False alarm reduction systems and related methods

• US 10,650,667 B1
• Filed: 11/19/2018
• Issued: 05/12/2020
• Est. Priority Date: 11/17/2017
• Status: Active Grant

• Current Assignee: Arizona Board of Regents (University of Arizona), Board of Regents of the University of Michigan (University of Michigan)
• Original Assignee: Arizona Board of Regents (University of Arizona)
• Inventors: Afghah, Fatemeh, Razi, Abolfazl, Najarian, Kayvan, Soroushmehr, Sayedmohammadreza
• Primary Examiner(s): Small, Naomi J
• Application Number:
  US16/195,585
• Time in Patent Office: 540 Days
• Field of Search: 340506
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/14542 for measuring blood gases A61B5/14551 takes precedence
• CPC Class Codes: A61B 5/361 Detecting fibrillation
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• 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
• CPC Class Codes: G08B 21/0453 worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing detecting, measuring or recording for diagnostic purposes A61B5/00
• CPC Class Codes: G08B 29/185 Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
• CPC Class Codes: G08B 29/188 Data fusion; cooperative systems, e.g. voting among different detectors

Abstract

Implementations of a system for determining the relevancy of a plurality of alarms may include: a plurality of sensors configured to be coupled to a patient, wherein the plurality of sensors is configured to gather physiological data, a medical monitoring device coupled to the plurality of sensors through a telecommunication channel, and wherein the medical monitoring device is configured to determine a physiological state of the patient using the physiological data. The medical monitoring device may be further configured to issue a plurality of alarm states, and a processing unit coupled to the medical monitoring device through a telecommunication channel, is then configured to evaluate the plurality of alarm states, determine the relevancy of each alarm state of the plurality of alarm states, and issue one or more alarms corresponding with each relevant alarm state to a computing device associated with a user.

Claims

1. A system for determining the relevancy of a plurality of alarms, the system comprising:

a plurality of sensors configured to be coupled to a patient, wherein the plurality of sensors is configured to gather physiological data;

a medical monitoring device coupled to the plurality of sensors through a telecommunication channel, wherein the medical monitoring device is configured to determine a physiological state of the patient using the physiological data, wherein the medical monitoring device is further configured to issue a plurality of alarm states; and

a processing unit coupled to the medical monitoring device through a telecommunication channel, wherein the processing unit is configured to evaluate the plurality of alarm states, determine the relevancy of each alarm state of the plurality of alarm states using a coalition-based feature selection method, and issue one or more alarms corresponding with each relevant alarm state to a computing device associated with a user;

wherein the coalition-based feature selection method includes a Banzhaf power and classifies a one or more chosen top informative alarms from the plurality of top informative alarms into false alarms and true alarms using a Bayes-Net classifier using the processing unit; and

wherein choosing the plurality of top informative alarms comprises determining a most informative subset of alarm states from among the plurality of alarm states, wherein determining further comprises establishing a relevance of the subset of alarm states to a target user and determining an interdependence among the subset of alarm states.

2. The system of claim 1, wherein the physiological data comprises one of electrocardiographic data, arterial blood pressure data, plethysmographic data, or any combination thereof.

3. The system of claim 1, wherein the sensors comprise one of an electrocardiogram sensor, an arterial blood pressure sensor, or a pulse oximeter.

4. The system of claim 1, wherein the plurality of alarm states comprises one of an alarm for asystole, an alarm for bradycardia, an alarm for tachycardia, an alarm for ventricular tachycardia, an alarm for ventricular fibrillation, and any combination thereof.

5. The system of claim 1, wherein the relevancy of the one or more alarm states is a true state or a false state.

6. The system of claim 1, wherein the Banzhaf power is defined as:

7. The system of claim 1, wherein the medical monitoring device further comprises a translating component, the translating component configured to convert each of a plurality of physiological signals from each of the plurality of sensors.

8. A method for determining the relevancy of a plurality of alarms, the method comprising:

gathering physiological data using a plurality of sensors, wherein the plurality of sensors is configured to be coupled to a patient;

determining a physiological state of the patient using the physiological data, using a medical monitoring device coupled to the plurality of sensors through a telecommunication channel;

using the medical monitoring device, issuing a plurality of alarm states;

evaluating the plurality of alarm states using a processing unit, the processing unit configured to use a coalition-based feature selection method;

determining the relevancy of each alarm state of the plurality of alarm states using the processing unit; and

issuing one or more alarms corresponding with each relevant alarm state to a computing device associated with a user;

wherein the coalition-based feature selection method includes a Banzhaf power and classifies a one or more chosen top informative alarms from the plurality of top informative alarms into false alarms and true alarms using a Bayes-Net classifier using the processing unit; and

wherein choosing the plurality of top informative alarms comprises determining a most informative subset of alarm states from among the plurality of alarm states, wherein determining further comprises establishing a relevance of the subset of alarm states to a target user and determining an interdependence among the subset of alarm states.

9. The method of claim 8, wherein the issuing one or more alarms further comprises issuing the one or more alarms to the computing device only after the relevancy of each alarm state from among the plurality of alarm states is determined to be true.

10. The method of claim 8, wherein the determining the physiological state of the patient further comprises translating each of a plurality of physiological signals from each of the plurality of sensors using a translating component on the medical monitoring device.

11. The method of claim 8, wherein the determining the relevancy of each alarm state of the plurality of alarm states further comprises choosing a plurality of top informative alarms from among the plurality of alarm states using a Banzhaf power and the processing unit.

12. The method of claim 11, wherein choosing the plurality of top informative alarms from among the plurality of alarm states using the Banzhaf power comprises using the Banzhaf power defined as:

13. The method of claim 8, wherein the determining the relevancy of each alarm state of the plurality of alarm states further comprises classifying a one or more chosen top informative alarms from a plurality of top informative alarms of the plurality of alarm states into false alarms and true alarms using a Bayes-Net classifier using the processing unit.

14. The method of claim 8, wherein the issuing one or more alarms corresponding with each relevant alarm state further comprises issuing an alarm to a desktop computing device or mobile computing device.

15. The method of claim 8, wherein issuing a plurality of alarm states further comprises issuing one of an alarm for asystole, an alarm for bradycardia, an alarm for tachycardia, an alarm for ventricular tachycardia, an alarm for ventricular fibrillation, and any combination thereof.

16. A method for issuing an alarm regarding a physiological state of a patient, the method comprising:

receiving a plurality of alarm states from a medical monitoring device at a processing unit through a telecommunication channel;

choosing a plurality of top informative alarms using a Banzhaf power and the processing unit;

classifying a one or more chosen top informative alarms from the plurality of top informative alarms into false alarms and true alarms using a Bayes-Net classifier using the processing unit; and

issuing at least one alarm to a computing device associated with a user if any one or more chosen top informative alarms is classified as true;

wherein choosing the plurality of top informative alarms further comprises determining a most informative subset of alarm states from among the plurality of alarm states, wherein determining further comprises establishing a relevance of the subset of alarm states to a target user and determining an interdependence among the subset of alarm states.

17. The method of claim 16, further comprising calculating interdependencies of the plurality of top informative alarms using the processing unit.

18. The method of claim 16, wherein choosing the plurality of top informative alarms using the Banzhaf power comprises using the Banzhaf power defined as: