System and method for detecting signal artifacts

• US 8,602,986 B2
• Filed: 08/06/2004
• Issued: 12/10/2013
• Est. Priority Date: 08/20/2003
• Status: Active Grant

• Current Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Ali, Walid
• Primary Examiner(s): Layno, Carl H
• Assistant Examiner(s): BEHRINGER, LUTHER G
• Application Number:
  US10/568,173
• Publication Number:
  US 20060247501A1
• Time in Patent Office: 3,413 Days
• Field of Search: 600/301, 600508-509, 600/513, 600/515, 382/131, 340/567, 381/66
• US Class Current: 600/301
• CPC Class Codes: A61B 5/02 Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 2218/02 Preprocessing

Abstract

A method and system are disclosed that detect signal artifacts in one or more event signals. The system and method may be used with a patient monitoring apparatus that adapts to a patient'"'"'s condition and distinguishes between clinically significant changes in the patient'"'"'s state verse clinically insignificant changes.

Claims

1. A device comprising:

a controller;

a memory coupled to the controller; and

an input interface which receives at least two event signals,

wherein the controller determines;

a global correlation matrix for the at least two event signals over a first period of time,

a local correlation matrix for the at least two event signals over a second period of time which is shorter than the first period of time,

a correlation vector indicative of a deviation between the local correlation matrix and the global correlation matrix,

an average of the correlation vector, and

whether an artifact was detected in one of the at least two event signals from the correlation vector and the average of the correlation vector.

2. The device according to claim 1 wherein said device is a patient monitoring system.

3. The device according to claim 2 wherein said at least two event signals are monitored patient data signals.

5. The device according to claim 1 further comprising a memory for recording the at least two event signals.

6. The device according to claim 1, wherein said device includes a server forming part of a client-server network.

4. A patient monitoring system comprising:

a controller;

a memory coupled to the controller;

an input interface configured to receive at least two event signals, the at least two event signals being patient monitored data signals;

wherein the controller determines whether an artifact is detected by;

repeatedly determining a global correlation for the at least two event signals over a first period of time,

repeatedly determining a local correlation for the at least two event signals over a second period of time which is shorter than the first period of time,

repeatedly determining a current deviation between the local correlation and the global correlation,

determining an average deviation of a plurality of the current deviations, and

determining whether an artifact was detected in one of the at least two event signals based on a difference between the current deviation and the average deviation; and

an alarm indicator coupled to the controller, the alarm indicator being triggered if at least one of the event signals crosses a preset threshold value and the controller determines that no artifact was detected in the at least one event signal.

7. A method for detecting a signal artifact in event signals, the method comprising the steps of:

receiving at least two event signals;

determining a global correlation for the at least two event signals over a first period of time;

determining a local correlation for the at least two event signals over a second period of time which is shorter than the first period of time;

repeatedly determining a current deviation between the local correlation and the global correlation;

determining an average deviation from a plurality of the determined current deviations;

comparing the current deviation and the average deviation to determine whether an artifact was detected in one of the at least two event signals; and

triggering an alarm indication in response to determining that an artifact was detected.

8. The method according to claim 7 wherein said method is used with a patient monitoring system.

9. The method according to claim 8 wherein said at least two event signals are monitored patient data signals.

10. The method according to claim 9, said method further comprising the step of:

providing the alarm indication in response to at least one of the event signals crossing a preset threshold value.

11. The method according to claim 7, said method further comprising the step of:

recording the at least two event signals.

12. The method according to claim 7, wherein said method is used in a server forming part of a client-server network.

13. A system for detecting a signal artifact in an event signal, comprising:

means for receiving at least two event signals;

means for determining a global correlation for the at least two event signals over a first period of time;

means for determining a local correlation for the at least two event signals over a second period of time which is shorter than the first period of time;

means for determining a deviation between a local correlation vector and a global correlation vector;

means for determining an average deviation from the deviation; and

means for determining whether an artifact was detected in one of the at least two event signals based upon the average deviation.

14. The system according to claim 13 wherein said system is a patient monitoring system.

15. The system according to claim 14 wherein said at least two event signals are patient monitored data signals.

16. The system according to claim 13 further including:

means for monitoring at least one physiological parameter of a patient and generating the at least two event signals, said at least two event signals conveying patient physiological parameter data.