Related Experiment Video
Updated: Aug 6, 2026
10:46
Sampling Cerebrospinal Fluid and Blood from Lateral Tail Vein in Rats During EEG Recordings
Published on: September 1, 2023
An algorithm for seizure detection in rodents
Lyna Kamintsky1, Gerben van Hameren1, Itai Weissberg2,3
1Department of Medical Neuroscience, Faculty of Medicine, Dalhousie University, Halifax, Nova Scotia, Canada.
Epilepsia Open
|June 4, 2025
Summary
This study introduces an artificial neural network (ANN) algorithm for automated seizure detection in epilepsy research. The AI software significantly improves the efficiency of analyzing electroencephalographic (EEG) recordings in rodent models.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Biomedical Engineering
Background:
- Epilepsy research heavily relies on long-term intracranial electroencephalographic (iEEG) recordings in animal models.
- Manual inspection of iEEG data for seizure detection is time-consuming and labor-intensive.
- Current methods lack efficiency for large-scale epilepsy studies.
Purpose of the Study:
- To develop and validate an artificial neural network (ANN) algorithm for automatic seizure detection in rodent epilepsy models.
- To provide an efficient and reliable tool for analyzing iEEG data in epilepsy research.
- To reduce the manual effort required for seizure identification in preclinical studies.
Main Methods:
- Trained an ANN algorithm on iEEG recordings from three mouse epilepsy models: pilocarpine-induced, albumin-induced, and synapsin triple knockout (STKO).
- Applied signal filtering, segmentation, and feature extraction for classifier training using a dataset of seizure and non-seizure recordings.
- Utilized forward selection analysis for optimal feature subset identification and developed a graphical user interface for data analysis and seizure detection.
Main Results:
- The developed system achieved high performance, with sensitivity and positive predictive value above 98% on over 2800 hours of iEEG recordings from 15 animals.
- The algorithm demonstrated reliability across different epilepsy models, including status epilepticus and post-traumatic epilepsy.
- Since 2010, the system has been successfully applied in numerous studies investigating seizure frequency in various rodent models.
Conclusions:
- The proposed ANN-based approach offers a reliable and efficient method for the automatic detection of seizures in mice and rats.
- This AI software streamlines epilepsy research by automating the analysis of EEG recordings.
- The algorithm has proven effective in diverse research settings over 15 years, supporting advancements in understanding epilepsy.
