Competing risk between in-hospital mortality and recovery: An application of DeepHit on COVID-19 clinical data

Abstract

Unexplained pneumonia appeared in Wuhan was soon determined to be a novel coronavirus disease, referred to as COVID-19. On March 11, 2020, WHO characterized COVID-19 as a pandemic and the virus has been recognized as a global threat. A plethora of studies is being carried out using various statistical and mathematical models to predict the probable evolution of this pandemic. Though most of them are focusing on building predictive models to assess mortality rates and risk, concentrating on the length of hospital stay can improve decision making and treatment plans. While modeling the length of stay, possible outcomes observed are either discharge or mortality. Modeling the duration of recovery and death provides valuable information for health officials to design proper strategies to reduce the burden on the health system during the outbreak. In this study, we are exploring this competing event aspect of the survival data obtained from COVID-19 patients using the state-of-the-art model DeepHit, a discrete survival model.