Nested combination tests with a time‐to‐event endpoint using a short‐term endpoint for design adaptations

Abstract

Adaptive trial methodology for multiarmed trials and enrichment designs has been extensively discussed in the past. A general principle to construct test procedures that control the family-wise Type I error rate in the strong sense is based on combination tests within a closed test. Using survival data, a problem arises when using information of patients for adaptive decision making, which are under risk at interim. With the currently available testing procedures, either no testing of hypotheses in interim analyses is possible or there are restrictions on the interim data that can be used in the adaptation decisions as, essentially, only the interim test statistics of the primary endpoint may be used. We propose a general adaptive testing procedure, covering multiarmed and enrichment designs, which does not have these restrictions. An important application are clinical trials, where short-term surrogate endpoints are used as basis for trial adaptations, and we illustrate how such trials can be designed. We propose statistical models to assess the impact of effect sizes, the correlation structure between the short-term and the primary endpoint, the sample size, the timing of interim analyses, and the selection rule on the operating characteristics.

Point and interval estimation in two‐stage adaptive designs with time to event data and biomarker‐driven subpopulation selection

“…Alternatives include t 1 being a prespecified date. 3 , 25 Stage 1 consists of the data that are used in the interim analysis, with the survival times being the lengths of continuous lines in Figure 2 . As described below, we obtain estimates from these data based on the distribution of the score statistic.…”

“…These rules are valid when t 1 and t 2 are determined as above, that is independently, and they ( t 1 and t 2 ) are either prespecified dates, correspond to observation of prespecified numbers of events or are based on any other method for prespecifying duration of trials with time-to-event data. 3 , 25 In the first, a fixed time between t 1 and is prespecified. This rule achieves approximate independence for whether or not stage 1 patients from the dropped partitions without events at t 1 are followed until , though this should be specified before the trial and also, they should only be followed as part of the trial if they continue with the allocated treatments and adhere to the trial protocol.…”

Predicting outcomes of phase III oncology trials with Bayesian mediation modeling of tumor response

“…A few authors have considered conducting interim analysis and improving decisions for clinical trials based on early data 36,37 as well as short-term endpoints. 20,[38][39][40][41] This article presented prediction methodology for clinical trials using Bayesian mediation models in conjunction with simulation techniques based on posterior predictive sampling. Modeling and simulation techniques have been broadly applied to clinical trials 21,42,43 to help ascertain the PK and pharmacodynamics of the novel drugs as well as investigate its potential benefit to patients.…”

Clinical Trials Impacted by the COVID-19 Pandemic: Adaptive Designs to the Rescue?

“…In particular, this is relevant to studies interrupted by COVID-19 as investigators may wish conduct an early or unplanned interim analysis using the pre-pandemic data. Several proposals have been made to use the information on early read-outs to inform the adaptation decision (e.g., Friede et al 2011;Rufibach, Chen, and Nguyen 2016;Jörgens et al 2019). Although the information is different from the primary outcome with all limitations that this might have, a greater proportion of subjects can contribute to the analysis.…”

“…Similarly, methods for applying flexible study designs to time-to-event data have also been developed (Brückner, Burger, and Brannath 2018;Jörgens et al 2019). When data are separated into stages by the occurrence of the primary event, the Type I error will be compromised if information other than the current logrank test statistic is used for interim decisions (Bauer and Posch 2004).…”