System and method for detecting abnormal respiration based on intracardiac electrogram signals using a pattern recognition device

• US 7,435,221 B1
• Filed: 11/10/2006
• Issued: 10/14/2008
• Est. Priority Date: 11/24/2004
• Status: Active Grant

• Current Assignee: Pacesetter Incorporated (Abbott Laboratories)
• Original Assignee: Pacesetter Incorporated (Abbott Laboratories)
• Inventors: Bharmi, Rupinder, de Chazal, Philip, Bornzin, Gene A., Benser, Michael E.
• Primary Examiner(s): Marmor, II; Charles A.
• Assistant Examiner(s): Natnithithadha; Navin
• Application Number:
  US11/558,819
• Time in Patent Office: 704 Days
• Field of Search: 600/481, 600/483, 600/484, 600500-503, 600508-529, 607 2- 32
• US Class Current: 600/484
• CPC Class Codes: A61B 5/0031 Implanted circuitry
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/08 Detecting, measuring or recording devices for evaluating the respiratory organs A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/0803 Recording apparatus specially adapted therefor
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/145 Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissuemeasuring of blood pressure or blood flow A61B5/02; non-radiation detecting or locating of foreign bodies in blood A61B5/06
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/353 Detecting P-waves
• CPC Class Codes: A61B 5/355 Detecting T-waves
• CPC Class Codes: A61B 5/366 Detecting abnormal QRS complex, e.g. widening
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• CPC Class Codes: A61B 5/4818 Sleep apnoea
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61N 1/3601 of respiratory organs
• CPC Class Codes: A61N 1/365 controlled by a physiological parameter, e.g. heart potential evoked response A61N1/371
• CPC Class Codes: A61N 1/37 Monitoring; Protecting
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Techniques are provided for detecting abnormal respiration within a patient based upon intracardiac electrogram (IEGM) signals or other electrical cardiac signals. Briefly, abnormal respiration is detected using a pattern recognition trained to discriminate normal and abnormal respiration based on morphological parameters and interval-based parameters extracted from the IEGM signals. In addition, techniques are described for distinguishing among different cardiac rhythm types within the patient while using one or more pattern classifiers or other pattern recognition devices.

Claims

1. A method for detecting abnormal respiration using an implantable medical device, the method comprising:

sensing cardiac electrical signals within a patient in which the device is implanted;

determining a cardiac rhythm type of the patient;

identifying cardiac cycles within the electrical signals;

detecting one or more parameters associated with the cardiac cycles and as a function of the cardiac rhythm type; and

detecting abnormal respiration by applying the parameters of the cardiac cycles to a device trained to discriminate between normal and abnormal respiration for the cardiac rhythm type.

2. The method of claim 1 wherein detecting abnormal respiration by applying the parameters of the cardiac cycles to the trained device is performed to discriminate between normal respiration and apneic/hypopneic respiration.

3. The method of claim 1 wherein detecting abnormal respiration by applying the parameters of the cardiac cycles to the trained device is performed to discriminate among normal respiration, obstructive apneic/hypopneic respiration and central apneic/hypopneic respiration.

4. The method of claim 1 wherein detecting one or more parameters includes detecting interval-based parameters associated with the cardiac cycles.

5. The method of claim 4 wherein the interval-based parameters include one or more of R-R, P-R, P-P and QT intervals.

6. The method of claim 1 wherein the morphological parameters include one or more of vPPI, tPDI, aPDI, ffPDI, and fftPDI.

7. The method of claim 1 wherein detecting parameters associated with the cardiac cycles includes extracting time-domain features from the parameters, the time-domain features being applied to the trained device.

8. The method of claim 7 wherein the time-domain features include mean and standard deviations of the parameters.

9. The method of claim 1 wherein detecting parameters associated with the cardiac cycles includes frequency features from the parameters, the frequency-domain features being applied to the trained device.

10. The method of claim 1 wherein detecting abnormal respiration by applying the parameters of the cardiac cycles to the trained device further includes evaluating a severity of abnormal respiration.

11. The method of claim 1 wherein detecting abnormal respiration by applying the parameters of the cardiac cycles to the trained device is performed by applying only those parameters detected within a particular epoch of time.

12. The method of claim 1 further including detecting whether the patient is asleep and wherein detecting abnormal respiration by applying the parameters of the cardiac cycles to the trained device is performed only using parameters detected while the patient is asleep.

13. The method of claim 1 wherein the implantable device is equipped to perform one or more of bi-ventricular and bi-atrial sensing and wherein detecting abnormal respiration is performed by applying parameters derived from cardiac cycles extracted from one or more of bi-ventricular and bi-atrial cardiac signals to the device trained to discriminate between normal and abnormal respiration.

14. The method of claim 1 wherein detecting abnormal respiration by applying the parameters of the cardiac cycles to the trained device is performed to discriminate between patients with substantially normal respiration and patients subject to abnormal respiration.

15. The method of claim 1 wherein detecting abnormal respiration by applying the parameters of the cardiac cycles to the trained device is performed to detect individual episodes of abnormal respiration.

16. A system for detecting abnormal respiration using an implantable medical device having a device trained to discriminating between normal and abnormal respiration, the system comprising:

means for sensing cardiac electrical signals within a patient in which the device is implanted;

means for determining a cardiac rhythm type;

means for identifying cardiac cycles within the electrical signals;

means for detecting one or more parameters associated with the cardiac cycles and as a function of the cardiac rhythm type;

means for discriminating between normal and abnormal respiration using the parameters of the cardiac cycles.