Electrocardiogram processing system for delineation and classification
Systems and methods are provided for analyzing electrocardiogram (ECG) data of a patient using a substantial amount of ECG data. The systems receive ECG data from a sensing device positioned on a patient such as one or more ECG leads. The system may include an application that communicates with an ECG platform running on a server(s) that processes and analyzes the ECG data, e.g., using neural networks for delineation of the cardiac signal and classification of various abnormalities, conditions and/or descriptors. The processed ECG data is communicated from the server(s) for display in a user-friendly and interactive manner with enhanced accuracy.
1. A system for analyzing electrocardiogram (ECG) data of a patient, the system comprising instructions stored on at least one server, the instructions configured to, when executed, cause the at least one server to:
obtain a set of patient ECG data corresponding to a patient, the set of patient ECG data generated over a plurality of time points as sampled by a sensing device;
process at least a portion of the set of patient ECG data using an algorithm to determine a presence of one or more abnormalities, conditions, or descriptors corresponding to a cardiac event associated with the set of patient ECG data, the algorithm trained using a plurality of sets of ECG data different from the set of patient ECG data;
generate information, based on the processing, to indicate the presence of the one or more abnormalities, conditions, or descriptors corresponding to a cardiac event associated with the set of patient ECG data; and
send the information corresponding to the presence of the one or more abnormalities, conditions, or descriptors determined for the set of patient ECG data for display.
2. The system of claim 1 , wherein the instructions stored on the at least one server are further configured to cause the at least one server to cause a device to display a heart rate density plot based on the set of patient ECG data, the heart rate density plot representing a density of heart rates of the patient as a function of time.
3. The system of claim 2 , wherein the heart rate density plot visually indicates the one or more abnormalities, conditions, or descriptors determined for the set of patient ECG data.
4. The system of claim 2 , wherein the instructions stored on the at least one server are further configured to cause the at least one server to generate the heart rate density plot to permit zoom in and zoom out interaction on the heart rate density plot.
5. The system of claim 2 , wherein the instructions stored on the at least one server are further configured to cause the at least one server to generate the heart rate density plot arranged with respect to a time axis and to permit navigating the heart rate density plot with respect to the time axis.
6. The system of claim 5 , wherein the instructions stored on the at least one server are further configured to cause the at least one server to generate an ECG strip, wherein the time axis includes a cursor and a position of the cursor on the time axis of the heart rate density plot corresponds to a time window of the ECG strip.
7. The system of claim 5 , wherein the instructions stored on the at least one server are further configured to (i) generate one or more label buttons corresponding to the heart rate density plot and (ii) cause the heart rate density plot to visually indicate the presence of one or more abnormalities, conditions, or descriptors when the one or more label buttons are engaged.
8. The system of claim 1 , wherein the instructions stored on the at least one server are further configured to cause the at least one server to generate a report including at least the information corresponding to the presence of the one or more abnormalities, conditions, or descriptors determined for the set of patient ECG data.
9. The system of claim 8 , wherein the report includes at least one heart rate density plot representing a density of heart rates of the patient as a function of time.
10. The system of claim 9 , wherein the report visually indicates the presence of the one or more abnormalities, conditions, or descriptors in the at least one heart rate density plot.
11. The system of claim 1 , wherein the instructions stored on the at least one server are further configured to cause the at least one server to pre-process the set of patient ECG data prior to processing the at least a portion of the set of patient ECG data using the algorithm, and wherein pre-processing the set of patient ECG data comprises removing noise from the set of patient ECG data or expressing the set of patient ECG data at a predetermined baseline frequency or both.
12. The system of claim 1 , wherein processing the at least a portion of the set of patient ECG data using the algorithm comprises using at least one algorithm to apply the at least a portion of the set of patient ECG data to a first neural network.
13. The system of claim 1 , wherein the algorithm utilizes machine learning to process the at least a portion of the set of patient ECG data and generate the information.
14. The system of claim 1 , wherein the instructions stored on the at least one server cause the at least one server to process the at least a portion of the set of patient ECG data using the algorithm to determine a likelihood of the presence of one or more abnormalities, conditions, or descriptors corresponding to a cardiac event associated with the set of patient ECG data.
15. The system of claim 14 , wherein the instructions stored on the at least one server, are further configured to cause the at least one server to compare the likelihood of a presence of one or more abnormalities, conditions, or descriptors to a threshold value, and wherein the information corresponding to the presence of the one or more abnormalities, conditions, or descriptors determined for the set of patient ECG data is sent for display if the likelihood of a presence of one or more abnormalities, conditions, or descriptors exceeds the threshold value.
16. The system of claim 1 , wherein the instructions stored on the at least one server cause the at least one server to generate information indicating the presence of multiple abnormalities, conditions, or descriptors corresponding to multiple cardiac events associated with the set of patient ECG data.
17. A computerized method for analyzing electrocardiogram (ECG) data of a patient, the computerized method comprising:
obtaining a set of patient ECG data corresponding to a patient, the set of patient ECG data generated over a plurality of time points as sampled by a sensing device;
processing at least a portion of the set of patient ECG data using an algorithm to determine a presence of one or more abnormalities, conditions, or descriptors corresponding to a cardiac event associated with the set of patient ECG data, the algorithm trained using a plurality of sets of ECG data different from the set of patient ECG data;
generating information, based on the processing, to indicate the presence of the one or more abnormalities, conditions, or descriptors corresponding to a cardiac event associated with the set of patient ECG data; and
sending the information corresponding to the presence of the one or more abnormalities, conditions, or descriptors determined for the set of patient ECG data for display.
18. The computerized method of claim 17 , further comprising causing a device to display a heart rate density plot based on the set of patient ECG data, the heart rate density plot representing a density of heart rates of the patient as a function of time.
19. The computerized method of claim 18 , wherein the heart rate density plot visually indicates the one or more abnormalities, conditions, or descriptors determined for the set of patient ECG data.
20. The computerized method of claim 17 , further comprising generating a report including at least the information corresponding to the presence of the one or more abnormalities, conditions, or descriptors determined for the set of patient ECG data.
21. The computerized method of claim 20 , wherein the report includes at least one heart rate density plot representing a density of heart rates of the patient as a function of time.
22. The computerized method of claim 17 , wherein all of the set of patient ECG data is processed by at least one server.
23. The computerized method of claim 17 , wherein the one or more abnormalities, conditions, or descriptors corresponding to a cardiac event comprise atrial fibrillation associated with the set of patient ECG data.
24. The computerized method of claim 17 , further comprising pre-processing the set of patient ECG data prior to processing the at least a portion of the set of patient ECG data using the algorithm, and wherein pre-processing the set of patient ECG data comprises removing noise from the set of patient ECG data or expressing the set of patient ECG data at a predetermined baseline frequency or both.
25. The computerized method of claim 17 , wherein processing the at least a portion of the set of patient ECG data using the algorithm comprises using at least one algorithm to apply the at least a portion of the set of patient ECG data to a first neural network.
26. The computerized method of claim 25 , wherein processing the at least a portion of the set of patient ECG data using the algorithm further comprises using the at least one algorithm to apply the at least a portion of the set of patient ECG data to one or more additional neural networks.
27. The computerized method of claim 17 , wherein the algorithm utilizes machine learning to process the at least a portion of the set of patient ECG data and generate the information.
28. The computerized method of claim 17 , further comprising generating information indicating the presence of multiple abnormalities, conditions, or descriptors corresponding to multiple cardiac events associated with the set of patient ECG data.
29. A non-transitory computer-readable memory medium configured to store instructions thereon that when loaded by at least one processor cause the at least one processor to:
obtain a set of patient ECG data corresponding to a patient, the set of patient ECG data generated over a plurality of time points as sampled by a sensing device;
process at least a portion of the set of patient ECG data using an algorithm to determine a presence of one or more abnormalities, conditions, or descriptors corresponding to a cardiac event associated with the set of patient ECG data, the algorithm trained using a plurality of sets of ECG data different from the set of patient ECG data;
generate information, based on the processing, to indicate the presence of the one or more abnormalities, conditions, or descriptors corresponding to a cardiac event associated with the set of patient ECG data; and
send the information corresponding to the presence of the one or more abnormalities, conditions, or descriptors determined for the set of patient ECG data for display.
30. The non-transitory computer-readable memory medium of claim 29 , wherein the instructions loaded by the at least one processor further cause the at least one processor to cause a device to display a heart rate density plot based on the set of patient ECG data, the heart rate density plot representing a density of heart rates of the patient as a function of time.