A Novel Evidence-Based Predictor Tool for Hospitalization and Length of Stay: Insights from COVID19 Patients in New York City
Abstract
Background
Coronavirus disease 2019 (COVID-19) has evolved into a true global pandemic infecting more than 30 million people worldwide. Predictive models for key outcomes have the potential to optimize resource utilization and patient outcome as outbreaks continue to occur worldwide. We aimed to design and internally validate a web-based calculator predictive of hospitalization and length of stay (LOS) in a large cohort of COVID-19 positive patients presenting to the Emergency Department (ED) in a New York City health system.
Methods
The study cohort consisted of consecutive adult (>18 years) patients presenting to the ED of one of the Mount Sinai Health System hospitals between March, 2020 and April, 2020 who were diagnosed with COVID-19. Logistic regression was utilized to construct predictive models for hospitalization and prolonged (>3 days) LOS. Discrimination was evaluated using area under the receiver operating curve (AUC). Internal validation with bootstrapping was performed, and a web-based calculator was implemented.
Results
The cohort consisted of 5859 patients with a hospitalization rate of 65% and a prolonged LOS rate of 75% among hospitalized patients. Independent predictors of hospitalization included older age (OR=6.29; 95% CI [1.83-2.63], >65 vs. 18-44), male sex (OR=1.35 [1.17-1.55]), chronic obstructive pulmonary disease (OR=1.74; [1.00-3.03]), hypertension (OR=1.39; [1.13-1.70]), diabetes (OR=1.45; [1.16-1.81]), chronic kidney disease (OR=1.69; [1.23-2.32]), elevated maximum temperature (OR=4.98; [4.28-5.79]), and low minimum oxygen saturation (OR=13.40; [10.59-16.96]). Predictors of extended LOS included older age (OR=1.03 [1.02-1.04], per year), chronic kidney disease (OR=1.91 [1.35-2.71]), elevated maximum temperature (OR=2.91 [2.40- 3.53]), and low minimum percent oxygen saturation (OR=3.89 [3.16-4.79]). AUCs of 0.881 and 0.770 were achieved for hospitalization and LOS, respectively. A calculator was made available under the following URL: <ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://covid19-outcome-prediction.shinyapps.io/COVID19_Hospitalization_Calculator/">https://covid19-outcome-prediction.shinyapps.io/COVID19_Hospitalization_Calculator/</ext-link>
Conclusion
The prediction tool derived from this study can be used to optimize resource allocation, guide quality of care, and assist in designing future studies on the triage and management of patients with COVID-19.
Related articles
Related articles are currently not available for this article.