APNEA DETECTION USING A CAPNOGRAPH

• US 20080300500A1
• Filed: 05/30/2007
• Published: 12/04/2008
• Est. Priority Date: 05/30/2007
• Status: Abandoned Application

• Current Assignee: Widemed Ltd.
• Original Assignee: Widemed Ltd.
• Inventors: Reisfeld, Daniel
• Application Number:
  US11/755,568
• Publication Number:
  US 20080300500A1
• Time in Patent Office: Days
• US Class Current: 600/532
• 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 5/087 Measuring breath flow
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/4818 Sleep apnoea
• 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 method for diagnosis includes receiving a signal indicative of a partial pressure of CO₂ in air expired by a patient during sleep. The signal is processed so as to detect a breathing-related event from a group of events consisting of apneas and hypopneas, and to classify the event as a central event or an obstructive event.

Claims

1. A method for diagnosis, comprising:

receiving a signal indicative of a partial pressure of CO₂ in air expired by a patient during sleep;

processing the signal so as to detect a breathing-related event from a group of events consisting of apneas and hypopneas, and to classify the event as a central event or an obstructive event; and

generating a record of an occurrence and classification of the event.

2. The method according to claim 1, wherein processing the signal comprises detecting a repetitive waveform in the signal prior to the event, and comparing the signal during the event to the detected waveform.

3. The method according to claim 2, wherein comparing the signal comprises detecting an apnea responsively to an interruption of the repetitive waveform.

4. The method according to claim 3, wherein processing the signal comprises classifying the apnea as central or obstructive responsively to a level of the signal during the interruption.

5. The method according to claim 4, wherein detecting the repetitive waveform comprises finding peak and baseline values of the repetitive waveform, and wherein classifying the apnea comprises identifying a central apnea when the level is closer to the peak value than to the baseline value, and identifying an obstructive apneas when the level is closer to the baseline value than to the peak value.

6. The method according to claim 2, wherein detecting the repetitive waveform comprises finding shape parameters of the waveform, and wherein comparing the signal comprises detecting a hypopnea responsively to a change in one or more of the shape parameters.

7. The method according to claim 6, wherein the shape parameters comprise a respective slope and a respective duration of one or more phases of the waveform, and wherein processing the signal comprises classifying the hypopnea as obstructive responsively to a change in the respective slope and the respective duration of at least one of the phases.

8. The method according to claim 2, wherein detecting the repetitive waveform comprises finding a peak level of the waveform/ and wherein comparing the signal comprises detecting a hypopnea responsively to an increase in the peak level over multiple cycles of the repetitive waveform.

9. The method according to claim 8, wherein processing the signal comprises identifying a pattern of Cheyne-Stokes breathing responsively to a succession of alternating increases and decreases of the peak level.

10. The method according to claim 1, wherein generating the record comprises detecting and recording an occurrence of Cheyne-Stokes breathing.

11. The method according to claim 10, and comprising determining a prognosis of heart failure (HF) in the patient based on the occurrence of the Cheyne-Stokes breathing.

12. Apparatus for diagnosis, comprising:

a sensor, which is configured to be coupled to a body of a patient during sleep and to output a signal indicative of a partial pressure of CO₂ in air expired by a patient; and

a processor, which is coupled to process the signal so as to detect a breathing-related event from a group of events consisting of apneas and hypopneas, and to classify the event as a central event or an obstructive event.

13. The apparatus according to claim 12, wherein the processor is configured to detect a repetitive waveform in the signal prior to the event, and to detect the event by comparing the signal during the event to the detected waveform.

14. The apparatus according to claim 13, wherein the processor is configured to detect an apnea responsively to an interruption of the repetitive waveform.

15. The apparatus according to claim 14, wherein the processor is configured to classify the apnea as central or obstructive responsively to a level of the signal during the interruption.

16. The apparatus according to claim 15, wherein the processor is configured to find peak and baseline values of the repetitive waveform, and to classify the apnea as a central apnea when the level is closer to the peak value than to the baseline value, and as an obstructive apneas when the level is closer to the baseline value than to the peak value.

17. The apparatus according to claim 13, wherein the processor is configured to find shape parameters of the waveform, and to detect a hypopnea responsively to a change in one or more of the shape parameters.

18. The apparatus according to claim 17, wherein the shape parameters comprise a respective slope and a respective duration of one or more phases of the waveform, and wherein the processor is configured to classify the hypopnea as obstructive responsively to a change in the respective slope and the respective duration of at least one of the phases.

19. The apparatus according to claim 13, wherein the processor is configured to find a peak level of the waveform, and to detect a hypopnea responsively to an increase in the peak level over multiple cycles of the repetitive waveform.

20. The apparatus according to claim 19, wherein the processor is configured to identify a pattern of Cheyne-Stokes breathing responsively to a succession of alternating increases and decreases of the peak level.

21. The apparatus according to claim 12, wherein the processor is configured to process the signal so as to detect an occurrence of Cheyne-Stokes breathing.

22. The apparatus according to claim 21, wherein the processor is configured to determine a prognosis of heart failure (HF) in the patient based on the occurrence of the Cheyne-Stokes breathing.

23. A computer-software product, comprising a computer-readable medium in which program instructions are stored, which instructions, when read by a computer, cause the computer to receive a signal indicative of a partial pressure of CO₂ in air expired by a patient during sleep, and to process the signal so as to detect a breathing-related event from a group of events consisting of apneas and hypopneas, and to classify the event as a central event or an obstructive event.

24. The product according to claim 23, wherein the instructions cause the computer to detect a repetitive waveform in the signal prior to the event, and to detect the event by comparing the signal during the event to the detected waveform.

25. The product according to claim 24, wherein the instructions cause the computer to detect an apnea responsively to an interruption of the repetitive waveform.

26. The product according to claim 25, wherein the instructions cause the computer to classify the apnea as central or obstructive responsively to a level of the signal during the interruption.

27. The product according to claim 26, wherein the instructions cause the computer to find peak and baseline values of the repetitive waveform, and to classify the apnea as a central apnea when the level is closer to the peak value than to the baseline value, and as an obstructive apneas when the level is closer to the baseline value than to the peak value.

28. The product according to claim 24, wherein the instructions cause the computer to find shape parameters of the waveform, and to detect a hypopnea responsively to a change in one or more of the shape parameters.

29. The product according to claim 28, wherein the shape parameters comprise a respective slope and a respective duration of one or more phases of the waveform, and wherein the instructions cause the computer to classify the hypopnea as obstructive responsively to a change in the respective slope and the respective duration of at least one of the phases.

30. The product according to claim 24, wherein the instructions cause the computer to find a peak level of the waveform, and to detect a hypopnea responsively to an increase in the peak level over multiple cycles of the repetitive waveform.

31. The product according to claim 30, wherein the instructions cause the computer to identify a pattern of Cheyne-Stokes breathing responsively to a succession of alternating increases and decreases of the peak level.

32. The product according to claim 23, wherein the instructions cause the computer to process the signal so as to detect an occurrence of Cheyne-Stokes breathing.

33. The product according to claim 32, wherein the instructions cause the computer to determine a prognosis of heart failure (HF) in the patient based on the occurrence of the Cheyne-Stokes breathing.