Machine learning methods to predict mechanical ventilation and mortality in patients with COVID-19.
Aged
COVID-19
/ mortality
Emergency Service, Hospital
/ trends
Female
Hospital Mortality
/ trends
Humans
Machine Learning
Male
Middle Aged
Pandemics
/ statistics & numerical data
Respiration, Artificial
/ statistics & numerical data
Retrospective Studies
Ventilators, Mechanical
/ statistics & numerical data
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2021
2021
Historique:
received:
23
11
2020
accepted:
15
03
2021
entrez:
1
4
2021
pubmed:
2
4
2021
medline:
14
4
2021
Statut:
epublish
Résumé
The Coronavirus disease 2019 (COVID-19) pandemic has affected millions of people across the globe. It is associated with a high mortality rate and has created a global crisis by straining medical resources worldwide. To develop and validate machine-learning models for prediction of mechanical ventilation (MV) for patients presenting to emergency room and for prediction of in-hospital mortality once a patient is admitted. Two cohorts were used for the two different aims. 1980 COVID-19 patients were enrolled for the aim of prediction ofMV. 1036 patients' data, including demographics, past smoking and drinking history, past medical history and vital signs at emergency room (ER), laboratory values, and treatments were collected for training and 674 patients were enrolled for validation using XGBoost algorithm. For the second aim to predict in-hospital mortality, 3491 hospitalized patients via ER were enrolled. CatBoost, a new gradient-boosting algorithm was applied for training and validation of the cohort. Older age, higher temperature, increased respiratory rate (RR) and a lower oxygen saturation (SpO2) from the first set of vital signs were associated with an increased risk of MV amongst the 1980 patients in the ER. The model had a high accuracy of 86.2% and a negative predictive value (NPV) of 87.8%. While, patients who required MV, had a higher RR, Body mass index (BMI) and longer length of stay in the hospital were the major features associated with in-hospital mortality. The second model had a high accuracy of 80% with NPV of 81.6%. Machine learning models using XGBoost and catBoost algorithms can predict need for mechanical ventilation and mortality with a very high accuracy in COVID-19 patients.
Sections du résumé
BACKGROUND
The Coronavirus disease 2019 (COVID-19) pandemic has affected millions of people across the globe. It is associated with a high mortality rate and has created a global crisis by straining medical resources worldwide.
OBJECTIVES
To develop and validate machine-learning models for prediction of mechanical ventilation (MV) for patients presenting to emergency room and for prediction of in-hospital mortality once a patient is admitted.
METHODS
Two cohorts were used for the two different aims. 1980 COVID-19 patients were enrolled for the aim of prediction ofMV. 1036 patients' data, including demographics, past smoking and drinking history, past medical history and vital signs at emergency room (ER), laboratory values, and treatments were collected for training and 674 patients were enrolled for validation using XGBoost algorithm. For the second aim to predict in-hospital mortality, 3491 hospitalized patients via ER were enrolled. CatBoost, a new gradient-boosting algorithm was applied for training and validation of the cohort.
RESULTS
Older age, higher temperature, increased respiratory rate (RR) and a lower oxygen saturation (SpO2) from the first set of vital signs were associated with an increased risk of MV amongst the 1980 patients in the ER. The model had a high accuracy of 86.2% and a negative predictive value (NPV) of 87.8%. While, patients who required MV, had a higher RR, Body mass index (BMI) and longer length of stay in the hospital were the major features associated with in-hospital mortality. The second model had a high accuracy of 80% with NPV of 81.6%.
CONCLUSION
Machine learning models using XGBoost and catBoost algorithms can predict need for mechanical ventilation and mortality with a very high accuracy in COVID-19 patients.
Identifiants
pubmed: 33793600
doi: 10.1371/journal.pone.0249285
pii: PONE-D-20-36839
pmc: PMC8016242
doi:
Types de publication
Journal Article
Multicenter Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0249285Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
JAMA. 2020 Apr 7;323(13):1239-1242
pubmed: 32091533
J Gen Intern Med. 2020 Aug;35(8):2516-2517
pubmed: 32519326
J Crit Care. 2021 Apr;62:25-30
pubmed: 33238219
JAMA. 2020 Mar 17;323(11):1061-1069
pubmed: 32031570
Lancet Infect Dis. 2020 Jul;20(7):773
pubmed: 32171390
J Thromb Haemost. 2020 Apr;18(4):844-847
pubmed: 32073213
PLoS One. 2020 Mar 3;15(3):e0229331
pubmed: 32126097
BMJ. 2020 May 22;369:m1966
pubmed: 32444366
J Clin Med. 2020 Jun 01;9(6):
pubmed: 32492874
Eur Respir J. 2020 Aug 20;56(2):
pubmed: 32616597
Am J Trop Med Hyg. 2020 Aug;103(2):605-608
pubmed: 32597389
medRxiv. 2020 May 22;:
pubmed: 32511520
Lancet. 2020 Mar 28;395(10229):1054-1062
pubmed: 32171076
Clin Infect Dis. 2020 Jul 28;71(15):769-777
pubmed: 32176772
JAMA. 2020 May 26;323(20):2052-2059
pubmed: 32320003