Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Patient-specific seizure onset detection.

Ali Shoeb1, Herman Edwards, Jack Connolly

  • 1Harvard-MIT Health Sciences and Technology, Medical Engineering and Medical Physics Program, Cambridge, MA, USA. ashoeb@mit.edu

Epilepsy & Behavior : E&B
|July 17, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Pediatric Reference Ranges for Glomerular Filtration Rate Determined by a Single Injection of <sup>99m</sup>Tc-DTPA.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same author

Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression.

Proceedings of machine learning research·2026
Same author

MultiMorph: On-demand Atlas Construction.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
Same author

A data-driven respiratory motion correction for pediatric DMSA renal SPECT imaging: A simulation study.

Medical physics·2026
Same author

Summary of the 2024 Update of the North American Guidelines for Pediatric Administered Radiopharmaceutical Activities.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2025
Same author

ESPWA: a deep learning-enabled tool for precision-based use of endocrine therapy in resource-limited settings.

bioRxiv : the preprint server for biology·2025

This study introduces an automated method for detecting epileptic seizure onset using patient-specific electroencephalography (EEG) data. The system accurately identifies seizures from EEG, enabling timely clinical interventions.

Area of Science:

  • Neurology
  • Biomedical Engineering
  • Signal Processing

Background:

  • Epileptic seizures require timely detection for effective clinical management.
  • Noninvasive electroencephalography (EEG) is a key tool for monitoring brain activity.
  • Patient-specific variations in EEG necessitate tailored detection methods.

Purpose of the Study:

  • To develop and validate an automated, patient-specific method for detecting epileptic seizure onset.
  • To leverage individual EEG patterns for improved seizure detection accuracy.
  • To enable prompt initiation of delay-sensitive clinical procedures post-seizure.

Main Methods:

  • Utilized wavelet decomposition to create feature vectors from EEG epochs.
  • Captured EEG morphology and spatial distribution within feature vectors.

Related Experiment Videos

  • Employed support vector machine (SVM) classification to distinguish seizure from non-seizure EEG.
  • Tested the automated method on noninvasive EEG data from 36 pediatric subjects.

    • Main Results:

    • Successfully detected 131 out of 139 seizure events.
    • Achieved detection within 8.0 ± 3.2 seconds of electrographic onset.
    • Reported 15 false detections over 60 hours of clinical EEG monitoring.
    • Demonstrated high accuracy in a diverse pediatric epilepsy cohort.

    Conclusions:

    • The developed patient-specific method offers an automated and effective approach to epileptic seizure detection.
    • The system's speed and accuracy support the timely execution of critical clinical interventions.
    • This technology holds potential for improving patient care in epilepsy management.