Outcome-adaptive randomisation in a multi-arm breast cancer trial

Research Square (Research Square)(2022)

引用 0|浏览1
暂无评分
摘要
Abstract Background To perform virtual re-executions of a breast cancer clinical trial with a time-to-event outcome to demonstrate what would have happened if the trial had used outcome-adaptive randomisation instead. Methods We aimed to retrospectively “re-execute” a randomised controlled trial that compared three chemotherapy regimens for women with metastatic breast cancer (ANZ 0001) using outcome-adaptive randomisation. We used computer simulations to estimate the power and mean number of participants randomised to inferior treatment of a large number of different candidate designs and shortlisted designs with the either highest power or the lowest number randomised to inferior treatment. Using the real-world data, we explored what would have happened had ANZ 0001 been conducted using these shortlisted designs. Results We shortlisted seven adaptive randomisation designs that had higher power and a lower number of participants allocated to inferior treatment compared to the original trial design. Adaptive randomised designs were able to reduce the average sample size of the control arm by up to 8.2% when one experimental arm was effective by up to 11.4% when both experimental arms were equally effective. The performance of the adaptive designs when applied to the real-world ANZ 0001 data was consistent with the simulations. Conclusion The shortlisted adaptive randomisation designs allocated somewhat fewer participants to inferior treatment while offering the same or better type I and II error rates compared to fixed designs.
更多
查看译文
关键词
breast cancer,outcome-adaptive,multi-arm
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要