Classification and analysis of outcome predictors in non-critically ill COVID-19 patients.
COVID-19
machine learning
non-critically ill
prediction
Journal
Internal medicine journal
ISSN: 1445-5994
Titre abrégé: Intern Med J
Pays: Australia
ID NLM: 101092952
Informations de publication
Date de publication:
04 2021
04 2021
Historique:
revised:
16
11
2020
received:
26
08
2020
accepted:
16
11
2020
pubmed:
10
4
2021
medline:
29
4
2021
entrez:
9
4
2021
Statut:
ppublish
Résumé
Early detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected patients who could develop a severe form of COVID-19 must be considered of great importance to carry out adequate care and optimise the use of limited resources. To use several machine learning classification models to analyse a series of non-critically ill COVID-19 patients admitted to a general medicine ward to verify if any clinical variables recorded could predict the clinical outcome. We retrospectively analysed non-critically ill patients with COVID-19 admitted to the general ward of the hospital in Pordenone from 1 March 2020 to 30 April 2020. Patients' characteristics were compared based on clinical outcomes. Through several machine learning classification models, some predictors for clinical outcome were detected. In the considered period, we analysed 176 consecutive patients admitted: 119 (67.6%) were discharged, 35 (19.9%) dead and 22 (12.5%) were transferred to intensive care unit. The most accurate models were a random forest model (M2) and a conditional inference tree model (M5) (accuracy = 0.79; 95% confidence interval 0.64-0.90, for both). For M2, glomerular filtration rate and creatinine were the most accurate predictors for the outcome, followed by age and fraction-inspired oxygen. For M5, serum sodium, body temperature and arterial pressure of oxygen and inspiratory fraction of oxygen ratio were the most reliable predictors. In non-critically ill COVID-19 patients admitted to a medical ward, glomerular filtration rate, creatinine and serum sodium were promising predictors for the clinical outcome. Some factors not determined by COVID-19, such as age or dementia, influence clinical outcomes.
Sections du résumé
BACKGROUND
Early detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected patients who could develop a severe form of COVID-19 must be considered of great importance to carry out adequate care and optimise the use of limited resources.
AIMS
To use several machine learning classification models to analyse a series of non-critically ill COVID-19 patients admitted to a general medicine ward to verify if any clinical variables recorded could predict the clinical outcome.
METHODS
We retrospectively analysed non-critically ill patients with COVID-19 admitted to the general ward of the hospital in Pordenone from 1 March 2020 to 30 April 2020. Patients' characteristics were compared based on clinical outcomes. Through several machine learning classification models, some predictors for clinical outcome were detected.
RESULTS
In the considered period, we analysed 176 consecutive patients admitted: 119 (67.6%) were discharged, 35 (19.9%) dead and 22 (12.5%) were transferred to intensive care unit. The most accurate models were a random forest model (M2) and a conditional inference tree model (M5) (accuracy = 0.79; 95% confidence interval 0.64-0.90, for both). For M2, glomerular filtration rate and creatinine were the most accurate predictors for the outcome, followed by age and fraction-inspired oxygen. For M5, serum sodium, body temperature and arterial pressure of oxygen and inspiratory fraction of oxygen ratio were the most reliable predictors.
CONCLUSIONS
In non-critically ill COVID-19 patients admitted to a medical ward, glomerular filtration rate, creatinine and serum sodium were promising predictors for the clinical outcome. Some factors not determined by COVID-19, such as age or dementia, influence clinical outcomes.
Identifiants
pubmed: 33835685
doi: 10.1111/imj.15140
pmc: PMC8250466
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
506-514Informations de copyright
© 2021 Royal Australasian College of Physicians.
Références
JAMA Netw Open. 2020 Jun 1;3(6):e2012270
pubmed: 32543702
JAMA. 2020 Mar 17;323(11):1061-1069
pubmed: 32031570
Lancet. 2020 Mar 28;395(10229):1054-1062
pubmed: 32171076
QJM. 2020 Nov 1;113(11):789-793
pubmed: 32652021
J Alzheimers Dis. 2020;76(2):475-479
pubmed: 32651326
Neurol Sci. 2020 Sep;41(9):2317-2324
pubmed: 32643133
Curr Opin Anaesthesiol. 2019 Apr;32(2):190-194
pubmed: 30817394
J Clin Med. 2020 Apr 24;9(4):
pubmed: 32344679
Virol J. 2020 Jul 8;17(1):96
pubmed: 32641059
Heart Lung. 2020 Nov-Dec;49(6):848-852
pubmed: 32593418
Am J Respir Crit Care Med. 2020 Jun 1;201(11):1372-1379
pubmed: 32242738
Med Clin (Barc). 2020 Oct 9;155(7):314-315
pubmed: 32651070
Acad Emerg Med. 2020 Jul;27(7):612-613
pubmed: 32506683
Acta Biomed. 2020 May 11;91(2):113-117
pubmed: 32420935
Intensive Care Med. 2020 Apr;46(4):576-578
pubmed: 32077996
N Engl J Med. 2020 Feb 20;382(8):727-733
pubmed: 31978945
J Hosp Infect. 2020 Sep;106(1):134-154
pubmed: 32652215
Eur Respir J. 2020 Jun 4;55(6):
pubmed: 32269086
Acta Biomed. 2020 May 11;91(2):106-112
pubmed: 32420934
Clin Microbiol Infect. 2020 Aug;26(8):1063-1068
pubmed: 32251842
Crit Care. 2020 Apr 30;24(1):188
pubmed: 32354360
J Nephrol. 2020 Aug;33(4):737-745
pubmed: 32602006
BMJ. 2020 Mar 26;368:m1091
pubmed: 32217556
Med Intensiva (Engl Ed). 2021 Jan-Feb;45(1):42-55
pubmed: 32646669
J Gerontol A Biol Sci Med Sci. 2020 Sep 16;75(9):1788-1795
pubmed: 32279081