System and method for ECG data classification for use in facilitating diagnosis of cardiac rhythm disorders

• US 10,849,523 B2
• Filed: 04/08/2019
• Issued: 12/01/2020
• Est. Priority Date: 09/25/2013
• Status: Active Grant

• Current Assignee: Bardy Diagnostics, Inc. (Baxter International Inc.)
• Original Assignee: Bardy Diagnostics, Inc. (Baxter International Inc.)
• Inventors: Bardy, Gust H., Dreisbach, Ezra M.
• Primary Examiner(s): Schaetzle, Kennedy
• Application Number:
  US16/378,312
• Publication Number:
  US 20190231210A1
• Time in Patent Office: 603 Days
• Field of Search: None
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/0245 by using sensing means generating electric signals, i.e. ECG signals
• CPC Class Codes: A61B 5/259 using conductive adhesive means, e.g. gels
• CPC Class Codes: A61B 5/282 Holders for multiple electrodes for introduction into the body A61B5/287
• CPC Class Codes: A61B 5/308 for electrocardiography [ECG]
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/333 Recording apparatus specially adapted therefor
• CPC Class Codes: A61B 5/339 Displays specially adapted therefor
• CPC Class Codes: A61B 5/341 Vectorcardiography [VCG]
• CPC Class Codes: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/361 Detecting fibrillation
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• CPC Class Codes: A61B 5/364 Detecting abnormal ECG interval, e.g. extrasystoles, ectopic heartbeats
• CPC Class Codes: A61B 5/6823 Trunk, e.g., chest, back, abdomen, hip
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence

Abstract

A system and method for ECG data classification for use in facilitating diagnosis of cardiac rhythm disorders is provided. ECG data is obtained via an electrocardiography monitor shaped for placement on a patient'"'"'s chest. The ECG data is divided into segments and noise detection analysis is applied to the ECG data segments. A noise classification or a valid classification is assigned to each segment of the ECG data. At least one ECG data segment assigned the noise classification and that includes ECG data that corresponds with feedback from the patient via the electrocardiography monitor is identified. The ECG data that corresponds with the patient feedback is removed from the identified ECG data segment with the noise classification. The ECG data segments assigned the noise classification are removed from further analysis.

Claims

1. A system for ECG data classification for use in facilitating diagnosis of cardiac rhythm disorders, comprising:

a patient feedback button on an electrocardiography device associated with a patient;

a database to store ECG data obtained via the electrocardiography monitor shaped for placement on a patient'"'"'s chest and a marker identifying patient feedback comprising the ECG data occurring during a press of the feedback button by the patient; and

a server comprising a central processing unit, memory, an input port to receive the ECG data from the database, and an output port, wherein the central processing unit is configured to;

divide the ECG data into segments;

generate a window within at least one of the ECG segments with the marker by identifying a predetermined time before and after one such instance of the patient feedback;

apply noise detection analysis to the ECG data segments;

assign one of a noise classification and a valid classification to each segment of ECG data;

identify at least one ECG data segment assigned the noise classification that includes the window with the ECG data that corresponds with the patient feedback;

remove the ECG data that corresponds with the window from the identified ECG data segment with the noise classification; and

retain the removed ECG data that corresponds with the window for analysis.

2. A system in accordance with claim 1, wherein the central processing unit assigns the valid classification to the ECG data that corresponds with the patient feedback.

3. A system in accordance with claim 1, wherein the central processing unit removes a portion of the ECG data located at a beginning of each segment prior to performing the noise detection analysis.

4. A system in accordance with claim 1, wherein the central processing unit calculates a noise data classification value and a valid data classification value for each segment during the noise detection analysis and performs one or more of:

assigning the noise classification to one of the segments when the noise data classification value exceeds the valid data classification value; and

assigning the valid classification when the noise data classification value fails to exceed the valid data classification value.

5. A system in accordance with claim 1, wherein the predetermined time before and after the patient feedback comprises one of the same time and different times.

6. A system in accordance with claim 1, wherein the central processing unit removes the noise classification from one such segment of ECG data when the window is the same length as or longer than the segment.

7. A system in accordance with claim 1, wherein the patient feedback comprises a press of a feedback button on the electrocardiography monitor.

8. A system in accordance with claim 1, wherein the ECG data segments are one of overlapping and contiguous.

9. A system in accordance with claim 1, wherein the noise detection analysis is performed via a convolutional neural network.

10. A method for ECG data classification for use in facilitating diagnosis of cardiac rhythm disorders, comprising:

monitoring an electrocardiography monitor with a feedback button for placement on a patient'"'"'s chest;

storing ECG data obtained via the electrocardiography monitor in a database;

storing in the database the ECG data and a marker identifying patient feedback comprising the ECG data occurring during a press of the feedback button by the patient;

performing by a server, the following;

dividing the ECG data into segments;

generating a window within at least one of the ECG segments with the marker by identifying a predetermined time before and after one such instance of the patient feedback;

applying noise detection analysis to the ECG data segments;

assigning one of a noise classification and a valid classification to each segment of ECG data;

identifying at least one ECG data segment assigned the noise classification that includes the window with the ECG data that corresponds with the patient feedback;

removing the ECG data that corresponds with the window from the identified ECG data segment with the noise classification; and

retaining the removed ECG data that corresponds with the window for analysis.

11. A method in accordance with claim 10, further comprising:

assigning the valid classification to the ECG data that corresponds with the patient feedback.

12. A method in accordance with claim 10, further comprising:

removing a portion of the ECG data located at a beginning of each segment prior to performing the noise detection analysis.

13. A method in accordance with claim 10, further comprising:

calculating a noise data classification value and a valid data classification value for each segment during the noise detection analysis; and

performing one or more of;

assigning the noise classification to one of the segments when the noise data classification value exceeds the valid data classification value; and

assigning the valid classification when the noise data classification value fails to exceed the valid data classification value.

14. A method in accordance with claim 10, wherein the predetermined time before and after the patient feedback comprises one of the same time and different times.

15. A method in accordance with claim 10, further comprising:

removing the noise classification from one such segment of ECG data when the window is the same length as or longer than the segment.

16. A method in accordance with claim 10, wherein the patient feedback comprises a press of a feedback button on the electrocardiography monitor.

17. A method in accordance with claim 10, wherein the ECG data segments are one of overlapping and contiguous.

18. A method in accordance with claim 10, wherein the noise detection analysis is performed via a convolutional neural network.