Temporal evolution of seizure burden for automated neonatal EEG classification

Typeset version

 

TY  - CONF
  - Temko, A., Stevenson, N., Marnane, W., Boylan, G. and Lightbody, G.
  - 34th Annual International IEEE EMBS Conference
  - Temporal evolution of seizure burden for automated neonatal EEG classification
  - 2012
  - August
  - Published
  - 1
  - ()
  - 4915
  - 4918
  - San Diego, CA, USA
  - 28-AUG-12
  - 01-SEP-12
  - The aim of this paper is to use recent advances in the clinical understanding of the temporal evolution of seizure burden in neonates with hypoxic ischemic encephalopathy to improve the performance of automated detection algorithms. Probabilistic weights are designed from temporal locations of neonatal seizure events relative to time of birth. These weights are obtained by fitting a skew-normal distribution to the temporal seizure density and introduced into the probabilistic framework of the previously developed neonatal seizure detector. The results are validated on the largest available clinical dataset, comprising 816.7 hours. By exploiting these priors, the ROC area is increased by 23% (relative) reaching 96.75%. The number of false detections per hour is decreased from 0.72 to 0.36, while maintaining the correct detection of seizure burden at 75%.
  - 10.1109/EMBC.2012.6347096
  - Science Foundation Ireland
  - 10/IN.1/B3036
DA  - 2012/08
ER  - 
@inproceedings{V161356245,
   = {Temko, A., Stevenson, N., Marnane, W., Boylan, G. and Lightbody, G.},
   = {34th Annual International IEEE EMBS Conference},
   = {{Temporal evolution of seizure burden for automated neonatal EEG classification}},
   = {2012},
   = {August},
   = {Published},
   = {1},
   = {()},
  pages = {4915--4918},
   = {San Diego, CA, USA},
  month = {Aug},
   = {01-SEP-12},
   = {{The aim of this paper is to use recent advances in the clinical understanding of the temporal evolution of seizure burden in neonates with hypoxic ischemic encephalopathy to improve the performance of automated detection algorithms. Probabilistic weights are designed from temporal locations of neonatal seizure events relative to time of birth. These weights are obtained by fitting a skew-normal distribution to the temporal seizure density and introduced into the probabilistic framework of the previously developed neonatal seizure detector. The results are validated on the largest available clinical dataset, comprising 816.7 hours. By exploiting these priors, the ROC area is increased by 23% (relative) reaching 96.75%. The number of false detections per hour is decreased from 0.72 to 0.36, while maintaining the correct detection of seizure burden at 75%.}},
   = {10.1109/EMBC.2012.6347096},
   = {Science Foundation Ireland},
   = {10/IN.1/B3036},
  source = {IRIS}
}
AUTHORSTemko, A., Stevenson, N., Marnane, W., Boylan, G. and Lightbody, G.
TITLE34th Annual International IEEE EMBS Conference
PUBLICATION_NAMETemporal evolution of seizure burden for automated neonatal EEG classification
YEAR2012
MONTHAugust
STATUSPublished
PEER_REVIEW1
TIMES_CITED()
SEARCH_KEYWORD
EDITORS
START_PAGE4915
END_PAGE4918
LOCATIONSan Diego, CA, USA
START_DATE28-AUG-12
END_DATE01-SEP-12
ABSTRACTThe aim of this paper is to use recent advances in the clinical understanding of the temporal evolution of seizure burden in neonates with hypoxic ischemic encephalopathy to improve the performance of automated detection algorithms. Probabilistic weights are designed from temporal locations of neonatal seizure events relative to time of birth. These weights are obtained by fitting a skew-normal distribution to the temporal seizure density and introduced into the probabilistic framework of the previously developed neonatal seizure detector. The results are validated on the largest available clinical dataset, comprising 816.7 hours. By exploiting these priors, the ROC area is increased by 23% (relative) reaching 96.75%. The number of false detections per hour is decreased from 0.72 to 0.36, while maintaining the correct detection of seizure burden at 75%.
FUNDED_BY
URL
DOI_LINK10.1109/EMBC.2012.6347096
FUNDING_BODYScience Foundation Ireland
GRANT_DETAILS10/IN.1/B3036