AUTOMATIC METHOD TO DELINEATE OR CATEGORIZE AN ELECTROCARDIOGRAM
Disclosed is a method for computerizing delineation and/or multi-label classification of an ECG signal, including: applying a neural network to the ECG, labelling the ECG, and optionally displaying the labels according to time with the ECG signal.
1 . A system for analyzing an electrocardiogram (ECG) signal corresponding to a patient, the system comprising at least one server and at least one processor configured to execute instructions to:
receive the ECG signal sampled from the patient over a plurality of time points;
determine delineation scores at each time point of the plurality of time points of at least a portion of the ECG signal, the delineation scores corresponding to multiple wave types at each time point;
determine a presence of a first wave type and a second wave type based on the at least a portion of an ECG signal and the delineation scores;
determine conduction information between the first wave type and the second wave type; and
generate information for display comprising a graphical representation of the at least a portion of the ECG signal and the conduction information between the first wave type and the second wave type.
2 . The system of claim 1 , wherein the conduction information indicates conduction between the first wave type and the second wave type.
3 . The system of claim 1 , wherein the conduction information indicates non-conduction between the first wave type and the second wave type.
4 . The system of claim 1 , wherein the first wave type is a P wave and the second wave type is a QRS wave.
5 . The system of claim 1 , wherein the at least one processor is further configured to execute instructions to generate information for display showing the first wave type as a first dot and the second wave type as a second dot.
6 . The system of claim 5 , wherein the conduction information comprises a line between the first dot and the second dot indicating conduction between the first wave type and the second wave type.
7 . The system of claim 1 , wherein the at least one processor is further configured to execute instructions to:
determine characterization information for the first wave type or the second wave type or both; and
generate information for display comprising the characterization information.
8 . The system of claim 7 , wherein the characterization information comprises a characterization of premature waves.
9 . The system of claim 8 , wherein the characterization information comprises a square associated with the premature wave for display.
10 . The system of claim 1 , wherein the at least one processor is further configured to execute instructions to:
determine a presence of additional first and second wave types at additional time points and additional conduction information relating thereto; and
generate information for a conduction pattern display comprising the additional conduction information between the additional first and second wave types.
11 . The system of claim 1 , wherein the visual indication of the conduction information is aligned with a location of the conduction information on the graphical representation of the at least a portion of the ECG signal.
12 . The system of claim 1 , wherein the at least one processor is further configured to execute instructions to:
determine a presence of one or more anomalies in the ECG signal; and
generate information for display indicating the presence of the one or more anomalies in the ECG signal.
13 . The system of claim 1 , wherein the at least one processor is configured to execute instructions to determine the delineation scores by applying the at least a portion of the ECG signal to a first neural network.
14 . The system of claim 13 , wherein the at least one processor is configured to execute instructions to determine anomaly information about the ECG signal via a second neural network.
15 . A computerized method for analyzing an electrocardiogram (ECG) signal corresponding to a patient, the computerized method comprising:
receiving the ECG signal sampled from the patient over a plurality of time points;
determining delineation scores at each time point of the plurality of time points of at least a portion of the ECG signal, the delineation scores corresponding to multiple wave types at each time point;
determining a presence of a first wave type and a second wave type based on the at least a portion of an ECG signal and the delineation scores;
determining conduction information between the first wave type and the second wave type; and
generating information for display comprising a graphical representation of the at least a portion of the ECG signal and the conduction information between the first wave type and the second wave type.
16 . The computerized method of claim 15 , wherein the conduction information indicates conduction between the first wave type and the second wave type.
17 . The computerized method of claim 15 , wherein the conduction information indicates non-conduction between the first wave type and the second wave type.
18 . The computerized method of claim 15 , wherein the first wave type is a P wave and the second wave type is a QRS wave.
19 . The computerized method of claim 15 , further comprising generating information for display showing the first wave type as a first dot and the second wave type as a second dot.
20 . The computerized method of claim 19 , wherein the conduction information comprises a line between the first dot and the second dot indicating conduction between the first wave type and the second wave type.
21 . The computerized method of claim 15 , further comprising:
determining a presence of additional first and second wave types at additional time points and additional conduction information relating thereto; and
generating information for a conduction pattern display comprising the additional conduction information between the additional first and second wave types.
22 . The computerized method of claim 15 , wherein the visual indication of the conduction information is aligned with a location of the conduction information on the graphical representation of the at least a portion of the ECG signal.
23 . The computerized method of claim 15 , further comprising:
determining a presence of one or more anomalies in the ECG signal; and
generating information for display indicating the presence of the one or more anomalies in the ECG signal.
24 . The computerized method of claim 15 , wherein determining the delineation scores comprises applying the at least a portion of the ECG signal to a first neural network.
25 . The computerized method of claim 24 , further comprising determining anomaly information about the ECG signal via a second neural network.
26 . A programmed routine for use with a computerized system for analyzing an electrocardiogram (ECG) signal obtained from a patient, the programmed routine comprising instructions that when executed:
receive the ECG signal sampled from the patient over a plurality of time points;
determine delineation scores at each time point of the plurality of time points of at least a portion of the ECG signal, the delineation scores corresponding to multiple wave types at each time point;
determine a presence of a first wave type and a second wave type based on the at least a portion of an ECG signal and the delineation scores;
determine conduction information between the first wave type and the second wave type; and
generate information for display comprising a graphical representation of the at least a portion of the ECG signal and the conduction information between the first wave type and the second wave type.