Application US20200015694

AUTOMATIC METHOD TO DELINEATE OR CATEGORIZE AN ELECTROCARDIOGRAM
[+] Show Details

US20200015694

1-4. (canceled) (0)

5. A computerized-method for classification of an electrocardiogram (ECG) signal obtained from a patient using a neural network, the method comprising: (10) (5)

training the neural network with a dataset of pre-characterized ECG signals to generate a trained neural network;

receiving the ECG signal sampled at a plurality of time points;

analyzing the ECG signal at the plurality of time points using the trained neural network;

computing scores based on the analyzed ECG signal to detect anomalies; and

assigning labels to the ECG signal based on the scores related to the detected anomalies.

6. The computerized-method of claim 5, further comprising denoising and removing a baseline of the ECG signal. (0)

7. The computerized-method of claim 5, further comprising determining a location of at least one anomaly in the EGG signal. (0)

8. The computerized-method of claim 5, wherein assigning labels to the ECG signal comprises assigning multiple labels for at least one time point of the plurality of time point. (0)

13. The computerized-method of claim 5, further comprising expressing the ECG signal at a selected frequency. (0)

14. The computerized-method of claim 5, further comprising displaying the scores related to the detected anomalies. (0)

15. The computerized-method of claim 5, further comprising displaying the labels and the ECG signal. (0)

16. The computerized-method of claim 5, wherein assigning labels to the ECG signal related to the detected anomalies is assigning labels of atrial fibrillation to the ECG signal. (0)

17. The computerized-method of claim 5, wherein: (0) (1)

18. The computerized-method of claim 5, further comprising expressing the detected anomalies as a vector of size q, with q being a number of anomalies to identify. (0)

19. The computerized-method of claim 5, wherein computing scores based on the analyzed ECG signal to detect anomalies comprises computing scores at each one of the plurality of time points. (0)

9-12. (canceled) (0)

20. A system for classification of an electrocardiogram (ECG) signal obtained from a patient using a neural network, the system comprising at least one server to: (10) (5)

train the neural network with a dataset of pre-characterized ECG signals to generate a trained neural network;

receive the ECG signal sampled at a plurality of time points;

analyze the ECG signal at the plurality of time points using the trained neural network;

compute scores based on the analyzed ECG signal to detect anomalies; and

assign labels to the ECG signal based on the scores related to the detected anomalies.

21. The system of claim 20, wherein the at least one server is configured to denoise and remove a baseline of the ECG signal. (0)

22. The system of claim 20, wherein the at least one server is configured to determine a location of at least one anomaly in the ECG signal. (0)

23. The system of claim 20, wherein the at least one server is configured to assign multiple labels for at least one time point of the plurality of time points. (0)

24. The system of claim 20, wherein the at least one server is configured to express the ECG signal at a selected frequency. (0)

25. The system of claim 20, wherein the at least one server is configured to generate information indicative of the scores related to the detected anomalies for display. (0)

26. The system of claim 20, wherein the at least one server is configured to generate information indicative of the labels and the ECG signal for display. (0)

27. The system of claim 20, wherein the at least one server is configured to assign labels of atrial fibrillation to the ECG signal. (0)

28. The system of claim 20, wherein the at least one server is configured to express the ECG signal as a matrix of size m×n with m fixed and at a predefined frequency. (0)

29. The system of claim 20, wherein the at least one server is configured to express the one or more anomalies as a vector of size q, with q being a number of anomalies to identify. (0)

30. The system of claim 20, wherein the at least one server is configured to compute scores based on the analyzed ECG signal at each one of the plurality of time points. (0)

31. A programmed routine comprising instructions that, when executed by at least one processor, cause the at least one processor to: (4) (5)

train the neural network with a dataset of pre-characterized ECG signals to generate a trained neural network;

receive the ECG signal sampled at a plurality of time points;

analyze the ECG signal at the plurality of time points using the trained neural network;

compute scores based on the analyzed ECG signal to detect anomalies; and

assign labels to the ECG signal based on the scores related to the detected anomalies.

32. The programmed routine of claim 31, further comprising instructions that, when executed by the at least one processor, cause the at least one processor to denoise and remove a baseline of the ECG signal. (0)

33. The programmed routine of claim 31, further comprising instructions that, when executed by the at least one processor, cause the at least one processor to determine a location of at least one anomaly in the ECG signal. (0)

34. The programmed routine of claim 31, further comprising instructions that, when executed by the at least one processor, cause the at least one processor to assign multiple labels for at least one time point of the plurality of time points. (0)

35. The programmed routine of claim 31, further comprising instructions that, when executed by the at least one processor, cause the at least one processor to compute scores based on the analyzed ECG signal at each one of the plurality of time points. (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20200015694

AUTOMATIC METHOD TO DELINEATE OR CATEGORIZE AN ELECTROCARDIOGRAM

Patent Matrix® Search