|
Abstract:
|
Competing risk and semi-competing risk situation are often encountered in clinical trials with time to event endpoint. The trial design can further be complicated if the underlying competing risk/ semi-competing event distribution differs between subgroups or the correlation of competing/semi-competing event varies in each subgroup due to the heterogeneity of the disease population. In recent COVID-19 clinical studies, the time to event, such as time to recovery and time to ventilation, have been considered as primary endpoints for treatment efficacy evaluation. Mortality is also one of the most important clinical outcomes of COVID-19, which becomes a competing risk or semi-competing risk event to any other type of endpoint. Furthermore, death is highly correlated with primary time to event of interest, but the correlation direction may differ between difference events. While competing risk and semi-competing risk have been thoroughly discussed and well established in open duration and number of events driven clinical trials, there is lack of discussion on this topic under heterogeneity population and correlation of the main events and competing event. To fill the gap, we use a set
|
