Automated Algorithm for Generalized Tonic–Clonic Epileptic Seizure Onset Detection Based on sEMG Zero-Crossing Rate

Research output: Contribution to journalJournal article – Annual report year: 2012Researchpeer-review

View graph of relations

Patients are not able to call for help during a generalized tonic–clonic epileptic seizure. Our objective was to develop a robust generic algorithm for automatic detection of tonic–clonic seizures, based on surface electromyography (sEMG) signals suitable for a portable device. Twenty-two seizures were analyzed from 11 consecutive patients. Our method is based on a high-pass filtering with a cutoff at 150 Hz, and monitoring a count of zero crossings with a hysteresis of $\pm 50\,\mu \hbox{V}$ . Based on data from one sEMG electrode (on the deltoid muscle), we achieved a sensitivity of 100% with a mean detection latency of 13.7 s, while the rate of false detection was limited to 1 false alarm per 24 h. The overall performance of the presented generic algorithm is adequate for clinical implementation.
Original languageEnglish
JournalI E E E Transactions on Biomedical Engineering
Issue number2
Pages (from-to)579-585
Publication statusPublished - 2012
CitationsWeb of Science® Times Cited: No match on DOI

    Research areas

  • Tonic–clonic, Epilepsy, Surface electromyography (sEMG), Seizure detection

Download statistics

No data available

ID: 6553823