Systems and methods for VOA model generation and use

• US 9,959,940 B2
• Filed: 03/10/2017
• Issued: 05/01/2018
• Est. Priority Date: 11/01/2012
• Status: Active Grant

• Current Assignee: Boston Scientific Neuromodulation Corporation (Boston Scientific Corporation)
• Original Assignee: Boston Scientific Neuromodulation Corporation (Boston Scientific Corporation)
• Inventors: Moffitt, Michael A., Steinke, G. Karl
• Primary Examiner(s): SITIRICHE, LUIS A
• Application Number:
  US15/456,351
• Publication Number:
  US 20170185741A1
• Time in Patent Office: 417 Days
• CPC Class Codes: A61N 1/36128 Control systems
• CPC Class Codes: A61N 1/37247 User interfaces, e.g. input or presentation means
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 3/086 using evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A computer implemented system and method provides a volume of activation (VOA) estimation model that receives as input two or more electric field values of a same or different data type at respective two or more positions of a neural element and determines based on such input an activation status of the neural element. A computer implemented system and method provides a machine learning system that automatically generates a computationally inexpensive VOA estimation model based on output of a computationally expensive system.

Claims

1. A system for estimating a volume of activation using a set of electrical stimulation settings, the system comprising:

a processor configured to;

receive electric field data and the set of electrical stimulation settings for use with a non-cylindrically symmetrical implanted leadwire;

apply the electric field data and the set of electrical stimulation settings to a volume of activation estimation model to determine a value for each of one of more locations for each of a plurality of neural elements, wherein the volume of activation estimation model either

     1) does not use as input a plurality of sets of values of an electrical field at different points in time,

     2) includes only linear equations generated based on observed functioning of a model that uses differential equations, or

     3) does not use more than one differential equation;

output an indication of an estimated volume of activation based on the values for each of the one or more locations for each of the neural elements; and

initiate a signal to convey the set of electrical stimulation settings to an implanted pulse generator to transmit signals via a leadwire for stimulation of patient tissue according to the set of electrical stimulation settings.

2. The system of claim 1, wherein the volume of activation estimation model is generated based on observed functioning of the model that uses differential equations, wherein the observed functioning comprises using machine learning to generate the volume of activation estimation model.

3. The system of claim 2, wherein the machine learning comprises decision tree analysis learning.

4. The system of claim 2, wherein the machine learning implements at least one of Artificial Neural Network (ANN), association rules, genetic algorithms, or support vector machines.

5. The system of claim 4, wherein the ANN learning implements pattern recognition with back-propagation of errors.

6. The system of claim 1, wherein the neural elements are axons.

7. The system of claim 6, wherein the axons are all copies of a same model axon, each plotted at a respective point relative to the leadwire.

8. The system of claim 1, wherein the electric field data comprises, for each of the plurality of neural elements, a value of an activating function at one or more locations along the neural element and the activating function is a second difference activating function.

9. The system of claim 1, wherein the one or more locations are nodes of Ranvié

r of the respective neural element.

10. The system of claim 1, wherein the electric field data comprises, for each of the plurality of neural elements, a value of an activating function at one or more locations along the neural element and the activating function comprises an activating function profile at a plurality of locations along the neural element.

11. The system of claim 1, wherein the volume of activation estimation model comprises a plurality of volume of activation estimation models, each of the volume of activation estimation models corresponding to a different pulse width.

12. A non-transitory computer-readable medium having instructions stored thereon and executable by a processor, the instructions comprising:

receiving electric field data and the set of electrical stimulation settings for use with a non-cylindrically symmetrical implanted leadwire;

applying the electric field data and the set of electrical stimulation settings to a volume of activation estimation model to determine a value for each of one of more locations for each of a plurality of neural elements, wherein the volume of activation estimation model either

     1) does not use as input a plurality of sets of values of an electrical field at different points in time,

     2) includes only linear equations generated based on observed functioning of a model that uses differential equations, or

     3) does not use more than one differential equation;

outputting an indication of an estimated volume of activation based on the values for each of the one or more locations for each of the neural elements; and

initiating a signal to convey the set of electrical stimulation settings to an implanted pulse generator to transmit signals via a leadwire for stimulation of patient tissue according to the set of electrical stimulation settings.

13. The non-transitory computer-readable medium of claim 12, wherein the volume of activation estimation model is generated based on observed functioning of the model that uses differential equations, wherein the observed functioning comprises using machine learning to generate the volume of activation estimation model.

14. The non-transitory computer-readable medium of claim 13, wherein the machine learning comprises decision tree analysis learning.

15. The non-transitory computer-readable medium of claim 13, wherein the machine learning implements at least one of Artificial Neural Network (ANN), association rules, genetic algorithms, or support vector machines.

16. The non-transitory computer-readable medium of claim 12, wherein the neural elements are axons.

17. The non-transitory computer-readable medium of claim 16, wherein the axons are all copies of a same model axon, each plotted at a respective point relative to the leadwire.

18. The non-transitory computer-readable medium of claim 12, wherein the electric field data comprises, for each of the plurality of neural elements, a value of an activating function at one or more locations along the neural element and the activating function is a second difference activating function.

19. The non-transitory computer-readable medium of claim 12, wherein the one or more locations are nodes of Ranvié

r of the respective neural element.

20. The non-transitory computer-readable medium of claim 12, wherein the volume of activation estimation model comprises a plurality of volume of activation estimation models, each of the volume of activation estimation models corresponding to a different pulse width.