Systems and methods for classifying ECG data

• US 10,595,737 B2
• Filed: 04/16/2018
• Issued: 03/24/2020
• Est. Priority Date: 04/29/2016
• Status: Active Grant

• Current Assignee: Infobionic, Inc.
• Original Assignee: Infobionic, Inc.
• Inventors: Korzinov, Lev, Baumann, Eric, McNamara, Anna
• Primary Examiner(s): Wehrheim, Lindsey G
• Application Number:
  US15/953,996
• Publication Number:
  US 20180228390A1
• Time in Patent Office: 708 Days
• CPC Class Codes: A61B 2560/0431 Portable apparatus, e.g. comprising a handle or case
• CPC Class Codes: A61B 5/0006 ECG or EEG signals
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/25 Bioelectric electrodes therefor
• CPC Class Codes: A61B 5/282 Holders for multiple electrodes for introduction into the body A61B5/287
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/364 Detecting abnormal ECG interval, e.g. extrasystoles, ectopic heartbeats
• CPC Class Codes: A61B 5/6801 specially adapted to be attached to or worn on the body surface
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61B 5/7475 User input or interface means, e.g. keyboard, pointing device, joystick
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: H04B 1/385 Transceivers carried on the body, e.g. in helmets
• CPC Class Codes: H04L 43/04 Processing captured monitoring data, e.g. for logfile generation
• CPC Class Codes: H04W 4/70 Services for machine-to-machine communication [M2M] or machine type communication [MTC]

Abstract

A computer-implemented method for processing ECG data may include: receiving, over an electronic network, ECG data, wherein the ECG data represents a plurality of heartbeats; analyzing the ECG data, by at least one processor, to determine whether each of the plurality of heartbeats is a normal heartbeat or an abnormal heartbeat; associating, by the at least one processor, each of the abnormal heartbeats with either only one of a plurality of existing templates or a new template; receiving, from a user, input related to each new template, wherein the input includes either: a) a confirmation that the new template represents an abnormal heartbeat, or b) a reclassification of the new template as representing a normal heartbeat or a different abnormal heartbeat; and in response to the user input, updating, by the at least one processor, a label of each of the heartbeats associated with each confirmed new template and each of the heartbeats associated with each reclassified new template. The ECG data may be received from a portable monitor configured to be carried on a patient'"'"'s body.

Claims

1. A computer-implemented method for classifying ECG data, comprising:

classifying, using at least one processor, heartbeats in ECG data as (i) normal heartbeats, (ii) abnormal heartbeats associated with one or more preexisting templates, or (iii) abnormal heartbeats associated with one or more new templates;

receiving user input related to each new template of the one or more new templates after the classifying step, wherein the input includes either (a) a confirmation that the new template represents an abnormal heartbeat, (b) a reclassification of the new template as a normal heartbeat, or (c) a reclassification of the new template as representing an abnormal heartbeat different than the abnormal heartbeat from the classifying step; and

after receiving the user input, determining, by the at least one processor, a total number of abnormal heartbeats as a sum of the heartbeats associated with (d) the one or more preexisting templates and (e) the one or more new templates representing an abnormal heartbeat.

2. The method of claim 1, wherein the method does not include repeating the classifying step between the step of receiving user input and the step of determining the total number of abnormal heartbeats.

3. The method of claim 1, wherein the classifying step includes comparing each heartbeat in the ECG data to at least one of the one or more preexisting templates.

4. The method of claim 3, wherein the classifying step further includes creating a new template of the one or more new templates if a characteristic of an abnormal heartbeat in the ECG data differs from the characteristic of each preexisting template of the one or more preexisting templates.

5. The method of claim 1, further including receiving the ECG data.

6. The method of claim 5, wherein the receiving step includes wirelessly receiving the ECG data from a portable device configured to be carried on a patient'"'"'s body.

7. The method of claim 1, wherein the abnormal heartbeats represent arrhythmias.

8. The method of claim 1, wherein the abnormal heartbeats represent premature ventricular contractions.

9. The method of claim 1, further including displaying the total number of abnormal heartbeats on a display device.

10. A system for classifying ECG data, comprising:

a data storage device that stores instructions for processing ECG data; and

one or more processors configured to execute the instructions to perform a method including;

classifying, using at least one processor, heartbeats in ECG data as (i) normal heartbeats, (ii) abnormal heartbeats associated with one or more preexisting templates, or (iii) abnormal heartbeats associated with one or more new templates;

receiving user input related to each new template of the one or more new templates after the classifying step, wherein the input includes either (a) a confirmation that the new template represents an abnormal heartbeat, (b) a reclassification of the new template as a normal heartbeat, or (c) a reclassification of the new template as representing an abnormal heartbeat different than the abnormal heartbeat from the classifying step; and

after receiving the user input, determining, by the at least one processor, a total number of abnormal heartbeats as a sum of the heartbeats associated with (d) the one or more preexisting templates and (e) the one or more new templates representing an abnormal heartbeat.

11. The system of claim 10, wherein the method performed by the one or more processors does not include repeating the classifying step between the step of receiving user input and the step of determining the total number of abnormal heartbeats.

12. The system of claim 10, wherein the classifying step includes comparing each heartbeat in the ECG data to at least one of the one or more preexisting templates.

13. The system of claim 12, wherein the classifying step further includes creating a new template of the one or more new templates if a characteristic of an abnormal heartbeat in the ECG data differs from the characteristic of each preexisting template of the one or more preexisting templates.

14. The system of claim 10, further including a wireless receiver, and the method performed by the one or more processors further includes wirelessly receiving the ECG data from a portable device configured to be carried on a patient'"'"'s body.

15. The system of claim 10, wherein the abnormal heartbeats represent arrhythmias.

16. A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to perform a method for classifying ECG data, the method including:

classifying, using at least one processor, heartbeats in ECG data as (i) normal heartbeats, (ii) abnormal heartbeats associated with one or more preexisting templates, or (iii) abnormal heartbeats associated with one or more new templates;

receiving user input related to each new template of the one or more new templates after the classifying step, wherein the input includes either (a) a confirmation that the new template represents an abnormal heartbeat, (b) a reclassification of the new template as a normal heartbeat, or (c) a reclassification of the new template as representing an abnormal heartbeat different than the abnormal heartbeat from the classifying step; and

after receiving the user input, determining, by the at least one processor, a total number of abnormal heartbeats as a sum of the heartbeats associated with (d) the one or more preexisting templates and (e) the one or more new templates representing an abnormal heartbeat.

17. The computer-readable medium of claim 16, wherein the method does not include repeating the classifying step between the step of receiving user input and the step of determining the total number of abnormal heartbeats.

18. The computer-readable medium of claim 16, wherein the classifying step includes comparing each heartbeat in the ECG data to at least one of the one or more preexisting templates.

19. The computer-readable medium of claim 18, wherein the classifying step further includes creating a new template of the one or more new templates if a characteristic of an abnormal heartbeat in the ECG data differs from the characteristic of each preexisting template of the one or more preexisting templates.

20. The computer-readable medium of claim 16, wherein the method further includes wirelessly receiving the ECG data from a portable device configured to be carried on a patient'"'"'s body.