About: Predicting Critical State after COVID-19 Diagnosis Using Real-World Data from 20152 Confirmed US Cases

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

About: Predicting Critical State after COVID-19 Diagnosis Using Real-World Data from 20152 Confirmed US Cases Goto Sponge NotDistinct Permalink

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

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Predicting Critical State after COVID-19 Diagnosis Using Real-World Data from 20152 Confirmed US Cases
Creator	Klopfenstein, Yannick Rinderknecht, Mike
Source	MedRxiv
abstract	The global COVID-19 pandemic caused by the virus SARS-CoV-2 has led to over 10 million confirmed cases, half a million deaths, and is challenging healthcare systems worldwide. With limited medical resources, early identification of patients with a high risk of progression to severe disease or a critical state is crucial. We present a prognostic model predicting critical state within 28 days following COVID-19 diagnosis trained on data from US electronic health records (EHR) within IBM Explorys, including demographics, comorbidities, symptoms, laboratory test results, insurance types, and hospitalization. Our entire cohort included 20152 COVID-19 cases, of which 3160 patients went into critical state or died. Random, stratified train-test splits were repeated 100 times to obtain a distribution of performance. The median and interquartile range of the areas under the receiver operating characteristic curve (ROC AUC) and the precision recall curve (PR AUC) were 0.863 [0.857, 0.866] and 0.539 [0.526, 0.550], respectively. Optimizing the decision threshold lead to a sensitivity of 0.796 [0.775, 0.821] and a specificity of 0.784 [0.769, 0.805]. Good model calibration was achieved, showing only minor tendency to over-forecast probabilities above 0.6. The validity of the model was demonstrated by the interpretability analysis confirming existing evidence on major risk factors (e.g., higher age and weight, male gender, diabetes, cardiovascular disease, and chronic kidney disease). The analysis also revealed higher risk for African Americans and %22self-pay patients%22. To the best of our knowledge, this is the largest dataset based on EHR used to create a prognosis model for COVID-19. In contrast to large-scale statistics computing odds ratios for individual risk factors, the present model combining a rich set of covariates can provide accurate personalized predictions enabling early treatment to prevent patients from progressing to a severe or critical state.
has issue date	2020-07-27(xsd:dateTime)
bibo:doi	10.1101/2020.07.24.20155192
has license	medrxiv
sha1sum (hex)	50743502ca824f9e0df083321b6944aa7bb2cd76
schema:url	https://doi.org/10.1101/2020.07.24.20155192
resource representing a document's title	Predicting Critical State after COVID-19 Diagnosis Using Real-World Data from 20152 Confirmed US Cases
resource representing a document's body	covid:50743502ca824f9e0df083321b6944aa7bb2cd76#body_text
is schema:about of	named entity 'lead' named entity 'AUC' named entity 'demographics' named entity 'DIED' named entity 'RECEIVER' named entity 'AREAS' named entity 'CONFIRMED' named entity 'FOLLOWING' named entity '857' named entity '550' named entity 'PREDICTING' named entity 'ENTIRE' named entity 'STATE' named entity 'LABORATORY TEST RESULTS' named entity '769' named entity 'WORLDWIDE' named entity 'medical' named entity 'led' named entity 'pandemic' named entity 'confirmed' named entity 'With' named entity 'median' named entity 'electronic health records' named entity 'critical' named entity 'IBM' named entity 'stratified' named entity 'limited' named entity 'worldwide' named entity 'COVID-19' named entity 'electronic health records' named entity 'virus' named entity 'EHR' named entity 'AUC' named entity 'interquartile range' named entity 'comorbidities' named entity 'global COVID-19 pandemic' named entity 'confidence intervals' named entity 'ICD code' named entity 'probability' named entity 'multiple testing' named entity 'Louisiana' named entity 'COVID-19' named entity 'New Orleans' named entity 'healthcare professionals' named entity 'database' named entity 'comorbidities' named entity 'Georgia' named entity 'non-parametric' named entity 'medRxiv' named entity 'XGBoost' named entity 'CC-BY-NC-ND 4.0' named entity 'Health Insurance Portability and Accountability Act' named entity 'RWE' named entity 'COVID-19' named entity 'Simani' named entity 'LOINC' named entity 'state entries' named entity 'probability' named entity 'COVID-19' named entity 'IBM' named entity 'longitudinal data' named entity 'RWE' named entity 'triage' named entity 'SARS-CoV-2' named entity 'correlation' named entity 'Johns Hopkins University' named entity 'acute respiratory distress syndrome' named entity 'New York City' named entity 'blood volume' named entity 'COVID-19' named entity 'COVID-19 disease' named entity 'ICD codes' named entity 'COVID-19' named entity 'medical equipment' named entity 'cardiovascular disease' named entity 'probability' named entity 'clinical trials' named entity 'EHR' named entity 'medRxiv' named entity 'asthma' named entity 'prognosis' named entity 'ROC' named entity 'HIPAA' named entity 'diabetes'

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