Signal regularity-based automated seizure detection system for scalp EEG monitoring 1

Deng Shan Shiau; J. J. Halford; K. M. Kelly; R. T. Kern; M. Inman; Jui Hong Chien; P. M. Pardalos; M. C.K. Yang; J. Ch Sackellares

doi:10.1007/s10559-010-9273-3

Signal regularity-based automated seizure detection system for scalp EEG monitoring ¹

Deng Shan Shiau, J. J. Halford, K. M. Kelly, R. T. Kern, M. Inman, Jui Hong Chien, P. M. Pardalos, M. C.K. Yang, J. Ch Sackellares

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

The purpose of the present study was to build a clinically useful automated seizure detection system for scalp EEG recordings. To achieve this, a computer algorithm was designed to translate complex multichannel scalp EEG signals into several dynamical descriptors, followed by the investigations of their spatiotemporal properties that relate to the ictal (seizure) EEG patterns as well as to normal physiologic and artifact signals. This paper describes in detail this novel seizure detection algorithm and reports its performance in a large clinical dataset.

Original language	English (US)
Pages (from-to)	922-935
Number of pages	14
Journal	Cybernetics and Systems Analysis
Volume	46
Issue number	6
DOIs	https://doi.org/10.1007/s10559-010-9273-3
State	Published - Nov 2010
Externally published	Yes

Keywords

Amplitude variation
Artifact rejection
False detection rate
Local maximum frequency
Pattern match regularity statistic (PMRS)
Scalp EEG
Seizure detection
Sensitivity

ASJC Scopus subject areas

General Computer Science

Access to Document

10.1007/s10559-010-9273-3

Cite this

@article{98afaf189a684a6fa1e4fc4922d7e417,

title = "Signal regularity-based automated seizure detection system for scalp EEG monitoring 1 ",

abstract = "The purpose of the present study was to build a clinically useful automated seizure detection system for scalp EEG recordings. To achieve this, a computer algorithm was designed to translate complex multichannel scalp EEG signals into several dynamical descriptors, followed by the investigations of their spatiotemporal properties that relate to the ictal (seizure) EEG patterns as well as to normal physiologic and artifact signals. This paper describes in detail this novel seizure detection algorithm and reports its performance in a large clinical dataset.",

keywords = "Amplitude variation, Artifact rejection, False detection rate, Local maximum frequency, Pattern match regularity statistic (PMRS), Scalp EEG, Seizure detection, Sensitivity",

author = "Shiau, {Deng Shan} and Halford, {J. J.} and Kelly, {K. M.} and Kern, {R. T.} and M. Inman and Chien, {Jui Hong} and Pardalos, {P. M.} and Yang, {M. C.K.} and Sackellares, {J. Ch}",

note = "Funding Information: 1This work was supported by the grants 5R01NS050582 (JCS) and 1R43NS064647 (DSS) from NIH-NINDS.",

year = "2010",

month = nov,

doi = "10.1007/s10559-010-9273-3",

language = "English (US)",

volume = "46",

pages = "922--935",

journal = "Cybernetics and Systems Analysis",

issn = "1060-0396",

publisher = "Springer New York",

number = "6",

}

TY - JOUR

T1 - Signal regularity-based automated seizure detection system for scalp EEG monitoring 1

AU - Shiau, Deng Shan

AU - Halford, J. J.

AU - Kelly, K. M.

AU - Kern, R. T.

AU - Inman, M.

AU - Chien, Jui Hong

AU - Pardalos, P. M.

AU - Yang, M. C.K.

AU - Sackellares, J. Ch

N1 - Funding Information: 1This work was supported by the grants 5R01NS050582 (JCS) and 1R43NS064647 (DSS) from NIH-NINDS.

PY - 2010/11

Y1 - 2010/11

N2 - The purpose of the present study was to build a clinically useful automated seizure detection system for scalp EEG recordings. To achieve this, a computer algorithm was designed to translate complex multichannel scalp EEG signals into several dynamical descriptors, followed by the investigations of their spatiotemporal properties that relate to the ictal (seizure) EEG patterns as well as to normal physiologic and artifact signals. This paper describes in detail this novel seizure detection algorithm and reports its performance in a large clinical dataset.

AB - The purpose of the present study was to build a clinically useful automated seizure detection system for scalp EEG recordings. To achieve this, a computer algorithm was designed to translate complex multichannel scalp EEG signals into several dynamical descriptors, followed by the investigations of their spatiotemporal properties that relate to the ictal (seizure) EEG patterns as well as to normal physiologic and artifact signals. This paper describes in detail this novel seizure detection algorithm and reports its performance in a large clinical dataset.

KW - Amplitude variation

KW - Artifact rejection

KW - False detection rate

KW - Local maximum frequency

KW - Pattern match regularity statistic (PMRS)

KW - Scalp EEG

KW - Seizure detection

KW - Sensitivity

UR - http://www.scopus.com/inward/record.url?scp=79952667362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952667362&partnerID=8YFLogxK

U2 - 10.1007/s10559-010-9273-3

DO - 10.1007/s10559-010-9273-3

M3 - Article

AN - SCOPUS:79952667362

SN - 1060-0396

VL - 46

SP - 922

EP - 935

JO - Cybernetics and Systems Analysis

JF - Cybernetics and Systems Analysis

IS - 6

ER -