dc.creator | Ansari, A. H. | |
dc.creator | Cherian, P. J. | |
dc.creator | Caicedo, A. | |
dc.creator | De Vos, M. | |
dc.creator | Naulaers, G. | |
dc.creator | Van Huffel, S. | |
dc.date.accessioned | 2020-08-28T15:49:32Z | |
dc.date.accessioned | 2022-09-22T14:12:46Z | |
dc.date.available | 2020-08-28T15:49:32Z | |
dc.date.available | 2022-09-22T14:12:46Z | |
dc.date.created | 2020-08-28T15:49:32Z | |
dc.identifier | ISBN: 978-1-5090-2810-8 | |
dc.identifier | EISBN: 978-1-5090-2809-2 | |
dc.identifier | https://repository.urosario.edu.co/handle/10336/28672 | |
dc.identifier | https://doi.org/10.1109/EMBC.2017.8037441 | |
dc.identifier.uri | http://repositorioslatinoamericanos.uchile.cl/handle/2250/3436815 | |
dc.description.abstract | In 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. | |
dc.language | eng | |
dc.publisher | IEEE | |
dc.relation | 39th 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. 2810-2813 | |
dc.relation | https://ieeexplore.ieee.org/abstract/document/8037441 | |
dc.relation | 2813 | |
dc.relation | 2810 | |
dc.relation | 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) | |
dc.rights | info:eu-repo/semantics/restrictedAccess | |
dc.rights | Restringido (Acceso a grupos específicos) | |
dc.source | 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) | |
dc.source | instname:Universidad del Rosario | |
dc.source | reponame:Repositorio Institucional EdocUR | |
dc.title | Improved neonatal seizure detection using adaptive learning | |
dc.type | bookPart | |