tetano
Editor, Senior Moderator
J Med Virol
. 2021 Feb 18.
doi: 10.1002/jmv.26890. Online ahead of print.
Two novel nomograms for predicting the risk of hospitalization or mortality due to COVID-19 by na?ve Bayesian classifier method
Eda Karaismailoglu[SUP] 1 [/SUP], Serkan Karaismailoglu[SUP] 2 [/SUP]
Affiliations
Abstract
Background: Coronavirus disease 2019 (COVID-19) has become a global pandemic that has affected millions of people worldwide. The presence of multiple risk factors for COVID-19 makes it difficult to plan treatment and optimize the use of medical resources.
Aim: The aim of this study is to determine potential risk factors for hospitalization or mortality in patients with COVID-19 via two novel naive Bayesian nomograms.
Materials and methods: The publicly available COVID-19 National data published by the Mexican Ministry of Health through the "Direcci?n General de Epidemiolog?a" website was analyzed. Univariable logistic regression was utilized to identify potential risk factors may affect hospitalization or mortality in patients with COVID-19. Na?ve Bayesian classifier method was implemented to predict nomograms. The nomograms were verified by area under the Receiver operating characteristic curve (AUC), classification accuracy (CA), F1 score, precision, recall, and calibration plot.
Results: A total of 979,430 patients (45.3 ? 15.9 years old, and 51.1% male) tested positive for COVID-19 from 1[SUP]st[/SUP] January to 22[SUP]nd[/SUP] November 2020. Among them, 22.3% of the patients were required hospitalization and 99,964 patients (9.8%) were dead. The most important risk factors to predict the probability of hospitalization and mortality were pneumonia, age, chronic kidney failure, chronic obstructive respiratory disease, and diabetes. The performance measures demonstrated good discrimination and calibration (hospitalization: AUC=0.896, CA=0.880; mortality: AUC=0.903, CA=0.899).
Conclusion: Two novel nomograms to estimate the risk of hospitalization and mortality were proposed, which could be used to facilitate individualized decision making for patients newly diagnosed with COVID-19. This article is protected by copyright. All rights reserved.
Keywords: COVID-19; hospitalization; mortality; nomogram; prediction; risk factor.
. 2021 Feb 18.
doi: 10.1002/jmv.26890. Online ahead of print.
Two novel nomograms for predicting the risk of hospitalization or mortality due to COVID-19 by na?ve Bayesian classifier method
Eda Karaismailoglu[SUP] 1 [/SUP], Serkan Karaismailoglu[SUP] 2 [/SUP]
Affiliations
- PMID: 33599308
- DOI: 10.1002/jmv.26890
Abstract
Background: Coronavirus disease 2019 (COVID-19) has become a global pandemic that has affected millions of people worldwide. The presence of multiple risk factors for COVID-19 makes it difficult to plan treatment and optimize the use of medical resources.
Aim: The aim of this study is to determine potential risk factors for hospitalization or mortality in patients with COVID-19 via two novel naive Bayesian nomograms.
Materials and methods: The publicly available COVID-19 National data published by the Mexican Ministry of Health through the "Direcci?n General de Epidemiolog?a" website was analyzed. Univariable logistic regression was utilized to identify potential risk factors may affect hospitalization or mortality in patients with COVID-19. Na?ve Bayesian classifier method was implemented to predict nomograms. The nomograms were verified by area under the Receiver operating characteristic curve (AUC), classification accuracy (CA), F1 score, precision, recall, and calibration plot.
Results: A total of 979,430 patients (45.3 ? 15.9 years old, and 51.1% male) tested positive for COVID-19 from 1[SUP]st[/SUP] January to 22[SUP]nd[/SUP] November 2020. Among them, 22.3% of the patients were required hospitalization and 99,964 patients (9.8%) were dead. The most important risk factors to predict the probability of hospitalization and mortality were pneumonia, age, chronic kidney failure, chronic obstructive respiratory disease, and diabetes. The performance measures demonstrated good discrimination and calibration (hospitalization: AUC=0.896, CA=0.880; mortality: AUC=0.903, CA=0.899).
Conclusion: Two novel nomograms to estimate the risk of hospitalization and mortality were proposed, which could be used to facilitate individualized decision making for patients newly diagnosed with COVID-19. This article is protected by copyright. All rights reserved.
Keywords: COVID-19; hospitalization; mortality; nomogram; prediction; risk factor.