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

Predictability analysis for an automated seizure prediction algorithm.

J Chris Sackellares1, Deng-Shan Shiau, Jose C Principe

  • 1Department of Biomedical Engineering, University of Florida, Gainesville, Florida, USA. Sackellares@mbi.ufl.edu

Journal of Clinical Neurophysiology : Official Publication of the American Electroencephalographic Society
|December 5, 2006
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

Evaluation of aquapuncture in the reduction of intraoperative hemorrhage in canine ovariohysterectomy.

American journal of veterinary research·2026
Same author

Human-AI Cooperation in Healthcare and Rehabilitation.

Delaware journal of public health·2026
Same author

Training sparse convolutional deep predictive coding networks with attention.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Taming polarized fitting: BLINEX-Pcomp with asymmetric risk penalty for robust Pcomp classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

A generative spike prediction model using behavioral reinforcement for re-establishing neural functional connectivity.

Nature computational science·2026
Same author

Efficacy of Chi-Huang cream as an anti-inflammatory and anti-pruritic agent in treating chronic pruritus.

Fitoterapia·2025
Same journal

Surface EEG to Identify Cognitive Motor Dissociation After Acute Brain Injury.

Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society·2026
Same journal

The Physics and Physiology of Electrical Stimulation of the Brain.

Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society·2026
Same journal

Neurophysiology in Postanoxic Encephalopathy: Pathophysiology, Prognosis, and Treatment.

Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society·2026
Same journal

A Review on the Functional Connectivity of the Human Opercular Cortex.

Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society·2026
Same journal

Surgical Aspects of Opercular Epilepsies.

Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society·2026
Same journal

Cost-Effectiveness of EEG Monitoring in Hypoxic-Ischemic Brain Injury After Cardiac Arrest.

Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society·2026
See all related articles

This study introduces an adaptive threshold seizure warning algorithm (ATSWA) that analyzes intracranial EEG signals to predict epileptic seizures. The ATSWA demonstrated significantly better performance than naive prediction methods, showing potential for seizure warning systems.

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Signal Processing

Background:

  • Epileptic seizures, particularly those of mesial temporal origin, exhibit detectable changes in intracranial EEG signals prior to onset.
  • Developing reliable seizure warning systems is crucial for improving patient quality of life and management.
  • Existing methods for seizure prediction often lack sufficient accuracy or rely on non-physiological signal characteristics.

Purpose of the Study:

  • To evaluate the performance of a novel adaptive threshold seizure warning algorithm (ATSWA) for predicting epileptic seizures.
  • To assess the impact of different seizure warning horizons (SWHs) on the algorithm's predictive capabilities.
  • To compare the ATSWA's effectiveness against statistical-based naive prediction algorithms.

Main Methods:

Related Experiment Videos

  • The study employed an adaptive threshold seizure warning algorithm (ATSWA) that detects convergence in Short-Term Maximum Lyapunov Exponent (STLmax) values from intracranial EEG electrode sites.
  • Performance was evaluated using three indices: Area Above ROC Curve (AAC), Predictability Power (PP), and Fraction of Time Under False Warnings (FTF).
  • The ATSWA was compared against periodic and random statistical prediction algorithms, with varying seizure warning horizons (SWHs).

Main Results:

  • The EEG-based ATSWA significantly outperformed both naive prediction algorithms (P < 0.05) in seizure warning.
  • Performance indices (AAC, PP, FTF) were found to be dependent on the selected seizure warning horizon (SWH).
  • The adaptive nature of the ATSWA allows for dynamic adjustments, potentially improving prediction accuracy across different seizure types or patient states.

Conclusions:

  • The developed EEG-based seizure warning method shows significant potential as a clinical tool for predicting epileptic seizures.
  • The adaptive threshold seizure warning algorithm (ATSWA) offers a promising approach for real-time seizure detection and warning.
  • Further research into optimizing seizure warning horizons (SWHs) could enhance the clinical utility of this EEG-based seizure prediction system.