Multiple stage morphology-based system detecting ventricular tachycardia and supraventricular tachycardia

• US 6,275,732 B1
• Filed: 06/17/1998
• Issued: 08/14/2001
• Est. Priority Date: 06/17/1998
• Status: Expired due to Fees

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Marcovecchio, Alan F., Hsu, William
• Primary Examiner(s): Kamm, William E.
• Application Number:
  US09/098,654
• Time in Patent Office: 1,154 Days
• Field of Search: 600/518, 607/14
• US Class Current: 607/14
• 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: A61N 1/3956 Implantable devices for applying electric shocks to the heart, e.g. for cardioversion
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A system for detecting ventricular tachycardia and supraventricular tachycardia using a multiple stage morphology based system. Cardiac signals are sensed from a patient'"'"'s heart and analyzed for the occurrence of a tachycardia event. When a tachycardia event is detected, the method and system analyzes a plurality of features of the sensed cardiac signals in two or more discrimination stages. Each of the two or more discrimination stages classify the tachycardia event as either a ventricular tachycardia or a candidate supraventricular tachycardia event. When a discrimination stage detects the occurrence of a ventricular tachycardia, therapy is delivered to the heart to treat the ventricular tachycardia.

Claims

1. A method, comprising:

sensing cardiac signals;

analyzing the sensed cardiac signals for a tachycardia event; and

during a tachycardia event, analyzing a plurality of features of the sensed cardiac signals in two or more discrimination stages, where each of the two or more discrimination stages classifies the tachycardia event as either a ventricular tachycardia or a candidate supraventricular tachycardia.

2. The method of claim 1, including delivering therapy for treating a ventricular tachycardia when a discrimination stage classifies the tachycardia event as a ventricular tachycardia.

3. The method of claim 1, where the two or more discrimination stages include a first discrimination stage, the first discrimination stage including:

measuring a width of sensed R-waves using the plurality of features from cardiac signals sensed during a tachycardia event;

comparing the width of each of the sensed R-waves to a template R-wave width;

classifying a cardiac signal as a ventricular tachycardia complex if the width of the sensed R-wave is greater than or equal to a predetermined value of the template R-wave width;

declaring a ventricular tachycardia when the number of ventricular tachycardia complexes reach a predetermined threshold; and

delivering therapy for treating the ventricular tachycardia when a ventricular tachycardia is declared.

4. The method of claim 3, including:

using a second discrimination stage to classify the cardiac signals, where the second discrimination stage includes;

analyzing a morphological similarity of the cardiac signals to a normal sinus rhythm template complex to determine if a ventricular tachycardia condition is present.

5. The method of claim 4, where analyzing the morphological similarity includes:

determining values for each of the plurality of features of the cardiac signals sensed during a tachycardia event;

determining a similarity value and a dissimilarity value for each of the cardiac signals, where the similarity value and the dissimilarity value are assessed relative to a plurality of features on normal sinus rhythm signals;

using the similarity value and the dissimilarity value to determine if each of the cardiac signals is a ventricular tachycardia complex;

declaring a ventricular tachycardia when the number of ventricular tachycardia complexes reach a predetermined threshold; and

delivering therapy for treating the ventricular tachycardia when a ventricular tachycardia is declared.

6. The method of claim 5, wherein the step of using the similarity value and the dissimilarity value include:

defining a boundary on a discrimination plane, where the boundary separates a ventricular tachycardia region from a non-ventricular tachycardia region;

classifying cardiac signals falling in the ventricular tachycardiac region as tachycardia complexes; and

classifying cardiac signals falling in the non-ventricular tachycardiac region as supraventricular tachycardia complexes.

7. The method of claim 5, including using the similarity value and the dissimilarity value to determine if each of the cardiac signals is a supraventricular tachycardia complex;

declaring a candidate supraventricular tachycardia when the number of ventricular tachycardia complexes reach a predetermined threshold.

8. The method of claim 7, including the act of declaring a supraventricular tachycardia when both the first discrimination stage and the second discrimination stage declare a candidate supraventricular tachycardia.

9. The method of claim 3, including setting the template R-wave width at an average R-wave width of a plurality of normal sinus rhythm cardiac signals.

10. The method of claim 3, including setting the predetermined value of the template R-wave width between 20 to 50 percent greater than the template R-wave width.

11. The method of claim 3, including classifying the sensed cardiac signal as a candidate supraventricular tachycardia complex if the width of the sensed R-wave is less than the predetermined value of the template R-wave width;

and

declaring a candidate supraventricular tachycardia when the number of candidate supraventricular tachycardia complexes reach the predetermined threshold.

12. The method of claim 11, where if the cardiac signals classified in the first discrimination stage indicate a candidate supraventricular tachycardia, then analyzing those cardiac signals in the second discrimination stage.

13. The method of claim 11, where if the cardiac signals classified in the first discrimination stage indicate a candidate supraventricular tachycardia, then acquiring further cardiac signals for classification in the second discrimination stage.