GENERATING AUTOMATED ALARMS FOR CLINICAL MONITORING

• US 20180078219A1
• Filed: 09/22/2016
• Published: 03/22/2018
• Est. Priority Date: 09/22/2016
• Status: Active Grant

• Current Assignee: Vital Connect, Inc.
• Original Assignee: Vital Connect, Inc.
• Inventors: Selvaraj, Nandakumar
• Granted Patent: US 11,647,967 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/14542 for measuring blood gases A61B5/14551 takes precedence
• CPC Class Codes: A61B 5/6833 Adhesive patches
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7207 of noise induced by motion artifacts
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B

Abstract

A method and system for providing health-monitoring alarm management have been disclosed. In a first aspect, the method comprises detecting at least one vital sign signal using a wearable sensor device and managing an alarm mechanism of the wearable sensor device based on the at least one vital sign signal. In a second aspect, the system comprises a sensor for detecting at least one vital sign signal, a processor coupled to the sensor, and a memory device coupled to the processor, wherein the memory device stores an application which, when executed by the processor, causes the processor to manage an alarm mechanism of the wearable sensor device based on the at least one vital sign signal.

Claims

1. A method for providing health-monitoring alarm management, the method comprising:

detecting at least one vital sign signal using a wearable sensor device; and

managing an alarm mechanism of the wearable sensor device based on the at least one vital sign signal.

2. The method of claim 1, wherein the managing further comprises:

filtering the at least one vital sign signal using a statistical filtration mechanism, wherein the statistical filtration mechanism applies a moving window of a predetermined number of samples to a current sample of the at least one vital sign signal to provide a real positive array; and

determining a mean value and a standard deviation value using the real positive array.

3. The method of claim 2, further comprising:

determining a statistical boundary comprising a lower threshold and an upper threshold, wherein the lower threshold and the upper threshold are calculated using the mean value, the standard deviation value, and a coefficient parameter.

4. The method of claim 3, further comprising:

determining whether the current sample is within the statistical boundary; and

in response to the current sample being outside the statistical boundary, labeling the current sample as an artifact and replacing the current sample with the mean value.

5. The method of claim 1, wherein the managing further comprises:

applying a moving window of a predetermined number of samples to a current sample of the at least one vital sign signal to provide a real positive array;

determining whether the predetermined number of samples of the real positive array are greater than or equal to a predetermined upper threshold; and

in response to the predetermined number of samples being greater than or equal to the predetermined upper threshold, sounding an alarm.

6. The method of claim 1, wherein the managing further comprises:

applying a moving window of a predetermined number of samples to a current sample of the at least one vital sign signal to provide a real positive array;

determining whether the predetermined number of samples of the real positive array are within a predetermined boundary comprising a lower threshold and an upper threshold; and

in response to the predetermined number of samples being outside the predetermined boundary, sounding an alarm.

7. The method of claim 6, wherein the lower threshold and the upper threshold of the predetermined boundary are selected based upon a type of the at least one vital sign signal.

8. The method of claim 1, wherein the managing further comprises:

applying a first moving window of a predetermined number of samples to a current sample of the at least one vital sign signal to provide a first real positive array;

determining a mean value and a standard deviation value using the first real positive array.

9. The method of claim 8, further comprising:

determining a trend boundary comprising a lower threshold and an upper threshold, wherein the lower threshold and the upper threshold are calculated using the mean value, the standard deviation value, and a coefficient parameter.

10. The method of claim 9, further comprising:

determining a dual moving window of a predetermined number of samples based on the trend boundary to provide a dual real positive array.

11. The method of claim 10, further comprising:

applying a fourth moving window of a predetermined number of samples to the current sample of the at least one vital sign signal to provide a fourth real positive array; and

combining the dual real positive array and the fourth real positive array to provide an adaptive trend boundary;

determining whether the predetermined number of samples of the fourth real positive array are within the adaptive trend boundary; and

in response to the predetermined number of samples being outside the adaptive trend boundary, sounding an alarm, wherein once the predetermined number of samples are no longer outside the adaptive trend boundary, turning off the alarm.

12. A system for providing health-monitoring alarm management, the system comprising a sensor for detecting at least one vital sign signal, a processor coupled to the sensor, and a memory device coupled to the processor, wherein the memory device stores an application which, when executed by the processor, causes the processor to:

manage an alarm mechanism of the wearable sensor device based on the at least one vital sign signal.

13. The system of claim 12, wherein to manage further comprises to:

filter the at least one vital sign signal using a statistical filtration mechanism of the application, wherein the statistical filtration mechanism applies a moving window of a predetermined number of samples to a current sample of the at least one vital sign signal to provide a real positive array; and

determine a mean value and a standard deviation value using the real positive array.

14. The system of claim 13, wherein the application further causes the processor to:

determine a statistical boundary comprising a lower threshold and an upper threshold, wherein the lower threshold and the upper threshold are calculated using the mean value, the standard deviation value, and a coefficient parameter.

15. The method of claim 14, wherein the application further causes the processor to:

determine whether the current sample is within the statistical boundary; and

in response to the current sample being outside the statistical boundary, label the current sample as an artifact and replace the current sample with the mean value.

16. The system of claim 12, wherein to manage further comprises to:

apply a moving window of a predetermined number of samples to a current sample of the at least one vital sign signal to provide a real positive array;

determine whether the predetermined number of samples of the real positive array are greater than or equal to a predetermined upper threshold; and

in response to the predetermined number of samples being greater than or equal to the predetermined upper threshold, sound an alarm.

17. The system of claim 12, wherein to manage further comprises to:

apply a moving window of a predetermined number of samples to a current sample of the at least one vital sign signal to provide a real positive array;

determine whether the predetermined number of samples of the real positive array are within a predetermined boundary comprising a lower threshold and an upper threshold; and

in response to the predetermined number of samples being outside the predetermined boundary, sound an alarm.

18. The system of claim 12, wherein to manage further comprises to:

apply a first moving window of a predetermined number of samples to a current sample of the at least one vital sign signal to provide a first real positive array;

determine a mean value and a standard deviation value using the first real positive array.

19. The system of claim 18, wherein the application further causes the processor to:

determine a trend boundary comprising a lower threshold and an upper threshold, wherein the lower threshold and the upper threshold are calculated using the mean value, the standard deviation value, and a coefficient parameter; and

determine a dual moving window of a predetermined number of samples based on the trend boundary to provide a dual real positive array.

20. The system of claim 19, wherein the application further causes the processor to:

applying a fourth moving window of a predetermined number of samples to the current sample of the at least one vital sign signal to provide a fourth real positive array; and

combine the dual real positive array and the fourth real positive array to provide an adaptive trend boundary;

determine whether the predetermined number of samples of the dual real positive array are within the adaptive trend boundary; and

in response to the predetermined number of samples being outside the adaptive trend boundary, sounding an alarm, wherein once the predetermined number of samples are no longer outside the adaptive trend boundary, turning off the alarm.