Dynamic selection of algorithms for arrhythmia detection

• US 8,285,371 B2
• Filed: 04/06/2010
• Issued: 10/09/2012
• Est. Priority Date: 04/22/2009
• Status: Active Grant

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Li, Dan, Kim, Jaeho, Thompson, Julie A., Sharma, Arjun
• Primary Examiner(s): Dietrich, Joseph
• Application Number:
  US12/754,955
• Publication Number:
  US 20100274146A1
• Time in Patent Office: 917 Days
• Field of Search: 600/509, 600/515, 600/518
• US Class Current: 600/515
• CPC Class Codes: A61B 5/0008 Temperature signals
• CPC Class Codes: A61B 5/0215 by means inserted into the body catheters A61M25/00
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/0245 by using sensing means generating electric signals, i.e. ECG signals
• CPC Class Codes: A61B 5/029 Measuring or recording blood output from the heart, e.g. minute volume A61B8/065 takes precedence
• CPC Class Codes: A61B 5/053 Measuring electrical impedance or conductance of a portion of the body
• CPC Class Codes: A61B 5/1455 using optical sensors, e.g. spectral photometrical oximeters
• 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: A61B 7/00 Instruments for auscultation
• CPC Class Codes: A61B 7/04 Electric stethoscopes microphones, acoustic transducers therefor H04R
• CPC Class Codes: A61N 1/3621 for treating or preventing abnormally high heart rate
• CPC Class Codes: A61N 1/36521 the parameter being derived from measurement of an electrical impedance
• CPC Class Codes: A61N 1/3655 controlled by body or blood temperature
• CPC Class Codes: A61N 1/36557 controlled by chemical substances in blood
• CPC Class Codes: A61N 1/36578 controlled by mechanical motion of the heart wall, e.g. measured by an accelerometer or microphone
• CPC Class Codes: A61N 1/36592 controlled by the heart rate variability
• CPC Class Codes: A61N 1/3702 Physiological parameters A61N1/365 takes precedence; evoked response A61N1/371
• CPC Class Codes: A61N 1/3962 in combination with another heart therapy
• 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

An apparatus comprises a first implantable sensor produces a first electrical sensor signal representative of cardiac depolarization events of a heart of a subject, a second implantable sensor that produces a second electrical sensor signal representative of hemodynamic function of the heart, a signal analyzer circuit, and an arrhythmia discrimination circuit. The signal analyzer circuit detects an arrhythmic event from the first sensor signal and calculates hemodynamic stability in response to the arrhythmic event detection using the second sensor signal. The arrhythmia discrimination circuit selects, according to a calculated hemodynamic stability produced by the signal analyzer circuit, an arrhythmia discrimination algorithm from among a plurality of candidate arrhythmia discrimination algorithms that are implementable by the arrhythmia discrimination circuit, classifies the detected arrhythmia using the selected arrhythmia discrimination algorithm, and provides the arrhythmia classification to a user or process.

Claims

1. An apparatus comprising:

a first implantable sensor configured to produce a first electrical sensor signal representative of cardiac depolarization events of a heart of a subject;

a second implantable sensor configured to produce a second electrical sensor signal representative of hemodynamic function of the heart;

a signal analyzer circuit, communicatively coupled to the first and second implantable sensors, configured to;

detect an arrhythmic event from the first sensor signal; and

calculate hemodynamic stability in response to the arrhythmic event detection using the second sensor signal; and

an arrhythmia discrimination circuit, communicatively coupled to the signal analyzer circuit and the first implantable sensor, configured to;

preselect the plurality of candidate arrhythmia discrimination algorithms from among a set of algorithms implementable by the arrhythmia classification circuit;

classify the detected arrhythmia using each of the candidate arrhythmia discrimination algorithms;

weight the arrhythmia classifications by the candidate algorithms according to the calculated hemodynamic stability;

ultimately classify the detected arrhythmia according to the weights; and

provide the arrhythmia classification to a user or process.

2. The apparatus of claim 1, wherein the arrhythmia discrimination circuit is configured to:

weight a first arrhythmia discrimination algorithm greater than a second arrhythmia discrimination algorithm when the hemodynamic stability calculation indicates that the arrhythmia is hemodynamically stable; and

weight the second arrhythmia discrimination algorithm greater than the first arrhythmia discrimination algorithm when the hemodynamic stability calculation indicates that the arrhythmia is hemodynamically unstable, wherein the first arrhythmia discrimination algorithm has higher specificity than the second arrhythmia discrimination algorithm and the second arrhythmia discrimination algorithm has higher sensitivity than the first arrhythmia discrimination algorithm.

3. The apparatus of claim 1, wherein the arrhythmia discrimination circuit is configured to:

quantize a level of hemodynamic stability or instability from a hemodynamic stability calculation; and

weight an arrhythmia discrimination algorithm according to the level of hemodynamic stability or instability.

4. The apparatus of claim 1, including a third sensor configured to produce a third electrical sensor signal representative of physiologic events of the subject, and wherein the arrhythmia discrimination circuit is configured to select an arrhythmia discrimination algorithm according to the calculated hemodynamic stability and according to physiologic information obtained from the third sensor signal.

5. The apparatus of claim 1, including:

a storage circuit, communicatively coupled to the arrhythmia discrimination circuit, configured to store information related to at least one of a patient indication or a patient demographic, and

wherein the arrhythmia discrimination circuit is configured to select an arrhythmia discrimination algorithm according to the weighting using the calculated hemodynamic stability and according to the at least one of the stored patient indication or patient demographic.

6. The apparatus of claim 1, wherein the candidate algorithms differ from each other in at least one of:

a feature extracted from the first sensor signal and used by a candidate algorithm in classifying the arrhythmia;

a rule used by a candidate algorithm to classify the arrhythmia;

or

a logic structure of a candidate algorithm.

7. The apparatus of claim 1, wherein the candidate algorithms include a default arrhythmia discrimination algorithm, and wherein the arrhythmia discrimination circuit is configured to determine, according to the calculated hemodynamic stability, whether to use the default algorithm or to switch to a different candidate algorithm.

8. The apparatus of claim 1, wherein the arrhythmia discrimination circuit is configured to preselect the candidate arrhythmia discrimination algorithms according to at least one of:

physiologic information obtained from a third electrical sensor signal;

a patient indication stored in a memory of the apparatus;

or

a patient demographic stored in the memory.

9. The apparatus of claim 1, wherein the signal analyzer circuit detects the arrhythmic event when detecting a ventricular rate or interval that satisfies an arrhythmia detection rate or interval threshold and that is sustained for a predetermined duration of time or number of beats.

10. A method comprising:

detecting an arrhythmic event of a heart of a subject using an implantable medical device (IMD);

monitoring an electrical sensor signal received from an implantable sensor, wherein the electrical sensor signal is representative of hemodynamic function of the heart;

calculating hemodynamic stability in response to the arrhythmic event detection using the sensor signal;

preselecting a plurality of candidate arrhythmia discrimination algorithms from among a set of algorithms implementable by the IMD;

classifying the detected arrhythmia using each of the candidate arrhythmia discrimination algorithms;

weighting the classifications by the candidate algorithms according to the calculated hemodynamic stability;

selecting the arrhythmia classification of a candidate arrhythmia discrimination algorithm according to the weighting; and

providing the arrhythmia classification to a user or process.

11. The method of claim 10, wherein weighting an arrhythmia discrimination algorithm includes:

weighting a first arrhythmia discrimination algorithm greater than a second arrhythmia discrimination algorithm when a hemodynamic stability calculation indicates that the arrhythmia is hemodynamically stable; and

weighting the second arrhythmia discrimination algorithm greater than the first arrhythmia discrimination algorithm when the hemodynamic stability calculation indicates that the arrhythmia is hemodynamically unstable, wherein the first arrhythmia discrimination algorithm has higher specificity than the second arrhythmia discrimination algorithm and the second arrhythmia discrimination algorithm has higher sensitivity than the first arrhythmia discrimination algorithm.

12. The method of claim 10,

wherein calculating hemodynamic stability includes quantizing a level of hemodynamic stability or instability from a hemodynamic stability calculation, and

wherein weighting an arrhythmia discrimination algorithm includes weighting an algorithm according to the level of hemodynamic stability or instability.

13. The method of claim 10, including monitoring a second electrical sensor signal, wherein the second sensor signal is representative of physiologic events of the subject, and wherein selecting an arrhythmia discrimination algorithm includes selecting an arrhythmia discrimination algorithm according to the calculated hemodynamic stability and according to physiologic information obtained from the second sensor signal.

14. The method of claim 10, wherein selecting an arrhythmia discrimination algorithm includes selecting an arrhythmia discrimination algorithm according to the weighting using the calculated hemodynamic stability and according to at least one of a patient indication or a patient demographic stored in the IMD.

15. The method of claim 10, wherein preselecting an arrhythmia discrimination algorithm includes preselecting an arrhythmia discrimination algorithm from among candidate algorithms that differ in at least one of:

a feature extracted from the sensor signal and used by a candidate algorithm to classify a detected arrhythmia;

a rule used by a candidate algorithm to classify the arrhythmia;

or

a logic structure of a candidate algorithm.

16. The method of claim 10, wherein the candidate algorithms include a default arrhythmia discrimination algorithm, and wherein selecting an arrhythmia discrimination algorithm includes determining, according to the calculated hemodynamic stability, whether to use the default algorithm or to switch to a more appropriate candidate algorithm.

17. The method of claim 10, wherein preselecting the plurality of candidate algorithms includes preselecting the candidate arrhythmia discrimination algorithms according to at least one of:

physiologic information obtained from a second sensor signal;

a patient indication stored in the IMD;

or

a patient demographic stored in the IMD.

18. The method of claim 10, wherein detecting an arrhythmic event includes detecting a ventricular rate or interval that satisfies an arrhythmia detection rate or interval threshold.