Weak supervision as an efficient approach for automated seizure detection in electroencephalography

Abstract Automated seizure detection from electroencephalography (EEG) would improve the quality of patient care while reducing medical costs, but achieving reliably high performance across patients has proven difficult. Convolutional Neural Networks (CNNs) show promise in addressing this problem, b...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Khaled Saab, Jared Dunnmon, Christopher Ré, Daniel Rubin, Christopher Lee-Messer
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/ff53b21a684b46adb56f53e342154ca4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ff53b21a684b46adb56f53e342154ca4
record_format	dspace
spelling	oai:doaj.org-article:ff53b21a684b46adb56f53e342154ca42021-12-02T13:39:29ZWeak supervision as an efficient approach for automated seizure detection in electroencephalography10.1038/s41746-020-0264-02398-6352https://doaj.org/article/ff53b21a684b46adb56f53e342154ca42020-04-01T00:00:00Zhttps://doi.org/10.1038/s41746-020-0264-0https://doaj.org/toc/2398-6352Abstract Automated seizure detection from electroencephalography (EEG) would improve the quality of patient care while reducing medical costs, but achieving reliably high performance across patients has proven difficult. Convolutional Neural Networks (CNNs) show promise in addressing this problem, but they are limited by a lack of large labeled training datasets. We propose using imperfect but plentiful archived annotations to train CNNs for automated, real-time EEG seizure detection across patients. While these weak annotations indicate possible seizures with precision scores as low as 0.37, they are commonly produced in large volumes within existing clinical workflows by a mixed group of technicians, fellows, students, and board-certified epileptologists. We find that CNNs trained using such weak annotations achieve Area Under the Receiver Operating Characteristic curve (AUROC) values of 0.93 and 0.94 for pediatric and adult seizure onset detection, respectively. Compared to currently deployed clinical software, our model provides a 31% increase (18 points) in F1-score for pediatric patients and a 17% increase (11 points) for adult patients. These results demonstrate that weak annotations, which are sustainably collected via existing clinical workflows, can be leveraged to produce clinically useful seizure detection models.Khaled SaabJared DunnmonChristopher RéDaniel RubinChristopher Lee-MesserNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 3, Iss 1, Pp 1-12 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Khaled Saab Jared Dunnmon Christopher Ré Daniel Rubin Christopher Lee-Messer Weak supervision as an efficient approach for automated seizure detection in electroencephalography
description	Abstract Automated seizure detection from electroencephalography (EEG) would improve the quality of patient care while reducing medical costs, but achieving reliably high performance across patients has proven difficult. Convolutional Neural Networks (CNNs) show promise in addressing this problem, but they are limited by a lack of large labeled training datasets. We propose using imperfect but plentiful archived annotations to train CNNs for automated, real-time EEG seizure detection across patients. While these weak annotations indicate possible seizures with precision scores as low as 0.37, they are commonly produced in large volumes within existing clinical workflows by a mixed group of technicians, fellows, students, and board-certified epileptologists. We find that CNNs trained using such weak annotations achieve Area Under the Receiver Operating Characteristic curve (AUROC) values of 0.93 and 0.94 for pediatric and adult seizure onset detection, respectively. Compared to currently deployed clinical software, our model provides a 31% increase (18 points) in F1-score for pediatric patients and a 17% increase (11 points) for adult patients. These results demonstrate that weak annotations, which are sustainably collected via existing clinical workflows, can be leveraged to produce clinically useful seizure detection models.
format	article
author	Khaled Saab Jared Dunnmon Christopher Ré Daniel Rubin Christopher Lee-Messer
author_facet	Khaled Saab Jared Dunnmon Christopher Ré Daniel Rubin Christopher Lee-Messer
author_sort	Khaled Saab
title	Weak supervision as an efficient approach for automated seizure detection in electroencephalography
title_short	Weak supervision as an efficient approach for automated seizure detection in electroencephalography
title_full	Weak supervision as an efficient approach for automated seizure detection in electroencephalography
title_fullStr	Weak supervision as an efficient approach for automated seizure detection in electroencephalography
title_full_unstemmed	Weak supervision as an efficient approach for automated seizure detection in electroencephalography
title_sort	weak supervision as an efficient approach for automated seizure detection in electroencephalography
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/ff53b21a684b46adb56f53e342154ca4
work_keys_str_mv	AT khaledsaab weaksupervisionasanefficientapproachforautomatedseizuredetectioninelectroencephalography AT jareddunnmon weaksupervisionasanefficientapproachforautomatedseizuredetectioninelectroencephalography AT christopherre weaksupervisionasanefficientapproachforautomatedseizuredetectioninelectroencephalography AT danielrubin weaksupervisionasanefficientapproachforautomatedseizuredetectioninelectroencephalography AT christopherleemesser weaksupervisionasanefficientapproachforautomatedseizuredetectioninelectroencephalography
_version_	1718392653945503744

Weak supervision as an efficient approach for automated seizure detection in electroencephalography

Ejemplares similares