Department of Biostatistics and Bioinformatics, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan.
Center for Data Science, Yokohama City University, Yokohama, Japan.
Ther Innov Regul Sci. 2020 Sep;54(5):1097-1105. doi: 10.1007/s43441-020-00126-2. Epub 2020 Feb 6.
Two issues in clinical trials with multiple endpoints were surveyed: (1) the terminology of multiple endpoints, the relationship between rare events and endpoints, and the differences in multiplicity adjustment between regions, and (2) the current practice on multiplicity adjustment and sample size calculation. This article summarizes the results of the survey on the second issue.
Eligible trials for this survey fulfilled the following conditions: (1) confirmatory phase 3 trial; (2) use of multiple primary endpoints, co-primary endpoints, key secondary endpoint(s) or composite endpoint(s); (3) inclusion of Japanese participants; and (4) protocols created in 2010 or later. The survey was conducted at member companies of the Japan Pharmaceutical Manufacturers Association from October 2017 to November 2017.
Useable responses were obtained from 78 trials in 13 companies based in Japan and 9 companies based in other countries. The Bonferroni procedure was mostly used in clinical trials with multiple primary endpoints, while multiple testing procedures that consider a hierarchy of endpoints or a structure of hypotheses were used in clinical trials with key secondary endpoint(s). In sample size calculation, we can consider the probability of study success, such as the probability of statistical significance in at least one comparison of primary endpoints; however, other probabilities were also considered. This survey reveals that multiplicity adjustment and the correlation of endpoints were not always considered in sample size calculation.
In clinical trials with multiple endpoints, clinical importance was considered when determining multiple testing procedures. Challenges remain with the definition of power, the consideration of multiple testing procedures and the correlation between endpoints in sample size calculation.
本次调查涉及临床试验中多个终点的两个问题：（1）多个终点的术语、罕见事件与终点的关系，以及不同地区间的多重性调整差异；（2）目前多重性调整和样本量计算的实践情况。本文总结了第二个问题的调查结果。
符合以下条件的试验有资格参与本次调查：（1）确证性 3 期试验；（2）使用多个主要终点、共同主要终点、关键次要终点或复合终点；（3）纳入日本参与者；（4）方案制定于 2010 年或之后。本次调查于 2017 年 10 月至 11 月在日本制药商协会的成员公司中进行。
基于来自 13 家日本公司和 9 家其他国家公司的 78 项试验，得到了可用的回复。在具有多个主要终点的临床试验中，大多使用了 Bonferroni 程序，而在具有关键次要终点的临床试验中，使用了考虑终点层次结构或假设结构的多重检验程序。在样本量计算中，我们可以考虑研究成功的概率，例如主要终点至少一个比较具有统计学意义的概率；但是，也考虑了其他概率。本次调查显示，在样本量计算中并不总是考虑多重性调整和终点的相关性。
在具有多个终点的临床试验中，在确定多重检验程序时，考虑了临床重要性。在样本量计算中，定义功效、考虑多重检验程序和终点之间的相关性方面仍存在挑战。
