System and method for interpreting electrocardiograms

• US 20060079795A1
• Filed: 10/13/2004
• Published: 04/13/2006
• Est. Priority Date: 10/13/2004
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Busche, Frederick D., Kelkar, Bhooshan P.
• Granted Patent: US 7,996,073 B2
• Time in Patent Office: Days
• US Class Current: 600/509
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle

Abstract

A system and method for interpreting electrocardiogram data. A system is provided that clusters raw electrocardiogram (EKG) data into clusters of EKG data; generates a predictive model for each cluster of EKG data; compares inputted patient EKG data with the clusters of EKG data to identify a matching cluster of EKG data; applies the predictive model associated with the matching cluster of EKG data to the inputted patient EKG data; and outputs diagnostic data.

Claims

1. An electrocardiogram (EKG) diagnosis system, comprising:

a sequence analysis system for clustering raw EKG data into clusters of EKG data; and

a predictive analysis system for generating a predictive model for each cluster of EKG data.

2. The EKG diagnosis system of claim 1, further comprising a system for associating a diagnosis with each cluster.

3. The EKG diagnosis system of claim 1, wherein the sequence analysis system includes a pattern time series algorithm for evaluating similarities among sets of EKG data.

4. The EKG diagnosis system of claim 1, wherein the predictive analysis system includes a radial basis function for generating the predictive models.

5. The EKG diagnosis system of claim 1, wherein the sequence analysis system includes a comparing system for comparing inputted patient EKG data with the clusters of EKG data to identify a matching cluster of EKG data.

6. The EKG diagnosis system of claim 5, wherein the predictive analysis system includes a system for applying the predictive model associated with the matching cluster of EKG data to the inputted patient EKG data, and for outputting diagnostic data.

7. The EKG diagnosis system of claim 6, wherein diagnostic data includes a diagnosis and a probability associated with the diagnosis.

8. A program product stored on a recordable medium for interpreting electrocardiogram (EKG) data, comprising:

means for clustering raw EKG data into clusters of EKG data; and

means for generating a predictive model for each cluster of EKG data.

9. The program product of claim 8, further comprising means for associating a diagnosis with each cluster.

10. The program product of claim 8, wherein the clustering means includes a pattern time series algorithm for evaluating similarities among sets of EKG data.

11. The program product of claim 8, wherein the generating means includes a radial basis function for generating the predictive models.

12. The program product of claim 8, further comprising means for comparing inputted patient EKG data with the clusters of EKG data to identify a matching cluster of EKG data.

13. The program product of claim 12, further comprising means for applying the predictive model associated with the matching cluster of EKG data to the inputted patient EKG data, and for outputting diagnostic data.

14. The program product of claim 13, wherein diagnostic data includes a diagnosis and a probability associated with the diagnosis.

15. A method for interpreting electrocardiogram (EKG) data, comprising:

clustering raw EKG data into clusters of EKG data; and

generating a predictive model for each cluster of EKG data.

16. The method of claim 15, further comprising the step of associating a diagnosis with each cluster.

17. The method of claim 15, wherein the clustering step utilizes a pattern time series algorithm for evaluating similarities among sets of EKG data.

18. The method of claim 15, wherein the generating step utilizes a radial basis function for generating the predictive models.

19. The method of claim 15, further comprising the steps of:

comparing inputted patient EKG data with the clusters of EKG data to identify a matching cluster of EKG data;

applying the predictive model associated with the matching cluster of EKG data to the inputted patient EKG data; and

outputting diagnostic data.

20. The method of claim 19, wherein diagnostic data includes a diagnosis and a probability associated with the diagnosis.

21. A method for deploying an application for interpreting electrocardiogram (EKG) data, comprising:

providing a computer infrastructure being operable to;

cluster raw EKG data into clusters of EKG data;

generate a predictive model for each cluster of EKG data;

compare inputted patient EKG data with the clusters of EKG data to identify a matching cluster of EKG data;

apply the predictive model associated with the matching cluster of EKG data to the inputted patient EKG data; and

output diagnostic data.

22. Computer software embodied in a propagated signal for interpreting electrocardiogram data, the computer software comprising instructions to cause a configuration computer to perform the following functions:

cluster raw EKG data into clusters of EKG data;

generate a predictive model for each cluster of EKG data;

compare inputted patient EKG data with the clusters of EKG data to identify a matching cluster of EKG data;

apply the predictive model associated with the matching cluster of EKG data to the inputted patient EKG data; and

output diagnostic data.