Evaluation of novel algorithm embedded in a wearable sEMG device for seizure detection
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Evaluation of novel algorithm embedded in a wearable sEMG device for seizure detection. / Conradsen, Isa; Beniczky, Sandor; Wolf, Peter; Jennum, Poul; Sorensen, Helge B D.
I: I E E E Engineering in Medicine and Biology Society. Conference Proceedings, Bind 2012, 2012, s. 2048-51.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Evaluation of novel algorithm embedded in a wearable sEMG device for seizure detection
AU - Conradsen, Isa
AU - Beniczky, Sandor
AU - Wolf, Peter
AU - Jennum, Poul
AU - Sorensen, Helge B D
PY - 2012
Y1 - 2012
N2 - We implemented a modified version of a previously published algorithm for detection of generalized tonic-clonic seizures into a prototype wireless surface electromyography (sEMG) recording device. The method was modified to require minimum computational load, and two parameters were trained on prior sEMG data recorded with the device. Along with the normal sEMG recording, the device is able to set an alarm whenever the implemented algorithm detects a seizure. These alarms are annotated in the data file along with the signal. The device was tested at the Epilepsy Monitoring Unit (EMU) at the Danish Epilepsy Center. Five patients were included in the study and two of them had generalized tonic-clonic seizures. All patients were monitored for 2-5 days. A double-blind study was made on the five patients. The overall result showed that the device detected four of seven seizures and had a false detection rate of 0.003/h or one in twelve days.
AB - We implemented a modified version of a previously published algorithm for detection of generalized tonic-clonic seizures into a prototype wireless surface electromyography (sEMG) recording device. The method was modified to require minimum computational load, and two parameters were trained on prior sEMG data recorded with the device. Along with the normal sEMG recording, the device is able to set an alarm whenever the implemented algorithm detects a seizure. These alarms are annotated in the data file along with the signal. The device was tested at the Epilepsy Monitoring Unit (EMU) at the Danish Epilepsy Center. Five patients were included in the study and two of them had generalized tonic-clonic seizures. All patients were monitored for 2-5 days. A double-blind study was made on the five patients. The overall result showed that the device detected four of seven seizures and had a false detection rate of 0.003/h or one in twelve days.
U2 - 10.1109/EMBC.2012.6346361
DO - 10.1109/EMBC.2012.6346361
M3 - Journal article
C2 - 23366322
VL - 2012
SP - 2048
EP - 2051
JO - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
JF - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
SN - 0589-1019
ER -
ID: 48473978