Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Epilepsy and Seizures: Overview

Epilepsy and Seizures: Overview

Epilepsy is a chronic neurological disease marked by recurrent, unpredictable seizures. These seizures are caused by abnormal electrical discharges in the brain, leading to behavior, sensation, or consciousness alterations. They can also cause transient impairment of awareness, interfering with daily activities.
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...

Seizures: Classification

Seizures: Classification

Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Gamma suppression correlates with thalamic stimulation therapeutic response in intractable epilepsy.

Epilepsia·2026

Same author

A computationally efficient adaptive phase response curve estimator for real-time closed-loop neuromodulation.

Journal of neural engineering·2026

Same author

Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential.

Proceedings of machine learning research·2026

Same author

Active Sensing Subserves Task-Level Control.

ArXiv·2026

Same author

Metric validation for detection of delayed and directed coupling.

Journal of neural engineering·2026

Same author

Rhythms in longitudinal thalamic recordings are linked to seizure risk.

Epilepsia·2026

Search research articles

Related Experiment Video

Updated: Mar 9, 2026

Preparation and Implantation of Electrodes for Electrically Kindling VGAT-Cre Mice to Generate a Model for Temporal Lobe Epilepsy

Preparation and Implantation of Electrodes for Electrically Kindling VGAT-Cre Mice to Generate a Model for Temporal Lobe Epilepsy

Published on: August 17, 2021

Seizure Control in a Computational Model Using a Reinforcement Learning Stimulation Paradigm.

Vivek Nagaraj¹, Andrew Lamperski², Theoden I Netoff³

¹1 Graduate Program in Neuroscience, University of Minnesota - Twin Cities, 312 Church St SE, Minneapolis, MN 55455, USA.

International Journal of Neural Systems

|December 30, 2016

Summary

This study introduces a reinforcement learning algorithm to optimize neuromodulation for seizure control. The adaptive algorithm refines stimulation frequency to minimize energy, improving therapeutic efficacy for patients with epilepsy.

Keywords:

Epilepsy closed-loop deep brain stimulation neuromodulation reinforcement learning

More Related Videos

Using a Bipolar Electrode to Create a Temporal Lobe Epilepsy Mouse Model by Electrical Kindling of the Amygdala

Using a Bipolar Electrode to Create a Temporal Lobe Epilepsy Mouse Model by Electrical Kindling of the Amygdala

Published on: June 29, 2022

Direct-current Stimulation and Multi-electrode Array Recording of Seizure-like Activity in Mice Brain Slice Preparation

Direct-current Stimulation and Multi-electrode Array Recording of Seizure-like Activity in Mice Brain Slice Preparation

Published on: June 7, 2016

Related Experiment Videos

Last Updated: Mar 9, 2026

Preparation and Implantation of Electrodes for Electrically Kindling VGAT-Cre Mice to Generate a Model for Temporal Lobe Epilepsy

Preparation and Implantation of Electrodes for Electrically Kindling VGAT-Cre Mice to Generate a Model for Temporal Lobe Epilepsy

Published on: August 17, 2021

Using a Bipolar Electrode to Create a Temporal Lobe Epilepsy Mouse Model by Electrical Kindling of the Amygdala

Using a Bipolar Electrode to Create a Temporal Lobe Epilepsy Mouse Model by Electrical Kindling of the Amygdala

Published on: June 29, 2022

Direct-current Stimulation and Multi-electrode Array Recording of Seizure-like Activity in Mice Brain Slice Preparation

Direct-current Stimulation and Multi-electrode Array Recording of Seizure-like Activity in Mice Brain Slice Preparation

Published on: June 7, 2016

Area of Science:

Computational Neuroscience
Neuromodulation
Machine Learning

Background:

Neuromodulation, including vagus nerve stimulation and deep brain stimulation, shows promise for intractable epilepsy but suffers from patient-specific variability.
Optimizing stimulation parameters for individual patients could enhance seizure control and reduce energy consumption and side effects.

Purpose of the Study:

To develop and evaluate a reinforcement learning algorithm for optimizing stimulation frequency in seizure control.
To minimize stimulation energy while effectively suppressing seizures using a patient-specific approach.

Main Methods:

Applied a temporal difference reinforcement learning algorithm (TD(0)) to the Epileptor computational model simulating seizure activity.
Introduced a specialized reward function and state-space discretization for applying reinforcement learning to the Epileptor model.
Derived a relationship between stimulation frequency and minimal pulse amplitude required for seizure suppression.

Main Results:

The TD(0) algorithm rapidly identified parameters for seizure control.
The algorithm successfully refined stimulation frequency to minimize energy, reliably converging to optimal parameters.
Demonstrated the adaptive nature of the algorithm, showing convergence to optimal solutions under varying inter-seizure intervals.

Conclusions:

Reinforcement learning offers a promising adaptive, patient-specific approach to optimize neuromodulation for epilepsy treatment.
This method enhances therapeutic efficacy by minimizing stimulation energy and adapting to individual patient needs over time.