文献速递流行病学与生物统计临床试验与 GCP

两阶段适应性无缝设计中使用短期和长期二分类结局的统计检验

Statistical tests for two-stage adaptive seamless design using short- and long-term binary outcomes.
PubMed 文献 · Stat Med · 2022-06-17

针对两阶段适应性无缝设计(第一阶段基于短期二分类终点选择最优试验组,第二阶段基于长期二分类终点比较疗效),提出基于双变量二项分布的精确条件检验作为最终分析,并引入mid-p方法改善精确检验的保守性;模拟研究显示所提精确方法在名义水平控制I型错误率,且在仅一个治疗有效的场景下比基于组合检验的方法更有把握度。

要点

  • 提出基于双变量二项分布的精确条件检验用于两阶段适应性无缝设计的最终分析。
  • 引入mid-p方法改善精确检验的保守性。
  • 模拟显示所提方法在名义水平控制I型错误率,且在仅一个治疗有效时比组合检验更有把握度。

核心结论

  • 所提精确方法在名义水平控制I型错误率,且在意仅一个治疗有效的场景下比基于组合检验的方法更有把握度。

研究设计与样本

  • 两阶段适应性无缝设计,第一阶段基于短期二分类终点选择最优试验组,第二阶段基于长期二分类终点比较所选治疗组与对照组。
  • 提出基于双变量二项分布的精确条件检验作为最终分析,并引入mid-p方法改善精确检验的保守性。
  • 通过模拟研究将所提方法与基于组合检验的方法进行比较。

主要发现

  • 所提精确方法在名义水平控制I型错误率,无论初始治疗数量或短期与长期终点之间的相关性如何。
  • 在仅一个治疗有效的场景下,所提方法在治疗比较的把握度上优于基于组合检验的方法。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

The adaptive seamless design combining phases II and III into a single trial has been shown growing interest for improving the efficiency of drug development, becoming the most frequent adaptive design type. It typically consists of two stages, the trial objectives being often different in each stage. The primary objectives are to select optimal experimental treatment group(s) in the first stage and compare the efficacy between the selected treatment and control groups in the second stage. In this article, we focus on a two-stage adaptive seamless design, for which treatment selection is based on the short-term binary endpoint and treatment comparison is based on the long-term binary endpoint. We thus propose an exact conditional test as a final analysis, based on the bivariate binomial distribution and given the selected treatment with the most promising short-term endpoint response rate from an interim analysis. Additionally, the mid- p $$ p $$ approach is incorporated to improve conservativeness for an exact test. Simulation studies were conducted to compare the proposed methods with a method based on the combination test. The proposed exact method controlled for type I error rate at the nominal level, regardless of the number of initial treatments or the correlation between short- and long-term endpoints. In terms of the treatment comparison power, the proposed methods are more powerful than that based on the combination test in the scenarios, with only one treatment being effective.

来源:Stat Med,查看原文。版权归原作者所有。

引用

  1. Takahashi K, Ishii R, Maruo K, et al. Statistical tests for two-stage adaptive seamless design using short- and long-term binary outcomes. Stat Med. 2022. PMID: 35713225. doi:10.1002/sim.9500

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。