AUTHOR=Zhu Yangjie , Yu Boyang , Tang Kang , Liu Tongtong , Niu Dongjun , Zhang Lulu TITLE=Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19 JOURNAL=Frontiers in Public Health VOLUME=11 YEAR=2023 URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2023.1194349 DOI=10.3389/fpubh.2023.1194349 ISSN=2296-2565 ABSTRACT=Background

Most existing prognostic models of COVID-19 require imaging manifestations and laboratory results as predictors, which are only available in the post-hospitalization period. Therefore, we aimed to develop and validate a prognostic model to assess the in-hospital death risk in COVID-19 patients using routinely available predictors at hospital admission.

Methods

We conducted a retrospective cohort study of patients with COVID-19 using the Healthcare Cost and Utilization Project State Inpatient Database in 2020. Patients hospitalized in Eastern United States (Florida, Michigan, Kentucky, and Maryland) were included in the training set, and those hospitalized in Western United States (Nevada) were included in the validation set. Discrimination, calibration, and clinical utility were evaluated to assess the model's performance.

Results

A total of 17 954 in-hospital deaths occurred in the training set (n = 168 137), and 1,352 in-hospital deaths occurred in the validation set (n = 12 577). The final prediction model included 15 variables readily available at hospital admission, including age, sex, and 13 comorbidities. This prediction model showed moderate discrimination with an area under the curve (AUC) of 0.726 (95% confidence interval [CI]: 0.722—0.729) and good calibration (Brier score = 0.090, slope = 1, intercept = 0) in the training set; a similar predictive ability was observed in the validation set.

Conclusion

An easy-to-use prognostic model based on predictors readily available at hospital admission was developed and validated for the early identification of COVID-19 patients with a high risk of in-hospital death. This model can be a clinical decision-support tool to triage patients and optimize resource allocation.