GBDS, Bristol Myers Squibb, Boudry, Switzerland.
GBDS, Bristol Myers Squibb, Berkeley Heights, New Jersey, USA.
Pharm Stat. 2023 Nov-Dec;22(6):1089-1103. doi: 10.1002/pst.2331. Epub 2023 Aug 12.
We consider outcome adaptive phase II or phase II/III trials to identify the best treatment for further development. Different from many other multi-arm multi-stage designs, we borrow approaches for the best arm identification in multi-armed bandit (MAB) approaches developed for machine learning and adapt them for clinical trial purposes. The best arm identification in MAB focuses on the error rate of identification at the end of the trial, but we are also interested in the cumulative benefit of trial patients, for example, the frequency of patients treated with the best treatment. In particular, we consider Top-Two Thompson Sampling (TTTS) and propose an acceleration approach for better performance in drug development scenarios in which the sample size is much smaller than that considered in machine learning applications. We also propose a variant of TTTS (TTTS2) which is simpler, easier for implementation, and has comparable performance in small sample settings. An extensive simulation study was conducted to evaluate the performance of the proposed approach in multiple typical scenarios in drug development.
我们考虑采用基于结果的 II 期或 II/III 期试验来确定最佳治疗方法以进一步开发。与许多其他多臂多阶段设计不同，我们借鉴了机器学习中多臂强盗（MAB）方法中用于最佳手臂识别的方法，并将其适应于临床试验目的。MAB 中的最佳手臂识别侧重于试验结束时识别的错误率，但我们也对试验患者的累积收益（例如，接受最佳治疗的患者的频率）感兴趣。特别是，我们考虑了 Top-Two Thompson Sampling (TTTS) 并提出了一种加速方法，以在药物开发场景中获得更好的性能，其中样本量比机器学习应用中考虑的要小得多。我们还提出了 TTTS 的一种变体（TTTS2），它更简单，易于实现，并且在小样本环境中的性能相当。进行了广泛的模拟研究，以评估所提出方法在药物开发中多种典型场景下的性能。
