Geller N L
J Clin Oncol. 1987 Sep;5(9):1485-90. doi: 10.1200/JCO.1987.5.9.1485.
Although interim analyses in cancer clinical trials are commonplace, clinical trials are usually designed with the implicit assumption that data analysis will occur only after the trial is completed. The design of randomized trials with planned interim analyses, "group sequential trials," is described and examples are given. A method to redesign trials in which unplanned interim analyses have been undertaken is described. Planned interim analysis should be considered whenever a cancer clinical trial is designed.
尽管癌症临床试验中的期中分析很常见，但临床试验的设计通常隐含着一个假设，即数据分析只会在试验完成后进行。本文描述了带有计划期中分析的随机试验（“成组序贯试验”）的设计并给出了示例。还描述了一种对已进行非计划期中分析的试验进行重新设计的方法。在设计任何癌症临床试验时都应考虑计划期中分析。
