SELECTION OF NEUROSTIMULATOR PARAMETER CONFIGURATIONS USING DECISION TREES

• US 20100070001A1
• Filed: 09/14/2009
• Published: 03/18/2010
• 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.
• Granted Patent: US 8,233,990 B2
• Time in Patent Office: Days
• US Class Current: 607/59
• CPC Class Codes: A61N 1/36071 Pain
• CPC Class Codes: A61N 1/36185 Selection of the electrode configuration
• CPC Class Codes: A61N 1/37252 Details of algorithms or data aspects of communication system, e.g. handshaking, transmitting specific data or segmenting data

Abstract

A selection of parameter configurations for a neurostimulator using decision trees may be employed by a programming device to allow a clinician or other user to select parameter configurations, and then program an implantable neurostimulator to deliver therapy using the selected parameter configurations. The programming device executes a parameter configuration search algorithm to guide the clinician in selection of parameter configurations. The search algorithm relies on a decision tree to identify optimum parameter configurations. A decision tree is useful in classifying observations in a data set based upon one or more attributes or fields within the data. The data set includes parameter configurations matched with observed ratings of efficacy on patients of a similar indication. The learned attribute, on which classification occurs, will be the optimum parameter configuration for a set of rated configurations used to produce the classification. The decision trees may be especially useful in identifying electrode configurations.

Claims

1. A method comprising:

selecting a first parameter configuration for a neurostimulator;

receiving an indication of observed efficacy of the first parameter configuration;

selecting a branch of a decision tree based on the indication of observed efficacy and a position of the first parameter configuration within the decision tree, wherein the decision tree comprises a plurality of nodes and branches and defines a hierarchy of possible parameter configurations for a neurostimulator, wherein each node defines an alternative parameter configuration from each of the other nodes, and each branch links one of the nodes to another of the nodes; and

selecting a second parameter configuration for the neurostimulator based on the selected branch of the decision tree.

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, and the electrodes are associated with different target regions within a body of a patient.

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

6. The method of claim 2, further comprising iteratively selecting additional electrode configurations for the neurostimulator based on the indication of observed efficacy of preceding electrode configurations and positions of the preceding electrode configurations within the decision tree, and terminating the iterative selection of the additional electrode configurations when one or more termination criteria are satisfied.

7. The method of claim 6, wherein the termination criteria include selection of one of the electrode configurations with an observed efficacy that satisfies a threshold efficacy.

8. The method of claim 7, wherein the termination criteria include an iteration limit.

9. The method of claim 2, further comprising:

iteratively selecting additional electrode configurations for the neurostimulator based on observed efficacy of preceding electrode configurations and positions of the preceding electrode configurations within the decision tree;

terminating the iterative selection of the additional electrode configurations at a final electrode configuration when one or more termination criteria are satisfied; and

programming the neurostimulator to employ the final electrode configuration in delivery of neurostimulation therapy.

10. The method of claim 9, wherein the neurostimulator is a spinal cord stimulator, and the final electrode configuration includes electrodes deployed on one more implanted spinal leads.

11. The method of claim 10, wherein the final electrode configuration defines a combination of two electrodes from a set of at least eight electrodes.

12. The method of claim 1, wherein the first parameter configuration includes a first electrode configuration and the second parameter configuration includes a second electrode configuration, wherein the first electrode configuration is defined by a root node in the decision tree, the method further comprising expanding the root node to produce a next-level node defining the second electrode configuration when the observed efficacy for the first electrode configuration does not satisfy a threshold efficacy.

13. The method of claim 12, further comprising receiving an indication of the efficacy of the second electrode configuration defined by the next-level node and further expanding the next-level node to produce one or more additional next-level nodes defining additional electrode configurations until one of the electrode configurations associated with one of the next-level nodes satisfies the threshold efficacy or an iteration limit is reached.

14. The method of claim 1, wherein selecting the first and second parameter configurations includes suggesting the first and second parameter configurations to a user.

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

16. The method of claim 1, further comprising updating the decision tree based on the observed efficacy.

17. The method of claim 16, wherein updating the decision tree comprises updating the decision tree based on the observed efficacy for a particular patient.

18. The method of claim 1, further comprising applying a first decision tree to determine a neurostimulation therapy type, neurostimulation device type, lead type and symptomatic indication, and applying a second decision tree based on the determination to select the second parameter configuration.