Background
Novel corona virus disease 2019 (COVID-19) is an urgent event in the worldwide. We aimed to develop and validate a practical model for early identifying and predicting which patients will be admitted to intensive care unit (ICU) based on a multi-center cohort in China.
Methods
Data from 1087 patients of laboratory-confirmed COVID-19 were collected from 49 sites between January 2 and February 28 2020 in Sichuan and Wuhan. Patients were randomly divided into the training and validation cohorts (7:3). The least absolute shrinkage and selection operator (LASSO) analysis and logistic regression analysis were employed for the development account. The performance of the nomogram was evaluated for the C-index, calibration, discrimination, and clinical usefulness. The nomogram was further assessed in a different cohort as external validation.
Results
The individualized prediction nomogram included 6 predictors, including age, respiratory rate, systolic blood pressure, smoking status, fever and chronic kidney disease. The model showed high discrimination ability in the training cohort (C-index = 0.829), which was confirmed in the external validation cohort (C-index = 0.776). In addition, the calibration plots confirmed good concordance for prediction the risk of ICU admission. Decision curve analysis showed that the prediction nomogram was clinically useful.
Conclusion
We established an early prediction model incorporating clinical characteristics that could be quickly obtained on hospital admission even in community health center. This model can be conveniently used to facilitate predicting the individual risk for ICU admission of COVID-19 patients and optimizing use of limited resources.