Cargando…

Deep‐learning approaches to identify critically Ill patients at emergency department triage using limited information

STUDY OBJECTIVE: Triage quickly identifies critically ill patients, facilitating timely interventions. Many emergency departments (EDs) use emergency severity index (ESI) or abnormal vital sign triggers to guide triage. However, both use fixed thresholds, and false activations are costly. Prior appr...

Descripción completa

Detalles Bibliográficos
Autores principales: Joseph, Joshua W., Leventhal, Evan L., Grossestreuer, Anne V., Wong, Matthew L., Joseph, Loren J., Nathanson, Larry A., Donnino, Michael W., Elhadad, Noémie, Sanchez, Leon D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7593422/
https://www.ncbi.nlm.nih.gov/pubmed/33145518
http://dx.doi.org/10.1002/emp2.12218
_version_ 1783601379450814464
author Joseph, Joshua W.
Leventhal, Evan L.
Grossestreuer, Anne V.
Wong, Matthew L.
Joseph, Loren J.
Nathanson, Larry A.
Donnino, Michael W.
Elhadad, Noémie
Sanchez, Leon D.
author_facet Joseph, Joshua W.
Leventhal, Evan L.
Grossestreuer, Anne V.
Wong, Matthew L.
Joseph, Loren J.
Nathanson, Larry A.
Donnino, Michael W.
Elhadad, Noémie
Sanchez, Leon D.
author_sort Joseph, Joshua W.
collection PubMed
description STUDY OBJECTIVE: Triage quickly identifies critically ill patients, facilitating timely interventions. Many emergency departments (EDs) use emergency severity index (ESI) or abnormal vital sign triggers to guide triage. However, both use fixed thresholds, and false activations are costly. Prior approaches using machinelearning have relied on information that is often unavailable during the triage process. We examined whether deep‐learning approaches could identify critically ill patients only using data immediately available at triage. METHODS: We conducted a retrospective, cross‐sectional study at an urban tertiary care center, from January 1, 2012–January 1, 2020. De‐identified triage information included structured (age, sex, initial vital signs) and textual (chief complaint) data, with critical illness (mortality or ICU admission within 24 hours) as the outcome. Four progressively complex deep‐learning models were trained and applied to triage information from all patients. We compared the accuracy of the models against ESI as the standard diagnostic test, using area under the receiver‐operator curve (AUC). RESULTS: A total of 445,925 patients were included, with 60,901 (13.7%) critically ill. Vital sign thresholds identified critically ill patients with AUC 0.521 (95% confidence interval [CI] = 0.519–0.522), and ESI <3 demonstrated AUC 0.672 (95% CI = 0.671–0.674), logistic regression classified patients with AUC 0.803 (95% CI = 0.802–0.804), 2‐layer neural network with structured data with AUC 0.811 (95% CI = 0.807–0.815), gradient tree boosting with AUC 0.820 (95% CI = 0.818–0.821), and the neural network model with textual data with AUC 0.851 (95% CI = 0.849–0.852). All successive increases in AUC were statistically significant. CONCLUSION: Deep‐learning techniques represent a promising method of augmenting triage, even with limited information. Further research is needed to determine if improved predictions yield clinical and operational benefits.
format Online
Article
Text
id pubmed-7593422
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-75934222020-11-02 Deep‐learning approaches to identify critically Ill patients at emergency department triage using limited information Joseph, Joshua W. Leventhal, Evan L. Grossestreuer, Anne V. Wong, Matthew L. Joseph, Loren J. Nathanson, Larry A. Donnino, Michael W. Elhadad, Noémie Sanchez, Leon D. J Am Coll Emerg Physicians Open General Medicine STUDY OBJECTIVE: Triage quickly identifies critically ill patients, facilitating timely interventions. Many emergency departments (EDs) use emergency severity index (ESI) or abnormal vital sign triggers to guide triage. However, both use fixed thresholds, and false activations are costly. Prior approaches using machinelearning have relied on information that is often unavailable during the triage process. We examined whether deep‐learning approaches could identify critically ill patients only using data immediately available at triage. METHODS: We conducted a retrospective, cross‐sectional study at an urban tertiary care center, from January 1, 2012–January 1, 2020. De‐identified triage information included structured (age, sex, initial vital signs) and textual (chief complaint) data, with critical illness (mortality or ICU admission within 24 hours) as the outcome. Four progressively complex deep‐learning models were trained and applied to triage information from all patients. We compared the accuracy of the models against ESI as the standard diagnostic test, using area under the receiver‐operator curve (AUC). RESULTS: A total of 445,925 patients were included, with 60,901 (13.7%) critically ill. Vital sign thresholds identified critically ill patients with AUC 0.521 (95% confidence interval [CI] = 0.519–0.522), and ESI <3 demonstrated AUC 0.672 (95% CI = 0.671–0.674), logistic regression classified patients with AUC 0.803 (95% CI = 0.802–0.804), 2‐layer neural network with structured data with AUC 0.811 (95% CI = 0.807–0.815), gradient tree boosting with AUC 0.820 (95% CI = 0.818–0.821), and the neural network model with textual data with AUC 0.851 (95% CI = 0.849–0.852). All successive increases in AUC were statistically significant. CONCLUSION: Deep‐learning techniques represent a promising method of augmenting triage, even with limited information. Further research is needed to determine if improved predictions yield clinical and operational benefits. John Wiley and Sons Inc. 2020-09-01 /pmc/articles/PMC7593422/ /pubmed/33145518 http://dx.doi.org/10.1002/emp2.12218 Text en © 2020 The Authors. JACEP Open published by Wiley Periodicals LLC on behalf of the American College of Emergency Physicians. This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made.
spellingShingle General Medicine
Joseph, Joshua W.
Leventhal, Evan L.
Grossestreuer, Anne V.
Wong, Matthew L.
Joseph, Loren J.
Nathanson, Larry A.
Donnino, Michael W.
Elhadad, Noémie
Sanchez, Leon D.
Deep‐learning approaches to identify critically Ill patients at emergency department triage using limited information
title Deep‐learning approaches to identify critically Ill patients at emergency department triage using limited information
title_full Deep‐learning approaches to identify critically Ill patients at emergency department triage using limited information
title_fullStr Deep‐learning approaches to identify critically Ill patients at emergency department triage using limited information
title_full_unstemmed Deep‐learning approaches to identify critically Ill patients at emergency department triage using limited information
title_short Deep‐learning approaches to identify critically Ill patients at emergency department triage using limited information
title_sort deep‐learning approaches to identify critically ill patients at emergency department triage using limited information
topic General Medicine
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7593422/
https://www.ncbi.nlm.nih.gov/pubmed/33145518
http://dx.doi.org/10.1002/emp2.12218
work_keys_str_mv AT josephjoshuaw deeplearningapproachestoidentifycriticallyillpatientsatemergencydepartmenttriageusinglimitedinformation
AT leventhalevanl deeplearningapproachestoidentifycriticallyillpatientsatemergencydepartmenttriageusinglimitedinformation
AT grossestreuerannev deeplearningapproachestoidentifycriticallyillpatientsatemergencydepartmenttriageusinglimitedinformation
AT wongmatthewl deeplearningapproachestoidentifycriticallyillpatientsatemergencydepartmenttriageusinglimitedinformation
AT josephlorenj deeplearningapproachestoidentifycriticallyillpatientsatemergencydepartmenttriageusinglimitedinformation
AT nathansonlarrya deeplearningapproachestoidentifycriticallyillpatientsatemergencydepartmenttriageusinglimitedinformation
AT donninomichaelw deeplearningapproachestoidentifycriticallyillpatientsatemergencydepartmenttriageusinglimitedinformation
AT elhadadnoemie deeplearningapproachestoidentifycriticallyillpatientsatemergencydepartmenttriageusinglimitedinformation
AT sanchezleond deeplearningapproachestoidentifycriticallyillpatientsatemergencydepartmenttriageusinglimitedinformation