📝 SummarXiv

Abstract

Clinical trials with time-to-event endpoints, such as overall survival (OS) or progression-free survival (PFS), are fundamental for evaluating new treatments, particularly in immuno-oncology. However, modern therapies, such as immunotherapies and targeted treatments, often exhibit delayed effects that challenge traditional trial designs. These delayed effects violate the proportional hazards assumption, which underpins standard statistical methods like the Cox proportional hazards model and the log-rank test. Careful planning is essential to ensure trials are appropriately designed to account for the timing and magnitude of these effects. Without this planning, interim analyses may lead to premature trial termination if the treatment effect is underestimated early in the study. We present an adaptive trial design framework that incorporates prior distributions, elicited from experts, for delayed treatment effects. By addressing the uncertainty surrounding delayed treatment effects, our approach enhances trial efficiency and robustness, minimizing the risk of premature termination and improving the detection of treatment benefits over time. We present an example illustrating how interim analyses, informed by prior distributions, can guide early stopping decisions. To facilitate the implementation of our framework, we have developed free, open-source software that enables researchers to integrate prior distributions into trial planning and decision-making. This software provides a flexible, accessible tool for designing trials that more accurately evaluate modern therapies through adaptive trial designs.