System and method for remotely monitoring functional activities

• US 6,440,067 B1
• Filed: 02/28/2000
• Issued: 08/27/2002
• Est. Priority Date: 02/28/2000
• Status: Expired due to Term

• Current Assignee: Altec Incorporated
• Original Assignee: Altec Incorporated
• Inventors: DeLuca, Carlo J., Roy, Serge H.
• Primary Examiner(s): Shaver, Kevin
• Assistant Examiner(s): Astorino, Michael C.
• Application Number:
  US09/513,942
• Time in Patent Office: 911 Days
• Field of Search: 706/924, 600/300-301, 600/500-508, 600/529-538, 600/544-545, 600/554-556, 600/585-595, 128/900, 128/903-904, 128/920-925, 434/265
• US Class Current: 600/300
• 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 5/389 Electromyography [EMG]
• 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: G08B 21/0453 worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing detecting, measuring or recording for diagnostic purposes A61B5/00
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: Y10S 128/92 Computer assisted medical diagnostics
• CPC Class Codes: Y10S 128/925 Neural network

Abstract

A method for remotely monitoring and identifying Functional Activities performed by a test subject, the method including the steps of (a) extracting a given type of signals from each of a predetermined set of muscles of a control subject during the performance thereby of a given Functional Activity; (b) processing the signals to provide therefor given parameters affected by the given Functional Activity; (c) storing the data obtained in step (b); and (d) repeating steps (a)-(c) for a plurality of other control subjects. The stored data then is utilized to establish a normative data base indicative of the given Functional Activity and further steps include (f) extracting the given type of signals from each of at least some of the predetermined set of muscles of a test subject during a given monitoring period; and (g) comparing the data base to the signals of step (f) to identify during the monitoring period portions thereof during which the test subject was performing the given Functional Activity.

Claims

1. A method for remotely monitoring and identifying functional activities performed by a test subject, the method comprising the steps of:

(a) extracting a given type of signals from each of a predetermined set of muscles of a control subject during the performance thereby of a given non-communicative functional activity;

(b) processing said signals to provide for said signals given non-communicative parameters affected by said given functional activity;

(c) storing data obtained in step (b);

(d) repeating steps (a)-(c) for a plurality of other control subjects;

(e) utilizing said data stored in steps (c) to establish a normative data base indicative of said given non-communicative functional activity;

(f) extracting said given type of signals from each of at least some of said predetermined set of muscles of a test subject during a given monitoring period during which said test subject is engaged in a variety of functional activities including non-rebilitative functional activities; and

(g) comparing said data base to said signals of step (f) to identify during said monitoring period portions thereof during which said test subject was performing said given non-communicative functional activity.

2. A method according to claim 1 wherein step (e) comprises passing said data through a classification algorithm to identify specific signal patterns which correspond to said given non-communicative functional activity.

3. A method according to claim 2 wherein said set includes a predetermined number of said muscles, step (e) further comprises identifying for said data base those signals extracted from a portion of said muscles having patterns most dependent on said given functional activity, and step (f) comprises extracting said signals only from said portion of said muscles.

4. A method according to claim 2 wherein said signals are biosignals.

5. A method according to claim 4 wherein said signals are EMG signals.

6. A method according to claim 5 wherein said given parameters comprise at least some taken from a group including root-mean square value, envelope, mean rectified value and frequency characteristics.

7. A method according to claim 1 wherein said set includes a predetermined number of said muscles, step (e) further comprises identifying for said data base those signals extracted from a portion of said muscles having patterns most dependent on said given functional activity, and step (f) comprises extracting said signals only from said portion of said muscles.

8. A method according to claim 7 wherein step (a) comprises attaching a sensor over each of said muscles.

9. A method according to claim 8 wherein said muscles comprise the Deltoid and the Erector Spinae.

10. A method according to claim 8 wherein said muscles comprise the Erector Spinae and a muscle in the front portion of the subject'"'"'s thigh.

11. A method according to claim 8 wherein said muscles comprise the Deltoid;

Erector Spinae and Vastus Lateralis.

12. A method according to claim 1 including the step of transmitting data representing the functional activities of the test subject between a location occupied thereby and a remote location for evaluation by testing personnel.

13. A method according to claim 12 wherein step (e) comprises passing said data through a classification algorithm to identify specific signal patterns which correspond to said given non-communicative functional activity.

14. A method according to claim 13 wherein said algorithm comprises a Neural Network or Fuzzy Logic technique.

15. A method according to claim 14 wherein said set includes a predetermined number of said muscles, step (e) further comprises identifying for said data base those signals extracted from a portion of said muscles having patterns most dependent on said non-communicative given functional activity, and step (f) comprises extracting said signals only from said portion of said muscles.

16. A method according to claim 1 wherein:

step (a) comprises extracting said signals from a plurality of different sets of muscles of control subjects during the performance of said variety of non-communicative functional activities;

step (b) comprises determining for said signals distinct given parameters which identify each of a plurality of predetermined ones of said non-communicative functional activities;

step (e) comprises establishing a plurality of normative data bases each indicative of a different one of said predetermined non-communicative functional activities;

step (f) comprises extracting said signals from each of at least some of said muscles of each said set; and

step (g) comprises comparing said data bases to said signals of step (f) to identify during said monitoring period portions thereof during which said test subject was performing each of said predetermined non-communicative functional activities.

17. A method according to claim 16 wherein step (e) comprises passing said data through a classification algorithm to identify specific signal patterns each of which correspond to a different one of said predetermined non-communicative functional activities.

18. A method according to claim 17 wherein each said set includes a predetermined number of said muscles, step (e) further comprises identifying for said data bases those signals extracted from a portion of said muscles from each said set patterns most dependent on said predetermined non-communicative functional activities, and step (f) comprises extracting said signals only from said portion of said muscles of each said set.

19. A method according to claim 17 wherein said signals are biosignals.

20. A method according to claim 19 wherein said signals are EMG signals.

21. A method according to claim 20 wherein said given parameters comprise at least some taken from a group including root-mean squared value, envelope, mean rectified value and frequency characteristics.

22. A method according to claim 21 wherein each said step includes a predetermined number of said muscles, step (e) further comprises identifying for said data bases those signals extracted from a portion of said muscles from each said set patterns most dependent on said predetermined non-communicative function activities, and step (f) comprises extracting said signals only from said portion of said muscles of each said set.

23. A method according to claim 21 wherein said algorithm comprises a neural Network or Fuzzy Logic.

24. A method according to claim 23 wherein each said step includes a predetermined number of said muscles, step (e) further comprises identifying for said data bases those signals extracted from a portion of said muscles from each said set patterns most dependent on said predetermined non-communicative function activities, and step (f) comprises extracting said signals only from said portion of said muscles of each said set.

25. A method according to claim 16 wherein said sets comprise muscles in at least two distinct body parts including a body part other than the forearm or hand.

26. A method according to claim 25 wherein said muscles comprise at least one shoulder muscle.

27. A method according to claim 26 wherein said muscles comprise the Deltoid.

28. A method according to claim 25 wherein said muscles comprise at least one trunk muscle.

29. A method according to claim 28 wherein said muscles comprise the Erector Spinae.

30. A method according to claim 25 wherein said muscles comprise at least one thigh muscle.

31. A method according to claim 30 wherein said muscles comprise the Lateralis.

32. A method for remotely monitoring and identifying non-communicative functional activities performed by a test subject having abnormalities of motor function, the method comprising the steps of:

(a) extracting a given type of signals from each of a predetermined set of muscles of the test subject during the performance thereby of a given non-communicative functional activity.

(b) processing said signals to provide for said signals given parameters affected by said non-communicative functional activity.

(c) storing data obtained in step (b);

(d) utilizing said data stored in step (c) to establish a normative data base indicative of said given non-communicative functional activity;

(e) extracting said given type of signals from at least some of said predetermined set of muscles of the test subject during a given monitoring period during which said test subject is engaged in a variety of functional activities including non-rebilitative functional activities; and

(f) comparing said data base to said signals of step (e) to identify during said monitoring period portions thereof during which the test subject was performing said given non-communicative functional activity.

33. A method according to claim 32 wherein step (d) comprises passing said data through a classification algorithm to identify specific signal patterns which correspond to said given non-communicative functional activity.

34. A method according to claim 33 wherein said set includes a predetermined number of said muscles, step (e) further comprises identifying for said data base those signals extracted from a portion of said muscles having patterns most dependent on said given non-communicative functional activity, and step (f) comprises extracting said signals only from said portion of said muscles.

35. A method according to claim 32 wherein:

step (a) comprises extracting said signals from a plurality of different sets of muscles of the test subject during the performance of said variety of non-communicative functional activities;

step (b) comprises determining for said signal distinct given parameters which identify each of a plurality of predetermined ones of said non-communicative functional activities;

step (c) comprises establishing a plurality of normative data bases each indicative of a different one of said predetermined non-communicative functional activities;

step (e) comprises extracting said signals from each of at least some of said muscles of each said set; and

step (f) comprises said data bases to said signals of step (e) to identify during said monitoring period portions thereof during which the test subject was performing each of said predetermined non-communicative functional activities.

36. A method according to claim 35 wherein step (d) comprises passing said data through a classification algorithm to identify specific signal patens which correspond to each said predetermined non-communicative functional activity.

37. A method according to claim 36 wherein each said step includes a predetermined number of said muscles, step (e) further comprises identifying for said data bases those signals extracted from a portion of said muscles from each said set patterns most dependent on each of said predetermined non-communicative functional activities, and step (f) comprises extracting said signals only from said portion of said muscles of each said set.

38. A system for remotely monitoring a test subject during a given period during which the test subject is performing a variety of non-communicative functional activities including non-rebilitative activities, the system comprising:

a plurality of sensors for providing signals in response to muscle activity, said sensors adapted for placement to extract said signals from predetermined muscles of the test subject;

processing means for determining certain parameters of said signals;

computer means programmed with a data base cataloging different patterns of said paramereters each produced by only specific predetermined ones of said non-communicative functional activities of the test subject, said computer means adapted to compute during said given monitoring period those portions thereof during which the test subject was performing each of said specific predetermined ones of said non-communicative functional activities; and

transmission means for transmitting data representing the non-communicative functional activities performed by the test subject between a location occupied by the test subject and a remote location for evaluation by testing personnel.

39. A system according to claim 38 wherein said sensors are adapted for attachment to the test subjects skin portions overlying the muscles, said processing means is carried by each said sensor, said computer means is in the location occupied by the test subject, and including repeater means adapted to be carried by the test subject and to transmit signals between said sensors and said computer means.

40. A system according to claim 39 wherein said transmission means comprises a telephone and/or Internet link between said computer means and said remote location.

41. A system according to claim 38 wherein said data base is established by a pattern classification algorithm.

42. A method according to claim 41 wherein said algorithm comprises a Neural Network or Fuzzy Logic technique.

43. A method according to claim 42 wherein said signals are biosignals.

44. A method according to claim 43 wherein said signals are EMG signals.