System and method for ECG data classification for use in facilitating diagnosis of cardiac rhythm disorders with the aid of a digital computer

• US 10,251,576 B2
• Filed: 03/23/2018
• Issued: 04/09/2019
• 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:
  US15/934,888
• Publication Number:
  US 20180206752A1
• Time in Patent Office: 382 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 with a patient button. A press of the patient button is identified within the ECG data. A button window with a segment of data prior to and after the button press is defined within the ECG data. The ECG data is divided into blocks. Noise detection analysis is applied to the data blocks. A classification of noise or valid data is assigned to each data block based on the noise detection analysis. At least one data block that overlaps the button window is assigned the noise classification. The at least one data block is trimmed to align with one of the start and end of the button window. The trimmed blocks assigned with the noise classification are removed from the data.

Claims

1. A system for ECG data classification for use in facilitating diagnosis of cardiac rhythm disorders with the aid of a digital computer, comprising:

a database to store ECG data obtained via an electrocardiography monitor comprising a patient button and an extended wear electrode patch, wherein the extended wear electrode patch comprises a backing, a pair of electrocardiographic electrodes conductively exposed on a contact surface of each end of the backing, a non-conductive receptacle adhered to an outward-facing surface of the backing and comprising a plurality of electrical pads, a battery electrically interfaced to a pair of the electrical pads on the non-conductive receptacle, and a circuit affixed on each end of the backing; 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;

identify within the ECG data at least one press of the patient button;

define within the ECG data a button window comprising a segment of data prior to and after the press of the patient button;

divide the ECG data into blocks;

apply noise detection analysis to the blocks of ECG data;

assign a classification comprising one of noise and valid data to each ECG data block based on the noise detection analysis;

identify at least one block of ECG data assigned the noise classification that overlaps the button window;

trim the at least one block of ECG data to align with one of the start and end of the button window; and

remove from the ECG data the blocks and the trimmed blocks assigned with the noise classification.

2. A system in accordance with claim 1, wherein the central processing unit performs an analysis of the ECG data after the blocks assigned the noise classification have been removed and identifies at least one cardiac event based on the analysis.

3. A system in accordance with claim 1, wherein the central processing unit performs the noise detection analysis by:

identifying features;

identifying repeating patterns of the features;

generating a matrix with the identified features and patterns;

generating at least one matrix with weights for the identified features and patterns; and

assigning a value for each of the noise classification and the valid classification to each block based on the weight matrix.

4. A system in accordance with claim 3, wherein the central processing unit determines the features by applying one or more sliding filters to the ECG data.

5. A system in accordance with claim 3, wherein the central processing unit selects one such block the classification assigned the highest value for that block.

6. A system in accordance with claim 5, wherein the central processing unit applies a time threshold to a period of identified noise in each of one or more blocks and assigns a noise classification to one such block when the noise classification has a higher value than the valid classification and the period of identified noise exceeds the time threshold.

7. A system in accordance with claim 6, wherein the central processing unit removes from each block of ECG data a predetermined amount of data from a beginning of the block from consideration during the noise detection analysis.

8. A system in accordance with claim 1, wherein the electrocardiography monitor further comprises:

a monitor recorder having a sealed housing adapted to be removably secured into the non-conductive receptacle of the electrode patch, wherein the scaled housing comprises a set of electrical contacts that protrude from a bottom surface and that correspond with further electrical pads on the non-conductive receptacle and comprising;

a micro-controller operable to sense electrocardiographic signals through the electrocardiographic electrodes via the pair of the electrical pads; and

a flash memory electrically interfaced with the micro-controller and operable to store samples of the electrocardiographic signals.

9. A system in accordance with claim 1, wherein one of the electrocardiographic electrodes is adhered to a region overlying the Xiphoid process on a patient'"'"'s chest and an other of the electrocardiographic electrodes is adhered to the region near the manubrium on the patient'"'"'s chest oriented centrally (in the midline) along the sternum upwards from the one electrocardiographic electrode.

10. A method for ECG data classification for use in facilitating diagnosis of cardiac rhythm disorders with the aid of a digital computer, comprising:

obtaining ECG data via an electrocardiography monitor comprising a patient button and an extended wear electrode patch, wherein the extended wear electrode patch comprises a backing, a pair of electrocardiographic electrodes conductively exposed on a contact surface of each end of the backing, a non-conductive receptacle adhered to an outward-facing surface of the backing and comprising a plurality of electrical pads, a battery electrically interfaced to a pair of the electrical pads on the non-conductive receptacle, and a circuit affixed on each end of the backing;

identifying within the ECG data at least one press of the patient button;

defining within the ECG data a button window comprising a segment of data prior to and after the press of the patient button;

dividing the ECG data into blocks;

applying noise detection analysis to the blocks of ECG data;

assigning a classification comprising one of noise and valid data to each ECG data block based on the noise detection analysis;

identifying at least one block of ECG data assigned the noise classification that overlaps the button window;

trimming the at least one block of ECG data to align with one of the start and end of the button window; and

removing from the ECG data the blocks and the trimmed blocks assigned with the noise classification.

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

performing an analysis of the ECG data after the blocks assigned the noise classification have been removed; and

identifying at least one cardiac event based on the analysis.

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

identifying features;

identifying repeating patterns of the features;

generating a matrix with the identified features and patterns;

generating at least one matrix with weights for the identified features and patterns; and

assigning a value for each of the noise classification and the valid classification to each block based on the weight matrix.

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

determining the features by applying one or more sliding filters to the ECG data.

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

selecting one such block the classification assigned the highest value for that block.

15. A method in accordance with claim 14, further comprising:

applying a time threshold to a period of identified noise in each of one or more blocks; and

assigning a noise classification to one such block when the noise classification has a higher value than the valid classification and the period of identified noise exceeds the time threshold.

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

from each block of ECG data, removing a predetermined amount of data from a beginning of the block from consideration during the noise detection analysis.

17. A method in accordance with claim 10, wherein the electrocardiography monitor further comprises:

a monitor recorder having a sealed housing adapted to be removably secured into the non-conductive receptacle of the electrode patch, wherein the sealed housing comprises a set of electrical contacts that protrude from a bottom surface and that correspond with further electrical pads on the non-conductive receptacle and comprising;

a micro-controller operable to sense electrocardiographic signals through the electrocardiographic electrodes via the pair of the electrical pads; and

a flash memory electrically interfaced with the micro-controller and operable to store samples of the electrocardiographic signals.

18. A method in accordance with claim 10, wherein one of the electrocardiographic electrodes is adhered to a region overlying the Xiphoid process on a patient'"'"'s chest and an other of the electrocardiographic electrodes is adhered to the region near the manubrium on the patient'"'"'s chest oriented centrally (in the midline) along the sternum upwards from the one electrocardiographic electrode.