Selection of neurostimulator parameter configurations using neural networks

• US 7,853,323 B2
• Filed: 06/29/2007
• Issued: 12/14/2010
• Est. Priority Date: 09/15/2003
• Status: Active Grant

• Current Assignee: Medtronic Incorporated (Medtronic Plc)
• Original Assignee: Medtronic Incorporated (Medtronic Plc)
• Inventors: Goetz, Steven M.
• Primary Examiner(s): Layno; Carl H
• Assistant Examiner(s): MALAMUD, DEBORAH LESLIE
• Application Number:
  US11/824,219
• Publication Number:
  US 20070276441A1
• Time in Patent Office: 1,264 Days
• Field of Search: 607/2, 607/5, 607/7, 607/27, 607 45- 46, 607 55- 57, 607/60, 607/116, 607/117, 600/546, 128/925, 706/48, 706 15- 16, 706/18, 706/19, 706/26, 706/34, 706/35, 706/44
• US Class Current: 607/2
• CPC Class Codes: A61N 1/3605 Implantable neurostimulators for stimulating central or peripheral nerve system
• CPC Class Codes: A61N 1/36071 Pain
• CPC Class Codes: A61N 1/37252 Details of algorithms or data aspects of communication system, e.g. handshaking, transmitting specific data or segmenting data
• CPC Class Codes: Y10S 128/925 Neural network

Abstract

In general, the invention is directed to a technique for selection of parameter configurations for a neurostimulator using neural networks. The technique may be employed by a programming device to allow a clinician to select parameter configurations, and then program an implantable neurostimulator to deliver therapy using the selected parameter configurations. The parameter configurations may include one or more of a variety of parameters, such as electrode configurations defining electrode combinations and polarities for an electrode set implanted in a patient. The electrode set may be carried by one or more implanted leads that are electrically coupled to the neurostimulator. In operation, the programming device executes a parameter configuration search algorithm to guide the clinician in the selection of parameter configurations. The search algorithm relies on a neural network that identifies potential optimum parameter configurations.

Claims

1. A method comprising:

receiving an indication of observed efficacy of stimulation delivered by a neurostimulator according to a first stimulation parameter configuration;

modifying a neural network based on the observed efficacy of the stimulation delivered according to the first stimulation parameter configuration, wherein the neural network comprises a plurality of interconnected nodes; and

identifying a second stimulation parameter configuration based on an output of the modified neural network.

2. The method of claim 1, wherein the parameter configurations include electrode configurations, each of the electrode configurations defining a combination of two or more electrodes for delivery of neurostimulation energy.

3. The method of claim 2, wherein each of the electrode configurations defines polarities for electrodes in the combination.

4. The method of claim 2, wherein the electrodes are carried by two or more implanted leads.

5. The method of claim 4, wherein the implanted leads are implanted proximate a portion of a spine of a patient.

6. The method of claim 1, wherein modifying the neural network includes modifying interconnection weights among the nodes in the neural network.

7. The method of claim 1, wherein the nodes in the neural network include input nodes identifying possible combinations of two or more electrodes, output nodes identifying suggested combinations of two or more electrodes, and hidden nodes interconnecting the input nodes and the output nodes with respective interconnection weights.

8. The method of claim 1, further comprising iteratively identifying a plurality of additional stimulation parameter configurations, each of the stimulation parameter configurations identified based on an output of the neural network as modified based on observed efficacy of stimulation delivered by the neurostimulation according to a preceding one of the plurality of stimulation parameter configurations.

9. The method of claim 8, further comprising terminating the iterative identification of additional stimulation parameter configurations when one or more termination criteria are satisfied.

10. The method of claim 9, wherein the termination criteria include selection of one of the stimulation parameter configurations with an observed efficacy that satisfies a threshold efficacy.

11. The method of claim 9, further comprising programming the neurostimulator to employ the final stimulation parameter configuration in delivery of neurostimulation therapy.

12. The method of claim 1, wherein identifying the second stimulation parameter configuration includes suggesting the second stimulation parameter configuration to a clinician.

13. The method of claim 1, wherein identifying the second stimulation parameter configuration comprises:

presenting a list of stimulation parameter configurations that includes the second stimulation parameter configuration to a user; and

ordering the list based on the output of the modified neural network.

14. The method of claim 1, wherein receiving an indication relating to observed efficacy includes receiving user input indicating observed efficacy.

15. A non-transitory computer-readable storage medium comprising instructions to cause a processor to:

receive an indication of observed efficacy of stimulation delivered by a neurostimulator according to a first stimulation parameter configuration;

modify a neural network based on the observed efficacy of the stimulation delivered according to the first stimulation parameter configuration, wherein the neural network comprises a plurality of interconnected nodes; and

identify a second stimulation parameter configuration based on an output of the modified neural network.

16. The computer-readable storage medium of claim 15, wherein the parameter configurations include electrode configurations, each of the electrode configurations defining a combination of two or more electrodes for delivery of neurostimulation energy.

17. The computer-readable storage medium of claim 16, wherein each of the electrode configurations defines polarities for electrodes in the combination.

18. The computer-readable storage medium of claim 16, wherein the electrodes are carried by two or more implanted leads.

19. The computer-readable storage medium of claim 15, wherein modifying the neural network includes modifying interconnection weights among the nodes in the neural network.

20. The computer-readable storage medium of claim 15, wherein the nodes in the neural network include input nodes identifying possible combinations of two or more electrodes, output nodes identifying suggested combinations of two or more electrodes, and hidden nodes interconnecting the input nodes and the output nodes with respective interconnection weights.

21. The computer-readable storage medium of claim 15, further comprising instructions that cause a processor to iteratively identify a plurality of additional stimulation parameter configurations, each of the stimulation parameter configurations identified based on an output of the neural network as modified based on observed efficacy of stimulation delivered by the neurostimulation according to a preceding one of the plurality of stimulation parameter configurations.

22. The computer-readable storage medium of claim 21, further comprising instructions that cause a processor to terminate the iterative identification of additional stimulation parameter configurations when one or more termination criteria are satisfied.

23. The computer-readable storage medium of claim 22, wherein the termination criteria include selection of one of the stimulation parameter configurations with an observed efficacy that satisfies a threshold efficacy.

24. The computer-readable storage medium of claim 22, further comprising instructions that cause a processor to program the neurostimulator to employ the final stimulation parameter configuration in delivery of neurostimulation therapy.

25. The computer-readable storage medium of claim 15, wherein the instructions that cause a processor to identify the second stimulation parameter configuration include instructions that cause a processor to suggest the second stimulation parameter configuration to a clinician.

26. The computer-readable storage medium of claim 15, wherein the instructions that cause a processor to identify the second stimulation parameter configuration comprise instructions that cause a processor to:

present a list of stimulation parameter configurations that includes the second stimulation parameter configuration to a user; and

order the list based on the output of the modified neural network.

27. The computer-readable storage medium of claim 15, wherein the indication relating to observed efficacy includes user input relating to observed efficacy.

28. A device comprising a processor programmed to:

receive an indication of observed efficacy of stimulation delivered by a neurostimulator according to a first stimulation parameter configuration;

modify a neural network based on the observed efficacy of the stimulation delivered according to the first stimulation parameter configuration, wherein the neural network comprises a plurality of interconnected nodes; and

identify a second stimulation parameter configuration based on an output of the modified neural network.

29. The device of claim 28, wherein the parameter configurations include electrode configurations, each of the electrode configurations defining a combination of two or more electrodes for delivery of neurostimulation energy.

30. The device of claim 29, wherein each of the electrode configurations defines polarities for electrodes in the combination.

31. The device of claim 29, wherein the electrodes are carried by two or more implanted leads.

32. The device of claim 28, wherein modifying the neural network includes modifying interconnection weights among the nodes in the neural network.

33. The device of claim 28, wherein the nodes in the neural network include input nodes identifying possible combinations of two or more electrodes, output nodes identifying suggested combinations of two or more electrodes, and hidden nodes interconnecting the input nodes and the output nodes with respective interconnection weights.

34. The device of claim 28, wherein the processor is programmed to iteratively identify a plurality of additional stimulation parameter configurations, each of the stimulation parameter configurations identified based on an output of the neural network as modified based on observed efficacy of stimulation delivered by the neurostimulation according to a preceding one of the plurality of stimulation parameter configurations.

35. The device of claim 34, wherein the processor is programmed to terminate the iterative identification of additional stimulation parameter configurations when one or more termination criteria are satisfied.

36. The device of claim 35, wherein the termination criteria include selection of one of the stimulation parameter configurations with an observed efficacy that satisfies a threshold efficacy.

37. The device of claim 28, wherein the processor is programmed to suggest the second stimulation parameter configuration to a clinician.

38. The device of claim 28, wherein the processor is programmed to:

present a list of stimulation parameter configurations that includes the second stimulation parameter configuration to a user; and

order the list based on the output of the modified neural network.

39. The device of claim 28, wherein the indication relating to observed efficacy includes user input relating to observed efficacy.

40. The device of claim 28, wherein the neurostimulator is implantable, and the device comprises an external programming device that communicates with the neurostimulator when implanted within a patient.