Posture state classification for a medical device

• US 8,388,555 B2
• Filed: 04/28/2010
• Issued: 03/05/2013
• Est. Priority Date: 01/08/2010
• Status: Active Grant

• Current Assignee: Medtronic Incorporated (Medtronic Plc)
• Original Assignee: Medtronic Incorporated (Medtronic Plc)
• Inventors: Panken, Eric J., Gaudreau, Amanda
• Primary Examiner(s): HINDENBURG, MAX F
• Application Number:
  US12/769,484
• Publication Number:
  US 20110172567A1
• Time in Patent Office: 1,042 Days
• Field of Search: 600/587, 600/595, 600/509
• US Class Current: 600/587
• CPC Class Codes: A61B 2560/0223 of calibration, e.g. protocols for calibrating sensors
• CPC Class Codes: A61B 2560/0475 Special features of memory means, e.g. removable memory cards
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/389 Electromyography [EMG]
• CPC Class Codes: A61B 5/4839 combined with drug delivery
• CPC Class Codes: A61B 5/686 Permanently implanted devices, e.g. pacemakers, other stimulators, biochips A61B5/6861 takes precedence
• 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 5/7282 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 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: A61B 5/7475 User input or interface means, e.g. keyboard, pointing device, joystick
• CPC Class Codes: A61N 1/36071 Pain
• CPC Class Codes: A61N 1/36535 controlled by body position or posture
• CPC Class Codes: A61N 1/37247 User interfaces, e.g. input or presentation means
• 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: G16H 50/20 : for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Techniques relate to operating a medical device in response to a detected posture state of a patient. A trigger event such as a request to modify how therapy is being delivered to the patient may cause a determination to be made as to whether the patient'"'"'s posture state is stable. If the posture state is stable, an association is created between the posture state and one or more therapy parameter values. Over time, a library of such associations is created that may reflect any posture state in three dimensional space, wherein a posture state comprises at least one of a posture and an activity component. The library of associations may be used to automatically control therapy delivery. Similar ones of the associations may automatically be grouped into posture state regions to facilitate more efficient classification of the patient'"'"'s posture state to control therapy delivery.

Claims

1. A system, comprising:

a sensor adapted to provide a signal indicative of a posture state of a patient;

one or more processors adapted to, based on the signal, determine a parameter value indicative of the posture state and determine whether the posture state of the patient is stable, and only if the posture state is stable, to create an association between the parameter value indicative of the posture state and a corresponding therapy parameter value; and

a memory adapted to store the association.

2. The system of claim 1, wherein the one or more processors are adapted to receive a trigger event and to determine, in response to the trigger event, whether the posture state of the patient is stable.

3. The system of claim 2, wherein the trigger event is one of a request for adjustment to therapy being provided to the patient or expiration of a timer.

4. The system of claim 1, wherein the memory is adapted to store one or more associations, each between a parameter value indicative of a respective posture state of the patient and a corresponding therapy parameter value, and wherein the one or more processors are adapted to receive from the sensor a signal indicative of a detected posture state of the patient, to determine whether the detected posture state is represented by one of the stored associations, and if so, to utilize the corresponding therapy parameter value to control delivery of therapy to the patient.

5. The system of claim 1, wherein the one or more processors are adapted to determine whether the posture state of the patient is stable based on programmable stability criteria.

6. The system of claim 5, wherein the stability criteria comprises requiring M of N successive samples of the signal to be within a predetermined threshold distance of a preceding sample.

7. The system of claim 6, wherein at least one of the M of N samples are obtained during a search window of time that has a predetermined duration and follows occurrence of a trigger event.

8. The system of claim 7, wherein the M of N samples are obtained during a stability window of time having a second predetermined duration, wherein the stability window of time at least partially overlaps with the search window of time.

9. The system of claim 5, wherein the stability criteria indicates a change in the posture state of the patient is underway.

10. The system of claim 1, wherein the memory is adapted to store one or more predetermined posture state definitions indicative of predefined posture states, and wherein the one or more processors are adapted to create the association only if the posture state of the patient is not one of the predetermined posture state definitions.

11. The system of claim 1, wherein the memory is adapted to store one or more associations, each between a parameter value indicative of a respective posture state of the patient and a corresponding therapy parameter value, and

wherein the one or more processors are adapted to receive from the sensor a signal indicative of a detected posture state of the patient, to determine whether the detected posture state is represented by one of the stored associations, and if so, to update the one of the stored associations based on the parameter value indicative of the detected posture state, and if not, to create a new association between the parameter value indicative of the detected posture state and a corresponding therapy parameter value.

12. The system of claim 11, wherein the one or more processors are adapted to determine whether the detected posture state is represented by one of the stored associations by determining whether any posture state represented by one of the stored associations is within a predetermined threshold distance of the detected posture state.

13. The system of claim 11, wherein the one or more processors are adapted to determine a posture state that reflects both the detected posture state and a posture state for the one of the stored associations and update the one of the stored associations with the determined posture state.

14. The system of claim 11, wherein the one or more processors are adapted to obtain the therapy parameter value for the new association based on a stored association for a posture state that is closest to the detected posture state or from the therapy parameter value most recently used to deliver therapy to the patient.

15. The system of claim 11, wherein the one or more processors are adapted to obtain the therapy parameter value for the new association based on a request to adjust therapy being delivered to the patient.

16. The system of claim 1, wherein the memory is adapted to store one or more associations, each between a parameter value indicative of a respective posture state of the patient and a corresponding therapy parameter value, and

wherein the one or more processors are adapted to group similar ones of the associations into respective posture state regions for use in classifying the posture state of the patient.

17. The system of claim 16, wherein the similar ones of the associations are spatially similar to one another.

18. The system of claim 17, wherein the similar ones of the associations have therapy parameter values that are similar to one another.

19. The system of claim 16, wherein the one or more processors are adapted to associate each posture state region with a therapy parameter value that is representative of therapy parameter values for associations grouped into the posture state region.

20. The system of claim 16, wherein the one or more processors are adapted to receive from the sensor a signal indicative of a detected posture state of the patient, to determine whether the detected posture state is represented by one of the posture state regions, and if so, to utilize a therapy parameter value corresponding to the one of the posture state regions to control delivery of therapy to the patient.

21. The system of claim 1, wherein the one or more processors are adapted to determine the parameter value indicative of the posture state from multiple samples of the signal obtained during a period of time during which the posture state of the patient is determined to be stable.

22. A method, comprising:

obtaining a signal indicative of a posture state of a patient;

determining, with one or more processors and based on the signal, a parameter value indicative of the posture state;

determining, with the one or more processors and based on the signal, whether the patient is in a stable posture state; and

only if the patient is in a stable posture state, storing an association between the parameter value indicative of the posture state and at least one therapy parameter value.

23. The method of claim 22, wherein obtaining the signal comprises obtaining the signal in response to receipt of a trigger event.

24. The method of claim 23, further comprising receiving the trigger event based on at least one of time of day, day of week, and a time since occurrence of a medical procedure.

25. The method of claim 22, wherein multiple associations are stored, each between a parameter value indicative of a posture state and at least one corresponding therapy parameter value, and further comprising:

obtaining a signal indicative of a detected posture state of the patient; and

if the detected posture state is one of the posture states for which any one of the multiple associations is stored, delivering therapy to the patient according to the at least one corresponding therapy parameter value for the one of the multiple associations.

26. The method of claim 22, wherein determining whether the patient is in a stable posture state comprises evaluating the signal based on selectable stability criteria.

27. The method of claim 22, wherein obtaining the signal comprises obtaining multiple samples indicative of a posture state, and

wherein determining whether the patient is in a stable posture state comprises determining whether M of N successive ones of the multiple samples are within a predetermined threshold distance of a preceding sample.

28. The method of claim 27, further comprising:

obtaining a trigger event; and

obtaining at least some of the M of N samples during a search window of time having a predetermined duration that is initiated in response to the trigger event.

29. The method of claim 28, further comprising obtaining the M of N samples during a stability window of time having a second predetermined duration, wherein the stability window of time at least partially overlaps with the search window of time.

30. The method of claim 22, wherein determining whether the patient is in a stable posture state comprises determining whether the signal indicates a transition in the posture state of the patient.

31. The method of claim 22, further comprising storing one or more posture state definitions, each associated with a predetermined posture state, and wherein storing an association between the parameter value indicative of the posture state and at least one therapy parameter value comprises storing the association only if the posture state indicated by the parameter value is not associated with any of the posture state definitions.

32. The method of claim 22, further comprising:

storing one or more associations, each between a parameter value indicative of a respective posture state and at least one therapy parameter value;

storing one or more posture state definitions, each associating a predetermined posture state and a therapy parameter value;

obtaining an indication of a detected posture state of the patient; and

if the detected posture state is one of the posture states for which any one or more of the associations are stored, delivering therapy to the patient according to the association stored for the detected posture state regardless of whether the detected posture state is also associated with one of the posture state definitions.

33. The method of claim 22, wherein multiple associations are stored, each between a parameter value indicative of a respective posture state and at least one corresponding therapy parameter, and further comprising:

receiving a signal indicative of a detected posture state of the patient;

determining whether the detected posture state is within a threshold distance of a posture state for which any one of the multiple associations is stored, and if so, updating the one of the multiple associations based on a parameter value indicative of the detected posture state, and if not, creating a new association between the parameter value indicative of the detected posture state and a corresponding therapy parameter value.

34. The method of claim 33, wherein updating the one of the multiple associations comprises updating the one of the multiple associations based on the parameter value indicative of the detected posture state and a parameter value indicative of a posture state that is within the threshold distance of the detected posture state.

35. The method of claim 33, wherein creating a new association comprises determining the corresponding therapy parameter value based on a therapy parameter value that is associated with a posture state of one of the multiple associations that is closest to the detected posture state or based on a therapy parameter value recently used to deliver therapy to the patient.

36. The method of claim 33, wherein creating a new association comprises determining the corresponding therapy parameter value based on a request to adjust therapy being delivered to the patient.

37. The method of claim 33, wherein the threshold distance is determined based on at least one of time of day, day of week, time elapsed since a medical procedure, and size of a memory used to store the multiple associations.

38. The method of claim 22, wherein multiple associations are stored, each between a parameter value indicative of a respective posture state and at least one corresponding therapy parameter, and further comprising:

creating at least one posture state region, each representing similar ones of the multiple associations; and

associating with each posture state region one or more corresponding therapy parameter values.

39. The method of claim 38, wherein the similar ones of the multiple associations are at least one of spatially similar or have similar corresponding therapy parameter values.

40. The method of claim 38, wherein creating at least one posture state region comprises applying a clustering function to the multiple associations.

41. The method of claim 38, further comprising:

obtaining a parameter value indicative of a detected posture state of the patient;

comparing the parameter value to the at least one posture state region; and

delivering therapy to the patient based on the comparison.

42. The method of claim 41, further comprising:

determining that the detected posture state is not represented by any of the at least one posture state regions;

comparing the parameter value indicative of the detected posture state to the multiple associations; and

delivering therapy to the patient based on the comparison between the parameter value indicative of the detected posture state and the multiple associations.

43. The method of claim 22, wherein determining the parameter value indicative of the posture state comprises determining the parameter value from multiple samples of the signal obtained during a period of time during which the posture state of the patient is determined to be stable.

44. An article of manufacture comprising a non-transitory computer-readable medium storing executable instructions to cause a processor to:

obtain, based on a sensor signal, a parameter value indicative of a posture state of a patient;

determine whether the parameter value indicates the patient is in a stable posture state; and

only if the patient is in a stable posture state, create an association between the parameter value indicative of the posture state and at least one therapy parameter value used to control delivery of therapy to the patient.

45. The computer-readable medium of claim 44, wherein the instructions further cause the processor to create the association as a modification to a previously-created association for a posture state that is within a predetermined threshold distance of the posture state indicated by the obtained parameter.

46. The computer-readable medium of claim 44, wherein the instructions further cause the processor to determine whether the posture state is stable during a stability window of time having a predetermined duration.

47. The computer-readable medium of claim 46, wherein the instructions further cause the processor to:

receive a trigger event;

initiate a search window of time having a predetermined duration; and

determine whether the posture state is stable during a stability window of time that at least partially overlaps the search window of time.

48. The computer-readable medium of claim 47, wherein the instructions further cause the processor to detect whether a shift in the posture state is likely occurring during a later portion of the stability window of time.

49. The computer-readable medium of claim 44, wherein the instructions further cause the processor to obtain the parameter value from multiple samples of the signal obtained during a period of time during which the posture state of the patient is determined to be stable.

50. A system, comprising:

processor means for obtaining a signal indicative of a posture state of a patient, for determining based on the signal whether the posture state is stable, for determined based on the signal a parameter value indicative of the posture state, and for creating an association between the parameter value indicative of the posture state and a corresponding therapy parameter value only if the at least one posture state is stable; and

memory means for storing the association.

51. A medical device, comprising:

a sensor adapted to provide a signal indicative of a posture state of a patient; and

one or more processors adapted to, based on the signal, determine a parameter value indicative of the posture state and determine whether the posture state of the patient is stable, and only if the posture state is stable, to create an association between the determined parameter value indicative of the posture state and a corresponding therapy parameter value.

52. The medical device of claim 51, wherein the one or more processors are adapted to receive a trigger event and to determine, in response to the trigger event, whether the posture state of the patient is stable.

53. The medical device of claim 51, wherein the one or more processors are adapted to receive from the sensor a signal indicative of a detected posture state of the patient, to determine whether the detected posture state is represented by the stored association, and if so, to utilize the corresponding therapy parameter value to control delivery of therapy to the patient.

54. The medical device of claim 51, wherein the one or more processors are adapted to determine whether the posture state of the patient is stable based on programmable stability criteria.

55. The medical device of claim 51, wherein the one or more processors are adapted to determine the parameter value indicative of the posture state from multiple samples of the signal obtained during a period of time during which the posture state of the patient is determined to be stable.

56. The medical device of claim 55, wherein the one or more processors are adapted to determine the parameter value indicative of the posture state from an average, a median, a most-frequently-occurring, a maximum, or a minimum of the multiple samples.

57. The medical device of claim 51, wherein the one or more processors are adapted to determine the parameter value indicative of the posture state from a weighting function and a previously-determined parameter value that is indicative of either the posture state or indicative of a different posture state.

58. The medical device of claim 51, wherein the one or more processors are adapted to obtain the therapy parameter value from a stored association for a different posture state, a therapy parameter value most recently used to deliver therapy to the patient, or a request to adjust therapy being delivered to the patient.