Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system

Isa Conradsen; Sandor Beniczky; Peter Wolf; Jonas R Henriksen; Thomas Sams; Helge B D Sorensen

doi:10.1109/IEMBS.2010.5627218

Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system

Isa Conradsen, Sandor Beniczky, Peter Wolf, Jonas R Henriksen, Thomas Sams, Helge B D Sorensen

Filadelfia

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › peer review

Abstract

An automatic Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) system is highly applicable for onset detection of epileptic seizures based on motion data. The modalities used are surface electromyography (sEMG), acceleration (ACC) and angular velocity (ANG). The new proposed automatic algorithm on motion data is extracting features as "log-sum" measures of discrete wavelet components. Classification into the two groups "seizure" versus "non-seizure" is made based on the support vector machine (SVM) algorithm. The algorithm performs with a sensitivity of 91-100%, a median latency of 1 second and a specificity of 100% on multi-modal data from five healthy subjects simulating seizures. The uni-modal algorithm based on sEMG data from the subjects and patients performs satisfactorily in some cases. As expected, our results clearly show superiority of the multi-modal approach, as compared with the uni-modal one.

Originalsprog	Engelsk
Sider (fra-til)	3269-72
Antal sider	4
Tidsskrift	Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
Vol/bind	2010
DOI	https://doi.org/10.1109/IEMBS.2010.5627218
Status	Udgivet - 2010

Adgang til dokumentet

10.1109/IEMBS.2010.5627218

Citationsformater

Conradsen, I., Beniczky, S., Wolf, P., Henriksen, J. R., Sams, T., & Sorensen, H. B. D. (2010). Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2010, 3269-72. https://doi.org/10.1109/IEMBS.2010.5627218

Conradsen, Isa ; Beniczky, Sandor ; Wolf, Peter et al. / Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system. I: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. 2010 ; Bind 2010. s. 3269-72.

@article{8f69add0b784429c9a460c6cc2bca61b,

title = "Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system",

abstract = "An automatic Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) system is highly applicable for onset detection of epileptic seizures based on motion data. The modalities used are surface electromyography (sEMG), acceleration (ACC) and angular velocity (ANG). The new proposed automatic algorithm on motion data is extracting features as {"}log-sum{"} measures of discrete wavelet components. Classification into the two groups {"}seizure{"} versus {"}non-seizure{"} is made based on the support vector machine (SVM) algorithm. The algorithm performs with a sensitivity of 91-100%, a median latency of 1 second and a specificity of 100% on multi-modal data from five healthy subjects simulating seizures. The uni-modal algorithm based on sEMG data from the subjects and patients performs satisfactorily in some cases. As expected, our results clearly show superiority of the multi-modal approach, as compared with the uni-modal one.",

keywords = "Actigraphy/instrumentation, Adult, Algorithms, Artificial Intelligence, Child, Preschool, Diagnosis, Computer-Assisted/methods, Electromyography/methods, Female, Humans, Male, Middle Aged, Monitoring, Ambulatory/instrumentation, Pattern Recognition, Automated/methods, Reproducibility of Results, Seizures/diagnosis, Sensitivity and Specificity",

author = "Isa Conradsen and Sandor Beniczky and Peter Wolf and Henriksen, {Jonas R} and Thomas Sams and Sorensen, {Helge B D}",

year = "2010",

doi = "10.1109/IEMBS.2010.5627218",

language = "English",

volume = "2010",

pages = "3269--72",

journal = "Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference",

issn = "2375-7477",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Conradsen, I, Beniczky, S , Wolf, P, Henriksen, JR, Sams, T & Sorensen, HBD 2010, 'Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system', Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, bind 2010, s. 3269-72. https://doi.org/10.1109/IEMBS.2010.5627218

Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system. / Conradsen, Isa; Beniczky, Sandor ; Wolf, Peter et al.

I: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, Bind 2010, 2010, s. 3269-72.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › peer review

TY - JOUR

T1 - Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system

AU - Conradsen, Isa

AU - Beniczky, Sandor

AU - Wolf, Peter

AU - Henriksen, Jonas R

AU - Sams, Thomas

AU - Sorensen, Helge B D

PY - 2010

Y1 - 2010

N2 - An automatic Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) system is highly applicable for onset detection of epileptic seizures based on motion data. The modalities used are surface electromyography (sEMG), acceleration (ACC) and angular velocity (ANG). The new proposed automatic algorithm on motion data is extracting features as "log-sum" measures of discrete wavelet components. Classification into the two groups "seizure" versus "non-seizure" is made based on the support vector machine (SVM) algorithm. The algorithm performs with a sensitivity of 91-100%, a median latency of 1 second and a specificity of 100% on multi-modal data from five healthy subjects simulating seizures. The uni-modal algorithm based on sEMG data from the subjects and patients performs satisfactorily in some cases. As expected, our results clearly show superiority of the multi-modal approach, as compared with the uni-modal one.

AB - An automatic Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) system is highly applicable for onset detection of epileptic seizures based on motion data. The modalities used are surface electromyography (sEMG), acceleration (ACC) and angular velocity (ANG). The new proposed automatic algorithm on motion data is extracting features as "log-sum" measures of discrete wavelet components. Classification into the two groups "seizure" versus "non-seizure" is made based on the support vector machine (SVM) algorithm. The algorithm performs with a sensitivity of 91-100%, a median latency of 1 second and a specificity of 100% on multi-modal data from five healthy subjects simulating seizures. The uni-modal algorithm based on sEMG data from the subjects and patients performs satisfactorily in some cases. As expected, our results clearly show superiority of the multi-modal approach, as compared with the uni-modal one.

KW - Actigraphy/instrumentation

KW - Adult

KW - Algorithms

KW - Artificial Intelligence

KW - Child, Preschool

KW - Diagnosis, Computer-Assisted/methods

KW - Electromyography/methods

KW - Female

KW - Humans

KW - Male

KW - Middle Aged

KW - Monitoring, Ambulatory/instrumentation

KW - Pattern Recognition, Automated/methods

KW - Reproducibility of Results

KW - Seizures/diagnosis

KW - Sensitivity and Specificity

U2 - 10.1109/IEMBS.2010.5627218

DO - 10.1109/IEMBS.2010.5627218

M3 - Conference article

C2 - 21096611

SN - 2375-7477

VL - 2010

SP - 3269

EP - 3272

JO - Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

JF - Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

ER -

Conradsen I, Beniczky S , Wolf P, Henriksen JR, Sams T, Sorensen HBD. Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. 2010;2010:3269-72. doi: 10.1109/IEMBS.2010.5627218

Seizure onset detection based on a Uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater