Detecting bursts in the EEG of very and extremely premature infants using a multi-feature approach

Show simple item record

dc.contributor.author O'Toole, John M.
dc.contributor.author Boylan, Geraldine B.
dc.contributor.author Lloyd, Rhodri O.
dc.contributor.author Goulding, Robert M.
dc.contributor.author Vanhatalo, Sampsa
dc.contributor.author Stevenson, Nathan J.
dc.date.accessioned 2018-01-29T11:31:01Z
dc.date.available 2018-01-29T11:31:01Z
dc.date.issued 2017-07
dc.identifier.citation O'Toole , J M , Boylan , G B , Lloyd , R O , Goulding , R M , Vanhatalo , S & Stevenson , N J 2017 , ' Detecting bursts in the EEG of very and extremely premature infants using a multi-feature approach ' , Medical Engineering & Physics , vol. 45 , pp. 42-50 . https://doi.org/10.1016/j.medengphy.2017.04.003
dc.identifier.other PURE: 97814744
dc.identifier.other PURE UUID: 825266db-6130-455b-9696-2193bb3869b0
dc.identifier.other WOS: 000403625100005
dc.identifier.other Scopus: 85017551785
dc.identifier.uri http://hdl.handle.net/10138/231702
dc.description.abstract Aim: To develop a method that segments preterm EEG into bursts and inter-bursts by extracting and combining multiple EEG features. Methods: Two EEG experts annotated bursts in individual EEG channels for 36 preterm infants with gestational age <30 weeks. The feature set included spectral, amplitude, and frequency-weighted energy features. Using a consensus annotation, feature selection removed redundant features and a support vector machine combined features. Area under the receiver operator characteristic (AUC) and Cohen's kappa (K) evaluated performance within a cross-validation procedure. Results: The proposed channel-independent method improves AUC by 4-5% over existing methods (p <0.001, n = 36), with median (95% confidence interval) AUC of 0.989 (0.973-0.997) and sensitivity -specificity of 95.8-94.4%. Agreement rates between the detector and experts' annotations, K = 0.72 (0.36-0.83) and K = 0.65 (0.32-0.81), are comparable to inter-rater agreement, K = 0.60 (0.21-0.74). Conclusions: Automating the visual identification of bursts in preterm EEG is achievable with a high level of accuracy. Multiple features, combined using a data-driven approach, improves on existing single-feature methods. (C) 2017 The Authors. Published by Elsevier Ltd on behalf of IPEM. en
dc.format.extent 9
dc.language.iso eng
dc.relation.ispartof Medical Engineering & Physics
dc.rights cc_by
dc.rights.uri info:eu-repo/semantics/openAccess
dc.subject Burst detection
dc.subject Electroencephalography
dc.subject Preterm infant
dc.subject Feature extraction
dc.subject Spectral analysis
dc.subject Support vector machine
dc.subject Inter-burst interval
dc.subject PRETERM INFANTS
dc.subject ACTIVITY TRANSIENTS
dc.subject RECORDINGS
dc.subject BORN
dc.subject ELECTROENCEPHALOGRAM
dc.subject SUPPRESSION
dc.subject SELECTION
dc.subject BRAIN
dc.subject 3111 Biomedicine
dc.subject 3124 Neurology and psychiatry
dc.title Detecting bursts in the EEG of very and extremely premature infants using a multi-feature approach en
dc.type Article
dc.contributor.organization Clinicum
dc.contributor.organization Department of Neurosciences
dc.contributor.organization Kliinisen neurofysiologian yksikkö
dc.contributor.organization HUS Medical Imaging Center
dc.description.reviewstatus Peer reviewed
dc.relation.doi https://doi.org/10.1016/j.medengphy.2017.04.003
dc.relation.issn 1350-4533
dc.rights.accesslevel openAccess
dc.type.version publishedVersion

Files in this item

Total number of downloads: Loading...

Files Size Format View
1_s2.0_S1350453317301042_main.pdf 1.083Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record