System and method for separating cardiac signals

• US 20050010120A1
• Filed: 07/03/2002
• Published: 01/13/2005
• Est. Priority Date: 07/05/2001
• Status: Active Grant

• Current Assignee: Sigmed Incorporated
• Original Assignee: Sigmed Incorporated
• Inventors: Jung, Tzyy- Ping, Duann, Jeng-Ren
• Granted Patent: US 7,941,205 B2
• Time in Patent Office: Days
• US Class Current: 600/509
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/339 Displays specially adapted therefor
• CPC Class Codes: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal

Abstract

EKG sensors ((150) are placed on a patient (140) to receive electrocardiogram (EKG) recording signals, which are typically combinations of original signals from different sources, such as pacemaker signals, QRS complex signals, and irregular oscillatory signals that suggest an arrhythmia condition. A computing module (120) uses independent component analysis to separate the recorded EKG signals. The separated signals are displayed to help physicians to analyze heart conditions and to identify probably locations of abnormal heart conditions. At least a portion of the separated signals can be further displayed in a chaos phase space portrait to help detect abnormality in heart conditions.

Claims

1. A medical system for separating electrocardiogram (EKG) signals;

comprising;

a receiving module configured to receive a plurality J of recorded EKG signals X_j from a plurality of EKG sensors;

a computing module configured to separate the received signals using independent component analysis to produce a plurality I of separated signals Y_i; and

a display module configured to display the separated signals.

2. The medical system of claim 1, wherein the display module is further configured to display at least a portion of the separated signals in a chaos phase space portrait.

3. The medical system of claim 2, wherein the separated signals include three components of QRS complex, and wherein the display module is further configured to display at least the three QRS complex components in a chaos phase space portrait.

4. The medical system of claim 1, wherein the computing module is configured to separate the recorded signals by multiplying the recorded signals by a matrix W_ij such that Y_i=W_ij*X_j.

5. The medical system of claim 1, wherein the computing module is configured to separate the recorded signals using a neural-network implemented method, the method comprising:

selecting a plurality I of bias weights W_i0 and a plurality I*J of scaling weights W_ij;

adjusting the bias weights W_i0 and the scaling weights W_ij to minimize information redundancy among separated signals; and

producing separated signals Y_i such that Y_i=Wij*X_j+W_i0.

6. The medical system of claim 1, further comprising a database storing a plurality of EKG signal triggers and corresponding diagnosis, and a matching module configured to match the separated signals with one or more of the stored EKG signal triggers.

7. A computer-implemented method of separating electrocardiogram (EKG) recording signals, the method comprising:

receiving a first plurality of EKG recording signals from EKG sensors placed on a patient;

separating the first plurality of EKG recording signals using independent component analysis to produce a second plurality of separated signals; and

displaying the separated signals.

8. The method of claim 7, further comprising displaying at least a portion of the separated signals in a chaos phase space portrait.

9. The method of claim 7, wherein the patient is a pregnant patient, and wherein the separated signals include separated signals originating from the pregnant patient and separated signals originating from a fetus.

10. The method of claim 7, wherein the displayed separated signals are used by a physician to determine the likelihood of arrhythmia in the patient.

11. The method of claim 7, wherein the displayed separated signals are used by a physician to determine the likelihood of myocardial infarction in the patient.

12. The method of claim 7, wherein each of the separated signals corresponds to a location on the patient body, wherein the displayed separated signals are used by a physician to determine the location of an abnormal heart condition in the patient according to the separated signals'"'"' corresponding locations.

13. A computer-assisted method of detecting arrhythmia in a patient, the method comprising:

placing a first plurality of EKG sensors on a patient to produce a first plurality of channels of recorded EKG signals;

sending the recorded signals to a computing module to separate the first plurality of EKG recorded signals into a first plurality of channels of separated signals using independent component analysis; and

reviewing a display of the separated signals to determine the existence of arrhythmia in the patient.

14. The method of claim 13, wherein reviewing a display of the separated signals comprises identifying a second set of one or more channels of separated signals that indicate arrhythmia, the method further comprising determining a probable location of arrhythmia according to the respective channel numbers of the second set of separated signals.

15. The method of claim 13, wherein placing a first plurality of EKG sensors comprises placing a plurality of EKG sensors on more than 10 body surface locations of a patient'"'"'s torso.

16. The method of claim 13, wherein placing a first plurality of EKG sensors comprises placing a plurality of EKG sensors on more than 40 body surface locations of a patient'"'"'s torso.

17. A cardiac rhythm management system comprising:

a cardiac signal recording module configured to record cardiac signals of a patient;

a computing module configured to separate the recorded cardiac signals into separated signals using independent component analysis;

a detection module configured to detect or predict an abnormal condition based on analyzing the separated cardiac signals; and

a treatment module configured to treat the patient when the abnormal condition is detected or predicted.

18. The cardiac rhythm management system of claim 17, wherein the detection module is configured to compare the separated signals with a plurality of stored triggers to determine whether the separated signals match a stored trigger.

19. A cardiac rhythm management system comprising:

a cardiac signal recording module configured to record cardiac signals of a patient;

a computing module configured to separate the recorded cardiac signals into separated signals using independent component analysis;

a detection module configured to detect or predict an abnormal condition based on analyzing the separated cardiac signals; and

a warning module configured to issue a warning when the abnormal condition is detected or predicted.

20. The cardiac rhythm management system of claim 19, wherein the detection module is configured to compare the separated signals with a plurality of stored triggers to determine whether the separated signals match a stored trigger.