifying the 1;

1 tachyarrhythmia based on whether a number of the arrhythmic heart beats that are correlated to the template heart beat equals or exceeds a predetermined threshold number; and

means for discriminating the 1;

1 tachyarrhythmia by analyzing a stability of the Fcc values if the number of the arrhythmic heart beats that are correlated to the template heart beat is smaller than the predetermined threshold number, the means for discriminating the 1;

1 tachyarrhythmia including;

means for computing a median Fcc being a median value of the plurality of Fcc values;

means for counting an Fcc spread number being a number of Fcc values of the plurality of Fcc values that are within a window centered at the Fcc_MED; and

means for discriminating the 1;

1 tachyarrhythmia based on the number of the arrhythmic heart beats that are correlated to the template heart beat, the median Fcc, and the Fcc spread number.

16. The system of claim 15, wherein the means for discriminating the 1:

1 tachyarrhythmia comprises means for classifying the 1;

1 tachyarrhythmia as one of a supraventricular tachyarrhythmia (SVT), a polymorphic ventricular tachyarrhythmia (PVT), and a monomorphic ventricular tachyarrhythmia (MVT).