Design and Analysis of Clinical Trials with Restricted Mean Survival Time

Mentor/Advisor: Xiaofei Wang, PhD Abstract: Restricted mean survival ��me (RMST), a summary of survival ��me up to a pre-specified clinically relevant trunca��on ��me, is increasingly recognized as a measure for treatment effect in recent biomedical studies with ��me-to-event endpoints. The difference or ra��o of RMST between two groups (e.g., treatment versus control) measures the rela��ve treatment effect concerning a gain or loss of survival ��me. The RMST offers greater flexibility compared to the hazard ra��o (HR), which is o��en es��mated from the Cox propor��onal hazards model under the propor��onal hazards (PH) assump��on. Due to delayed treatment effects or other biomedical reasons, the PH assump��on is o��en violated in oncology and cardiovascular trials, leading to biased es��ma��on and misleading interpreta��ons of treatment effects. Compared to HR, RMST requires no PH assump��on and offers a more straigh��orward interpreta��on of treatment effects.