AUTOMATED CALIBRATION OF POSTURE STATE CLASSIFICATION FOR A MEDICAL DEVICE

• US 20110172562A1
• Filed: 04/28/2010
• Published: 07/14/2011
• Est. Priority Date: 01/08/2010
• Status: Active Grant

• Current Assignee: Medtronic Incorporated (Medtronic Plc)
• Original Assignee: Medtronic Incorporated (Medtronic Plc)
• Inventors: Goetz, Steven, Davenport, Lynn, Fehrmann, Elizabeth A., Davis, Jon P., Dewing, Wende L., Panken, Eric J., Sahasrabudhe, Rajeev M., Gokaldas, Shyam
• Granted Patent: US 9,149,210 B2
• Time in Patent Office: Days
• 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 by classifying a detected posture state of a patient. This classification may be performed by comparing the detected posture state of the patient to posture state definitions available within the system. Each definition may be described in terms of a parameter (e.g., vector) indicative of a direction in three-dimensional space. The posture state definitions may be calibrated by automatically estimating values for these parameters, thereby eliminating the need for the patient to assume each posture state during the calibration process to capture actual parameter values. According to another aspect, the estimated parameter values may be updated as the patient assumes various postures during a daily routine. For instance, estimated vectors initially used to calibrate the posture state definitions may be changed over time to more closely represent posture states the patient actually assumes, and to further adapt to changes in a patient'"'"'s condition.

Claims

1. A medical device, comprising:

a memory adapted to store posture state definitions for classifying a posture state of a patient; and

a processor adapted to obtain a reference vector having a predetermined relationship to a housing of the medical device and to automatically estimate from the reference vector a parameter value for at least one of the posture state definitions.

2. The device of claim 1, wherein the device is adapted to be disposed in a substantially fixed manner with respect to the patient, and wherein the reference vector is determined prior to a time the device is disposed with respect to the patient.

3. The device of claim 1, further comprising a sensor adapted to provide an indication of the posture state of the patient, and wherein the processor is adapted to obtain from the sensor a captured estimated vector that estimates a parameter value for at least one of the posture state definitions.

4. The device of claim 3, wherein the captured estimated vector is obtained in response to occurrence of a trigger event that occurs without participation of a user of the device.

5. The device of claim 3, wherein the captured estimated vector is obtained when a patient assumes a posture state that is an approximation of one of the defined posture states.

6. The device of claim 5, wherein the processor is adapted to obtain the captured estimated vector without active participation on the part of the patient.

7. The device of claim 3, wherein the processor is adapted to derive from at least one of the reference vector and the captured estimated vector an estimate of a parameter value for at least one of the posture state definitions.

8. The device of claim 7, wherein the processor is adapted to

derive from the reference vector an estimated value for a vector associated with a Lying Back posture state definition,

utilize the captured estimated vector as an estimated value for a vector associated with an Upright posture state definition, and

derive as a cross-product of the captured estimated vector and the reference vector an estimated value for a vector associated with a Lying posture state definition.

9. The device of claim 7, wherein the processor is adapted to automatically update one or more of the parameter values for the posture states based on posture states assumed by the patient.

10. The device of claim 7, wherein the derived parameter vector is derived based on an angular relationship with at least one of the reference vector and the captured estimated vector.

11. The device of claim 1, further comprising a sensor adapted to provide an indication of the posture state of the patient, and wherein the posture state definitions are described in a coordinate system of the sensor.

12. The device of claim 1, wherein the processor is adapted to utilize the posture state definitions to classify the posture state of the patient, and

further comprising a therapy module to deliver therapy to the patient according to the posture state classification.

13. The device of claim 1, further comprising a user interface that allows a user to selectively create a visual representation of a posture state definition for display by the user interface.

14. A system, comprising:

a device as in claim 1; and

a programmer adapted to initiate obtaining the captured estimated vector.

15. A method, comprising:

obtaining a reference vector having a predetermined relationship to a housing of a medical device;

employing the reference vector to obtain at least one estimated vector that estimates a posture state of the patient;

using, by a processor, the at least one estimated vector to generate one or more posture state definitions; and

classifying a posture state of a patient based on the posture state definitions.

16. The method of claim 15, wherein classifying the posture state is performed while the medical device is disposed in a substantially-fixed relationship to the patient, and further comprising determining the reference vector from a sensor before the medical device is disposed in relation to the patient.

17. The method of claim 15, further comprising:

obtaining from a sensor an estimated vector that estimates a corresponding posture state of the patient; and

using, by the processor, the estimated vector to generate one of the posture state definitions.

18. The method of claim 17, wherein obtaining the estimated vector from the sensor comprises obtaining the estimated vector based on occurrence of a trigger event.

19. The method of claim 18, wherein the trigger event comprises receiving input from a programmer.

20. The method of claim 18, wherein the trigger event comprises detecting from the sensor that the patient is undergoing a predetermined activity level.

21. The method of claim 15, further comprising automatically selecting a tolerance for each of the posture state definitions that describes a spatial region in three-dimensional space relative to a corresponding one of the estimated vectors.

22. The method of claim 15, further comprising:

capturing one or more samples of detected vectors indicative of posture states assumed by the patient; and

revising the estimated vectors based on the samples.

23. The method of claim 15, further comprising:

manipulating an avatar into a representation of a selected posture state; and

automatically using the representation to generate one or more posture state definitions.

24. The method of claim 23, wherein the representation identifies an angular relationship used to generate the one or more posture state definitions.

25. The method of claim 15, further comprising delivering therapy to the patient based on the posture state definitions.

26. A system comprising:

a housing to be disposed in a substantially-fixed relationship in reference to a patient;

a storage device to store defined posture state vectors, each being used to define a corresponding posture state of the patient; and

a processor adapted to obtain a reference vector that is determined prior to a time the housing is disposed in reference to the patient, to utilize the reference vector to estimate a respective value for one or more of the defined posture state vectors for one or more of the defined posture states, and to use the one or more defined posture states to classify the posture state of the patient.

27. The system of claim 26, further comprising:

a sensor to capture an estimated vector; and

wherein the processor is further adapted to utilize the captured estimated vector to estimate a respective value for one or more of the defined posture state vectors for one or more of the defined posture states, and to use the one or more defined posture states to classify the posture state of the patient.

28. The system of claim 26, wherein the processor is further adapted to determine a respective value for one or more of the defined posture state vectors based on an angular relationship with at least one of the captured estimated vector and the reference vector.

29. The system of claim 26, wherein the processor is further adapted to determine a respective value for one or more of the defined posture state vectors based on a function applied to at least one of the captured estimated vector and the reference vector.

30. The system of claim 26, wherein the processor is adapted to utilize the captured estimated vector to estimate the respective value based on a trigger event.

31. The system of claim 30, further comprising a programmer, and wherein the trigger event comprises input provided via the programmer.

32. The system of claim 30, further comprising a sensor adapted to provide an indication of activity of the patient, and wherein the trigger event is based on the indication of activity.

33. The system of claim 26, wherein the reference vector has a predetermined relationship to a reference surface of a housing and wherein the processor is adapted to utilize the reference vector to estimate a vector for a Lying Back posture state.

34. The system of claim 26, wherein the processor is adapted to update over time an estimated value of a defined posture state vector based on an output of a sensor obtained while the patient occupies a corresponding one of the defined posture states.

35. The system of claim 26, further comprising a user interface adapted to allow a user to create an avatar representation of a posture state of a patient to be included in a display for controlling operation of the system.

36. A system, comprising:

means for obtaining a reference vector and for employing the reference vector to obtain at least one estimated vector that estimates a posture state of the patient;

means for using the at least one estimated vector to automatically generate one or more posture state definitions;

means for classifying a posture state of a patient based on the posture state definitions; and

means for delivering therapy to the patient based on the posture state classification.