System and method for classifying cardiac depolarization complexes with multi-dimensional correlation

• US 20040015090A1
• Filed: 02/17/2003
• Published: 01/22/2004
• Est. Priority Date: 06/05/2001
• Status: Abandoned Application

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Sweeney, Robert J., Hsu, William
• Application Number:
  US10/369,096
• Publication Number:
  US 20040015090A1
• Time in Patent Office: Days
• US Class Current: 600/510
• CPC Class Codes: A61B 5/283 Invasive
• CPC Class Codes: A61B 5/35 by template matching
• 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 1/39622 Pacing therapy
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A system and method for classifying cardiac depolarization complexes in which waveforms of a depolarization complex are sensed by separate electrodes and correlated with template waveforms of a template depolarization complex. The system is particularly suitable for incorporation into a cardiac rhythm management device such as an implantable cardioverter/defibrillator or pacemaker in order to facilitate arrhythmia prediction and/or prevention.

Claims

1. A method for classifying a sensed cardiac depolarization complex, comprising:

sensing a plurality of depolarization waveforms resulting from a cardiac depolarization complex with a plurality of separate electrodes and generating digital samples of the sensed waveforms over a defined period of time to result in a sample set for each sensed waveform;

storing the sample set of each sensed waveform in a sensed sample array and subtracting a mean waveform value from each array member;

storing a sample set of each corresponding waveform of a template depolarization complex in a template sample array and subtracting a mean waveform value from each array member;

computing a correlation sum for the sensed depolarization complex and the template depolarization complex by multiplying each sensed sample array member by a corresponding template sample array member and summing the results of each such multiplication;

computing an autocorrelation sum for the sensed complex by multiplying each sensed sample array member by itself and summing the results of each such multiplication;

computing an autocorrelation sum for the template complex by multiplying each template sample array member by itself and summing the results of each such multiplication;

computing a multi-dimensional correlation between the sensed and template depolarization complexes by dividing the correlation sum for the sensed and template complexes by the square root of the product of the autocorrelation sum for the sensed complex and the autocorrelation sum for the template complex; and

,

wherein the sensed depolarization complex is classified as being equivalent to the template complex if the multi-dimensional correlation exceeds a specified value.

2. The method of claim 1 wherein the mean values for the template and sensed waveforms are specified values for each such waveform.

3. The method of claim 2 further comprising averaging samples of a sensed waveform to compute a mean value for that waveform.

4. The method of claim 1 wherein samples of the sensed and template waveforms at a particular sampling time are grouped into a sensed complex vector and template complex vector, respectively, such that a correlation or autocorrelation sum constitutes a dot product of the vectors summed over the sample set.

5. The method of claim 4 further comprising adding one or more parameter features to the sensed and template complex vectors, wherein a parameter feature is defined as the deviation from a mean value of a measurable parameter related to a cardiac depolarization complex.

6. The method of claim 5 wherein a parameter feature added to the sensed complex vector and the template complex vector is a signal amplitude associated with a depolarization complex.

7. The method of claim 5 wherein a parameter feature added to the sensed complex vector and the template complex vector is a time interval associated with a depolarization complex.

8. The method of claim 7 wherein a parameter feature added to the sensed complex vector and the template complex vector is a QRS duration.

9. The method of claim 7 wherein a parameter feature added to the sensed complex vector and the template complex vector is a QT interval.

10. The method of claim 7 wherein a parameter feature added to the sensed complex vector and the template complex vector is an ST segment duration.

12. The device of claim 1 wherein the mean values for the template and sensed waveforms are specified values for each such waveform.

13. The device of claim 12 wherein the processor is programmed to average samples of the sensed waveforms to compute a mean value.

11. A cardiac rhythm management device having incorporated therein a system for classifying sensed cardiac depolarization complexes, comprising:

a plurality of sensing channels for sensing waveforms of a cardiac depolarization complex and for converting the sensed waveforms into digitized samples;

a processor and associated memory interfaced to the sensing channels; and

,

wherein the processor is programmed to;

store digital samples of the sensed waveforms for each sensed waveform over a defined period of time to result in a sample set;

store the sample set of each sensed waveform in a sensed sample array and subtracting a mean waveform value from each array member;

store a sample set of each corresponding waveform of a template depolarization complex in a template sample array and subtracting a mean waveform value from each array member;

compute a correlation sum for the sensed depolarization complex and the template depolarization complex by multiplying each sensed sample array member by a corresponding template sample array member and summing the results of each such multiplication;

compute an autocorrelation sum for the sensed complex by multiplying each sensed sample array member by itself and summing the results of each such multiplication;

compute an autocorrelation sum for the template complex by multiplying each template sample array member by itself and summing the results of each such multiplication;

compute a multi-dimensional correlation between the sensed and template depolarization complexes by dividing the correlation sum for the sensed and template complexes by the square root of the product of the autocorrelation sum for the sensed complex and the autocorrelation sum for the template complex; and

,

classify the sensed depolarization complex as being equivalent to the template complex if the multi-dimensional correlation exceeds a specified value.

14. The device of claim 11 wherein the processor is programmed to group samples of the sensed and template waveforms at a particular sampling time into a sensed complex vector and template complex vector, respectively, such that a correlation or autocorrelation sum constitutes a dot product of the vectors summed over the sample set.

15. The device of claim 14 wherein the processor is programmed to add one or more parameter features to the sensed and template complex vectors, wherein a parameter feature is defined as the deviation from a mean value of a measurable parameter related to a cardiac depolarization complex.

16. The device of claim 15 wherein a parameter feature added to the sensed complex vector and the template complex vector is a signal amplitude associated with a depolarization complex.

17. The device of claim 15 wherein a parameter feature added to the sensed complex vector and the template complex vector is a time interval associated with a depolarization complex.

18. The device of claim 17 wherein a parameter feature added to the sensed complex vector and the template complex vector is a QRS duration.

19. The device of claim 17 wherein a parameter feature added to the sensed complex vector and the template complex vector is a QT interval.

20. The device of claim 17 wherein a parameter feature added to the sensed complex vector and the template complex vector is an ST segment duration.