Adaptive seamless clinical trials using early outcomes for treatment or subgroup selection: Methods, simulation model and their implementation in R

Abstract

Adaptive seamless designs combine confirmatory testing, a domain of phase III trials, with features such as treatment or subgroup selection, typically associated with phase II trials. They promise to increase the efficiency of development programmes of new drugs, e.g. in terms of sample size and / or development time. It is well acknowledged that adaptive designs are more involved from a logistical perspective and require more upfront planning, often in form of extensive simulation studies, than conventional approaches. Here we present a framework for adaptive treatment and subgroup selection using the same notation, which links the somewhat disparate literature on treatment selection on one side and on subgroup selection on the other. Furthermore, we introduce a flexible and yet efficient simulation model that serves both designs. As primary endpoints often take a long time to observe, interim analyses are frequently informed by early outcomes. Therefore, all methods presented accommodate both, interim analyses informed by the primary outcome or an early outcome. The R package asd, previously developed to simulate designs with treatment selection, was extended to include subpopulation selection (so-called adaptive enrichment designs). Here we describe the functionality of the R package asd and use it to present some worked-up examples motivated by clinical trials in chronic obstructive pulmonary disease and oncology. The examples illustrate various features of the R package providing at the same time insights into the operating characteristics of adaptive seamless studies.

A conditional error function approach for adaptive enrichment designs with continuous endpoints

“…They cover a variety of methods, eg, the CT approach, group‐sequential designs, and the CEF approach . Both treatment and subgroup selection based on the primary as well as early outcomes are considered by Friede et al They also showcased the R package asd , which was recently extended to subpopulation selection. Lately, so‐called multi‐arm multistage designs have gained some attention by authors trying to extend the methodology of group‐sequential methods to more than two treatment arms, eg, Magirr et al and Ghosh et al They faced similar problems concerning multivariate distributions and computational efficiency.…”

Adaptive trial designs in diagnostic accuracy research

“…In adaptive seamless designs combining aspects of different development phases such as learning about the optimal dose or population with confirmatory testing, multiple hypotheses are considered. Control of the familywise type I error probability in the strong sense can be achieved by, eg, using combination tests on intersection hypotheses in a closed test procedure . Considering adaptive designs for treatment or subgroup selection, the methods and aspects of their implementation have been comprehensively described (eg, simulation models and software) in a forthcoming manuscript …”

Efficient Adaptive Designs for Clinical Trials of Interventions for COVID-19

“…Consequently, this approach allows for testing in MAMS trials controlling the FWER in a strong sense. R packages are available for confirmatory adaptive designs in the multi-arm setting, such as asd (Friede, Stallard, and Parsons 2020 ) and rpact (rpact 2020 ), with MAMS (Jaki, Pallmann, and Magirr 2019 ) also having an extension for dealing with unexpected design modifications.…”