# US 6,266,554 B1 · System and method for classifying cardiac complexes

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 6,266,554 B1
- Document ID: US6266554B1
- Status: Granted
- Kind: B1
- Application number: 09/249,128
- Filed: 1999-02-12
- Granted: 2001-07-24
- Earliest claimed: 1999-02-12
- Assignees: Cardiac Pacemakers, Inc.
- Inventors: William Hsu; Joseph Martin Smith
- Web page: https://patentgrep.com/patent/US6266554B1

## CPC

- A61B 5/35: by template matching
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- A61N 1/3622: {comprising two or more electrodes co-operating with different heart regions}
- A61N 1/3704: {Circuits specially adapted therefor, e.g. for sensitivity control}
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- A61N: ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY (measurement of bioelectric currents A61B; surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body A61B18/00; anaesthetic apparatus in general A61M; incandescent lamps H01K; infrared radiators for heating H05B)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A system and a method for classifying cardiac complexes based on cardiac information derived from two or more cardiac signals. Two or more cardiac signals containing cardiac complexes are monitored. A cardiac complex in the two or more cardiac signals is isolated in an analysis window. The morphology of the cardiac complex in each of the two or more cardiac signals is then compared to the morphology of a template cardiac complex representing a predetermined cardiac condition. Based on this comparison, the cardiac complex is classified as either belonging or not belonging to the predetermined cardiac condition.

## Claims

### Claim 1

A method, comprising:
monitoring a first signal and a second signal representative of electrical cardiac activity;
detecting a cardiac complex in each of the first signal and the second signal;
analyzing at least the first signal to detect a tachycardia episode;
when the tachycardia episode is detected, detecting the cardiac complex in the first signal and the second signal;
locating a predetermined feature in the cardiac complex detected in the first signal and a first NSR representative complex, wherein the predetermined feature includes a repeatably identifiable complex section common to the cardiac complex detected in the first signal and the first NSR representative complex;
aligning the predetermined feature in the cardiac complex detected in the first signal and the first NSR representative complex;
comparing the cardiac complex detected in the second signal to a second NSR representative complex; and
classifying the cardiac complex as an arrhythmic cardiac complex based on the comparison of the morphology of the cardiac complex in the second cardiac signal to the second NSR representative complex.

### Claim 2 (depends on 1)

The method of claim 1, including detecting a plurality of normal sinus rhythm (NSR) cardiac complexes in the first signal and the second signal;
determining the first NSR representative complex from the plurality of NSR cardiac complexes detected in the first signal; and
determining the second NSR representative complex from the plurality of NSR cardiac complexes detected in the second signal.

### Claim 3 (depends on 1)

The method of claim 1, where the repeatably identifiable complex section common to the cardiac complex detected in the first signal and the first NSR representative complex is a maximum deflection of the first signal.

### Claim 4 (depends on 3)

The method of claim 3, where the maximum deflection is along an R-wave sensed in the cardiac complex detected in the first signal and in the first NSR representative complex.

### Claim 5 (depends on 1)

The method of claim 1, where the repeatably identifiable complex section common to the cardiac complex detected in the first signal and the first NSR representative complex is a predetermined deviation of the first signal from a baseline signal indicating a beginning of the cardiac complex and the first NSR representative complex.

### Claim 6 (depends on 1)

The method of claim 1, where the repeatably identifiable complex section common to the cardiac complex detected in the first signal and the first NSR representative complex is a return of the first signal to a baseline signal for each of the cardiac complex and the first NSR representative complex for a predetermined time period indicating an ending of the cardiac complex and the first NSR representative complex.

### Claim 7 (depends on 1)

The method of claim 1, where the second NSR representative complex has a second NSR morphology and the cardiac complex detected in the second signal has a second signal morphology, and comparing the cardiac complex detected in the second signal to the second NSR representative complex includes comparing the second NSR morphology to the second signal morphology to determine whether the cardia complex is an arrhythmic complex.

### Claim 8 (depends on 7)

The method of claim 7, where comparing the second NSR morphology to the second signal morphology includes utilizing a correlation waveform analysis algorithm.

### Claim 9 (depends on 1)

The method of claim 1, where monitoring the first signal includes sensing electrical cardiac activity through a far-field sensing channel, and sensing the second signal includes sensing electrical cardiac activity through a near-field sensing channel.

### Claim 10 (depends on 1)

The method of claim 1, where monitoring the first signal includes sensing electrical cardiac activity through a near-field sensing channel, and sensing the second signal includes sensing electrical cardiac activity through a far-field sensing channel.

### Claim 11 (depends on 2)

The method of claim 2, including detecting at least a portion of a QRS-complex in each of the plurality of NSR cardiac complexes;
determining the first NSR representative complex from the at least a portion of the QRS-complex in each of the plurality of NSR cardiac complexes detected in the first signal;
determining the second NSR representative complex from the at least a portion of the QRS-complex in each of the plurality of NSR cardiac complexes detected in the second signal;
detecting a QRS-complex in the cardiac complex,
comparing the second NSR morphology to the second signal morphology to determine whether the cardia complex is a ventricular tachycardia complex;
determining a percentage of the ventricular tachycardia complex in a plurality of cardiac complexes sensed during the tachycardia episode; and
applying therapy for treating a ventricular tachycardia when the percentage of the ventricular tachycardia complex exceeds a predetermined percentage threshold.

### Claim 12 (depends on 11)

The method of claim 11, where the predetermined percentage threshold is 50 percent.

### Claim 13

A method, comprising:
monitoring two or more cardiac signals representative of electrical cardiac activity;
detecting a cardiac complex in each of the two or more cardiac signals;
locating at least one predetermined feature in the cardiac complex for each of the two or more cardiac signals, wherein the at least one predetermined feature includes a repeatably identifiable complex portion;
generating a scalar value as a function of a position of the at least one predetermined feature for each of the two or more cardiac signals;
using the scalar values to create a cardiac vector, where the cardiac vector represents the cardiac complex comparing the cardiac vector to one or more classification vectors, where each of the one or more classification vectors represents a predetermined cardiac condition;
determining a similarity coefficient from each comparison of the cardiac vector and the one or more classification vectors; and
classifying the cardiac complex as the predetermined cardiac condition when the cardiac complex similarity coefficient exceed a predetermined threshold.

### Claim 14 (depends on 13)

The method of claim 13, where detecting the cardiac complex includes isolating the cardiac complex in an analysis window.

### Claim 15 (depends on 13)

The method of claim 13, where the at least one predetermined feature in the cardiac complex is a maximum deflection of the two or more cardiac signals.

### Claim 16 (depends on 13)

The method of claim 13, where the at least one predetermined feature in the cardiac complex is a predetermined deviation of the two or more cardiac signals from a baseline signal indicating a beginning of the cardiac complex.

### Claim 17 (depends on 13)

The method of claim 13, where the at least one predetermined feature in the cardiac complex is a return of the two or more cardiac signal to a baseline signal for a predetermined time period indicating an ending of the cardiac complex.

### Claim 18 (depends on 13)

The method of claim 13, where the scalar value is a time the at least one predetermined feature of the cardiac complex occurred.

### Claim 19 (depends on 13)

The method of claim 13, where the scalar value is a difference in time between the occurrence of two of the at least one predetermined feature.

### Claim 20 (depends on 13)

The method of claim 13, where the scalar value is a magnitude of the position of the at least one predetermined feature for each of the two or more cardiac signals.

### Claim 21 (depends on 13)

The method of claim 13, where determining a similarity coefficient comprises determining a mean square error value from each comparison of the cardiac vector and the one or more classification vectors.

### Claim 22 (depends on 13)

The method of claim 13, including aligning the cardiac vector with each of the one or more classification vectors prior to comparing the cardiac vector, where the cardiac vector includes element positions occupied by the scalar values, and each of the one or more classification vectors includes an equal number of element positions as the element positions of the cardiac vector, wherein the element positions of the one or more classification vectors are occupied by scalar values representing the predetermined cardiac condition, and wherein the cardiac vector is aligned with a classification vector of the one or more classification vectors by adjusting each scalar value of the cardiac vector so one of the element positions of the cardiac vector equals a scalar value in a corresponding element position in a classification vector.

### Claim 23

A method, comprising:
monitoring a first cardiac signal and a second cardiac signal;
detecting a cardiac complex in each of the first cardiac signal and the second cardiac signal;
comparing the morphology of the cardiac complex in the first cardiac signal to a first template morphology and comparing the morphology of the cardiac complex in the second cardiac signal to a second template morphology; and
classifying the cardiac complex as one of a predetermined arrhythmic complex based on the comparison of the morphology of the cardiac complex in the first cardiac signal and the second cardiac signal to the first template morphology and the second template morphology.

### Claim 24 (depends on 23)

The method of claim 23, where monitoring the first cardiac signal and the second cardiac signal comprises monitoring the first cardiac signal from a first cardiac region and the second cardiac signal from a second cardiac region.

### Claim 25 (depends on 23)

The method of claim 23, including deriving the first template morphology from cardiac complexes sensed from approximately the first cardiac region.

### Claim 26 (depends on 23)

The method of claim 23, including deriving the second template morphology from cardiac complexes sensed from approximately the second cardiac region.

### Claim 27 (depends on 23)

The method of claim 23, including:
monitoring a third cardiac signal;
detecting the cardiac complex in the third cardiac signal;
comparing the morphology of the cardiac complex in the third cardiac signal to a third template morphology; and
classifying the cardiac complex as one of the predetermined arrhythmic complex based on the comparison of the morphology of the cardiac complex in the first cardiac signal, the second cardiac signal and the third cardiac signal to the first template morphology, the second template morphology and the third template morphology.

### Claim 28 (depends on 27)

The method of claim 27, where monitoring the third cardiac signal comprises monitoring the third cardiac signal from a third cardiac region.

### Claim 29 (depends on 28)

The method of claim 28, including deriving the third template morphology from cardiac complexes sensed from approximately the third cardiac region.

### Claim 30

A system, comprising:
at least one catheter having at least a first cardiac electrode and a second cardiac electrode;
a sensing system attached to the first cardiac electrode and the second cardiac electrode, wherein the sensing system senses a first signal and a second signal representative of electrical cardiac activity;
a morphology analyzer circuit coupled to the sensing system, wherein the morphology analyzer circuit locates a position of at least one predetermined feature in the morphology of the cardiac complex in the first signal and the second signal and generates two or more scalar values as a function of the position of the at least one predetermined feature for each of the first signal and the second signal;
a template generator coupled to the morphology analyzer, wherein the template generator circuit creates a cardiac complex vector from the two or more scalar values generated by morphology analyzer circuit; and
a signal feature comparison circuit coupled to the morphology analyzer circuit and the template generator circuit, wherein the signal feature comparison circuit compares the cardiac complex vector to one or more classification vectors to classify the cardiac complex.

### Claim 31 (depends on 30)

The system of claim 30, wherein the at least one predetermined feature is a maximum deflection of the first signal and the second signal.

### Claim 32 (depends on 30)

The system of claim 30, wherein the at least one predetermined feature is a predetermined deviation of the of the first signal and the second signal from a baseline signal indicating a beginning of the cardiac complex.

### Claim 33 (depends on 30)

The system of claim 30, wherein the at least one predetermined feature is a return of the first signal and the second signal to a baseline signal for a predetermined time period indicating an ending of the cardiac complex.

### Claim 34 (depends on 30)

The system of claim 30, wherein the scalar value is a time the at least one predetermined feature in the morphology of the cardiac complex occurred.

### Claim 35 (depends on 30)

The system of claim 30, wherein the scalar value is a difference in time between the occurrence of a first predetermined feature and a second predetermined feature.

### Claim 36 (depends on 30)

The system of claim 30, wherein the scalar value is a magnitude of the position of the at least one predetermined feature of the first signal and the second signal.

### Claim 37 (depends on 30)

The system of claim 30, wherein the signal feature comparison circuit determines a similarity coefficient for each comparison of the cardiac vector to the one or more classification vectors, and classifies the cardiac complex as a predetermined cardiac condition when the similarity coefficient exceed a predetermined threshold.

### Claim 38 (depends on 30)

The system of claim 30, wherein the signal feature comparison circuit aligns the cardiac vector with each of the one or more classification vectors prior to comparing the vectors, where the cardiac vector includes element positions occupied by the scalar values, and each of the one or more classification vectors includes an equal number of element positions as the element positions of the cardiac vector, wherein the element positions of the one or more classification vectors are occupied by scalar values representing the predetermined cardiac condition, and wherein the cardiac vector is aligned with a classification vector of the one or more classification vectors by adjusting each scalar value of the cardiac vector so one of the element positions of the cardiac vector equals a scalar value in a corresponding element position in a classification vector.

### Claim 39

A system, comprising:
at least one catheter having at least a first cardiac electrode and a second cardiac electrode;
a sensing system attached to the first cardiac electrode and the second cardiac electrode, wherein the sensing system senses a first signal and a second signal representative of electrical cardiac activity;
a template generator circuit coupled to the sensing system, wherein the template generator circuit determines a first NSR representative complex and a second NSR representative complex from a plurality cardiac complexes sensed during normal sinus rhythm;
a morphology analyzer circuit coupled to the sensing system, where the morphology analyzer circuit locates a predetermined feature in a cardiac complex detected in the first signal and in the first NSR representative complex, wherein the predetermined feature includes a repeatably identifiable complex section common to the cardiac complex detected in the first signal and the first NSR representative complex; and
a signal feature comparison circuit coupled to the morphology analyzer circuit and the template generator circuit, where the signal feature comparison circuit aligns the predetermined feature in the cardiac complex monitored in the first signal with the predetermined feature on the first NSR representative complex and compares the cardiac complex monitored in the second signal to the second NSR representative complex to determine whether the cardiac complex is an arrhythmic complex.

### Claim 40 (depends on 39)

The system of claim 39, where the morphology analyzer circuit locates the predetermined feature at a maximum deflection of the cardiac complex detected in the first signal and in the first NSR representative complex.

### Claim 41 (depends on 40)

The method of claim 40, where the maximum deflection is along an R-wave sensed in the cardiac complex detected in the first signal and in the first NSR representative complex.

### Claim 42 (depends on 39)

The system of claim 39, where the morphology analyzer circuit locates the predetermined feature at a beginning of the cardiac complex detected in the first signal and the first NSR representative complex as indicated by a predetermined deviation of the first signal from a baseline signal.

### Claim 43 (depends on 39)

The system of claim 39, where the morphology analyzer circuit locates the predetermined feature at an ending of the cardiac complex detected in the first signal and the first NSR representative complex as indicated by a return of the first signal to a baseline signal for a predetermined time period.

### Claim 44 (depends on 39)

The system of claim 39, where the sensing system includes a far-field sensing channel over which the first signal is monitored and a near-field sensing channel over which the second signal is monitored.

### Claim 45 (depends on 39)

The system of claim 39, where the sensing system includes a near-field sensing channel over which the first signal is monitored and a far-field sensing channel over which the second signal is monitored.

### Claim 46 (depends on 39)

The system of claim 39, where the second NSR representative complex has a second NSR morphology and the cardiac complex detected in the second signal has a second signal morphology, and the signal feature comparison circuit compares the second NSR morphology to the second signal morphology to determine whether the cardiac complex is an arrhythmic complex.

### Claim 47 (depends on 46)

The system of claim 46, where the signal feature comparison circuit uses a correlation waveform analysis algorithm to compare the second NSR morphology to the second signal morphology.

### Claim 48 (depends on 39)

The system of claim 39, where the sensing system senses at least a portion of a QRS-complex in the first signal and the second signal, the template generator circuit determines the first NSR representative complex and the second NSR representative complex from the at least a portion of the QRS-complexes sensed during normal sinus rhythm, and the signal feature comparison circuit compares the QRS-complex monitored in the second signal to the QRS-complex in the second NSR representative complex to determine whether the cardiac complex a ventricular tachycardia complex.

### Claim 49 (depends on 48)

The system of claim 48, where the signal feature comparison circuit determines a percentage of ventricular tachycardia complexes for a plurality of cardiac complexes, and the control system applies therapy for treating a ventricular tachycardia when the percentage of ventricular tachycardia complexes exceeds a predetermined percentage threshold.

### Claim 50 (depends on 49)

The system of claim 49, where the predetermined percentage threshold is 50 percent.