Prediction of Patients with COVID-19 Requiring Intensive Care: A Cross-sectional Study Based on Machine-learning Approach from Iran.
COVID-19
Intensive care
Iran
Machine-learning
Prediction
Regression
Journal
Indian journal of critical care medicine : peer-reviewed, official publication of Indian Society of Critical Care Medicine
ISSN: 0972-5229
Titre abrégé: Indian J Crit Care Med
Pays: India
ID NLM: 101208863
Informations de publication
Date de publication:
Jun 2022
Jun 2022
Historique:
entrez:
15
7
2022
pubmed:
16
7
2022
medline:
16
7
2022
Statut:
ppublish
Résumé
Prioritizing the patients requiring intensive care may decrease the fatality of coronavirus disease-2019 (COVID-19). To develop, validate, and compare two models based on machine-learning methods for predicting patients with COVID-19 requiring intensive care. In 2021, 506 suspected COVID-19 patients, with clinical presentations along with radiographic findings, were laboratory confirmed and included in the study. The primary end-point was patients with COVID-19 requiring intensive care, defined as actual admission to the intensive care unit (ICU). The data were randomly partitioned into training and testing sets (70% and 30%, respectively) without overlapping. A decision-tree algorithm and multivariate logistic regression were performed to develop the models for predicting the cases based on their first 24 hours data. The predictive performance of the models was compared based on the area under the receiver operating characteristic curve (AUC), sensitivity, and accuracy of the models. A 10-fold cross-validation decision-tree model predicted cases requiring intensive care with the AUC, accuracy, and sensitivity of 97%, 98%, and 94.74%, respectively. The same values in the machine-learning logistic regression model were 75%, 85.62%, and 55.26%, respectively. Creatinine, smoking, neutrophil/lymphocyte ratio, temperature, respiratory rate, partial thromboplastin time, white blood cell, Glasgow Coma Scale (GCS), dizziness, international normalized ratio, O In an Iranian population, our decision-based machine-learning method offered an advantage over logistic regression for predicting patients requiring intensive care. This method can support clinicians in decision-making, using patients' early data, particularly in low- and middle-income countries where their resources are as limited as Iran. Sabetian G, Azimi A, Kazemi A, Hoseini B, Asmarian N, Khaloo V, This study was approved by the Ethical Committee of Shiraz University of Medical Sciences (IR.SUMS.REC.1399.018).
Sections du résumé
Background
UNASSIGNED
Prioritizing the patients requiring intensive care may decrease the fatality of coronavirus disease-2019 (COVID-19).
Aims and objectives
UNASSIGNED
To develop, validate, and compare two models based on machine-learning methods for predicting patients with COVID-19 requiring intensive care.
Materials and methods
UNASSIGNED
In 2021, 506 suspected COVID-19 patients, with clinical presentations along with radiographic findings, were laboratory confirmed and included in the study. The primary end-point was patients with COVID-19 requiring intensive care, defined as actual admission to the intensive care unit (ICU). The data were randomly partitioned into training and testing sets (70% and 30%, respectively) without overlapping. A decision-tree algorithm and multivariate logistic regression were performed to develop the models for predicting the cases based on their first 24 hours data. The predictive performance of the models was compared based on the area under the receiver operating characteristic curve (AUC), sensitivity, and accuracy of the models.
Results
UNASSIGNED
A 10-fold cross-validation decision-tree model predicted cases requiring intensive care with the AUC, accuracy, and sensitivity of 97%, 98%, and 94.74%, respectively. The same values in the machine-learning logistic regression model were 75%, 85.62%, and 55.26%, respectively. Creatinine, smoking, neutrophil/lymphocyte ratio, temperature, respiratory rate, partial thromboplastin time, white blood cell, Glasgow Coma Scale (GCS), dizziness, international normalized ratio, O
Conclusion
UNASSIGNED
In an Iranian population, our decision-based machine-learning method offered an advantage over logistic regression for predicting patients requiring intensive care. This method can support clinicians in decision-making, using patients' early data, particularly in low- and middle-income countries where their resources are as limited as Iran.
How to cite this article
UNASSIGNED
Sabetian G, Azimi A, Kazemi A, Hoseini B, Asmarian N, Khaloo V,
Ethics approval
UNASSIGNED
This study was approved by the Ethical Committee of Shiraz University of Medical Sciences (IR.SUMS.REC.1399.018).
Identifiants
pubmed: 35836646
doi: 10.5005/jp-journals-10071-24226
pmc: PMC9237161
doi:
Types de publication
Journal Article
Langues
eng
Pagination
688-695Informations de copyright
Copyright © 2022; The Author(s).
Déclaration de conflit d'intérêts
Source of support: Nil Conflict of interest: None
Références
Am Heart J. 2010 Aug;160(2):308-14
pubmed: 20691837
PLoS One. 2020 Oct 19;15(10):e0240711
pubmed: 33075088
Lancet. 2020 Mar 28;395(10229):1054-1062
pubmed: 32171076
Int J Infect Dis. 2020 Jul;96:131-135
pubmed: 32376308
Exp Clin Transplant. 2019 Dec;17(6):775-783
pubmed: 30968757
J Clin Med. 2020 Jun 01;9(6):
pubmed: 32492874
Epidemiol Infect. 2020 Aug 12;148:e175
pubmed: 32782035
BMC Pediatr. 2022 Apr 12;22(1):199
pubmed: 35413854
Jpn J Infect Dis. 2021 Sep 22;74(5):458-464
pubmed: 33642427
Diagnosis (Berl). 2020 May 26;7(2):91-96
pubmed: 32352401
BMC Emerg Med. 2021 Jun 10;21(1):68
pubmed: 34112088
Biomed Res Int. 2022 Apr 25;2022:3964063
pubmed: 35509709
J Med Virol. 2020 Oct;92(10):1733-1734
pubmed: 32242950
BMC Public Health. 2018 May 2;18(1):574
pubmed: 29716568
Sci Rep. 2020 Feb 20;10(1):3118
pubmed: 32080330
BMC Infect Dis. 2021 Jul 7;21(1):656
pubmed: 34233638
N Engl J Med. 2020 Jun 11;382(24):2372-2374
pubmed: 32302078
Lancet Infect Dis. 2020 Jun;20(6):669-677
pubmed: 32240634
Clin Appl Thromb Hemost. 2019 Jan-Dec;25:1076029619887437
pubmed: 31775524
Health Care Manag Sci. 2013 Jun;16(2):119-28
pubmed: 23132123
J Intensive Care. 2021 Jan 29;9(1):16
pubmed: 33514443
Adv Exp Med Biol. 2021;1327:3-22
pubmed: 34279825
Microsc Res Tech. 2021 Jul;84(7):1462-1474
pubmed: 33522669
BMC Public Health. 2021 Jun 7;21(1):1087
pubmed: 34098928
Chest. 2013 Jan;143(1):196-206
pubmed: 23276842
Aging Dis. 2020 May 13;11(4):874-894
pubmed: 32765952
J Med Internet Res. 2020 Jun 30;22(6):e19636
pubmed: 32544071
JAMA. 2020 May 12;323(18):1843-1844
pubmed: 32159775
Clin J Am Soc Nephrol. 2020 Nov 6;15(11):1549-1556
pubmed: 32943396
Front Public Health. 2021 Jul 19;9:711762
pubmed: 34350154
Biometrics. 1988 Sep;44(3):837-45
pubmed: 3203132
Am J Respir Crit Care Med. 2020 Sep 15;202(6):812-821
pubmed: 32584597
Ear Nose Throat J. 2021 Jan;100(1):29-30
pubmed: 32931322
Acad Radiol. 2020 Dec;27(12):1665-1678
pubmed: 33046370