Clinical Predictive Models for COVID-19: Systematic Study
BackgroundCOVID-19 is a rapidly emerging respiratory disease caused by SARS-CoV-2. Due to the rapid human-to-human transmission of SARS-CoV-2, many health care systems are at risk of exceeding their health care capacities, in particular in terms of SARS-CoV-2 tests, hospital...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
JMIR Publications
2020-10-01
|
Series: | Journal of Medical Internet Research |
Online Access: | http://www.jmir.org/2020/10/e21439/ |
id |
doaj-dd89d7109dd5467ab182577e0c09c22a |
---|---|
record_format |
Article |
spelling |
doaj-dd89d7109dd5467ab182577e0c09c22a2021-04-02T18:55:51ZengJMIR PublicationsJournal of Medical Internet Research1438-88712020-10-012210e2143910.2196/21439Clinical Predictive Models for COVID-19: Systematic StudySchwab, PatrickDuMont Schütte, AugustDietz, BenediktBauer, Stefan BackgroundCOVID-19 is a rapidly emerging respiratory disease caused by SARS-CoV-2. Due to the rapid human-to-human transmission of SARS-CoV-2, many health care systems are at risk of exceeding their health care capacities, in particular in terms of SARS-CoV-2 tests, hospital and intensive care unit (ICU) beds, and mechanical ventilators. Predictive algorithms could potentially ease the strain on health care systems by identifying those who are most likely to receive a positive SARS-CoV-2 test, be hospitalized, or admitted to the ICU. ObjectiveThe aim of this study is to develop, study, and evaluate clinical predictive models that estimate, using machine learning and based on routinely collected clinical data, which patients are likely to receive a positive SARS-CoV-2 test or require hospitalization or intensive care. MethodsUsing a systematic approach to model development and optimization, we trained and compared various types of machine learning models, including logistic regression, neural networks, support vector machines, random forests, and gradient boosting. To evaluate the developed models, we performed a retrospective evaluation on demographic, clinical, and blood analysis data from a cohort of 5644 patients. In addition, we determined which clinical features were predictive to what degree for each of the aforementioned clinical tasks using causal explanations. ResultsOur experimental results indicate that our predictive models identified patients that test positive for SARS-CoV-2 a priori at a sensitivity of 75% (95% CI 67%-81%) and a specificity of 49% (95% CI 46%-51%), patients who are SARS-CoV-2 positive that require hospitalization with 0.92 area under the receiver operator characteristic curve (AUC; 95% CI 0.81-0.98), and patients who are SARS-CoV-2 positive that require critical care with 0.98 AUC (95% CI 0.95-1.00). ConclusionsOur results indicate that predictive models trained on routinely collected clinical data could be used to predict clinical pathways for COVID-19 and, therefore, help inform care and prioritize resources.http://www.jmir.org/2020/10/e21439/ |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Schwab, Patrick DuMont Schütte, August Dietz, Benedikt Bauer, Stefan |
spellingShingle |
Schwab, Patrick DuMont Schütte, August Dietz, Benedikt Bauer, Stefan Clinical Predictive Models for COVID-19: Systematic Study Journal of Medical Internet Research |
author_facet |
Schwab, Patrick DuMont Schütte, August Dietz, Benedikt Bauer, Stefan |
author_sort |
Schwab, Patrick |
title |
Clinical Predictive Models for COVID-19: Systematic Study |
title_short |
Clinical Predictive Models for COVID-19: Systematic Study |
title_full |
Clinical Predictive Models for COVID-19: Systematic Study |
title_fullStr |
Clinical Predictive Models for COVID-19: Systematic Study |
title_full_unstemmed |
Clinical Predictive Models for COVID-19: Systematic Study |
title_sort |
clinical predictive models for covid-19: systematic study |
publisher |
JMIR Publications |
series |
Journal of Medical Internet Research |
issn |
1438-8871 |
publishDate |
2020-10-01 |
description |
BackgroundCOVID-19 is a rapidly emerging respiratory disease caused by SARS-CoV-2. Due to the rapid human-to-human transmission of SARS-CoV-2, many health care systems are at risk of exceeding their health care capacities, in particular in terms of SARS-CoV-2 tests, hospital and intensive care unit (ICU) beds, and mechanical ventilators. Predictive algorithms could potentially ease the strain on health care systems by identifying those who are most likely to receive a positive SARS-CoV-2 test, be hospitalized, or admitted to the ICU.
ObjectiveThe aim of this study is to develop, study, and evaluate clinical predictive models that estimate, using machine learning and based on routinely collected clinical data, which patients are likely to receive a positive SARS-CoV-2 test or require hospitalization or intensive care.
MethodsUsing a systematic approach to model development and optimization, we trained and compared various types of machine learning models, including logistic regression, neural networks, support vector machines, random forests, and gradient boosting. To evaluate the developed models, we performed a retrospective evaluation on demographic, clinical, and blood analysis data from a cohort of 5644 patients. In addition, we determined which clinical features were predictive to what degree for each of the aforementioned clinical tasks using causal explanations.
ResultsOur experimental results indicate that our predictive models identified patients that test positive for SARS-CoV-2 a priori at a sensitivity of 75% (95% CI 67%-81%) and a specificity of 49% (95% CI 46%-51%), patients who are SARS-CoV-2 positive that require hospitalization with 0.92 area under the receiver operator characteristic curve (AUC; 95% CI 0.81-0.98), and patients who are SARS-CoV-2 positive that require critical care with 0.98 AUC (95% CI 0.95-1.00).
ConclusionsOur results indicate that predictive models trained on routinely collected clinical data could be used to predict clinical pathways for COVID-19 and, therefore, help inform care and prioritize resources. |
url |
http://www.jmir.org/2020/10/e21439/ |
work_keys_str_mv |
AT schwabpatrick clinicalpredictivemodelsforcovid19systematicstudy AT dumontschutteaugust clinicalpredictivemodelsforcovid19systematicstudy AT dietzbenedikt clinicalpredictivemodelsforcovid19systematicstudy AT bauerstefan clinicalpredictivemodelsforcovid19systematicstudy |
_version_ |
1721550556836659200 |