A stochastically curtailed two‐arm randomised phaseIItrial design for binary outcomes

Abstract

Summary Randomised controlled trials are considered the gold standard in trial design. However, phase II oncology trials with a binary outcome are often single‐arm. Although a number of reasons exist for choosing a single‐arm trial, the primary reason is that single‐arm designs require fewer participants than their randomised equivalents. Therefore, the development of novel methodology that makes randomised designs more efficient is of value to the trials community. This article introduces a randomised two‐arm binary outcome trial design that includes stochastic curtailment (SC), allowing for the possibility of stopping a trial before the final conclusions are known with certainty. In addition to SC, the proposed design involves the use of a randomised block design, which allows investigators to control the number of interim analyses. This approach is compared with existing designs that also use early stopping, through the use of a loss function comprised of a weighted sum of design characteristics. Comparisons are also made using an example from a real trial. The comparisons show that for many possible loss functions, the proposed design is superior to existing designs. Further, the proposed design may be more practical, by allowing a flexible number of interim analyses. One existing design produces superior design realisations when the anticipated response rate is low. However, when using this design, the probability of rejecting the null hypothesis is sensitive to misspecification of the null response rate. Therefore, when considering randomised designs in phase II, we recommend the proposed approach be preferred over other sequential designs.

Positioning imatinib for pulmonary arterial hypertension: A phase I/II design comprising dose finding and single‐arm efficacy

“…Part 2 of PIPAH builds on experience with the best tolerated dose from Part 1. Here, the use of a multi-stage design, either a two-stage Simon design or a multi-stage design using stochastic curtailment, 33,34 permits an early decision on futility and/or efficacy. Such designs reduce the number of participants receiving an inefficacious treatment and allow investigators to consider other treatments sooner, while increasing the speed with which an efficacious treatment can be identified and the next phase planned.…”

“…Permitting curtailment of either kind in a trial design can result in a design with more appealing properties than an equivalent Simon design. In particular, designs using curtailment may be superior in terms of a combination of the following three criteria: maximum sample size N , expected sample size if response rate p = p 0 = 0.1 (ESS( p 0 )), that is, if the treatment does not work and expected sample size if response rate p = p 1 = 0.27 (ESS( p 1 )), that is, if the treatment works 33,34 . One example of such a design is shown in Fig.…”

Multi-outcome trials with a generalised number of efficacious outcomes

“…The lower and upper conditional power thresholds were set to CP L = 0.3 and CP U = 0.95 respectively. For some previous uses of conditional power, the maximum lower threshold for CP was set equal to the response rate for which the trial was powered [28,30]. Here, there is no such obvious association to be made between CP threshold, a probability and effect size, a continuous value.…”

Unified exact design with early stopping rules for single arm clinical trials with multiple endpoints

“…proposed curtailed designs allowing a trial to be terminated early for efficacy or futility after evaluating the response of every patient. 13 Ivanova et al. constructed a Pocock-type boundary to continuously monitor toxicity in Phase II clinical trials.…”

“…proposed a recursive formula to calculate the exact probability of accepting or rejecting a null hypothesis for multiple stage designs with a binary endpoint 26 and similar approaches have been adopted by some of the previously cited continuous monitoring designs. 12,13 In this work, we extend the univariate recursive relationship to calculate the exact probabilities of making go/no go decisions in single-arm clinical trials with multiple binary valued endpoints. Based on the extended recursive relationship, we propose the unified exact design, which provides a unified statistical framework for making futility, efficacy and/or toxicity stopping decisions in early phase clinical trials with mutiple-stage or continuous monitoring design.…”