About: Development and Prospective Validation of a Transparent Deep Learning Algorithm for Predicting Need for Mechanical Ventilation

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Development and Prospective Validation of a Transparent Deep Learning Algorithm for Predicting Need for Mechanical Ventilation Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Development and Prospective Validation of a Transparent Deep Learning Algorithm for Predicting Need for Mechanical Ventilation
Creator	North, Crystal Mukerji, Shibani Brenner, Laura Brandon Westover, M Hibbert, Kathryn Malhotra, Atul Robbins, Gregory Shao, Yu-Ping Carlile, Morgan Nemati, Shamim Paul, Paulina Shashikumar, Supreeth Wardi, Gabriel
Source	MedRxiv; Medline
abstract	IMPORTANCE: Objective and early identification of hospitalized patients, and particularly those with novel coronavirus disease 2019 (COVID-19), who may require mechanical ventilation is of great importance and may aid in delivering timely treatment. OBJECTIVE: To develop, externally validate and prospectively test a transparent deep learning algorithm for predicting 24 hours in advance the need for mechanical ventilation in hospitalized patients and those with COVID-19. DESIGN: Observational cohort study SETTING: Two academic medical centers from January 01, 2016 to December 31, 2019 (Retrospective cohorts) and February 10, 2020 to May 4, 2020 (Prospective cohorts). PARTICIPANTS: Over 31,000 admissions to the intensive care units (ICUs) at two hospitals. Additionally, 777 patients with COVID-19 patients were used for prospective validation. Patients who were placed on mechanical ventilation within four hours of their admission were excluded. MAIN OUTCOME(S) and MEASURE(S): Electronic health record (EHR) data were extracted on an hourly basis, and a set of 40 features were calculated and passed to an interpretable deep-learning algorithm to predict the future need for mechanical ventilation 24 hours in advance. Additionally, commonly used clinical criteria (based on heart rate, oxygen saturation, respiratory rate, FiO2 and pH) was used to assess future need for mechanical ventilation. Performance of the algorithms were evaluated using the area under receiver-operating characteristic curve (AUC), sensitivity, specificity and positive predictive value. RESULTS: After applying exclusion criteria, the external validation cohort included 3,888 general ICU and 402 COVID-19 patients. The performance of the model (AUC) with a 24-hour prediction horizon at the validation site was 0.882 for the general ICU population and 0.918 for patients with COVID-19. In comparison, commonly used clinical criteria and the ROX score achieved AUCs in the range of 0.773 - 0.782 and 0.768 - 0.810 for the general ICU population and patients with COVID-19, respectively. CONCLUSIONS and RELEVANCE: A generalizable and transparent deep-learning algorithm improves on traditional clinical criteria to predict the need for mechanical ventilation in hospitalized patients, including those with COVID-19. Such an algorithm may help clinicians with optimizing timing of tracheal intubation, better allocation of mechanical ventilation resources and staff, and improve patient care.
has issue date	2020-06-03(xsd:dateTime)
bibo:doi	10.1101/2020.05.30.20118109
bibo:pmid	32577682
has license	medrxiv
sha1sum (hex)	84279e08999fd9292ae251de9536958f00a58199
schema:url	https://doi.org/10.1101/2020.05.30.20118109
resource representing a document's title	Development and Prospective Validation of a Transparent Deep Learning Algorithm for Predicting Need for Mechanical Ventilation
has PubMed identifier	32577682
schema:publication	medRxiv : the preprint server for health sciences
resource representing a document's body	covid:84279e08999fd9292ae251de9536958f00a58199#body_text
is schema:about of	named entity 'Algorithm' named entity 'Predicting' named entity 'timely' named entity 'great' named entity 'delivering' named entity 'Deep Learning' named entity 'Ventilation' named entity 'sore throat' named entity 'UCSD' named entity 'delirium' named entity 'peer review' named entity 'FiO2' named entity 'peer review' named entity 'mechanical ventilation' named entity 'mechanical ventilation' named entity 'intubation' named entity 'invasive mechanical ventilation' named entity 'United States' named entity 'COVID-19' named entity 'peer review' named entity 'Massachusetts General Hospital' named entity 'ROC curves' named entity 'emergency department' named entity 'FiO2' named entity 'peer review' named entity 'peer review' named entity 'deep learning' named entity 'machine learning' named entity 'mechanical ventilation' named entity 'informed consent' named entity 'mechanical ventilation' named entity 'respiratory failure' named entity 'deep learning' named entity 'COVID-19 pandemic' named entity 'peer review' named entity 'Gradient Descent' named entity 'standard deviation' named entity 'respiratory rate' named entity 'organ failure' named entity 'intubate' named entity 'UCSD' named entity 'magnesium' named entity 'vital signs' named entity 'sedation' named entity 'troponin' named entity 'COVID' named entity 'mechanical ventilation' named entity 'reference range' named entity 'medRxiv' named entity 'peer review' named entity 'deep learning' named entity 'intubation' named entity 'UCSD' named entity 'L1-L2' named entity 'Charlson comorbidity index' named entity 'COVID-19' named entity 'peer review' named entity 'overfitting' named entity 'carbon dioxide' named entity 'cardiovascular collapse' named entity 'ICU' named entity 'peer review' named entity 'intubation' named entity 'medRxiv' named entity 'respiratory failure' named entity 'cough' named entity 'non-invasive ventilation' named entity 'peer review' named entity 'mechanical ventilation' named entity 'University of California, San Diego'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software