Episodical and Continuous ECG Monitoring

• US 20180042502A1
• Filed: 08/10/2016
• Published: 02/15/2018
• Est. Priority Date: 08/10/2016
• Status: Active Grant

• Current Assignee: ZEPP
• Original Assignee: Huami, Inc.
• Inventors: Wang, Fei, Wang, Yuanxiang
• Granted Patent: US 10,441,180 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 2560/0209 adapted for power saving
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/0006 ECG or EEG signals
• CPC Class Codes: A61B 5/0008 Temperature signals
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/053 Measuring electrical impedance or conductance of a portion of the body
• CPC Class Codes: A61B 5/067 using accelerometers or gyroscopes
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/259 using conductive adhesive means, e.g. gels
• CPC Class Codes: A61B 5/333 Recording apparatus specially adapted therefor
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/389 Electromyography [EMG]
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: A61B 5/6823 Trunk, e.g., chest, back, abdomen, hip
• CPC Class Codes: A61B 5/6824 Arm or wrist
• CPC Class Codes: A61B 5/721 using a separate sensor to detect motion or using motion information derived from signals other than the physiological signal to be measured

Abstract

Monitoring heart activity using a wearable device, including receiving, from the wearable device, an electrocardiograph (ECG) signal and a motion signal associated with an individual upon contact with the wearable device; in response to receiving the ECG signal and the motion signal associated with the individual, determining, by a computing device, a position of the wearable device in contact with the individual; and determining, by the computing device, a heart activity monitoring mode for operating the wearable device, based on the position of the wearable device in contact with the individual.

Claims

1. A method for monitoring heart activity using a wearable device, comprising:

receiving, from the wearable device, an electrocardiograph (ECG) signal and a motion signal associated with an individual upon contact with the wearable device;

in response to receiving the ECG signal and the motion signal associated with the individual, determining, by a computing device, a position of the wearable device in contact with the individual; and

determining, by the computing device, a heart activity monitoring mode for operating the wearable device, based on the position of the wearable device in contact with the individual.

2. The method of claim 1, further comprising:

in response to detecting the individual in contact with the wearable device for monitoring heart activity, generating, by the wearable device, the electrocardiograph (ECG) signal and the motion signal associated with the individual, wherein the motion signal is at least one of an accelerometer signal and a gyroscope signal.

3. The method of claim 1, wherein the wearable device and the computing device are the same device.

4. The method of claim 1, wherein determining, by a computing device, a position of the wearable device in contact with the individual further comprises one of:

determining, by the computing device, the position of the wearable device in contact with the individual based on at least one of the motion signal and the ECG signal.

5. The method of claim 1, wherein determining, by the computing device, a heart activity monitoring mode for operating the wearable device, based on the position of the wearable device in contact with the individual further comprises:

in response to the position of the wearable device in contact with the individual being determined to be in a chest position, determining the heart activity monitoring mode for operating the wearable device as a first mode indicative of continuous monitoring of ECG signals received by the wearable device; and

in response to the position of the wearable device in contact with the individual being determined to be in a wrist position, determining the heart activity monitoring mode for operating the wearable device as a second mode indicative of episodic monitoring of ECG signals received by the wearable device.

6. The method of claim 5, further comprising:

pre-processing the ECG signal to generate a denoised signal;

based on a determination of the wearable device being in the first mode indicative of continuous monitoring of ECG signals, detecting R peaks from the denoised signal;

processing the ECG signal by segmenting the denoised signal based on the detected R peaks; and

at least one of;

responsive to the processed ECG signal matching a predefined profile of a known individual, determining a first predicted label indicating the individual is the known individual;

responsive to the processed ECG signal matching a profile of a known heart disease, determining a second predicted label indicating that the individual is associated with the known heart disease; and

determining a health status for association with a profile of the individual based on the processed ECG signal, wherein the health status is related to one or more of weight, heart activity, fatigue level, stress level, heart age, heart activity variability, and heart condition associated with the individual.

7. The method of claim 5, further comprising:

pre-processing the ECG signal to generate a denoised signal;

based on a determination of the wearable device being in the second mode indicative of episodic monitoring of ECG signals, extracting one or more features from the denoised signal;

classifying the one or more features extracted from the denoised signal using a trained classifier to determine at least one of;

a first predicted label indicating the individual is the known individual; and

a second predicted label indicating that the individual is associated with the known heart disease; and

a health status for association with a profile of the individual based on the processed ECG signal, wherein the health status is related to one or more of weight, heart activity, fatigue level, stress level, heart age, heart activity variability, and heart condition associated with the individual.

8. The method of claim 1, wherein the position of the wearable device in contact with the individual is selected from at least a wrist position and a chest position, and the heart activity monitoring mode for operating the wearable device is selected from at least a first mode indicative of continuous monitoring of ECG signals and a second mode indicative of episodic monitoring of the ECG signals, wherein the ECG signals are received by the wearable device.

9. The method of claim 8, further comprising:

in response to the position of the wearable device in contact with the individual being determined to be in the chest position, identifying a unipolar chest lead for measuring the ECG signals, wherein the unipolar chest lead comprises one of leads V1, V2, V3, V4, V5, and V6; and

in response to the position of the wearable device in contact with the individual being determined to be in the wrist position, identifying a bipolar limb lead formed upon the individual'"'"'s contact with a first and second electrodes of the wearable device, wherein the bipolar limb lead comprises one of leads I, II, and III.

10. The method of claim 1, wherein the wearable device comprises a measurement component configured to be removably attached to at least one of a first accessory component capable of being attached to the individual'"'"'s chest and a second accessory component capable of being worn on the individual'"'"'s wrist.

11. A system, comprising:

a measurement component, comprising;

an electrocardiogram (ECG) sensor, comprising;

a first electrode, wherein a first ECG lead configured to generate an ECG signal is formed upon an individual'"'"'s contact with the first electrode; and

a second electrode, wherein a second ECG lead configured to generate the ECG signal is formed upon the individual'"'"'s contact with the first and second electrodes; and

a motion sensor configured to generate a motion signal based on the individual'"'"'s movement; and

an analysis component, comprising;

a non-transitory memory; and

a processor configured to execute instructions stored in the non-transitory memory to;

receive, from the ECG sensor, the ECG signal;

receive, from the motion sensor, the motion signal;

determine a position of the measurement component in contact with the individual based on the motion signal; and

determine a heart activity monitoring mode for operating the measurement component, based on the position of the measurement component in contact with the individual.

12. The system of claim 11, wherein the analysis component further comprises instructions stored in the non-transitory memory executed by the processor to determine the position of the measurement component in contact with the individual based on at least one of the motion signal and the ECG signal.

13. The system of claim 11, wherein the analysis component further comprises instructions stored in the non-transitory memory executed by the processor to:

in response to a determination that the position of the measurement component in contact with the individual is a chest position, determine the heart activity monitoring mode for operating the measurement component as a first mode indicative of continuous monitoring of ECG signals received by the measurement component; and

in response to a determination that the position of the measurement component in contact with the individual is a wrist position, determine the heart activity monitoring mode for operating the measurement component as a second mode indicative of episodic monitoring of ECG signals received by the measurement component.

14. The system of claim 13, wherein the analysis component further comprises instructions stored in the non-transitory memory executed by the processor to:

pre-process the ECG signal to generate a denoised signal;

based on a determination of the measurement component being in the first mode indicative of continuous monitoring of ECG signals, detect R peaks from the denoised signal;

process the ECG signal by segmenting the denoised signal based on the detected R peaks; and

at least one of;

responsive to the processed ECG signal matching a predefined profile of a known individual, determine a first predicted label indicating the individual is the known individual;

responsive to the processed ECG signal matching a profile of a known heart disease, determine a second predicted label indicating that the individual is associated with the known heart disease; and

determine a health status for association with a profile of the individual based on the processed ECG signal, wherein the health status is related to one or more of weight, heart activity, fatigue level, stress level, heart age, heart activity variability, and heart condition associated with the individual.

15. The system of claim 13, wherein the analysis component further comprises instructions stored in the non-transitory memory executed by the processor to:

pre-process the ECG signal to generate a denoised signal;

based on a determination of the measurement component being in the second mode indicative of episodic monitoring of ECG signals, extract one or more features from the denoised signal;

classify the one or more features extracted from the denoised signal using a trained classifier to determine at least one of;

a first predicted label indicating the individual is the known individual; and

a second predicted label indicating that the individual is associated with the known heart disease; and

a health status for association with a profile of the individual based on the processed ECG signal, wherein the health status is related to one or more of weight, heart activity, fatigue level, stress level, heart age, heart activity variability, and heart condition associated with the individual.

16. The system of claim 13, wherein at least one of the analysis component and the measurement component further comprises instructions stored in the non-transitory memory executed by the processor to:

in response to the position of the measurement component in contact with the individual being determined to be in the chest position, identify a unipolar chest lead for measuring the ECG signals, wherein the unipolar chest lead comprises one of leads V1, V2, V3, V4, V5, and V6; and

in response to the position of the measurement component in contact with the individual being determined to be in the wrist position, identify a bipolar limb lead formed upon the individual'"'"'s contact with a first and second electrodes of the measurement component, wherein the bipolar limb lead comprises one of leads I, II, and III.

17. The system of claim 13, wherein the measurement component is configured to be removably attached to at least one of a first accessory component capable of being attached to the individual'"'"'s chest and a second accessory component capable of being worn on the individual'"'"'s wrist.

18. The system of claim 11, wherein the ECG signal and the motion signal associated with the individual are generated by the measurement component upon detecting the individual in contact with the measurement component for monitoring heart activity, and the motion sensor comprises at least one of an accelerometer and a gyroscope.

19. An apparatus for monitoring heart activity, comprising:

a non-transitory memory; and

a processor configured to execute instructions stored in the non-transitory memory to;

receive an electrocardiograph (ECG) signal and a motion signal associated with an individual upon contact with a wearable device;

in response to receiving the ECG signal and the motion signal associated with the individual, determine a position of the wearable device in contact with the individual; and

determine a heart activity monitoring mode for operating the wearable device, based on the position of the wearable device in contact with the individual, wherein the position of the wearable device in contact with the individual is selected from at least a wrist position and a chest position, and the heart activity monitoring mode for operating the wearable device is selected from at least a first mode indicative of continuous monitoring of ECG signals and a second mode indicative of episodic monitoring of the ECG signals.

20. The apparatus of claim 19, wherein the instructions stored in the non-transitory memory executed by the processor further comprise instructions to:

pre-process the ECG signal to generate a denoised signal;

based on a determination of the measurement component being in the first mode indicative of continuous monitoring of ECG signals,

detect R peaks from the denoised signal;

process the ECG signal by segmenting the denoised signal based on the detected R peaks; and

at least one of;

responsive to the processed ECG signal matching a predefined profile of a known individual, determine a first predicted label indicating the individual is the known individual;

responsive to the processed ECG signal matching a profile of a known heart disease, determine a second predicted label indicating that the individual is associated with the known heart disease; and

determine a health status for association with a profile of the individual based on the processed ECG signal, wherein the health status is related to one or more of weight, heart activity, fatigue level, stress level, heart age, heart activity variability, and heart condition associated with the individual; and

based on a determination of the measurement component being in the second mode indicative of episodic monitoring of ECG signals,

extract one or more features from the denoised signal;

classify the one or more features extracted from the denoised signal using a trained classifier to determine at least one of;

a first predicted label indicating the individual is the known individual; and

a second predicted label indicating that the individual is associated with the known heart disease; and

a health status for association with a profile of the individual based on the processed ECG signal, wherein the health status is related to one or more of weight, heart activity, fatigue level, stress level, heart age, heart activity variability, and heart condition associated with the individual.