Optimization of an NLEO-based algorithm for automated detection of spontaneous activity transients in early preterm EEG

Kirsi Palmu; Nathan J. Stevenson; Sverre Wikström; Lena Hellström-Westas; Sampsa Vanhatalo; J. Matias Palva

doi:10.1088/0967-3334/31/11/N02

Optimization of an NLEO-based algorithm for automated detection of spontaneous activity transients in early preterm EEG

Kirsi Palmu^*, Nathan J. Stevenson, Sverre Wikström, Lena Hellström-Westas, Sampsa Vanhatalo, J. Matias Palva

^*Corresponding author for this work

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

44 Citations (Scopus)

Abstract

We propose here a simple algorithm for automated detection of spontaneous activity transients (SATs) in early preterm electroencephalography (EEG). The parameters of the algorithm were optimized by supervised learning using a gold standard created from visual classification data obtained from three human raters. The generalization performance of the algorithm was estimated by leaveone-out cross-validation. The mean sensitivity of the optimized algorithm was 97% (range 91-100%) and specificity 95% (76-100%). The optimized algorithm makes it possible to systematically study brain state fluctuations of preterm infants.

Original language	English
Journal	Physiological Measurement
Volume	31
Issue number	11
DOIs	https://doi.org/10.1088/0967-3334/31/11/N02
Publication status	Published - Nov 2010
MoE publication type	A1 Journal article-refereed

Keywords

Automated detection
Burst
EEG
NLEO
Preterm
SAT

Access to Document

10.1088/0967-3334/31/11/N02

OpenUrl availability

Full text

Cite this

@article{5c1bc6929bf3444b93ff8f1d9fd6c920,

title = "Optimization of an NLEO-based algorithm for automated detection of spontaneous activity transients in early preterm EEG",

abstract = "We propose here a simple algorithm for automated detection of spontaneous activity transients (SATs) in early preterm electroencephalography (EEG). The parameters of the algorithm were optimized by supervised learning using a gold standard created from visual classification data obtained from three human raters. The generalization performance of the algorithm was estimated by leaveone-out cross-validation. The mean sensitivity of the optimized algorithm was 97% (range 91-100%) and specificity 95% (76-100%). The optimized algorithm makes it possible to systematically study brain state fluctuations of preterm infants.",

keywords = "Automated detection, Burst, EEG, NLEO, Preterm, SAT",

author = "Kirsi Palmu and Stevenson, {Nathan J.} and Sverre Wikstr{\"o}m and Lena Hellstr{\"o}m-Westas and Sampsa Vanhatalo and Palva, {J. Matias}",

year = "2010",

month = nov,

doi = "10.1088/0967-3334/31/11/N02",

language = "English",

volume = "31",

journal = "Physiological Measurement",

issn = "0967-3334",

publisher = "IOP Publishing Ltd.",

number = "11",

}

TY - JOUR

T1 - Optimization of an NLEO-based algorithm for automated detection of spontaneous activity transients in early preterm EEG

AU - Palmu, Kirsi

AU - Stevenson, Nathan J.

AU - Wikström, Sverre

AU - Hellström-Westas, Lena

AU - Vanhatalo, Sampsa

AU - Palva, J. Matias

PY - 2010/11

Y1 - 2010/11

N2 - We propose here a simple algorithm for automated detection of spontaneous activity transients (SATs) in early preterm electroencephalography (EEG). The parameters of the algorithm were optimized by supervised learning using a gold standard created from visual classification data obtained from three human raters. The generalization performance of the algorithm was estimated by leaveone-out cross-validation. The mean sensitivity of the optimized algorithm was 97% (range 91-100%) and specificity 95% (76-100%). The optimized algorithm makes it possible to systematically study brain state fluctuations of preterm infants.

AB - We propose here a simple algorithm for automated detection of spontaneous activity transients (SATs) in early preterm electroencephalography (EEG). The parameters of the algorithm were optimized by supervised learning using a gold standard created from visual classification data obtained from three human raters. The generalization performance of the algorithm was estimated by leaveone-out cross-validation. The mean sensitivity of the optimized algorithm was 97% (range 91-100%) and specificity 95% (76-100%). The optimized algorithm makes it possible to systematically study brain state fluctuations of preterm infants.

KW - Automated detection

KW - Burst

KW - EEG

KW - NLEO

KW - Preterm

KW - SAT

UR - http://www.scopus.com/inward/record.url?scp=78149322321&partnerID=8YFLogxK

U2 - 10.1088/0967-3334/31/11/N02

DO - 10.1088/0967-3334/31/11/N02

M3 - Article

C2 - 20938065

AN - SCOPUS:78149322321

VL - 31

JO - Physiological Measurement

JF - Physiological Measurement

SN - 0967-3334

IS - 11

ER -

Optimization of an NLEO-based algorithm for automated detection of spontaneous activity transients in early preterm EEG

Abstract

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this