SYSTEMS AND METHODS FOR DETECTING ARRHYTHMIA FROM A PHYSIOLOGICAL SIGNAL

• US 20130138002A1
• Filed: 11/30/2011
• Published: 05/30/2013
• Est. Priority Date: 11/30/2011
• Status: Active Grant

• Current Assignee: Covidien LP (Medtronic Plc)
• Original Assignee: Nellcor Puritan Bennett LLC (Medtronic Plc)
• Inventors: Ochs, James, Weng, Binwei
• Granted Patent: US 8,755,871 B2
• Time in Patent Office: Days
• US Class Current: 600/508
• 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 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/7225 Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation A61B5/30, A61B5/316 take precedence; transformers for specific applications H01F38/00; amplifiers H03F
• CPC Class Codes: A61B 5/7228 Signal modulation applied to the input signal sent to patient or subject; demodulation to recover the physiological signal modulation H03C
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence

Abstract

Arrhythmia may impact the determination of physiological information from a physiological signal. A patient monitoring system may detect the presence of arrhythmia based on changes in the physiological signal. Derived value data sets may be extracted from the physiological signal and calculations performed to generate arrhythmia features. The arrhythmia features may be used to generate an arrhythmia indicator that may indicate the presence of arrhythmia in the physiological signal.

Claims

1. A method for detecting arrhythmia from a physiological signal, the method comprising:

extracting, using processing equipment, a plurality of derived value data sets associated with the physiological signal;

determining, using processing equipment, a plurality of arrhythmia features based on the derived value data sets, wherein the arrhythmia features comprise an entropy feature; and

generating, using processing equipment, an arrhythmia indicator based on the arrhythmia features.

2. The method of claim 1, wherein the derived value data sets comprise a pulse rate data set, a kurtosis data set, and a b/a ratio data set.

3. The method of claim 1 wherein the arrhythmia features further comprise a standard deviation feature.

4. The method of claim 1 wherein the arrhythmia features further comprise a dot product feature.

5. The method of claim 1, wherein generating the arrhythmia indicator comprises:

calculating a distance value based on the plurality of arrhythmia features;

comparing the distance value to a threshold distance value; and

generating the arrhythmia indicator based on the distance value and the threshold distance value.

6. The method of claim 5 wherein comparing the distance value comprises determining whether the distance value falls within a range of values based on the threshold distance value.

7. The method of claim 6 wherein the range of values is less than a positive threshold distance value and greater than a negative threshold distance value.

8. The method of claim 5 wherein calculating the distance value comprises:

modifying each of the plurality of arrhythmia features based on one or more weighting factors; and

calculating the distance value based on the modified arrhythmia features and a bias term.

9. The method of claim 1 wherein generating the arrhythmia indicator comprises determining a confidence value.

10. The method of claim 1 further comprising determining respiration information based on the arrhythmia indicator.

11. A patient monitoring system comprising:

an interface configured to receive a physiological signal; and

a processor configured to;

extract a plurality of derived value data sets associated with the physiological signal;

determine a plurality of arrhythmia features based on the derived value data sets, wherein the arrhythmia features comprise an entropy feature; and

generate an arrhythmia indicator based on the arrhythmia features.

12. The patient monitoring system of claim 11, wherein the derived value data sets comprise a pulse rate data set, a kurtosis data set, and a b/a ratio data set.

13. The patient monitoring system of claim 11 wherein the arrhythmia features further comprise a standard deviation feature.

14. The patient monitoring system of claim 11 wherein the arrhythmia features further comprise a dot product feature.

15. The patient monitoring system of claim 11, wherein the processor is further configured to:

calculate a distance value based on the plurality of arrhythmia features;

compare the distance value to a threshold distance value; and

generate the arrhythmia indicator based on the distance value and the threshold distance value.

16. The patient monitoring system of claim 15 wherein the processor is further configured to determine whether the distance value falls within a range of values based on the threshold distance value.

17. The patient monitoring system of claim 16 wherein the range of values is less than a positive threshold distance value and greater than a negative threshold distance value.

18. The patient monitoring system of claim 15 wherein the processor is further configured to:

modify each of the plurality of arrhythmia features based on one or more weighting factors; and

calculate the distance value based on the modified arrhythmia features and a bias term.

19. The patient monitoring system of claim 11 wherein the arrhythmia indicator comprises an arrhythmia confidence value.

20. The patient monitoring system of claim 11 wherein the processor is further configured to determine respiration information based on the arrhythmia indicator.