Ítem
Solo Metadatos

Improved neonatal seizure detection using adaptive learning

Mostrar el registro sencillo de la publicación
dc.creatorAnsari, A. H.spa
dc.creatorCherian, P. J.spa
dc.creatorCaicedo, A.spa
dc.creatorDe Vos, M.spa
dc.creatorNaulaers, G.spa
dc.creatorVan Huffel, S.spa
dc.date.accessioned2020-08-28T15:49:32Z
dc.date.available2020-08-28T15:49:32Z
dc.date.created2017-09-14spa
dc.description.abstractIn neonatal intensive care units performing continuous EEG monitoring, there is an unmet need for around-the-clock interpretation of EEG, especially for recognizing seizures. In recent years, a few automated seizure detection algorithms have been proposed. However, these are suboptimal in detecting brief-duration seizures (<; 30s), which frequently occur in neonates with severe neurological problems. Recently, a multi-stage neonatal seizure detector, composed of a heuristic and a data-driven classifier was proposed by our group and showed improved detection of brief seizures. In the present work, we propose to add a third stage to the detector in order to use feedback of the Clinical Neurophysiologist and adaptively retune a threshold of the second stage to improve the performance of detection of brief seizures. As a result, the false alarm rate (FAR) of the brief seizure detections decreased by 50% and the positive predictive value (PPV) increased by 18%. At the same time, for all detections, the FAR decreased by 35% and PPV increased by 5% while the good detection rate remained unchanged.eng
dc.format.mimetypeapplication/pdf
dc.identifier.doihttps://doi.org/10.1109/EMBC.2017.8037441
dc.identifier.issnISBN: 978-1-5090-2810-8
dc.identifier.issnEISBN: 978-1-5090-2809-2
dc.identifier.urihttps://repository.urosario.edu.co/handle/10336/28672
dc.language.isoengspa
dc.publisherIEEEspa
dc.relation.citationEndPage2813
dc.relation.citationStartPage2810
dc.relation.citationTitle2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
dc.relation.ispartof39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), ISBN: 978-1-5090-2810-8;EISBN: 978-1-5090-2809-2 (2017); pp. 2810-2813spa
dc.relation.urihttps://ieeexplore.ieee.org/abstract/document/8037441spa
dc.rights.accesRightsinfo:eu-repo/semantics/restrictedAccess
dc.rights.accesoRestringido (Acceso a grupos específicos)spa
dc.source2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)spa
dc.source.instnameinstname:Universidad del Rosario
dc.source.reponamereponame:Repositorio Institucional EdocUR
dc.subject.keywordPediatricsspa
dc.subject.keywordDetectorsspa
dc.subject.keywordElectroencephalographyspa
dc.subject.keywordFeature extractionspa
dc.subject.keywordMonitoringspa
dc.subject.keywordTrainingspa
dc.subject.keywordSensitivityspa
dc.titleImproved neonatal seizure detection using adaptive learningspa
dc.title.TranslatedTitleDetección mejorada de convulsiones neonatales mediante aprendizaje adaptativospa
dc.typebookParteng
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersion
dc.type.spaParte de librospa
Archivos
Colecciones
Libros