Improved neonatal seizure detection using adaptive learning

A. H. Ansari, P. J. Cherian, A. Caicedo, M. De Vos, G. Naulaers, S. Van Huffel

Resultado de la investigación: Capítulo en Libro/Reporte/ConferenciaContribución a la conferencia

2 Citas (Scopus)

Resumen

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.

Idioma originalInglés estadounidense
Título de la publicación alojada2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Subtítulo de la publicación alojadaSmarter Technology for a Healthier World, EMBC 2017 - Proceedings
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas2810-2813
Número de páginas4
ISBN (versión digital)9781509028092
DOI
EstadoPublicada - sep 13 2017
Publicado de forma externa
Evento39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017 - Jeju Island, República de Corea
Duración: jul 11 2017jul 15 2017

Serie de la publicación

NombreProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (versión impresa)1557-170X

Conferencia

Conferencia39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017
País/TerritorioRepública de Corea
CiudadJeju Island
Período7/11/177/15/17

All Science Journal Classification (ASJC) codes

  • Procesamiento de senales
  • Ingeniería biomédica
  • Visión artificial y reconocimiento de patrones
  • Informática aplicada a la salud

Huella

Profundice en los temas de investigación de 'Improved neonatal seizure detection using adaptive learning'. En conjunto forman una huella única.

Citar esto