Detection and classification of breathing patterns

• US 6,840,907 B1
• Filed: 04/17/2000
• Issued: 01/11/2005
• Est. Priority Date: 04/14/1999
• Status: Expired due to Term

• Current Assignee: ResMed Pty Ltd. (ResMed Incorporated)
• Original Assignee: Resmed Limited (ResMed Incorporated)
• Inventors: Brydon, John William Ernest
• Primary Examiner(s): Hindenburg, Max F.
• Assistant Examiner(s): Natnithithadha, Navin
• Application Number:
  US10/257,316
• Time in Patent Office: 1,730 Days
• Field of Search: 600/529, 600/532, 600/534, 600/538
• US Class Current: 600/534
• CPC Class Codes: A61B 2562/0247 Pressure sensors
• CPC Class Codes: A61B 2562/043 in a linear array
• CPC Class Codes: A61B 5/113 occurring during breathing
• CPC Class Codes: A61B 5/6892 Mats
• 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 5/7264 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: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A respiratory analysis system for monitoring a respiratory variable for a patient. The system comprises a sensor array for accommodating a patient to be in contact therewith and a processing means. Then array has a plurality of independent like sensors for measuring respiratory movement at different locations on the patient to generate a set of independent respiratory movement signals. The processing means receives and processes the movement signals to derive a classification of individual breaths using, for each breath, the respective phase and/or amplitude of each movement sensor signal within the set for that breath.

Claims

1. A respiratory analysis system for monitoring a respiratory variable for a patient, the system comprising:

a sensor array for accommodating a patient to be in contact therewith, the array having a plurality of independent sensors for measuring respiratory movement at different locations on the patient to generate a set of independent respiratory movement signals; and

a processor to receive and process said movement signals to derive a classification of individual breaths using, for each breath, at least one of a respective phase and an amplitude of each movement signal within the set for that breath, wherein the processor is operable to determine the period, and thus the frequency, of a breath from the set of signals, and for each sensor, to determine a vector defining at least one of the amplitude and the phase of the breath frequency component present in the signal, the set of vectors being the breath classification.

2. A system as claimed in claim 1, further comprising a pre-processor to receive said movement signals, and to pre-process them by at least one of equalizing each movement signal and deconvolving spatially the movement signals, thereby isolating each signal from all others and pass said pre-processed signals to said processor.

3. A system as claimed in claim 1, further including at least one of output and storage means for at least one of outputting and storing the respiratory variable.

4. A respiratory analysis system as claimed in claim 1, wherein the processor is further operable diagnostically to compare said breath classifications between at least two breaths to detect altered breathing patterns.

5. A respiratory analysis system for monitoring a respiratory variable for a patient, the system comprising:

a sensor array for accommodating a patient to be in contact therewith, the array having a plurality of independent sensors for measuring respiratory movement at different locations on the patient to generate a set of independent respiratory movement signals; and

a processor to receive and process said movement signals to derive a classification of individual breaths using, for each breath, at least one of a respective phase and an amplitude of each movement signal within the set for that breath;

wherein the processor is further operable diagnostically to compare said breath classifications between at least two breaths to detect altered breathing patterns.

6. A respiratory analysis system as claimed in claim 5, wherein the comparison is performed by a cross-correlation of at least one of the amplitude and the phase of the respective set of signals.

7. A respiratory analysis system as claimed in claim 5, wherein the comparison is performed by a cross-correlation of the respective vectors of the breaths.

8. A respiratory analysis system as claimed in claim 7, wherein the cross-correlation is performed by a scalar multiplication of and subsequent summation of corresponding pairs of sensor amplitude and/or phase vectors of the two breaths being compared.

9. A method for monitoring at least one respiratory variable for a patient, the method comprising:

measuring respiratory movement at different locations on a patient to generate a set of independent respiratory movement signals; and

processing said movement signals to derive a classification of individual breaths using, for each breath, at least one of a respective phase and an amplitude of each movement signal with the set for that breath,

whereby the processing comprises determining the period, and thus the frequency, of a breath from the set of signals, and deriving the breath classification from a vector defining at least one of the amplitude and the phase of the breath frequency component present in the signal.

10. A method as claimed in claim 9, whereby said comparison comprises cross-correlating at least one of the amplitudes and the phases of the respective set of signals.

11. A method as claimed in claim 9, further comprising comparing two said classifications to detect altered breathing patterns.

12. A method for monitoring at least one respiratory variable for a patient, the method comprising:

measuring respiratory movement at different locations on a patient to generate a set of independent respiratory movement signals;

processing said movement signals to derive a classification of individual breaths using, for each breath, at least one of a respective phase and an amplitude of each movement signal with the set for that breath; and

comparing two said classifications to detect altered breathing patterns.

13. A method as claimed in claim 12, whereby said comparison comprises cross-correlating at least one of the amplitudes and the phases of the respective set of signals.

14. A method as claimed in claim 13, whereby the cross-correlation comprises the scalar multiplication of and subsequent summation of corresponding pairs of at least one of sensor amplitude and phase vectors of the two breaths being compared.

15. A method for determining whether two breaths are similar comprising:

monitoring a plurality of independent patient movement signals;

identifying the portions of said signals which correspond to each breath;

for said portions, calculating the phase and amplitude of corresponding periodic functions;

determining a vector for each breath in accordance with said phases and amplitudes;

calculating a measure of the correlation between the vectors for the two breaths; and

if said measure is greater than a threshold, determining that the breaths are similar.

16. A method as claimed in claim 15, wherein said correlation is the dot product of the two vectors.

17. A method as claimed in claim 16, wherein said threshold is 0.9.

18. A method for determining whether two breaths are different comprising:

monitoring a plurality of independent patient movement signals;

identifying the portions of said signals which correspond to each breath;

for said portions, calculating the phase and amplitude of corresponding periodic functions;

determining a vector for each breath in accordance with said phases and amplitudes;

calculating a measure of the correlation between the vectors for the two breaths; and

if said measure is less than a threshold, determining that the breaths are different.

19. A method as claimed in claim 18, wherein said correlation is the dot product of the two vectors.

20. A method as claimed in claim 19, wherein said threshold is 0.6.