Objective

Early triage of patients with coronavirus disease 2019 (COVID-19) is pivotal in managing the disease. However, studies on the clinical risk score system of the risk factors for the development of severe disease are limited. Hence, we conducted a clinical risk score system for severe illness, which might optimize appropriate treatment strategies.

Methods

We conducted a retrospective, single-center study at the JinYinTan Hospital from January 24, 2020 to March 31, 2020. We evaluated the demographic, clinical, and laboratory data and performed a 10-fold cross-validation to split the data into a training set and validation set. We then screened the prognostic factors for severe illness using the least absolute shrinkage and selection operator (LASSO) and logistic regression, and finally conducted a risk score to estimate the probability of severe illness in the training set. Data from the validation set were used to validate the score.

Results

A total of 295 patients were included. From 49 potential risk factors, 3 variables were measured as the risk score: neutrophil to lymphocyte ratio (OR, 1.27; 95% CI, 1.15–1.39), albumin (OR, 0.76; 95% CI, 0.70–0.83), and chest computed tomography abnormalities (OR, 2.01; 95% CI, 1.41–2.86) and the AUC of the validation cohort was 0.822 (95% CI, 0.7667–0.8776).

Conclusion

This report may help define the potential of developing severe illness in patients with COVID-19 at an early stage, which might be related to the neutrophil to lymphocyte ratio, albumin, and chest computed tomography abnormalities.