Development and validation of a model for individualized prediction of hospitalization risk in 4,536 patients with COVID-19.
Adult
Aged
Betacoronavirus
/ genetics
COVID-19
Clinical Decision-Making
Coronavirus Infections
/ physiopathology
Disease Progression
Female
Forecasting
/ methods
Hospitalization
/ trends
Humans
Male
Middle Aged
Models, Statistical
Nomograms
Pandemics
Pneumonia, Viral
/ physiopathology
Prognosis
Retrospective Studies
Reverse Transcriptase Polymerase Chain Reaction
Risk Factors
SARS-CoV-2
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2020
2020
Historique:
received:
24
04
2020
accepted:
27
07
2020
entrez:
12
8
2020
pubmed:
12
8
2020
medline:
29
8
2020
Statut:
epublish
Résumé
Coronavirus Disease 2019 is a pandemic that is straining healthcare resources, mainly hospital beds. Multiple risk factors of disease progression requiring hospitalization have been identified, but medical decision-making remains complex. To characterize a large cohort of patients hospitalized with COVID-19, their outcomes, develop and validate a statistical model that allows individualized prediction of future hospitalization risk for a patient newly diagnosed with COVID-19. Retrospective cohort study of patients with COVID-19 applying a least absolute shrinkage and selection operator (LASSO) logistic regression algorithm to retain the most predictive features for hospitalization risk, followed by validation in a temporally distinct patient cohort. The final model was displayed as a nomogram and programmed into an online risk calculator. One healthcare system in Ohio and Florida. All patients infected with SARS-CoV-2 between March 8, 2020 and June 5, 2020. Those tested before May 1 were included in the development cohort, while those tested May 1 and later comprised the validation cohort. Demographic, clinical, social influencers of health, exposure risk, medical co-morbidities, vaccination history, presenting symptoms, medications, and laboratory values were collected on all patients, and considered in our model development. 4,536 patients tested positive for SARS-CoV-2 during the study period. Of those, 958 (21.1%) required hospitalization. By day 3 of hospitalization, 24% of patients were transferred to the intensive care unit, and around half of the remaining patients were discharged home. Ten patients died. Hospitalization risk was increased with older age, black race, male sex, former smoking history, diabetes, hypertension, chronic lung disease, poor socioeconomic status, shortness of breath, diarrhea, and certain medications (NSAIDs, immunosuppressive treatment). Hospitalization risk was reduced with prior flu vaccination. Model discrimination was excellent with an area under the curve of 0.900 (95% confidence interval of 0.886-0.914) in the development cohort, and 0.813 (0.786, 0.839) in the validation cohort. The scaled Brier score was 42.6% (95% CI 37.8%, 47.4%) in the development cohort and 25.6% (19.9%, 31.3%) in the validation cohort. Calibration was very good. The online risk calculator is freely available and found at https://riskcalc.org/COVID19Hospitalization/. Retrospective cohort design. Our study crystallizes published risk factors of COVID-19 progression, but also provides new data on the role of social influencers of health, race, and influenza vaccination. In a context of a pandemic and limited healthcare resources, individualized outcome prediction through this nomogram or online risk calculator can facilitate complex medical decision-making.
Sections du résumé
BACKGROUND
Coronavirus Disease 2019 is a pandemic that is straining healthcare resources, mainly hospital beds. Multiple risk factors of disease progression requiring hospitalization have been identified, but medical decision-making remains complex.
OBJECTIVE
To characterize a large cohort of patients hospitalized with COVID-19, their outcomes, develop and validate a statistical model that allows individualized prediction of future hospitalization risk for a patient newly diagnosed with COVID-19.
DESIGN
Retrospective cohort study of patients with COVID-19 applying a least absolute shrinkage and selection operator (LASSO) logistic regression algorithm to retain the most predictive features for hospitalization risk, followed by validation in a temporally distinct patient cohort. The final model was displayed as a nomogram and programmed into an online risk calculator.
SETTING
One healthcare system in Ohio and Florida.
PARTICIPANTS
All patients infected with SARS-CoV-2 between March 8, 2020 and June 5, 2020. Those tested before May 1 were included in the development cohort, while those tested May 1 and later comprised the validation cohort.
MEASUREMENTS
Demographic, clinical, social influencers of health, exposure risk, medical co-morbidities, vaccination history, presenting symptoms, medications, and laboratory values were collected on all patients, and considered in our model development.
RESULTS
4,536 patients tested positive for SARS-CoV-2 during the study period. Of those, 958 (21.1%) required hospitalization. By day 3 of hospitalization, 24% of patients were transferred to the intensive care unit, and around half of the remaining patients were discharged home. Ten patients died. Hospitalization risk was increased with older age, black race, male sex, former smoking history, diabetes, hypertension, chronic lung disease, poor socioeconomic status, shortness of breath, diarrhea, and certain medications (NSAIDs, immunosuppressive treatment). Hospitalization risk was reduced with prior flu vaccination. Model discrimination was excellent with an area under the curve of 0.900 (95% confidence interval of 0.886-0.914) in the development cohort, and 0.813 (0.786, 0.839) in the validation cohort. The scaled Brier score was 42.6% (95% CI 37.8%, 47.4%) in the development cohort and 25.6% (19.9%, 31.3%) in the validation cohort. Calibration was very good. The online risk calculator is freely available and found at https://riskcalc.org/COVID19Hospitalization/.
LIMITATION
Retrospective cohort design.
CONCLUSION
Our study crystallizes published risk factors of COVID-19 progression, but also provides new data on the role of social influencers of health, race, and influenza vaccination. In a context of a pandemic and limited healthcare resources, individualized outcome prediction through this nomogram or online risk calculator can facilitate complex medical decision-making.
Identifiants
pubmed: 32780765
doi: 10.1371/journal.pone.0237419
pii: PONE-D-20-11909
pmc: PMC7418996
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Validation Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0237419Subventions
Organisme : NCATS NIH HHS
ID : UL1 TR002548
Pays : United States
Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
Pharmacol Res. 2017 Nov;125(Pt A):21-38
pubmed: 28619367
Lancet. 2020 Mar 28;395(10229):1054-1062
pubmed: 32171076
MMWR Morb Mortal Wkly Rep. 2020 May 08;69(18):551-556
pubmed: 32379733
Diagn Progn Res. 2018 May 04;2:7
pubmed: 31093557
J Virol. 2020 Mar 17;94(7):
pubmed: 31996437
Cell Discov. 2020 Mar 16;6:14
pubmed: 32194980
J Infect. 2020 May;80(5):e1-e6
pubmed: 32171869
Ann Intern Med. 2015 Jan 6;162(1):55-63
pubmed: 25560714
Lancet Oncol. 2020 Mar;21(3):335-337
pubmed: 32066541
J Biomed Inform. 2019 Jul;95:103208
pubmed: 31078660
Clin Med (Lond). 2020 Jul;20(4):e114-e119
pubmed: 32620590
JAMA. 2020 Apr 7;323(13):1239-1242
pubmed: 32091533
J Biomed Inform. 2009 Apr;42(2):377-81
pubmed: 18929686
MMWR Morb Mortal Wkly Rep. 2020 Apr 17;69(15):458-464
pubmed: 32298251
JAMA. 1982 May 14;247(18):2543-6
pubmed: 7069920
Cell. 2016 Oct 20;167(3):643-656.e17
pubmed: 27768888
MMWR Morb Mortal Wkly Rep. 2020 Apr 10;69(14):419-421
pubmed: 32271724
Semin Urol Oncol. 2002 May;20(2):79-81
pubmed: 12030248
Chin Med J (Engl). 2020 May 5;133(9):1032-1038
pubmed: 32118640
Ann Transl Med. 2018 Feb;6(3):42
pubmed: 29610734