System and method of discovering, detecting and classifying alarm patterns for electrophysiological monitoring systems

• US 7,679,504 B2
• Filed: 05/16/2007
• Issued: 03/16/2010
• Est. Priority Date: 05/16/2007
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Wang, Xi, Johnson, Timothy L., Treacy, Stephen T.
• Primary Examiner(s): Crosland; Donnie L
• Application Number:
  US11/749,400
• Publication Number:
  US 20080284582A1
• Time in Patent Office: 1,035 Days
• Field of Search: 340/506, 340/505, 340/523
• US Class Current: 340/506
• 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 5/02455 provided with high/low alarm devices
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• 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: G06F 2218/12 Classification; Matching
• CPC Class Codes: G08B 21/04 responsive to non-activity, e.g. of elderly persons G08B21/06 takes precedence
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 70/60 relating to pathologies
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A system and method for electrophysiological monitoring system including a plurality of sensors configured to detect one or more health parameters of a patient and a monitoring device configured to receive a plurality of sensing signals from the sensors and output a monitoring signal representative of an alarm sequence, wherein the alarm sequence comprises a set of alarm events identified in the sensing signals. The system also includes an on-line monitoring module configured to generate a suffix tree data structure in response to the monitoring signal to identify alarm patterns from the set of alarm events and classify the alarm sequence in response to the occurrences of alarm patterns in the alarm sequence. The on-line monitoring module is further configured to alert monitoring personnel of an alarm condition after processing the alarm sequence in real-time.

Claims

1. An electrophysiological monitoring system comprising:

a plurality of sensors configured to detect one or more health parameters of a patient;

a monitoring device configured to receive a plurality of sensing signals from the sensors and output a monitoring signal representative of an alarm sequence, wherein the alarm sequence comprises a set of alarm events identified in the sensing signals; and

an on-line monitoring module configured to;

generate a suffix tree data structure in response to the monitoring signal to identify alarm patterns from the set of alarm events;

classify the alarm sequence in response to the occurrences of alarm patterns in the alarm sequence; and

alert monitoring personnel of an alarm condition after processing the alarm sequence in real-time.

2. The electrophysiological monitoring system of claim 1 further comprising a real-time pattern display coupled to the monitoring station to allow viewing of the alarm sequence.

3. The electrophysiological monitoring system of claim 2 further comprising an external storage facility coupled to the monitoring station to store alarm pattern types.

4. The electrophysiological monitoring system of claim 2 further comprising an external storage facility coupled to the monitoring station to store classifications of alarm sequences.

5. The electrophysiological monitoring system of claim 2 further comprising an external storage facility which includes a database to store classifications of alarm sequences and alarm pattern types wherein the external storage facility is coupled to the monitoring station via a communications link that allows information to be accessed in real-time from the database when the alarm sequence is processed in real-time.

6. A method for electrophysiological monitoring comprising steps of:

receiving a monitoring signal derived from a patient wherein the monitoring signal provides an alarm sequence;

developing a suffix substring data structure to identify a plurality of alarm patterns from the alarm sequence;

generating an incidence vector that determines a relative incidence of each type of alarm pattern with respect to the plurality of alarm patterns in the alarm sequence;

grouping the incidence vector in a cluster using a clustering algorithm;

classifying one or more patients according to their pattern incident rates which are obtained by extraction of (possibly concurrent) alarm patterns and

storing the classification of the incidence vector in a database.

7. The method of claim 6 wherein the monitoring signal includes a plurality of sensing signals that sense physiological health parameters of a patient.

8. The method of claim 6 wherein the suffix substring data structure is programmed to identify alarm patterns greater than a first length, the first length corresponding to a minimum length of an alarm pattern to be identified.

9. The method of claim 8 wherein the suffix substring data structure is programmed to identify alarm patterns in an alarm sequence between the first length and a second length, wherein the second length is greater than the first length, and wherein the second length corresponds to a maximum length of an alarm pattern to be identified.

10. The method of claim 6 further comprising associating the cluster with a patient condition using a support vector machine algorithm.

11. The method of claim 6 wherein the clustering algorithm is a K-means clustering algorithm.

12. A method for electrophysiological monitoring that detects and classifies alarm patterns comprising steps of:

receiving a monitoring signal from a patient wherein the monitoring signal provides an alarm sequence, wherein the alarm sequence includes at least one alarm pattern;

developing a suffix substring data structure in real-time to identify alarm patterns of medical interest contained in the alarm sequence;

generating an incidence vector in response to the suffix substring data structure;

classifying the alarm sequence to a classification cluster using a classification algorithm based on the incidence vector; and

alerting monitoring personnel to indicate a condition corresponding to the cluster after processing the alarm sequence in real-time.

13. The method of claim 12 further comprising alerting monitoring personnel to indicate a condition when an alarm sequence is partially detected in real-time thereby allowing medical personnel to pro-actively respond to the condition before the condition worsens.

14. The method of claim 12 wherein the step of receiving the monitoring signal comprises receiving at least one physiological sensing signal derived from the patient.

15. The method of claim 12 further comprising identifying an alarm sequence greater than a first length, the first length corresponding to a minimum length of an alarm pattern to be identified.

16. The method of claim 15 wherein the suffix substring data structure is programmed to identify alarm sequences between the first length and a second length, wherein the second length is greater than the first length and corresponds to a maximum length of an alarm pattern to be identified.

17. The method of claim 12 further comprising determining the classification cluster by an unsupervised learning algorithm.

18. The method of claim 17 wherein determining comprises determining the classification cluster by a support vector machine algorithm.

19. The method of claim 12 further comprising determining the classification cluster by a supervised learning process.

20. The method of claim 19 wherein the supervised learning process is conducted by one or more qualified medical personnel.

21. The method of claim 12 further comprising identifying a new alarm pattern type in the alarm sequence in response to the generated suffix substring data structure and storing the new alarm pattern type in a database.