Development and validation of a simple-to-use nomogram to predict the deterioration and survival of patients with COVID-19.

ABSTRACT

BACKGROUND: COVID-19 pandemic has forced physicians to quickly determine the patient's condition and choose treatment strategies. This study aimed to build and validate a simple tool that can quickly predict the deterioration and survival of COVID-19 patients. METHODS: A total of 351 COVID-19 patients admitted to the Third People's Hospital of Yichang between 9 January to 25 March 2020 were retrospectively analyzed. Patients were randomly grouped into training (n = 246) or a validation (n = 105) dataset. Risk factors associated with deterioration were identified using univariate logistic regression and least absolute shrinkage and selection operator (LASSO) regression. The factors were then incorporated into the nomogram. Kaplan-Meier analysis was used to compare the survival of patients between the low- and high-risk groups divided by the cut-off point. RESULTS: The least absolute shrinkage and selection operator (LASSO) regression was used to construct the nomogram via four parameters (white blood cells, C-reactive protein, lymphocyte≥0.8 × 109/L, and lactate dehydrogenase ≥400 U/L). The nomogram showed good discriminative performance with the area under the receiver operating characteristic (AUROC) of 0.945 (95% confidence interval 0.91-0.98), and good calibration (P = 0.539). Besides, the nomogram showed good discrimination performance and good calibration in the validation and total cohorts (AUROC = 0.979 and AUROC = 0.954, respectively). Decision curve analysis demonstrated that the model had clinical application value. Kaplan-Meier analysis illustrated that low-risk patients had a significantly higher 8-week survival rate than those in the high-risk group (100% vs 71.41% and P < 0.0001). CONCLUSION: A simple-to-use nomogram with excellent performance in predicting deterioration risk and survival of COVID-19 patients was developed and validated. However, it is necessary to verify this nomogram using a large-scale multicenter study.