Some of these predictors are based on quantification of the radiologist’s visual assessment of CT images 6, 7, 8. Chest imaging can help clinicians to decide whether to admit or discharge patients with mild COVID-19 symptoms, whether to admit patients with moderate-to-severe COVID-19 symptoms to a regular ward or an intensive care unit (ICU), and to provide information about therapeutic management of hospitalized patients with moderate-to-severe COVID-19 symptoms 2.Ĭhest computed tomography (CT) is the most sensitive chest imaging method for COVID-19 3, 4, 5 therefore, several image-based prognostic predictors have been reported for chest CT. Recently, the WHO published specific recommendations about the use of chest imaging for the management of COVID-19 patients 2.
Therefore, a fast and accurate clinical assessment of disease progression and mortality of patients with COVID-19 is vital for logistic planning and for management of the patients.
According to the World Health Organization (WHO), the first nine months of 2020 saw more than 34 million COVID-19 infections and more than 1 million deaths worldwide 1, and these numbers are still increasing rapidly. The rapid increase in the number of patients who have the coronavirus disease 2019 (COVID-19) has introduced major challenges for healthcare services worldwide. The results indicate that U-survival can be used to provide automated and objective prognostic predictions for the management of COVID-19 patients. In an evaluation of 383 COVID-19 positive patients from two hospitals, the prognostic bootstrap prediction performance of U-survival was significantly higher (P < 0.0001) than those of existing laboratory and image-based reference predictors both for COVID-19 progression (maximum concordance index: 91.6% ) and for mortality (88.7% ), and the separation between the Kaplan–Meier survival curves of patients stratified into low- and high-risk groups was largest for U-survival (P < 3 × 10 –14). We developed an automated image-based survival prediction model, called U-survival, which combines deep learning of chest CT images with the established survival analysis methodology of an elastic-net Cox survival model. Therefore, fast and accurate clinical assessment of COVID-19 progression and mortality is vital for the management of COVID-19 patients. The rapid increase of patients with coronavirus disease 2019 (COVID-19) has introduced major challenges to healthcare services worldwide.