System and method to select among trajectories for therapeutic stimulation of a target volume region within the brain

1 . A method for selecting a trajectory within a brain for insertion of a stimulation probe for deep brain stimulation treatment of an individual afflicted with a neurological illness, condition, or disorder, the method comprising:

extending, via one or more processors, one or more microelectrodes along a plurality of trajectories within the brain of the individual;

receiving, via the one or more microelectrodes, electrophysiology data at a plurality of increments along each of the plurality of trajectories, the electrophysiology data being indicative of neural activity of the individual;

utilizing, via the one or more processors, a machine learning model to generate a score for each of the plurality of trajectories of the individual based on the received electrophysiology data of the individual; and

selecting, via the one or more processors, the trajectory for insertion of the stimulation probe within the brain of the individual based on a comparison of the score of the trajectory with a threshold and/or a comparison of the respective scores among the plurality of trajectories,

wherein the machine learning model has been trained prior to utilization using a set of training data, the set of training data including (i) clinically determined tissue activation volumes with positive results of other similarly afflicted individuals and (ii) electrophysiology data of the other similarly afflicted individuals.

2 . The method of claim 1 , wherein parameters of the set of training data include any of the following frequencies: alpha, low beta, high beta, low gamma, high gamma, high-frequency oscillations (HFO), or high-frequency band (HFB).

3 . The method of claim 1 , wherein parameters of the set of training data include any of the following frequencies: delta interacting with low beta, delta interacting with high gamma, theta interacting with alpha, theta interacting with high-frequency band (HFB), alpha interacting with low beta, alpha interacting with high beta, alpha interacting with low gamma, alpha interacting with high-frequency oscillations (HFO), low beta interacting with high-frequency band (HFB), high beta interacting with high gamma, low gamma interacting with high-frequency oscillations (HFO); low gamma interacting with high-frequency band (HFB); high gamma interacting with high-frequency oscillations (HFO), or high gamma interacting with high-frequency band (HFB).

4 . The method of claim 1 , further comprising:

implanting a stimulation probe along the selected trajectory within the brain of the individual; and

activating the stimulation probe to stimulate the brain of the individual patient.

5 . The method of claim 4 , wherein activating the stimulation probe includes one or more activation contacts and/or one or more leads.

6 . The method of claim 1 , wherein the plurality of increments are spaced 0.5 mm apart along the trajectory and includes 6 seconds of microelectrode recording (MER).

7 . The method of claim 6 , wherein the microelectrode recordings are received within a range between 15 mm above a target and 5 mm below the target.

8 . The method of claim 7 , wherein the target is the subthalamic nucleus of the brain.

9 . The method of claim 1 , wherein selecting the trajectory is based on a comparison of the score of the trajectory with a threshold and/or a comparison of the respective scores among the plurality of trajectories.

10 . A system for selecting a trajectory within a brain for insertion of a stimulation probe for deep brain stimulation treatment of an individual afflicted with a neurological illness, condition, or disorder, the system comprising:

one or more processors;

a user interface;

one or more microelectrodes;

a stimulation probe; and

a non-transitory computer-readable memory coupled to the one or more processors, the user interface, the one or more microelectrodes, and the stimulation probe, wherein the non-transitory computer-readable memory including instructions stored thereon on that, when executed by the one or more processors, cause the system to:

extend the one or more microelectrodes along a plurality of trajectories within the brain of the individual;

receive, via the one or more microelectrodes, electrophysiology data at a plurality of increments along each of the plurality of trajectories, the electrophysiology data being indicative of neural activity of the individual;

utilize a machine learning model to generate a score for each of the plurality of trajectories of the individual based on the received corresponding electrophysiology data of the individual; and

select the trajectory for insertion of the stimulation probe within the brain of the individual based on a comparison of the score of the trajectory with a threshold and/or a comparison of the respective scores among the plurality of trajectories,

wherein the machine learning model has been trained prior to utilization using a set of training data, the set of training data including (i) clinically determined tissue activation volumes with positive results of other similarly afflicted individuals and (ii) electrophysiology data of the other similarly afflicted individuals.

11 . The system of claim 10 , wherein the instructions further cause the system to:

implant the stimulation probe along the selected stimulation trajectory within the brain of the individual; and

activate the stimulation probe to stimulate the brain of the individual.

12 . The system of claim 11 , wherein the stimulation probe includes one or more activation contacts and/or one or more leads.

13 . The system of claim 10 , wherein parameters of the set of training data include any of the following frequencies: alpha, low beta, high beta, low gamma, high gamma, high-frequency oscillations (HFO), or high-frequency band (HFB) spike rate.

14 . The system of claim 10 , wherein parameters of the set of training data include any of the following interactions of frequencies: delta interacting with low beta, delta interacting with high gamma, theta interacting with alpha, theta interacting with high-frequency band (HFB), alpha interacting with low beta, alpha interacting with high beta, alpha interacting with low gamma, alpha interacting with high-frequency oscillations (HFO), low beta interacting with high-frequency band (HFB), high beta interacting with high gamma, low gamma interacting with high-frequency oscillations (HFO); low gamma interacting with high-frequency band (HFB); high gamma interacting with high-frequency oscillations (HFO), or high gamma interacting with high-frequency band (HFB).

15 . The system of claim 10 , wherein the plurality of increments are spaced 0.5 mm apart along the trajectory and includes 6 seconds of microelectrode recording (MER).

16 . The system of claim 15 , wherein the microelectrode recordings are received within a range between 15 mm above a target and 5 mm below the target.

17 . The system of claim 16 , wherein the target is the subthalamic nucleus of the brain.

18 . The system of claim 10 , wherein the instructions that cause the system to select the trajectory cause the system to select the trajectory based on a comparison of the score of the trajectory with a threshold and/or a comparison among the respective scores of the plurality of trajectories.

19 . A non-transitory computer-readable memory operatively coupled to a deep brain stimulation system, the deep brain stimulation system including one or more processors, a user interface, one or more microelectrodes, and a stimulation probe, wherein the non-transitory computer-readable memory including instructions stored thereon on that, when executed by the one or more processors, cause the deep brain stimulation system to:

extend the one or more microelectrodes along a plurality of trajectories within a brain of an individual;

receive, via the one or more microelectrodes, electrophysiology data at a plurality of increments along each of the plurality of trajectories, the electrophysiology data being indicative of neural activity of the individual;

utilize a machine learning model to generate a score for each of the plurality of trajectories of the individual based on the received corresponding electrophysiology data of the individual; and

select a trajectory for insertion of the stimulation probe within the brain of the individual based on a comparison of the score of the trajectory with a threshold and/or a comparison of the respective scores among the plurality of trajectories,

wherein the machine learning model has been trained prior to utilization using a set of training data, the set of training data including (i) clinically determined tissue activation volumes with positive results of other similarly afflicted individuals and (ii) electrophysiology data of the other similarly afflicted individuals.

20 . The non-transitory computer-readable memory of claim 19 , wherein the instructions further cause the deep brain stimulation system to:

implant the stimulation probe along the selected stimulation trajectory within the brain of the individual; and

activate the stimulation probe to stimulate the brain of the individual patient.