Method and apparatus for identifying constituent signal components from a plurality of evoked physiological composite signals

• US 6,936,012 B2
• Filed: 06/18/2002
• Issued: 08/30/2005
• Est. Priority Date: 06/18/2001
• Status: Active Grant

• Current Assignee: Neurometrix, Inc.
• Original Assignee: Neurometrix, Inc.
• Inventors: Wells, Martin D.
• Primary Examiner(s): Hindenburg, Max F.
• Assistant Examiner(s): SZMAL, BRIAN SCOTT
• Application Number:
  US10/174,153
• Publication Number:
  US 20030032889A1
• Time in Patent Office: 1,169 Days
• Field of Search: 600/554, 600/300, 600/547, 600/544, 367/134, 702/19, 455/501, 708/109
• US Class Current: 600/554
• CPC Class Codes: A61B 5/053 Measuring electrical impedance or conductance of a portion of the body
• CPC Class Codes: A61B 5/1106 to assess neuromuscular blockade, e.g. to estimate depth of anaesthesia
• CPC Class Codes: A61B 5/4041 Evaluating nerves condition
• CPC Class Codes: A61B 5/7217 of noise originating from a therapeutic or surgical apparatus, e.g. from a pacemaker
• 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

Abstract

A novel application of independent component analysis (ICA) to data acquired by a single sensor. The technique exploits the unique relationship between multiple physiologic (source) and electronic (artifact) components in surface recorded sensory nerve action potential (SNAP) waveforms that are evoked by different activating magnitudes. A forward model of the SNAP is developed and used to test the approach on a simplified data simulation. The method is applied to experimental data and shown to be effective at separating artifact and source components and reconstructing artifact-free traces. A method of automated reconstruction for use within an expert system is also disclosed.

Claims

1. A method for identifying constituent signal components from a plurality of evoked physiological composite signals, said method comprising:

activating a subject'"'"'s anatomy so as to generate the plurality of composite signals, wherein at least two of said composite signals comprise distinct mixtures of the same constituent signal components;

recording, at a single anatomical site, the composite signals; and

performing blind source separation on the composite signals so as to identify the constituent signal components.

2. A method according to claim 1 wherein said blind source separation is performed so as to identify the amount that each constituent signal component contributes to the composite signals.

3. A method according to claim 1 wherein said blind source separation is performed using independent component analysis.

4. A method according to claim 1 wherein at least one of the constituent signal components is an evoked neuromuscular response.

5. A method according to claim 4 wherein the evoked neuromuscular response is a compound muscle action potential (CMAP).

6. A method according to claim 4 wherein the evoked neuromuscular response is a sensory nerve action potential (SNAP).

7. A method according to claim 1 wherein at lease one of the constituent signal components is a directly recorded artifact of activating a subject'"'"'s anatomy.

8. A method according to claim 1 wherein activating a subject'"'"'s anatomy involves activating neuromuscular tissue.

9. A method according to claim 8 wherein the neuromuscular tissue comprises a peripheral nerve.

10. A method according to claim 1 wherein a subject'"'"'s anatomy is activated with different levels of the same type of stimuli.

11. A method according to claim 10 wherein the stimuli comprises electrical stimuli.

12. A method according to claim 10 wherein the stimuli comprises mechanical stimuli.

13. A method according to claim 10 wherein the stimuli comprises magnetic stimuli.

14. A method according to claim 1 wherein the method comprises the additional step of removing a constituent signal component from a composite signal so as to yield a calculated composite signal.

15. A method according to claim 14 wherein the removed constituent signal component comprises a directly recorded artifact of activating the subject'"'"'s anatomy.

16. A method according to claim 1 wherein the method comprises the additional step of removing a plurality of constituent signal components from a composite signal so as to yield a calculated composite signal.

17. A method according to claim 1 wherein the method comprises the additional step of constructing a calculated composite signal from at least one of the identified constituent signal components.

18. A method according to claim 17 wherein said calculated composite signal reduces the contribution of directly recorded artifacts of activating the subject'"'"'s anatomy vis-à

-vis the original composite signal.

19. A method according to claim 1 wherein the method comprises the additional step of relating the identified signal components to their underlying phenomena.

20. A method according to claim 19 wherein the underlying phenomena is anatomical function.

21. A method according to claim 19 wherein the underlying phenomena is an artifact of activating the subject'"'"'s anatomy.

22. A method according to claim 1 wherein the blind source separation is performed so as to separate out several constituent signal components, each of which results from anatomical function.

48. A method according to claim 1 wherein the subject'"'"'s anatomy is activated at at least two separate anatomical sites.

23. Apparatus for identifying constituent signal components from a plurality of evoked physiological composite signals, said apparatus comprising:

activating means for activating a subject'"'"'s anatomy so as to generate the plurality of composite signals, wherein at least two of said composite signals comprise distinct mixtures of the same constituent signal components;

recording means for recording, at a single anatomical site, the composite signals; and

separation means for performing blind source separation on the composite signals so as to identify the constituent signal components.

24. Apparatus according to claim 23 wherein said separation means are adapted to identify the amount that each constituent signal component contributes to the composite signals.

25. Apparatus according to claim 23 wherein said separation means are adapted to use independent component analysis.

26. Apparatus according to claim 23 wherein at least one of the constituent signal components is an evoked neuromuscular response.

27. Apparatus according to claim 26 wherein the evoked neuromuscular response is a compound muscle action potential (CMAP).

28. Apparatus according to claim 26 wherein the evoked neuromuscular response is a sensory nerve action potential (SNAP).

29. Apparatus according to claim 23 wherein at lease one of the constituent signal components is a directly recorded artifact of activating the subject'"'"'s anatomy.

30. Apparatus according to claim 23 wherein said activating means are adapted to activate neuromuscular tissue.

31. Apparatus according to claim 30 wherein the neuromuscular tissue comprises a peripheral nerve.

32. Apparatus according to claim 23 wherein said activating means are adapted to activate the subject'"'"'s anatomy with different levels of the same type of stimuli.

33. Apparatus according to claim 32 wherein the stimuli comprises electrical stimuli.

34. Apparatus according to claim 32 wherein the stimuli comprises mechanical stimuli.

35. Apparatus according to claim 32 wherein the stimuli comprises magnetic stimuli.

36. Apparatus according to claim 23 wherein the apparatus comprises removal means for removing a constituent signal component from a composite signal so as to yield a calculated composite signal.

37. Apparatus according to claim 36 wherein the removed constituent signal component comprises a directly recorded artifact of activating the subject'"'"'s anatomy.

38. Apparatus according to claim 23 wherein the apparatus comprises removal means for removing a plurality of constituent signal components from a composite signal so as to yield a calculated composite signal.

39. Apparatus according to claim 23 wherein the apparatus comprises reconstruction means for constructing a calculated composite signal from at least one of the identified constituent signal components.

40. Apparatus according to claim 39 wherein said calculated composite signal reduces the contribution of directly recorded artifacts of activating the subject'"'"'s anatomy vis-a-vis the original composite signals.

41. Apparatus according to claim 23 wherein the apparatus comprises relating means for relating the identified signal components to their underlying phenomena.

42. Apparatus according to claim 41 wherein said relating means comprises a discrimination algorithm running on a computer.

43. Apparatus according to claim 41 wherein the underlying phenomena is anatomical function.

44. Apparatus according to claim 41 wherein the underlying phenomena is an artifact of activating the subject'"'"'s anatomy.

45. Apparatus according to claim 23 wherein the blind source separation is performed so as to separate out several constituent signal components, each of which results from anatomical function.

49. A method according to claim 23 wherein said activating means activate the subject'"'"'s anatomy at at least two separate anatomical sites.

46. A method for identifying constituent signal components from a plurality of evoked physiological composite signals, said method comprising:

activating a subject'"'"'s anatomy so as to generate the plurality of composite signals, wherein at least two of said composite signals comprise distinct mixtures of the same constituent signal components;

recording, at a single anatomical site, the composite signals; and

processing the composite signals so as to identify the constituent signal components.

47. Apparatus for identifying constituent signal components from a plurality of evoked physiological composite signals, said apparatus comprising:

activating means for activating a subject'"'"'s anatomy so as to generate the plurality of composite signals, wherein at least two of said composite signals comprise distinct mixtures of the same constituent signal components;

recording means for recording, at a single anatomical site, the composite signals; and

processing the composite signals so as to identify the constituent signal components.