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

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

Preoperative limbic cortical thinning in mesial temporal lobe epilepsy surgical candidates is associated with pre-existing and de novo postoperative depression.

Epileptic disorders : international epilepsy journal with videotape·2026

Same author

Moving artificial intelligence from research to real-world clinical use in neurology.

Nature reviews. Neurology·2026

Same author

Magnetoencephalographic source imaging improves localization of the epileptogenic zone in multimodal imaging evaluation.

Epilepsia·2026

Same author

Seizure relapse in new onset epilepsy: It is not always drug resistance.

Epilepsia·2026

Same author

Investigating short-term antiseizure medication effects on interictal epileptiform discharges in idiopathic generalized epilepsy.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026

Same author

Comparison of volume- and surface-based magnetic resonance imaging morphometry algorithms in the detection of focal cortical dysplasia.

Epilepsia·2026

Search research articles

Related Experiment Video

Updated: May 10, 2025

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Published on: September 27, 2024

Deep learning-based detection of generalized convulsive seizures using a wrist-worn accelerometer.

Antoine Spahr¹, Adriano Bernini¹, Pauline Ducouret¹

¹NeuroDigital@NeuroTech, Department of Clinical Neurosciences, Lausanne University Hospital (CHUV), University of Lausanne, Lausanne, Switzerland.

|April 23, 2025

Summary

This summary is machine-generated.

A new deep learning algorithm for smartwatches can automatically detect convulsive seizures (CSs) with high accuracy. This tunable system offers a promising tool for epilepsy management, achieving 96% sensitivity and a low false alarm rate.

Keywords:

deep learning epilepsy focal‐to‐bilateral tonic–clonic seizures generalized tonic–clonic seizure seizure detection wearable

More Related Videos

Inducing Post-Traumatic Epilepsy in a Mouse Model of Repetitive Diffuse Traumatic Brain Injury

Inducing Post-Traumatic Epilepsy in a Mouse Model of Repetitive Diffuse Traumatic Brain Injury

Published on: February 10, 2020

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Published on: June 21, 2019

Related Experiment Videos

Last Updated: May 10, 2025

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Published on: September 27, 2024

Inducing Post-Traumatic Epilepsy in a Mouse Model of Repetitive Diffuse Traumatic Brain Injury

Inducing Post-Traumatic Epilepsy in a Mouse Model of Repetitive Diffuse Traumatic Brain Injury

Published on: February 10, 2020

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Published on: June 21, 2019

Area of Science:

Neurology
Biomedical Engineering
Artificial Intelligence

Background:

Convulsive seizures (CSs) pose significant risks, necessitating reliable detection methods.
Current seizure detection relies heavily on manual observation or complex EEG setups.
Automated detection using wearable sensors offers a scalable solution for continuous monitoring.

Purpose of the Study:

To develop and validate a deep learning algorithm for automated detection of generalized or bilateral convulsive seizures (CSs).
To integrate this algorithm into off-the-shelf smartwatches for real-world application.
To enable tunable sensitivity for personalized epilepsy management.

Main Methods:

A prospective, multi-center study involving 384 patients with video electroencephalography (vEEG) monitoring.
Utilized wrist-worn 3D-accelerometer data as input for an ensemble-based convolutional neural network (CNN).
Trained and evaluated the 'Episave' model on independent datasets, focusing on accelerometer amplitude and tunable sensitivity via quantile aggregation.

Main Results:

The Episave model achieved 96% sensitivity and a low false alarm rate (<1/8 days) on an independent test set.
Optimal performance was observed with a 60% aggregation quantile, yielding 98% sensitivity in cross-validation.
Median detection latency was 26 seconds, with one missed seizure attributed to sensor obstruction.

Conclusions:

Deep learning applied to single-sensor accelerometer data demonstrates high performance for CS detection.
The developed algorithm offers tunable sensitivity, adapting to individual patient needs.
This technology holds potential for integration into smartwatches, enhancing epilepsy monitoring and patient care.