Biometric Research Branch, National Cancer Institute, Bethesda, MD, USA.
Clin Trials. 2010 Jun;7(3):197-208. doi: 10.1177/1740774510369019. Epub 2010 Apr 27.
The ultimate goal of a phase III randomized clinical trial designed to demonstrate superiority of a new versus standard therapy is to provide sufficiently compelling evidence to affect clinical practice. To balance patient interests against the need for acquiring evidence it is desirable to stop a study for inefficacy as soon as convincing evidence that the new therapy is not beneficial becomes available.
To discuss potential deficiencies in some commonly used inefficacy monitoring rules and to propose a comprehensive inefficacy monitoring procedure.
The proposed approach is developed using clinical, logistical, and statistical considerations. The new approach is compared to the commonly used inefficacy rules in a simulation study.
Some of the commonly used inefficacy rules are suboptimal with respect to the strength of evidence required for stopping throughout the trial: too conservative in the middle and/or too aggressive at the end. Our approach allows timely stopping (a) if the new therapy is harmful, and (b) if the interim data provides convincing evidence that the new therapy has no tangible benefit. Relative to common inefficacy rules, our procedure is shown to result in potentially fewer treated patients and shorter study duration under the null hypothesis with only a minor loss of power under the alternative hypothesis.
The proposed procedure is applicable to superiority designs with well-defined clinical objectives.
The proposed inefficacy approach is attractive from statistical, clinical, and logistical standpoints. By decreasing average stopping times relative to the commonly used boundaries, our rule lessens patient exposure to inactive treatments, improves resource utilization, and accelerates dissemination of important clinical information. At the same time, the proposed rule provides a clear benchmark for providing compelling evidence that the new therapy is not beneficial. Clinical Trials 2010; 7: 197-208. http://ctj.sagepub.com.
旨在证明新疗法优于标准疗法的 III 期随机临床试验的最终目标是提供足够有力的证据来影响临床实践。为了在平衡患者利益与获取证据的需求之间取得平衡，一旦有令人信服的证据表明新疗法无益，就应尽快停止无效的研究。
讨论一些常用无效监测规则的潜在缺陷，并提出一种综合的无效监测程序。
使用临床、逻辑和统计方面的考虑来开发建议的方法。在模拟研究中，将新方法与常用无效规则进行比较。
一些常用的无效规则在整个试验中停止所需的证据强度方面存在不足：在中间阶段过于保守，而在最后阶段过于激进。我们的方法允许及时停止（a）如果新疗法有害，以及（b）如果中期数据提供了令人信服的证据表明新疗法没有实际益处。与常用的无效规则相比，我们的程序在零假设下显示出潜在的治疗患者更少且研究持续时间更短，而在替代假设下仅略微降低了功效。
所提出的程序适用于具有明确临床目标的优势设计。
从统计学、临床和逻辑的角度来看，所提出的无效方法具有吸引力。通过相对于常用边界减少平均停止时间，我们的规则减少了患者接触无效治疗的机会，提高了资源利用效率，并加速了重要临床信息的传播。同时，该规则为提供令人信服的证据表明新疗法无益提供了明确的基准。临床试验 2010; 7: 197-208. http://ctj.sagepub.com.
