Designing and analysing clinical trials in mental health: an evidence synthesis approach

Abstract

Objective When planning a clinical study, evidence on the treatment effect is often available from previous studies. However, this evidence is mostly ignored for the analysis of the new study. This is unfortunate, since using it could lead to a smaller study without compromising power. We describe a design that addresses this issue. Methods We use a Bayesian meta-analytic model to incorporate the available evidence in the analysis of the new study. The shrinkage estimate for the new study integrates the evidence from the other studies. At the planning phase of the study, it allows a statistically justified reduction of the sample size. Results The design is illustrated using data from an Food and Drug Administration (FDA) review of lurasidone for the treatment of schizophrenia. Three studies inform the meta-analysis before the new study is conducted. Results from an additional phase III study, which were not available at the time of the FDA review, are then used for the actual analysis. Conclusions In the presence of reliable and relevant evidence, the design offers a way to conduct a smaller study without compromising power. It therefore fills a gap between the assessment of evidence and its actual use in the design and analysis of studies. INTRODUCTIONClinical trials are a cornerstone of evidence-based medicine. The impressive number of more than 220 000 registered trials in the electronic database http://www.clinicaltrials.gov supports this statement, and further growth at an accelerated rate is likely. While this number shows the importance of clinical research, it also reveals that typically more than one clinical study investigating the same treatment (or interventions) is conducted. When designing a clinical study, it is therefore good practice to review the literature 1 and assess the body of evidence. This will provide information on the previous experience in the field and relevant topics such as commonly used end points, challenges with missing data and expected patient enrolment. It may also undermine the need for a new study.1 2 The latter is specifically important since resources to fund studies are limited and competition is high, whether in academia or industry. While all of the preceding reasons justify the need to conduct a systematic review before starting a new study, this is even more critical for statistical reasons. Defining end points, analysis sets, primary and secondary analyses and, most importantly, the sample size calculation critically depends on realistic and reliable assumptions. However, for all of these tasks, the information (data) from the review is used only indirectly in the new study. For example, an estimated treatment effect from a meta-analysis can serve as the base for the sample size calculation, yet it will not contribute to the actual analysis of the study. This is unfortunate, since it means that in the actual analysis, we ignore what we know already. Using the information in the analysis, too, could lead to a smaller study or to higher power. The question t...

Minimizing Patient Burden Through the Use of Historical Subject-Level Data in Innovative Confirmatory Clinical Trials: Review of Methods and Opportunities

“…There are, however, several illustrative examples in the recent literature of how the types of historical borrowing methodologies discussed here could be applied in a late phase development for a broader range of disease areas. For example, Wandel and Roychoudhary discuss how Bayesian meta-analytic priors could be used to reduce the sample size requirements for a new phase 3 study in schizophrenia using historical data from two phase 2 studies and one previous phase 3 study 92 ; Dejardin et al compare several of the dynamic borrowing methods summarized in Table 3 for including historical controls in the design of a phase 3 non-inferiority trial of a novel antibacterial agent. 93 In the near future, we expect and hope to see more examples of successful regulatory approvals in larger disease areas and/or larger trials, based on the approaches discussed in the Review of Bayesian Approaches and Review of Frequentist Propensity Score Approaches sections of this paper.…”

Applying Meta-Analytic-Predictive Priors with the R Bayesian Evidence Synthesis Tools

“…Important decisions should arguably be evidence based, especially in medicine (Eddy 1990;Wandel and Roychoudhury 2016). For example, decisions regarding design and analysis of clinical trials are important for trial sponsors, patients, physicians and policy makers.…”

Dynamic Historical Data Borrowing Using Weighted Average

“…While Dejardin et al. (2018), Wandel and Roychoudhury (2016), and many other studies demonstrated successful cases with approvals, regulatory's evaluation and recommendation call for rigorous statistical methodologies when augmenting current control data with historical data. This is due to the concerns of potential bias in treatment effect estimation, and Type‐1 error rate inflation in hypothesis testing, among many others, when historical data are borrowed.…”

“…To more efficiently and timely deliver safe and efficacious treatment to patients in need, regulatory agencies have demonstrated willingness to accept the use of historical controls in clinical trials (Goodman, 1988;ICH Harmonised Tripartite Guideline, 2000;European Medicines Agency, 2006). While Dejardin et al (2018), Wandel and Roychoudhury (2016), and many other studies demonstrated successful cases with approvals, regulatory's evaluation and recommendation call for rigorous statistical methodologies when augmenting current control data with historical data. This is due to the concerns of potential bias in treatment effect estimation, and Type-1 error rate inflation in hypothesis testing, among many others, when historical data are borrowed.…”