Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach

Abstract The vast quantities of data generated and collected in the Intensive Care Unit (ICU) have given rise to large retrospective datasets that are frequently used for observational studies. The temporal nature and fine granularity of much of the data collected in the ICU enable the pursuit of pr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Brandon Chan, Brian Chen, Alireza Sedghi, Philip Laird, David Maslove, Parvin Mousavi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/4fff9556148740bcbd4c95666c95345e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4fff9556148740bcbd4c95666c95345e
record_format	dspace
spelling	oai:doaj.org-article:4fff9556148740bcbd4c95666c95345e2021-12-02T15:39:57ZGeneralizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach10.1038/s41598-020-67952-02045-2322https://doaj.org/article/4fff9556148740bcbd4c95666c95345e2020-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-67952-0https://doaj.org/toc/2045-2322Abstract The vast quantities of data generated and collected in the Intensive Care Unit (ICU) have given rise to large retrospective datasets that are frequently used for observational studies. The temporal nature and fine granularity of much of the data collected in the ICU enable the pursuit of predictive modeling. In particular, forecasting acute hypotensive episodes (AHE) in intensive care patients has been of interest to researchers in critical care medicine. Given an advance warning of an AHE, care providers may be prompted to search for evolving disease processes and help mitigate negative clinical outcomes. However, the conventionally adopted definition of an AHE does not account for inter-patient variability and is restrictive. To reflect the wider trend of global clinical and research efforts in precision medicine, we introduce a patient-specific definition of AHE in this study and propose deep learning based models to predict this novel definition of AHE in data from multiple independent institutions. We provide extensive evaluation of the models by studying their accuracies in detecting patient-specific AHEs with lead-times ranging from 10 min to 1 hour before the onset of the event. The resulting models achieve AUROC values ranging from 0.57–0.87 depending on the lead time of the prediction. We demonstrate the generalizability and robustness of our approach through the use of independent multi-institutional data.Brandon ChanBrian ChenAlireza SedghiPhilip LairdDavid MasloveParvin MousaviNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-10 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Brandon Chan Brian Chen Alireza Sedghi Philip Laird David Maslove Parvin Mousavi Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach
description	Abstract The vast quantities of data generated and collected in the Intensive Care Unit (ICU) have given rise to large retrospective datasets that are frequently used for observational studies. The temporal nature and fine granularity of much of the data collected in the ICU enable the pursuit of predictive modeling. In particular, forecasting acute hypotensive episodes (AHE) in intensive care patients has been of interest to researchers in critical care medicine. Given an advance warning of an AHE, care providers may be prompted to search for evolving disease processes and help mitigate negative clinical outcomes. However, the conventionally adopted definition of an AHE does not account for inter-patient variability and is restrictive. To reflect the wider trend of global clinical and research efforts in precision medicine, we introduce a patient-specific definition of AHE in this study and propose deep learning based models to predict this novel definition of AHE in data from multiple independent institutions. We provide extensive evaluation of the models by studying their accuracies in detecting patient-specific AHEs with lead-times ranging from 10 min to 1 hour before the onset of the event. The resulting models achieve AUROC values ranging from 0.57–0.87 depending on the lead time of the prediction. We demonstrate the generalizability and robustness of our approach through the use of independent multi-institutional data.
format	article
author	Brandon Chan Brian Chen Alireza Sedghi Philip Laird David Maslove Parvin Mousavi
author_facet	Brandon Chan Brian Chen Alireza Sedghi Philip Laird David Maslove Parvin Mousavi
author_sort	Brandon Chan
title	Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach
title_short	Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach
title_full	Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach
title_fullStr	Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach
title_full_unstemmed	Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach
title_sort	generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/4fff9556148740bcbd4c95666c95345e
work_keys_str_mv	AT brandonchan generalizabledeeptemporalmodelsforpredictingepisodesofsuddenhypotensionincriticallyillpatientsapersonalizedapproach AT brianchen generalizabledeeptemporalmodelsforpredictingepisodesofsuddenhypotensionincriticallyillpatientsapersonalizedapproach AT alirezasedghi generalizabledeeptemporalmodelsforpredictingepisodesofsuddenhypotensionincriticallyillpatientsapersonalizedapproach AT philiplaird generalizabledeeptemporalmodelsforpredictingepisodesofsuddenhypotensionincriticallyillpatientsapersonalizedapproach AT davidmaslove generalizabledeeptemporalmodelsforpredictingepisodesofsuddenhypotensionincriticallyillpatientsapersonalizedapproach AT parvinmousavi generalizabledeeptemporalmodelsforpredictingepisodesofsuddenhypotensionincriticallyillpatientsapersonalizedapproach
_version_	1718385871786344448

Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach

Ejemplares similares