Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation.

<h4>Background</h4>Among patients with acute respiratory failure requiring prolonged mechanical ventilation, tracheostomies are typically placed after approximately 7 to 10 days. Yet half of patients admitted to the intensive care unit receiving tracheostomy will die within a year, often...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Naomi George, Edward Moseley, Rene Eber, Jennifer Siu, Mathew Samuel, Jonathan Yam, Kexin Huang, Leo Anthony Celi, Charlotta Lindvall
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/92393c1977564ebd8bf4c41d658874cc
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:92393c1977564ebd8bf4c41d658874cc
record_format dspace
spelling oai:doaj.org-article:92393c1977564ebd8bf4c41d658874cc2021-12-02T20:09:52ZDeep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation.1932-620310.1371/journal.pone.0253443https://doaj.org/article/92393c1977564ebd8bf4c41d658874cc2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0253443https://doaj.org/toc/1932-6203<h4>Background</h4>Among patients with acute respiratory failure requiring prolonged mechanical ventilation, tracheostomies are typically placed after approximately 7 to 10 days. Yet half of patients admitted to the intensive care unit receiving tracheostomy will die within a year, often within three months. Existing mortality prediction models for prolonged mechanical ventilation, such as the ProVent Score, have poor sensitivity and are not applied until after 14 days of mechanical ventilation. We developed a model to predict 3-month mortality in patients requiring more than 7 days of mechanical ventilation using deep learning techniques and compared this to existing mortality models.<h4>Methods</h4>Retrospective cohort study. Setting: The Medical Information Mart for Intensive Care III Database. Patients: All adults requiring ≥ 7 days of mechanical ventilation. Measurements: A neural network model for 3-month mortality was created using process-of-care variables, including demographic, physiologic and clinical data. The area under the receiver operator curve (AUROC) was compared to the ProVent model at predicting 3 and 12-month mortality. Shapley values were used to identify the variables with the greatest contributions to the model.<h4>Results</h4>There were 4,334 encounters divided into a development cohort (n = 3467) and a testing cohort (n = 867). The final deep learning model included 250 variables and had an AUROC of 0.74 for predicting 3-month mortality at day 7 of mechanical ventilation versus 0.59 for the ProVent model. Older age and elevated Simplified Acute Physiology Score II (SAPS II) Score on intensive care unit admission had the largest contribution to predicting mortality.<h4>Discussion</h4>We developed a deep learning prediction model for 3-month mortality among patients requiring ≥ 7 days of mechanical ventilation using a neural network approach utilizing readily available clinical variables. The model outperforms the ProVent model for predicting mortality among patients requiring ≥ 7 days of mechanical ventilation. This model requires external validation.Naomi GeorgeEdward MoseleyRene EberJennifer SiuMathew SamuelJonathan YamKexin HuangLeo Anthony CeliCharlotta LindvallPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 6, p e0253443 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Naomi George
Edward Moseley
Rene Eber
Jennifer Siu
Mathew Samuel
Jonathan Yam
Kexin Huang
Leo Anthony Celi
Charlotta Lindvall
Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation.
description <h4>Background</h4>Among patients with acute respiratory failure requiring prolonged mechanical ventilation, tracheostomies are typically placed after approximately 7 to 10 days. Yet half of patients admitted to the intensive care unit receiving tracheostomy will die within a year, often within three months. Existing mortality prediction models for prolonged mechanical ventilation, such as the ProVent Score, have poor sensitivity and are not applied until after 14 days of mechanical ventilation. We developed a model to predict 3-month mortality in patients requiring more than 7 days of mechanical ventilation using deep learning techniques and compared this to existing mortality models.<h4>Methods</h4>Retrospective cohort study. Setting: The Medical Information Mart for Intensive Care III Database. Patients: All adults requiring ≥ 7 days of mechanical ventilation. Measurements: A neural network model for 3-month mortality was created using process-of-care variables, including demographic, physiologic and clinical data. The area under the receiver operator curve (AUROC) was compared to the ProVent model at predicting 3 and 12-month mortality. Shapley values were used to identify the variables with the greatest contributions to the model.<h4>Results</h4>There were 4,334 encounters divided into a development cohort (n = 3467) and a testing cohort (n = 867). The final deep learning model included 250 variables and had an AUROC of 0.74 for predicting 3-month mortality at day 7 of mechanical ventilation versus 0.59 for the ProVent model. Older age and elevated Simplified Acute Physiology Score II (SAPS II) Score on intensive care unit admission had the largest contribution to predicting mortality.<h4>Discussion</h4>We developed a deep learning prediction model for 3-month mortality among patients requiring ≥ 7 days of mechanical ventilation using a neural network approach utilizing readily available clinical variables. The model outperforms the ProVent model for predicting mortality among patients requiring ≥ 7 days of mechanical ventilation. This model requires external validation.
format article
author Naomi George
Edward Moseley
Rene Eber
Jennifer Siu
Mathew Samuel
Jonathan Yam
Kexin Huang
Leo Anthony Celi
Charlotta Lindvall
author_facet Naomi George
Edward Moseley
Rene Eber
Jennifer Siu
Mathew Samuel
Jonathan Yam
Kexin Huang
Leo Anthony Celi
Charlotta Lindvall
author_sort Naomi George
title Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation.
title_short Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation.
title_full Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation.
title_fullStr Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation.
title_full_unstemmed Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation.
title_sort deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation.
publisher Public Library of Science (PLoS)
publishDate 2021
url https://doaj.org/article/92393c1977564ebd8bf4c41d658874cc
work_keys_str_mv AT naomigeorge deeplearningtopredictlongtermmortalityinpatientsrequiring7daysofmechanicalventilation
AT edwardmoseley deeplearningtopredictlongtermmortalityinpatientsrequiring7daysofmechanicalventilation
AT reneeber deeplearningtopredictlongtermmortalityinpatientsrequiring7daysofmechanicalventilation
AT jennifersiu deeplearningtopredictlongtermmortalityinpatientsrequiring7daysofmechanicalventilation
AT mathewsamuel deeplearningtopredictlongtermmortalityinpatientsrequiring7daysofmechanicalventilation
AT jonathanyam deeplearningtopredictlongtermmortalityinpatientsrequiring7daysofmechanicalventilation
AT kexinhuang deeplearningtopredictlongtermmortalityinpatientsrequiring7daysofmechanicalventilation
AT leoanthonyceli deeplearningtopredictlongtermmortalityinpatientsrequiring7daysofmechanicalventilation
AT charlottalindvall deeplearningtopredictlongtermmortalityinpatientsrequiring7daysofmechanicalventilation
_version_ 1718375076681744384