To address this urgent issue, a predictive risk score estimating whether a hospitalized patient with COVID-19 would be inclined to develop critical illness was developed. A retrospective cohort of 1590 patients with COVID-19 from 575 hospitals in 31 provincial administrative regions was included. By using the least absolute shrinkage and selection operator model, 19 common clinical variables (clinical features and blood test results, chest X-ray (CXR) abnormality, age, exposure to Wuhan, first and highest body temperature, respiratory rate, systolic blood pressure, hemoptysis, dyspnea, skin rash, unconsciousness, number of comorbidities, COPD, cancer, oxygen saturation levels, neutrophils, neutrophil-to-lymphocyte ratio, lactate dehydrogenase, direct bilirubin, and creatinine levels) remained to predict the likelihood of progressing to critical illness [72]. The deployment of an artificial intelligence (AI) system allowed a deep learning-based survival model to further establish an online calculation tool, which could differentiate patients with COVID-19 from those with other forms of common pneumonia [73].