Estimating Survival of Hospitalized COVID-19 Patients from Admission Information

ABSTRACT

BackgroundChinese studies reported predictors of severe disease and mortality associated with coronavirus disease 2019 (COVID-19). A generalizable and simple survival calculator based on data from US patients hospitalized with COVID-19 has not yet been introduced. ObjectiveDevelop and validate a clinical tool to predict 7-day survival in patients hospitalized with COVID-19. DesignRetrospective and prospective cohort study. SettingThirteen acute care hospitals in the New York City area. ParticipantsAdult patients hospitalized with a confirmed diagnosis of COVID-19. The development and internal validation cohort included patients hospitalized between March 1 and May 6, 2020. The external validation cohort included patients hospitalized between March 1 and May 5, 2020. MeasurementsDemographic, laboratory, clinical, and outcome data were extracted from the electronic health record. Optimal predictors and performance were identified using least absolute shrinkage and selection operator (LASSO) regression with receiver operating characteristic curves and measurements of area under the curve (AUC). ResultsThe development and internal validation cohort included 11{square}095 patients with a median age of 65 years [interquartile range (IQR) 54-77]. Overall 7-day survival was 89%. Serum blood urea nitrogen, age, absolute neutrophil count, red cell distribution width, oxygen saturation, and serum sodium were identified as the 6 optimal of 42 possible predictors of survival. These factors constitute the NOCOS (Northwell COVID-19 Survival) Calculator. Performance in the internal validation, prospective validation, and external validation were marked by AUCs of 0.86, 0.82, and 0.82, respectively. LimitationsAll participants were hospitalized within the New York City area. ConclusionsThe NOCOS Calculator uses 6 factors routinely available at hospital admission to predict 7-day survival for patients hospitalized with COVID-19. The calculator is publicly available at https//feinstein.northwell.edu/NOCOS. Trial registrationN/A Funding SourceThis work was supported by grants R24AG064191 from the National Institute on Aging, R01LM012836 from the National Library of Medicine, and K23HL145114 from the National Heart Lung and Blood Institute.