Closed-loop externally powered electrical cortical stimulations (xcs)

A system comprising:

• one or more processors;
• one or more non-transitory computer-readable media storing instructions, which, when executed by the system, cause the system to perform a set of actions including:
• receiving neural data capturing brain activities in real-time from one or more neuromodulation devices that are placed epidurally over one or more cortical regions of a subject to trigger one or more stimulations, wherein a neuromodulation device of the one or more neuromodulation devices is surgically implanted into a skull of the subject via a bur hole procedure;
• predicting a brain state of a set of brain states by processing the neural data via one or more analytical techniques that are configured to identify patterns associated with the brain activities that correlate with the brain state of the set of brain states;
• determining, based on the predicted brain state, a set of stimulation parameters associated with each stimulation of one or more stimulations via a state transition model that is configured to learn a relationship between the set of stimulation parameters and a brain state transition;
• triggering, via the one or more neuromodulation devices, the one or more stimulations over the one or more cortical regions of the subject, wherein the one or more stimulations are generated with respect to the determined set of stimulation parameters, and wherein the one or more stimulations are configured to perturb the brain activities with respect to a treatment therapy;
• monitoring one or more neural responses in real-time recorded by the one or more neuromodulation devices in response to the triggered one or more stimulations;
• and
• dynamically adjusting, based on the one or more neural responses, one or more stimulation parameters associated with each stimulation of the one or more stimulations in a closed loop via a controller, wherein the adjustment is configured with respect to the treatment therapy by guiding the brain activities through targeted brain state transitions that are learned from the state transition model, and wherein the treatment therapy includes enhancing target engagement, maintaining target engagement, reducing side effect, and preventing relapse.

A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors to perform a set pf actions including:

• receiving neural data capturing brain activities in real-time from one or more neuromodulation devices that are placed epidurally over one or more cortical regions of a subject to trigger one or more stimulations, wherein a neuromodulation device of the one or more neuromodulation devices is surgically implanted into a skull of the subject via a bur hole procedure;
• predicting a brain state of a set of brain states by processing the neural data via one or more analytical techniques that are configured to identify patterns associated with the brain activities that correlate with the brain state of the set of brain states;
• determining, based on the predicted brain state, a set of stimulation parameters associated with each stimulation of one or more stimulations via a state transition model that is configured to learn a relationship between the set of stimulation parameters and a brain state transition;
• triggering, via the one or more neuromodulation devices, the one or more stimulations over the one or more cortical regions of the subject, wherein the one or more stimulations are generated with respect to the determined set of stimulation parameters, and wherein the one or more stimulations are configured to perturb the brain activities with respect to a treatment therapy;
• monitoring one or more neural responses in real-time recorded by the one or more neuromodulation devices in response to the triggered one or more stimulations;
• and
• dynamically adjusting, based on the one or more neural responses, one or more stimulation parameters associated with each stimulation of the one or more stimulations in a closed loop via a controller, wherein the adjustment is configured with respect to the treatment therapy by guiding the brain activities through targeted brain state transitions that are learned from the state transition model, and wherein the treatment therapy includes enhancing target engagement, maintaining target engagement, reducing side effect, and preventing relapse.