CORONAVIRUS DISEASE SURVIVAL TIME MODEL FOR FORECASTING

Abstract

The term "survival analysis" refers to statistical techniques for data analysis where the time until the occurrence of the desired event serves as the outcome variable. Time to event analysis is another name for survival analysis. Applications for survival analysis are fairly broad and include things like calculating a population's survival rate or contrasting the survival of two or more groups. Cox regression analysis is a highly well-liked and frequently applied technique among them. Data on disease states are typically obtained at random epochs or at periodic epochs during follow-up in research looking at biological changes between states of Coronavirus infection and the start of COVID-19 in the human immune system. For instance, after the COVID enters a person's bloodstream by a route of transmission, it progresses through numerous stages that are linked to the depletion of B cells before becoming COVID-19. This study presents the Cox's approach for simulating the link between variables influencing the development of two disease states, namely I= the time epoch of COVID infection and P= the time epoch of COVID-19. Incubation period (IP) or survival time is the precise interval of time between "P and I." It is shown how Cox's model works with several personal infective factors and how well it can estimate the percentage of COVID-19 victims with the same completed length of IP. Such forecast values are then established for a synthetically simulated data set.