A Machine Learning Approach for Mortality Prediction in COVID-19 Pneumonia: Development and Evaluation of the Piacenza Score.
COVID-19
artificial intelligence
machine learning
modeling
mortality
pneumonia
prediction
prognostic score
Journal
Journal of medical Internet research
ISSN: 1438-8871
Titre abrégé: J Med Internet Res
Pays: Canada
ID NLM: 100959882
Informations de publication
Date de publication:
31 05 2021
31 05 2021
Historique:
received:
29
03
2021
accepted:
16
05
2021
revised:
15
05
2021
pubmed:
18
5
2021
medline:
12
6
2021
entrez:
17
5
2021
Statut:
epublish
Résumé
Several models have been developed to predict mortality in patients with COVID-19 pneumonia, but only a few have demonstrated enough discriminatory capacity. Machine learning algorithms represent a novel approach for the data-driven prediction of clinical outcomes with advantages over statistical modeling. We aimed to develop a machine learning-based score-the Piacenza score-for 30-day mortality prediction in patients with COVID-19 pneumonia. The study comprised 852 patients with COVID-19 pneumonia, admitted to the Guglielmo da Saliceto Hospital in Italy from February to November 2020. Patients' medical history, demographics, and clinical data were collected using an electronic health record. The overall patient data set was randomly split into derivation and test cohorts. The score was obtained through the naïve Bayes classifier and externally validated on 86 patients admitted to Centro Cardiologico Monzino (Italy) in February 2020. Using a forward-search algorithm, 6 features were identified: age, mean corpuscular hemoglobin concentration, PaO The Piacenza score exhibited an area under the receiver operating characteristic curve (AUC) of 0.78 (95% CI 0.74-0.84, Brier score=0.19) in the internal validation cohort and 0.79 (95% CI 0.68-0.89, Brier score=0.16) in the external validation cohort, showing a comparable accuracy with respect to the 4C score and to the naïve Bayes model with a priori chosen features; this achieved an AUC of 0.78 (95% CI 0.73-0.83, Brier score=0.26) and 0.80 (95% CI 0.75-0.86, Brier score=0.17), respectively. Our findings demonstrated that a customizable machine learning-based score with a purely data-driven selection of features is feasible and effective for the prediction of mortality among patients with COVID-19 pneumonia.
Sections du résumé
BACKGROUND
Several models have been developed to predict mortality in patients with COVID-19 pneumonia, but only a few have demonstrated enough discriminatory capacity. Machine learning algorithms represent a novel approach for the data-driven prediction of clinical outcomes with advantages over statistical modeling.
OBJECTIVE
We aimed to develop a machine learning-based score-the Piacenza score-for 30-day mortality prediction in patients with COVID-19 pneumonia.
METHODS
The study comprised 852 patients with COVID-19 pneumonia, admitted to the Guglielmo da Saliceto Hospital in Italy from February to November 2020. Patients' medical history, demographics, and clinical data were collected using an electronic health record. The overall patient data set was randomly split into derivation and test cohorts. The score was obtained through the naïve Bayes classifier and externally validated on 86 patients admitted to Centro Cardiologico Monzino (Italy) in February 2020. Using a forward-search algorithm, 6 features were identified: age, mean corpuscular hemoglobin concentration, PaO
RESULTS
The Piacenza score exhibited an area under the receiver operating characteristic curve (AUC) of 0.78 (95% CI 0.74-0.84, Brier score=0.19) in the internal validation cohort and 0.79 (95% CI 0.68-0.89, Brier score=0.16) in the external validation cohort, showing a comparable accuracy with respect to the 4C score and to the naïve Bayes model with a priori chosen features; this achieved an AUC of 0.78 (95% CI 0.73-0.83, Brier score=0.26) and 0.80 (95% CI 0.75-0.86, Brier score=0.17), respectively.
CONCLUSIONS
Our findings demonstrated that a customizable machine learning-based score with a purely data-driven selection of features is feasible and effective for the prediction of mortality among patients with COVID-19 pneumonia.
Identifiants
pubmed: 33999838
pii: v23i5e29058
doi: 10.2196/29058
pmc: PMC8168638
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e29058Informations de copyright
©Geza Halasz, Michela Sperti, Matteo Villani, Umberto Michelucci, Piergiuseppe Agostoni, Andrea Biagi, Luca Rossi, Andrea Botti, Chiara Mari, Marco Maccarini, Filippo Pura, Loris Roveda, Alessia Nardecchia, Emanuele Mottola, Massimo Nolli, Elisabetta Salvioni, Massimo Mapelli, Marco Agostino Deriu, Dario Piga, Massimo Piepoli. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 31.05.2021.
Références
JAMA. 2020 Aug 25;324(8):782-793
pubmed: 32648899
Clin Chem Lab Med. 2020 Jun 25;58(7):1131-1134
pubmed: 32119647
Lancet. 2021 Jan 16;397(10270):199-207
pubmed: 33453782
NPJ Digit Med. 2021 Feb 4;4(1):15
pubmed: 33542473
J Med Virol. 2020 Nov;92(11):2718-2724
pubmed: 32515500
BMJ. 2020 Apr 7;369:m1328
pubmed: 32265220
Acad Emerg Med. 2016 Mar;23(3):269-78
pubmed: 26679719
Life Sci. 2020 Aug 1;254:117788
pubmed: 32475810
Diabetes Metab Syndr. 2020 Jul - Aug;14(4):337-339
pubmed: 32305024
Engineering (Beijing). 2020 Nov 28;:
pubmed: 33282444
Sensors (Basel). 2021 Jan 24;21(3):
pubmed: 33498892
Circulation. 2006 Mar 21;113(11):1424-33
pubmed: 16534009
J Am Heart Assoc. 2018 Oct 16;7(20):e009594
pubmed: 30371285
BMJ. 2020 Sep 9;370:m3339
pubmed: 32907855
J Med Internet Res. 2021 May 31;23(5):e29058
pubmed: 33999838
N Engl J Med. 2020 Apr 30;382(18):1708-1720
pubmed: 32109013
Lancet. 2020 Mar 28;395(10229):1054-1062
pubmed: 32171076
Stat Med. 2015 Sep 20;34(21):2941-57
pubmed: 25980520
PLoS One. 2020 Nov 12;15(11):e0239172
pubmed: 33180787
Eur Respir J. 2020 Aug 27;56(2):
pubmed: 32366491
J Med Internet Res. 2020 Oct 6;22(10):e21439
pubmed: 32976111
Lancet Digit Health. 2020 Oct;2(10):e516-e525
pubmed: 32984797