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

Publication: Research - peer-reviewJournal article – Annual report year: 2012

### DOI

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 language English IEEE Transactions on Biomedical Engineering 2012 59 2 579-585 00189294 http://dx.doi.org/10.1109/TBME.2011.2178094 Published
Citations Web of Science® Times Cited: 6

### Keywords

• Tonic–clonic, Epilepsy, Surface electromyography (sEMG), Seizure detection
Select render style:
APAAuthorCBEHarvardMLAStandardVancouverShortLong
PDF