Systems and methods for VOA model generation and use
View Patent ↗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.
1. A system for estimating a volume of activation using a set of electrical stimulation settings, the system comprising:
a processor configured to:
provide a plurality of separate volume of activation estimation models, wherein at least a different one of the volume of activation estimation models corresponding to each of a plurality of categories determined using electric field data and a machine learning system based on differences in at least one characteristic of the electrical field data, wherein each of the categories, and the corresponding at least one of the volume of activation estimation models, is identified for one or more values or ranges of values of one or more electrical stimulation settings that characterize the electrical field data categorized into the category;
receive a set of electrical stimulation settings for use with a leadwire;
select, based on a value of at least one of the electrical stimulation settings in the set of electrical stimulation settings, a one of the volume of activation estimation models that is categorized to be used for that value of the at least one of the electrical stimulation settings;
apply the set of electrical stimulation settings to the selected one of the volume of activation estimation models to determine an estimated volume of activation;
output an indication of the estimated volume of activation; 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 set of electrical stimulation settings are for use with a directional leadwire.
3. The system of claim 1 , wherein applying the set of electrical stimulation settings comprises applying the set of electrical stimulation settings to the selected one of the volume of activation estimation models to determine a value for each of one of more locations for each of a plurality of neural elements.
4. The system of claim 1 , wherein the at least one of the electrical stimulation settings comprises a pulse width.
5. The system of claim 4 , wherein the plurality of separate volume of activation estimation models comprises separate volume of activation estimation models for each of a plurality of pulse widths or pulse width ranges.
6. The system of claim 4 , wherein the plurality of separate volume of activation estimation models comprises separate volume of activation estimation models for each of a plurality of different pulse width combinations.
7. The system of claim 1 , wherein the at least one of the electrical stimulation settings comprises a leadwire arrangement parameter.
8. The system of claim 1 , wherein providing the plurality of separate volume of activation estimation models comprises
receiving the electric field data for a plurality of different electrical stimulation settings;
categorizing the electrical field data using the machine learning system into the plurality of categories based on the differences in the at least one characteristic of the electrical field data;
identifying, for each of the categories, the at least one of the values or ranges of values of the one or more of the electrical stimulation setting that characterize the electrical field data categorized into the category; and
generating, for each of the categories, the at least one of the volume of activation estimation models for use with the category.
9. The system of claim 8 , wherein the generating comprises generating, for each of the categories, the least one of the volume of activation estimation models, wherein the at least one of the volume of activation estimation models either 1) is generated using machine learning, 2) includes only linear equations generated based on observed functioning of a non-linear neural element model that uses differential equations, or 3) does not use more than one differential equation.
10. The system of claim 8 , wherein receiving the electrical field data comprises receiving the electric field data for the plurality of different electrical stimulation settings for use with a directional leadwire.
11. The system of claim 8 , wherein the one or more electrical stimulation settings comprises a pulse width.
12. The system of claim 8 , wherein the one or more electrical stimulation settings comprises a leadwire arrangement parameter.
13. The system of claim 8 , wherein the at least one characteristic of the electrical field data is a profile of an activating field represented by the electrical field data.
14. The system of claim 8 , wherein categorizing the electrical field data comprises categorizing the electrical field data using decision tree analysis learning.
15. The system of claim 8 , wherein categorizing the electrical field data comprises categorizing the electrical field data using at least one of an Artificial Neural Network (ANN), association rules, genetic algorithms, or support vector machines.
16. The system of claim 15 , wherein categorizing the electrical field data comprises categorizing the electrical field data using the ANN and implements pattern recognition with back-propagation of errors.
17. A system for estimating a volume of activation using a set of electrical stimulation settings, the system comprising:
a processor configured to:
provide a plurality of separate volume of activation estimation models, wherein at least a different one of the volume of activation estimation models corresponding to each of a plurality of categories determined using electric field data and a machine learning system based on differences in at least one characteristic of the electrical field data, wherein each of the categories, and the corresponding at least one of the volume of activation estimation models, is identified used for one or more patient anatomical structures that characterize the electrical field data categorized into the category;
receive a selection of a patient anatomical structure and a set of electrical stimulation settings for use with a directional leadwire to stimulate the selected patient anatomical structure;
select, based on the selected patient anatomical structure, a one of the volume of activation estimation models that is categorized to be used for the selected patient anatomical structure;
apply the set of electrical stimulation settings to the selected one of the volume of activation estimation models to determine an estimated volume of activation;
output an indication of the estimated volume of activation; 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.
18. The system of claim 17 , wherein the set of electrical stimulation settings are for use with a directional leadwire.
19. The system of claim 17 , wherein applying the set of electrical stimulation settings comprises applying the set of electrical stimulation settings to the selected volume of activation estimation model to determine a value for each of one of more locations for each of a plurality of neural elements.
20. The system of claim 17 , wherein providing the plurality of separate volume of activation estimation models comprises
receiving the electric field data for a plurality of the patient anatomical structures;
categorizing the electrical field data using the machine learning system into the plurality of categories based on the differences in the at least one characteristic of the electrical field data;
identifying, for each of the categories, at least one of the different patient anatomical structures that characterize the electrical field data categorized into the category; and
generating, for each of the categories, the at least one of the volume of activation estimation models for use with the category.