design_considerations_in_clinical_trials_with_cure_rate_survival_data_a_case_study_in_oncology.pharm_stat10.1002pst.1840_资料5.Image.Marked.pdf

Received: 12 March 2017 Revised: 19 August 2017 Accepted: 10 October 2017 DOI: 10.1002/pst.1840 M A I N P A P E R Design considerations in clinical trials with cure rate survival data: A case study in oncology Steven Sun1 | Grace Liu1 | Tianmeng Lyu2 | Fubo Xue3 | Tzu‐Min Yeh1 | Sudhakar Rao1 1 Janssen Research and Development, Summary LLC, Raritan, New Jersey, USA 2 Division of Biostatistics, School of Public For clinical trials with time‐to‐event as the primary endpoint, the clinical cutoff Health, University of Minnesota, is often event‐driven and the log‐rank test is the most commonly used statistical Minneapolis, Minnesota, USA method for evaluating treatment effect. However, this method relies on the 3 Janssen China Research Development proportional hazards assumption in that it has the maximal power in this Center Beijing, Beijing, China circumstance. In certain disease areas or populations, some patients can be Correspondence curable and never experience the events despite a long follow‐up. The event Grace Liu, Janssen Research and accumulation may dry out after a certain period of follow‐up and the treatment Development LLC Raritan New Jersey United States. effect could be reflected as the combination of improvement of cure rate and Email: gliu9@ the delay of events for those uncurable patients. Study power depends on both cure rate improvement and hazard reduction. In this paper, we illustrate these practical issues using simulation studies and