Multi parametric classfication of cardiovascular sound

• US 8,684,943 B2
• Filed: 06/26/2007
• Issued: 04/01/2014
• Est. Priority Date: 06/26/2006
• Status: Active Grant

• Current Assignee: Acarix A/S (Acarix AB)
• Original Assignee: Acarix A/S (Acarix AB)
• Inventors: Schmidt, Samuel Emil, Struijk, Johannes Jan, Graff, Claus
• Primary Examiner(s): MALAMUD, DEBORAH LESLIE
• Application Number:
  US12/308,754
• Publication Number:
  US 20100160807A1
• Time in Patent Office: 2,471 Days
• Field of Search: 600508-509, 600514-515, 600/528
• US Class Current: 600/528
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/02007 Evaluating blood vessel condition, e.g. elasticity, compliance
• CPC Class Codes: A61B 5/7239 using differentiation including higher order derivatives
• 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: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 7/04 Electric stethoscopes microphones, acoustic transducers therefor H04R
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method, system, stethoscope and server for classifying a cardiovascular sound recorded from a living subject. The method comprises the steps of: identifying diastolic and/or systolic segments of the cardiovascular sound; dividing at least one of the identified diastolic and/or systolic segments into a number of sub-segments comprising at least a first sub-segment and at least a second sub-segment; extracting from the first sub-segment at least a first signal parameter characterizing a first property of the cardiovascular sound, extracting from the second sub-segment at least a second signal parameter characterizing a second property of the cardiovascular sound; and classifying the cardiovascular sound using the at least first signal parameter and the at least second signal parameter in a multivariate classification method.

Claims

1. A method of classifying a cardiovascular sound recorded from a living subject, said method comprises the steps of:

identifying diastolic and/or systolic segments of said cardiovascular sound;

dividing at least one of said identified diastolic and/or systolic segments into a number of sub-segments comprising at least a first sub-segment and at least a second sub-segment;

identifying noisy sub-segments;

discarding said noisy sub-segments;

extracting from said first sub-segment at least a first signal parameter characterizing a first property of said cardiovascular sound, extracting from said second sub-segment at least a second signal parameter characterizing a second property of said cardiovascular sound, wherein said first and second sub-segments from which said at least first and second signal parameters are respectively extracted are from the same diastolic or systolic segment; and

classifying said cardiovascular sound using said at least first signal parameter and said at least second signal parameter using a multiparametric discriminate function.

2. A method according to claim 1, wherein said at least first signal parameter and/or said at least second signal parameter are being extracted from at least two of said number of sub-segments of the same diastolic or systolic segment.

3. A method. according to claim 2, wherein said step of classifying said cardiovascular sound comprises the step of:

calculating the mean value of said at least first signal parameter and/or said at least second signal parameter extracted from at least two of said number of subsegments of the same diastolic or systolic segment, and using said mean value in said multiparametric discriminate function.

4. A method according to claim 2, wherein said step of classifying said cardiovascular sound comprises the steps of:

classifying at least one of said number of sub-segments using said at least first signal parameter and said at least second signal parameter using said multiparametric discriminate function, where both said at least first signal parameter and said at least second signal parameter are in being extracted from said at least one of said number of sub-segments, and

classifying said cardiovascular sound based on said classifying of said at least one of said number of subsegments.

5. A method according to claim 1, wherein said method further comprises the steps of:

identifying non stationary sub-segments, and

discarding said non stationary sub-segments prior to said steps of extracting said at least first signal parameter and/or extracting said at least second signal parameter.

6. A method according to claim 1, wherein at least A part of said first sub-segment is overlapping at least a part of said second sub-segment.

7. A method according to claim 1, wherein said method further comprises the steps of modelling at least one of said number of sub-segments and extracting said at least first signal parameter and/or said at least second signal parameter from said model.

8. A method according to claim 1, wherein said at least first signal parameter and/or said at least second signal parameter is a frequency level parameter describing a frequency level property of at least one frequency component of at least one of said number of sub-segments.

9. A method according to claim 1, wherein said at least first signal parameter and/or said at least second signal parameter are complexity parameters describing the complexity of at least one of said number of sub-segments.

10. A method according to claim 1, wherein at least one of said identified diastolic and/or systolic segments is divided into at least 8 sub-segments.

11. A computer-readable medium having stored therein instructions for causing a processing unit to execute a method according to claim 1.

12. A server device connected to a communication network comprising:

receiving means adapted to receive a cardiovascular sound recorded from a living subject through said communication network,

storing means adapted to store said received cardiovascular sound, and

a computer-readable medium and a processing unit, said computer-readable medium having stored therein instructions for causing said processing unit to execute a method according to claim 1 and thereby classify said received cardiovascular sound.

13. A server device according to claim 12, wherein said receiving means are further adapted to receive said cardiovascular sound from a client connected to said communication network.

14. A server device according to claim 12, wherein said server device further comprises means for sending said classification of said cardiovascular sound to at least one client unit connected to said communication network.

25. A stethoscope comprising:

recording means adapted to record a cardiovascular sound from a living subject,

storing means adapted to store said recorded cardiovascular sound, and

a computer-readable medium and a processing unit, said computer-readable medium having stored therein instructions for causing said processing unit to execute a method according to claim 1 and thereby classify said recorded cardiovascular sound.

15. A system for classifying a cardiovascular sound recorded from a living subject, said system comprising:

processing means for identifying the diastolic and/or systolic segments of said cardiovascular sound;

processing means for dividing at least one of said identified diastolic and/or systolic segments into a number of sub-segments comprising at least a first sub-segment and at least a second sub-segment;

processing means for identifying noisy sub-segments;

processing means for discarding said noisy sub-segments;

processing means for extracting from said first sub-segment at least a first signal parameter characterizing a first property of said cardiovascular sound, and processing means for extracting from said second sub-segment at least a second signal parameter characterizing a second property of said cardiovascular sound, wherein said first and second sub-segments from which said at least first and second signal parameters are respectively extracted from the same diastolic or systolic segment;

processing means for classifying said cardiovascular sound using said at least first signal parameter and said at least second signal parameter using a multiparametric discriminate function.

16. A method according to claim 15, wherein said processing means for extracting said at least first signal parameter and/or said processing means for extracting said at least second signal parameter is adapted to extract said at least first signal parameter and/or said at least second signal parameter from at least two of said number of sub-segments of the same diastolic or systolic segment.

17. A. system according to claim 16, wherein said processing means for classifying said cardiovascular sound is adapted to calculate the mean value of said at least first signal parameter and/or said at east second signal parameter extracted from at least two of said number of sub-segments of the same diastolic or systolic segment, and using said mean value in said multiparametric discriminate function.

18. A system according to claim 16, wherein said means for classifying said cardiovascular sound is adapted to classify at least one of said number of sub-segments using said at least first signal parameter and said at least second signal parameter using said multiparametric discriminate function and to classify said cardiovascular sound based on said classifying of said at least one of said number of sub-segments.

19. A system according to claim 15, wherein said system further comprises:

processing means for identifying the non stationary sub-segments, and

processing means for discarding said non stationary sub-segments prior to extracting said at least first signal parameter and/or extracting said at least second signal parameter.

20. A system according to claim 15, wherein said processing means for dividing at least one of said identified diastolic and/or systolic segments into a number of sub segments is adapted to overlap at least a part of said first sub-segment with at least a part of said second sub-segment.

21. A system according to claim 16, wherein said system further comprises processing means for modelling at least one of said number of sub-segments and processing means for extracting said at least first signal parameter and/or said at least second signal parameter from said model.

22. A system according to claim 15, wherein said processing means for extracting said at least first signal parameter and/or said at least second signal parameter is adapted to extract at least one frequency level parameter describing a frequency level property of at least one frequency component of at least one of said number of sub-segments.

23. A system according to claim 15, wherein said processing means for extracting said at least first signal parameter and/or said at least second signal parameter is adapted to extract at least one complexity parameter describing the complexity of at least one of said number of sub-segments.

24. A system according to claim 15, wherein said processing means for dividing at least one of said identified diastolic and/or systolic segments into a number of identified diastolic and/or systolic segments into at least a 8 sub-segments.