Method and device for apnea and hypopnea detection

• US 9,649,087 B2
• Filed: 05/17/2012
• Issued: 05/16/2017
• Est. Priority Date: 05/17/2011
• Status: Active Grant

• Current Assignee: University Health Network
• Original Assignee: University Health Network
• Inventors: Fernie, Geoffrey Roy, Alshaer, Hisham, Bradley, T. Douglas
• Primary Examiner(s): Stout, Michael C
• Assistant Examiner(s): Kolderman, Nicholas E
• Application Number:
  US14/117,922
• Publication Number:
  US 20140194780A1
• Time in Patent Office: 1,825 Days
• CPC Class Codes: A61B 2562/0204 Acoustic sensors
• CPC Class Codes: A61B 5/087 Measuring breath flow
• CPC Class Codes: A61B 5/4818 Sleep apnoea
• CPC Class Codes: A61B 5/6803 Head-worn items, e.g. helmets, masks, headphones or goggles
• CPC Class Codes: A61B 5/7257 using Fourier transforms
• 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 7/003 Detecting lung or respiration noise
• CPC Class Codes: A61B 7/04 Electric stethoscopes microphones, acoustic transducers therefor H04R

Abstract

Disclosed herein is a method and device for apnea and hypopnea detection. In one embodiment, a method is provided for detecting apneas and hypopneas from a digitized breath sound recording acquired from a candidate suspected of sleep apnea. The method comprises scanning an amplitude profile of the digitized breath sound recording to identify a prospect event segment; evaluating characteristics of the prospect event segment for consistency with one or more preset apnea-specific criteria; classifying the prospect event segment as representative of an apnea upon it satisfying each of the one or more apnea-specific criteria; evaluating the prospect event characteristics for consistency with one or more preset hypopnea-specific criteria distinct from the apnea-specific criteria; and classifying the prospect event segment as representative of a hypopnea upon it satisfying each of the one or more hypopnea-specific criteria.

Claims

1. A computer-implemented method, automatically implemented by one or more processors of a computing system, for detecting apneas and hypopneas from a digitized breath sound recording acquired from a candidate suspected of sleep apnea, the method comprising:

scanning by at least one processor an amplitude profile of said digitized breath sound recording to identify a prospect event segment;

evaluating by at least one processor characteristics of said prospect event segment for consistency with one or more preset apnea-specific criteria;

classifying by at least one processor said prospect event segment as representative of an apnea upon it satisfying each of said one or more apnea-specific criteria;

evaluating by at least one processor the characteristics of said prospect event for consistency with one or more preset hypopnea-specific criteria distinct from said apnea-specific criteria;

classifying by at least one processor said prospect event segment as representative of a hypopnea upon it satisfying each of said one or more hypopnea-specific criteria; and

outputting indication of a candidate'"'"'s condition as a function of each said classified apnea and hypopnea;

wherein said prospect event is characterized by a falling edge and a rising edge temporally separated by a low-amplitude segment;

wherein said one or more apnea-specific criteria comprise a minimum apnea event amplitude depth threshold; and

wherein said one or more hypopnea-specific criteria comprise

a distinct minimum hypopnea event amplitude depth threshold shallower than said minimum apnea event amplitude depth threshold, and wherein said distinct hypopnea event amplitude depth threshold comprises both a minimum pre-apneic depth threshold and a distinct post-apneic depth threshold.

2. The method of claim 1, the characteristics of said prospect event being evaluated for consistency with said one or more preset hypopnea-specific criteria only upon said characteristics failing to satisfy at least one of said one or more apnea-specific criteria.

3. The method of claim 1, said scanning step comprising scanning said amplitude profile to identify multiple prospect event segments, the method further comprising sequentially repeating steps subsequent to said scanning step for each of said identified prospect event segments.

4. The method of claim 1, further comprising increasing an apnea/hypopnea count for each said classified apnea and hypopnea, wherein said outputting comprises outputting a severity index representative of said candidate'"'"'s condition as a function of said count.

5. The method of claim 1, said pre-apneic depth threshold being shallower than said post-apneic depth threshold.

6. The method of claim 1, said scanning step comprising scanning said amplitude profile for segments satisfying a minimum prospect event depth threshold, said minimum prospect event depth threshold at least as shallow as said minimum hypopnea event amplitude depth threshold.

7. The method of claim 1, said one or more hypopnea-specific criteria further comprising a minimum decreasing amplitude gradient for said falling edge.

8. The method of claim 1, further comprising defining said amplitude profile as a breath-to-breath amplitude profile over time.

9. The method of claim 1, further comprising extracting breath sounds associated with expiration, and defining said amplitude profile solely as a function of said extracted expiration breath sounds.

10. The method of claim 1, further comprising recording said breath sounds via a microphone embedded within a face mask to be worn by said candidate during sleep, the microphone disposed at a distance from a nose and mouth area of the candidate'"'"'s face to be exposed to and thereby acquire oral and nasal expiratory airflow sounds.

11. The method of claim 1, wherein said outputting comprises outputting said indication via a user interface.

12. A non-transitory computer-readable medium comprising statements and instructions stored thereon for implementation by one or more processors of a computing system to detect apneas and hypopneas from a digitized breath sound recording acquired from a candidate suspected of sleep apnea that cause the computer system to perform the following operations:

scan by at least one processor an amplitude profile of said digitized breath sound recording to identify a prospect event segment;

evaluate by at least one processor characteristics of said prospect event segment for consistency with one or more preset apnea-specific criteria;

classify by at least one processor said prospect event segment as representative of an apnea upon it satisfying each of said one or more apnea-specific criteria;

evaluate by at least one processor the characteristics of said prospect event for consistency with one or more preset hypopnea-specific criteria distinct from said apnea-specific criteria;

classify by at least one processor said prospect event segment as representative of a hypopnea upon it satisfying each of said one or more hypopnea-specific criteria; and

output indication of a candidate'"'"'s condition as a function of each said classified apnea and hypopnea;

wherein said prospect event is characterized by a falling edge and a rising edge temporally separated by a low-amplitude segment;

wherein said one or more apnea-specific criteria comprise a minimum apnea event amplitude depth threshold; and

wherein said one or more hypopnea-specific criteria comprise

a distinct minimum hypopnea event amplitude depth threshold shallower than said minimum apnea amplitude depth threshold, and wherein said distinct hypopnea event amplitude depth threshold comprises both a minimum pre-apneic depth threshold and a distinct post-apneic depth threshold.

16. The non-transitory computer-readable medium of claim 12, further comprising statements and instructions that cause the processors to increase an apnea/hypopnea count for each said classified apnea and hypopnea, and wherein said output indication comprises a severity index representative of said candidate'"'"'s condition and output as a function of said count.

17. The non-transitory computer-readable medium of claim 12, said pre-apneic depth threshold being shallower than said post-apneic depth threshold.

18. The non-transitory computer-readable medium of claim 12, said one or more hypopnea-specific criteria further comprising a minimum decreasing amplitude gradient for said falling edge.

13. A system for detecting apneas and hypopneas from a digitized breath sound recording acquired from a candidate suspected of sleep apnea, the system comprising:

one or more processors;

memory storing instructions, the instructions comprising instructions that, when executed by the one or more processors, cause the processors to;

scan by at least one processor an amplitude profile of said digitized breath sound recording to identify a prospect event segment;

evaluate by at least one processor characteristics of said prospect event segment for consistency with one or more preset apnea-specific criteria;

classify by at least one processor said prospect event segment as representative of an apnea upon it satisfying each of said one or more apnea-specific criteria;

evaluate by at least one processor the characteristics of said prospect event for consistency with one or more preset hypopnea-specific criteria distinct from said apnea-specific criteria;

classify by at least one processor said prospect event segment as representative of a hypopnea upon it satisfying each of said one or more hypopnea-specific criteria; and

output indication of a candidate'"'"'s condition as a function of each said classified apnea and hypopnea,

wherein said prospect event is characterized by a falling edge and a rising edge temporally separated by a low-amplitude segment;

wherein said one or more apnea-specific criteria comprise a minimum apnea event amplitude depth threshold; and

wherein said one or more hypopnea-specific criteria comprise

a distinct minimum hypopnea event amplitude depth threshold shallower than said minimum apnea amplitude depth threshold, and wherein said distinct hypopnea event amplitude depth threshold comprises both a minimum pre-apneic depth threshold and a distinct post-apneic depth threshold.

14. The system of claim 13, further comprising a face mask having a microphone mounted thereon and reproducibly disposable, upon the candidate wearing the mask, at a distance above a nose and mouth area of the candidate so to intercept and capture expiratory airflow sounds emanating therefrom to be digitized for processing.

15. The system of claim 14, said mask further comprising a removable data storage medium operatively coupled to said microphone for storing recorded breath sounds thereon prior to processing.

19. The system of claim 14, wherein said memory further comprises statements and instructions to increase an apnea/hypopnea count for each said classified apnea and hypopnea, and wherein said output indication comprises a severity index representative of said candidate'"'"'s condition and output as a function of said count.

20. A computer-implemented method, automatically implemented by one or more processors of a computing system, for detecting apneas and hypopneas from a digitized breath sound recording acquired from a candidate suspected of sleep apnea, the method comprising:

scanning by at least one processor an amplitude profile of said digitized breath sound recording to identify a prospect event segment;

evaluating by at least one processor characteristics of said prospect event segment for consistency with one or more preset apnea-specific criteria;

classifying by at least one processor said prospect event segment as representative of an apnea upon it satisfying each of said one or more apnea-specific criteria;

evaluating by at least one processor the characteristics of said prospect event for consistency with one or more preset hypopnea-specific criteria distinct from said apnea-specific criteria;

classifying by at least one processor said prospect event segment as representative of a hypopnea upon it satisfying each of said one or more hypopnea-specific criteria; and

outputting indication of a candidate'"'"'s condition as a function of each said classified apnea and hypopnea;

wherein said prospect event is characterized by a falling edge and a rising edge temporally separated by a low-amplitude segment;

wherein said one or more apnea-specific criteria comprise a minimum apnea event amplitude depth threshold;

wherein said one or more hypopnea-specific criteria comprise a distinct minimum hypopnea event amplitude depth threshold shallower than said minimum apnea event amplitude depth threshold; and

wherein said scanning step comprises scanning said amplitude profile for segments satisfying a minimum prospect event depth threshold, said minimum prospect event depth threshold at least as shallow as said minimum hypopnea event amplitude depth threshold.

21. A system for detecting apneas and hypopneas from a digitized breath sound recording acquired from a candidate suspected of sleep apnea, the system comprising:

one or more processors;

memory storing instructions, the instructions comprising instructions that, when executed by the one or more processors, cause the processors to;

scan by at least one processor an amplitude profile of said digitized breath sound recording to identify a prospect event segment;

evaluate by at least one processor characteristics of said prospect event segment for consistency with one or more preset apnea-specific criteria;

classify by at least one processor said prospect event segment as representative of an apnea upon it satisfying each of said one or more apnea-specific criteria;

evaluate by at least one processor the characteristics of said prospect event for consistency with one or more preset hypopnea-specific criteria distinct from said apnea-specific criteria;

classify by at least one processor said prospect event segment as representative of a hypopnea upon it satisfying each of said one or more hypopnea-specific criteria; and

output indication of a candidate'"'"'s condition as a function of each said classified apnea and hypopnea;

wherein said prospect event is characterized by a falling edge and a rising edge temporally separated by a low-amplitude segment;

wherein said one or more apnea-specific criteria comprise a minimum apnea event amplitude depth threshold;

wherein said one or more hypopnea-specific criteria comprise a distinct minimum hypopnea event amplitude depth threshold shallower than said minimum apnea amplitude depth threshold; and

wherein said scanning step comprises scanning said amplitude profile for segments satisfying a minimum prospect event depth threshold, said minimum prospect event depth threshold at least as shallow as said minimum hypopnea event amplitude depth threshold.

22. A non-transitory computer-readable medium comprising statements and instructions stored thereon for implementation by one or more processors of a computing system to detect apneas and hypopneas from a digitized breath sound recording acquired from a candidate suspected of sleep apnea that cause the computer system to perform the following operations:

scan by at least one processor an amplitude profile of said digitized breath sound recording to identify a prospect event segment;

evaluate by at least one processor characteristics of said prospect event segment for consistency with one or more preset apnea-specific criteria;

classify by at least one processor said prospect event segment as representative of an apnea upon it satisfying each of said one or more apnea-specific criteria;

evaluate by at least one processor the characteristics of said prospect event for consistency with one or more preset hypopnea-specific criteria distinct from said apnea-specific criteria;

classify by at least one processor said prospect event segment as representative of a hypopnea upon it satisfying each of said one or more hypopnea-specific criteria; and

output indication of a candidate'"'"'s condition as a function of each said classified apnea and hypopnea;

wherein said prospect event is characterized by a falling edge and a rising edge temporally separated by a low-amplitude segment;

wherein said one or more apnea-specific criteria comprise a minimum apnea event amplitude depth threshold;

wherein said one or more hypopnea-specific criteria comprise a distinct minimum hypopnea event amplitude depth threshold shallower than said minimum apnea amplitude depth threshold; and

wherein said scanning step comprises scanning said amplitude profile for segments satisfying a minimum prospect event depth threshold, said minimum prospect event depth threshold at least as shallow as said minimum hypopnea event amplitude depth threshold.