About: Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong

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

About: Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong 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
title	Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong
Creator	Cao, Zhidong Liu, Tong Cheung, Zhang, Qingpeng Tse, Gary Wong, Kei Cheung, Yung Chi, Ian Dajun, Daniel Frcpath, Wu Kk, William Lee, Sharen Man, Bernard Man, Yung Phd, Zeng Zhang Phd, Qingpeng Zhou, Jiandong
source	MedRxiv
abstract	Background: The coronavirus disease 2019 (COVID-19) has become a pandemic, placing significant burdens on the healthcare systems. In this study, we tested the hypothesis that a machine learning approach incorporating hidden nonlinear interactions can improve prediction for Intensive care unit (ICU) admission. Methods: Consecutive patients admitted to public hospitals between 1st January and 24th May 2020 in Hong Kong with COVID-19 diagnosed by RT-PCR were included. The primary endpoint was ICU admission. Results: This study included 1043 patients (median age 35 (IQR: 32-37; 54% male). Nineteen patients were admitted to ICU (median hospital length of stay (LOS): 30 days, median ICU LOS: 16 days). ICU patients were more likely to be prescribed angiotensin converting enzyme inhibitors/angiotensin receptor blockers, anti-retroviral drugs lopinavir/ritonavir and remdesivir, ribavirin, steroids, interferon-beta and hydroxychloroquine. Significant predictors of ICU admission were older age, male sex, prior coronary artery disease, respiratory diseases, diabetes, hypertension and chronic kidney disease, and activated partial thromboplastin time, red cell count, white cell count, albumin and serum sodium. A tree-based machine learning model identified most informative characteristics and hidden interactions that can predict ICU admission. These were: low red cells with 1) male, 2) older age, 3) low albumin, 4) low sodium or 5) prolonged APTT. A five-fold cross validation confirms superior performance of this model over baseline models including XGBoost, LightGBM, random forests, and multivariate logistic regression. Conclusions: A machine learning model including baseline risk factors and their hidden interactions can accurately predict ICU admission in COVID-19.
has issue date	2020-07-02(xsd:dateTime)
bibo:doi	10.1101/2020.06.30.20143651
has license	medrxiv
sha1sum (hex)	13fe1c87c57eac57291ce04002f923cccd7514ab
schema:url	https://doi.org/10.1101/2020.06.30.20143651
resource representing a document's title	Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong
resource representing a document's body	covid:13fe1c87c57eac57291ce04002f923cccd7514ab#body_text
is schema:about of	named entity 'prediction' named entity 'risk factors' named entity 'patients' named entity 'APPROACH' named entity 'CORONAVIRUS DISEASE 2019' named entity 'PREDICTION' named entity 'NONLINEAR' named entity 'SIGNIFICANT' named entity 'pandemic' named entity 'hypothesis' named entity 'nonlinear' named entity 'ICU' named entity 'Hong Kong' named entity 'retrospective cohort study' named entity 'XGBoost' named entity 'ACEI' named entity 'CC-BY 4.0 International license' named entity 'remdesivir' named entity 'APTT' named entity 'APTT' named entity 'COVID' named entity 'cerebrovascular disease' named entity 'interferon-beta' named entity 'logistic regression' named entity 'EBM' named entity 'comorbidities' named entity 'ribavirin' named entity 'probability' named entity 'serum sodium' named entity 'COVID' named entity 'Kaletra' named entity 'overfitting' named entity 'Hong Kong Island' named entity 'carrying capacity' named entity 'ICU' named entity 'MERS' named entity 'respiratory diseases' named entity 'anti-viral drug' named entity 'COVID' named entity 'interferon-beta' named entity 'remdesivir' named entity 'comorbidities' named entity 'Univariate' named entity 'ACEI' named entity 'univariate' named entity 'Canadian' named entity 'hepatitis' named entity 'medRxiv' named entity 'ICU' named entity 'hypertension' named entity 'logistic regression' named entity 'hypertension' named entity 'respiratory diseases' named entity 'ICU' named entity 'statistically significant' named entity 'CC-BY 4.0 International license' named entity 'antibodies' named entity 'cardiovascular disease' named entity 'medRxiv' named entity 'EBM' named entity 'Kowloon District' named entity 'triglycerides' named entity 'red blood cells' named entity 'ICU' named entity 'hydroxychloroquine' named entity 'interaction effects' named entity 'Kaletra' named entity 'ICU' named entity 'simple model'

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 © 2009-2025 OpenLink Software