Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA19104, USA.
Biostatistics and Research Decision Sciences, Merck & Co., Inc, Kenilworth, NJ 07033, USA.
Contemp Clin Trials. 2022 May;116:106741. doi: 10.1016/j.cct.2022.106741. Epub 2022 Mar 28.
A basket trial investigates the effects of one drug on multiple tumor indications. To discontinue potentially inactive indications early, an interim futility analysis is usually conducted for each indication individually once it reaches the pre-specified sample size. As enrollment rates vary among indications, the futility decisions for slow-enrolling indications could be made much later than other fast-enrolling indications, which could delay the overall decision for the trial significantly. To accelerate the futility decision in early-stage exploratory basket trials and potentially reallocate resources to other compounds earlier while still controlling the global type-I and type-II errors, we propose an optimal two-stage basket trial design with one aggregated futility analysis by aggregating (e.g., pooling) all indications together. The total sample size across all indications is pre-specified for the futility analysis, while the sample size per indication can be adapted to the enrollment rate. The final analysis is performed using the pruning and pooling approach (Chen et al. 2016). The design parameters are optimized by minimizing the expected total sample size under the null hypothesis, while explicitly controlling the global type-I and the type-II error rates. Simulation studies demonstrate that the proposed design has better operating characteristics than the designs with individual futility analysis (Zhou et al. 2019; Wu et al. 2021), while allowing for earlier futility decision.
篮子试验研究一种药物对多种肿瘤适应证的影响。为了尽早停止潜在无效的适应证，可以在每个适应证达到预定样本量后单独对其进行中期无效性分析。由于各适应证的入组率不同，入组较慢的适应证的无效性决策可能比其他入组较快的适应证晚得多，这可能会显著延迟试验的总体决策。为了加速早期探索性篮子试验中的无效性决策，并在控制总体Ⅰ类和Ⅱ类错误的同时更早地将资源重新分配给其他化合物，我们提出了一种具有一个汇总无效性分析的最优两阶段篮子试验设计，该分析通过将所有适应证汇总（例如，合并）来实现。所有适应证的总样本量在无效性分析中预先指定，而每个适应证的样本量可以根据入组率进行调整。最终分析采用修剪和合并方法（Chen 等人，2016）进行。通过在零假设下最小化预期的总样本量来优化设计参数，同时明确控制总体Ⅰ类和Ⅱ类错误率。模拟研究表明，与具有单独无效性分析的设计相比（Zhou 等人，2019；Wu 等人，2021），该设计具有更好的操作特性，同时允许更早地进行无效性决策。
