Application US20190332729

CALIBRATION OF SIMULATED CARDIOGRAMS
[+] Show Details

US20190332729

1. A method performed by a computing system for identifying simulated cardiograms that are similar to a patient cardiogram, the simulated cardiograms generated based on simulated pacings and the patient cardiogram generated based on a patient pacing of a patient, the method comprising: (10) (4)

identifying first simulated cardiograms whose simulated pacings are similar to the patient pacing;

identifying, from the first simulated cardiograms, second simulated cardiograms generated based on a simulated heart with a simulation orientation that is similar to a patient orientation of the patient's heart;

identifying, from the second simulated cardiograms, third simulated cardiograms that represent action potentials that are similar to the action potential represented by the patient cardiogram; and

identifying, from the third simulated cardiograms, calibrated simulated cardiograms that represent conduction velocities that are similar to the conduction velocity represented by the patient cardiogram.

2. The method of claim 1 further comprising: (1) (2)

4. The method of claim 1 wherein the cardiogram is an electrocardiogram. (0)

5. The method of claim 1 wherein the cardiogram is a vectorcardiogram. (0)

6. The method of claim 1 wherein a pacing includes a pacing location and a pacing rate. (0)

7. The method of claim 1 wherein similarity of action potentials is based on cardiograms that are normalized in magnitude and in duration. (0)

8. The method of claim 1 wherein the similarity of conduction velocities is based on cardiograms that are normalized in magnitude. (0)

9. The method of claim 1 wherein the simulated cardiograms are identified from a collection of simulated cardiograms generated based on a simulated structural disease similar to a patient structural disease of the patient. (0)

10. The method of claim 1 wherein the simulated cardiograms are identified from a collection of simulated cardiograms based on the similarity of cardiac geometry of a simulated cardiogram to patient cardiac geometry of the patient. (0)

11. The method of claim 1 wherein the similarity of orientations is based on simulated cardiac vectors that are similar to patient cardiac vectors of the patient, the cardiac vectors for cardiac cycle phases at cardiac locations. (0)

12. The method of claim 1 wherein the simulated cardiograms are identified from a collection of simulated cardiograms generated based on a simulated disease substrate similar to a patient disease substrate of the patient. (0)

13. A method performed by a computing system for identifying simulated cardiograms that are similar to a patient cardiogram, the method comprising: (4) (2)

determining morphological similarity of simulated cardiograms to the patient cardiogram based on morphology; and

identifying similar simulated cardiograms based on morphological similarity.

14. The method of claim 13 wherein the determining of morphological similarity includes: (2) (2)

17. The method of claim 13 further comprising training a classifier using training data that includes the identified similar simulated cardiograms labeled with a configuration parameter. (0)

18. The method of claim 13 further comprising determining cardiac geometry similarity of simulated cardiograms to the patient cardiogram wherein the identifying is further based on cardiac geometry similarity. (1) (0)

20. The method of claim 13 further comprising determining disease substrate similarity of simulated cardiograms to the patient cardiogram wherein the identifying is further based on disease substrate similarity. (0)

21. One or more computing systems for identifying simulated cardiograms that are similar to a patient cardiogram, the one or more computing systems comprising: (4) (2)

one or more computer-readable storage mediums for storing computer-executable instructions for controlling the one or more computing systems to: determine orientation similarity of simulated cardiograms to the patient cardiogram based on orientation;

determine electrophysiological similarity of simulated cardiograms to the patient cardiogram; and

identify similar simulated cardiograms based on orientation similarity and electrophysiological similarity; and

one or more processors for executing the computer-executable instructions stored in the one or more computer-readable storage mediums.

22. The one or more computing systems of claim 21 wherein the computer-executable instructions further control the one or more computing systems to determine disease substrate similarity of the simulated cardiograms to the patient cardiogram and wherein the computer-executable instructions to identify similar simulated cardiograms is further based on disease substrate similarity. (0)

23. The one or more computing systems of claim 21 wherein the computer-executable instructions further control the one or more computing systems to determine pacing similarity of the simulated cardiograms to the patient cardiogram and wherein the computer-executable instructions to identify similar simulated cardiograms is further based on pacing similarity. (0)

24. The one or more computing systems of claim 21 wherein the electrophysiological similarity is based on action potential similarity and conduction velocity similarity. (1) (0)

26. The one or more computing systems of claim 21 wherein the computer-executable instructions further control the one or more computing systems to train a classifier using training data that includes the identified similar simulated cardiograms labeled with a configuration parameter. (0)

27. A method performed by a computing system for mapping simulated cardiograms to patient cardiograms of a patient, the method comprising: (1) (3)

identifying simulated cardiograms that match the patient cardiograms based on configuration parameters and pacing locations;

training a mapping function to map the identified simulated cardiograms to the patient cardiograms; and

applying the trained mapping function to simulated cardiograms to generate transformed simulated cardiograms.

28. The method of claim 27 further comprising training a patient-specific model classifier based on the transformed simulated cardiograms. (0)

29. A method performed by one or more computing systems for calibrating the orientation of a simulated vectorcardiogram (“VCG”) to a patient VCG, the method comprising: (2) (5)

displaying a representation of the simulated VCG;

displaying a representation of the patient VCG;

receiving from a user an indication to rotate one of the displayed representations;

receiving from the user an indication that the rotated representation and the other representation are aligned; and

generating a transformation matrix based on rotation of the rotated representation.

30. The method of claim 29 wherein the representations are displayed within a torso. (0)

31. The method of claim 29 wherein a representation of the simulated VCG is displayed with a representation of a heart based on cardiac geometry associated with the simulated VCG. (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20190332729

CALIBRATION OF SIMULATED CARDIOGRAMS

Patent Matrix® Search