A COVID-19 Mortality Prediction Model for Korean Patients Using Nationwide Korean Disease Control and Prevention Agency Database (preprint)

ABSTRACT

The experience of the early nationwide COVID-19 pandemic in South Korea had led to an early shortage of medical resources. For efficient resource allocation, accurate prediction for the prognosis or mortality of confirmed patients is essential. Therefore, the aim of this study was to develop an accurate model for predicting COVID-19 mortality using epidemiolocal and clinical variables and for identifying high risk group of confirmed patients. Clinical and epidemiolocal variables of 4,049 patients with confirmed COVID-19 between January 20, 2020 and April 30, 2020 collected by Korean Disease Control and Prevention Agency were used. Among 4,049 total confirmed patients, 223 patients were dead while 3,826 patients were released from isolation. Patients who had the following risk factors showed significantly higher risk scores age over 60 years, male, difficulty breathing, diabetes, cancer, dementia, change of consciousness, and hospitalized in intensive care unit. High accuracy was shown for both the development set (n = 2,467) and the validation set (n = 1,582), with AUC of 0.96 and 0.97, respectively. The prediction model developed in this study based on clinical features and epidemiological factors could be used for screening high risk group of patients and for evidence-based allocation of medical resources.