Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning

Despite broad application during labor and delivery, there remains considerable debate about the value of electronic fetal monitoring (EFM). EFM includes the surveillance of fetal heart rate (FHR) patterns in conjunction with the mother's uterine contractions, providing a wealth of data about f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Martin G. Frasch, Shadrian B. Strong, David Nilosek, Joshua Leaverton, Barry S. Schifrin
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	cardiotocography deep learning-artificial neural network (DL-ANN) fetal brain injury convolutional neural network (CNN) prevention Pediatrics RJ1-570
Acceso en línea:	https://doaj.org/article/870863a945dd4e5e959b9a25dcea6bd7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:870863a945dd4e5e959b9a25dcea6bd7
record_format	dspace
spelling	oai:doaj.org-article:870863a945dd4e5e959b9a25dcea6bd72021-12-03T06:11:32ZDetection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning2296-236010.3389/fped.2021.736834https://doaj.org/article/870863a945dd4e5e959b9a25dcea6bd72021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fped.2021.736834/fullhttps://doaj.org/toc/2296-2360Despite broad application during labor and delivery, there remains considerable debate about the value of electronic fetal monitoring (EFM). EFM includes the surveillance of fetal heart rate (FHR) patterns in conjunction with the mother's uterine contractions, providing a wealth of data about fetal behavior and the threat of diminished oxygenation and cerebral perfusion. Adverse outcomes universally associate a fetal injury with the failure to timely respond to FHR pattern information. Historically, the EFM data, stored digitally, are available only as rasterized pdf images for contemporary or historical discussion and examination. In reality, however, they are rarely reviewed systematically or purposefully. Using a unique archive of EFM collected over 50 years of practice in conjunction with adverse outcomes, we present a deep learning framework for training and detection of incipient or past fetal injury. We report 94% accuracy in identifying early, preventable fetal injury intrapartum. This framework is suited for automating an early warning and decision support system for maintaining fetal well-being during the stresses of labor. Ultimately, such a system could enable obstetrical care providers to timely respond during labor and prevent both urgent intervention and adverse outcomes. When adverse outcomes cannot be avoided, they can provide guidance to the early neuroprotective treatment of the newborn.Martin G. FraschShadrian B. StrongDavid NilosekJoshua LeavertonBarry S. SchifrinFrontiers Media S.A.articlecardiotocographydeep learning-artificial neural network (DL-ANN)fetal brain injuryconvolutional neural network (CNN)preventionPediatricsRJ1-570ENFrontiers in Pediatrics, Vol 9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	cardiotocography deep learning-artificial neural network (DL-ANN) fetal brain injury convolutional neural network (CNN) prevention Pediatrics RJ1-570
spellingShingle	cardiotocography deep learning-artificial neural network (DL-ANN) fetal brain injury convolutional neural network (CNN) prevention Pediatrics RJ1-570 Martin G. Frasch Shadrian B. Strong David Nilosek Joshua Leaverton Barry S. Schifrin Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning
description	Despite broad application during labor and delivery, there remains considerable debate about the value of electronic fetal monitoring (EFM). EFM includes the surveillance of fetal heart rate (FHR) patterns in conjunction with the mother's uterine contractions, providing a wealth of data about fetal behavior and the threat of diminished oxygenation and cerebral perfusion. Adverse outcomes universally associate a fetal injury with the failure to timely respond to FHR pattern information. Historically, the EFM data, stored digitally, are available only as rasterized pdf images for contemporary or historical discussion and examination. In reality, however, they are rarely reviewed systematically or purposefully. Using a unique archive of EFM collected over 50 years of practice in conjunction with adverse outcomes, we present a deep learning framework for training and detection of incipient or past fetal injury. We report 94% accuracy in identifying early, preventable fetal injury intrapartum. This framework is suited for automating an early warning and decision support system for maintaining fetal well-being during the stresses of labor. Ultimately, such a system could enable obstetrical care providers to timely respond during labor and prevent both urgent intervention and adverse outcomes. When adverse outcomes cannot be avoided, they can provide guidance to the early neuroprotective treatment of the newborn.
format	article
author	Martin G. Frasch Shadrian B. Strong David Nilosek Joshua Leaverton Barry S. Schifrin
author_facet	Martin G. Frasch Shadrian B. Strong David Nilosek Joshua Leaverton Barry S. Schifrin
author_sort	Martin G. Frasch
title	Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning
title_short	Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning
title_full	Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning
title_fullStr	Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning
title_full_unstemmed	Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning
title_sort	detection of preventable fetal distress during labor from scanned cardiotocogram tracings using deep learning
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/870863a945dd4e5e959b9a25dcea6bd7
work_keys_str_mv	AT martingfrasch detectionofpreventablefetaldistressduringlaborfromscannedcardiotocogramtracingsusingdeeplearning AT shadrianbstrong detectionofpreventablefetaldistressduringlaborfromscannedcardiotocogramtracingsusingdeeplearning AT davidnilosek detectionofpreventablefetaldistressduringlaborfromscannedcardiotocogramtracingsusingdeeplearning AT joshualeaverton detectionofpreventablefetaldistressduringlaborfromscannedcardiotocogramtracingsusingdeeplearning AT barrysschifrin detectionofpreventablefetaldistressduringlaborfromscannedcardiotocogramtracingsusingdeeplearning
_version_	1718373883059372032

Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning

Ejemplares similares