Optimal design of clinical trials comparing several treatments with a control

Abstract

Clinical trials are often designed to compare several treatments with a common control arm in pairwise fashion. In this paper we study optimal designs for such studies, based on minimizing the total number of patients required to achieve a given level of power. A common approach when designing studies to compare several treatments with a control is to achieve the desired power for each individual pairwise treatment comparison. However, it is often more appropriate to characterize power in terms of the family of null hypotheses being tested, and to control the probability of rejecting all, or alternatively any, of these individual hypotheses. While all approaches lead to unbalanced designs with more patients allocated to the control arm, it is found that the optimal design and required number of patients can vary substantially depending on the chosen characterization of power. The methods make allowance for both continuous and binary outcomes and are illustrated with reference to two clinical trials, one involving multiple doses compared to placebo and the other involving combination therapy compared to mono-therapies. In one example a 55% reduction in sample size is achieved through an optimal design combined with the appropriate characterization of power.

Cluster-randomised controlled trials of individual and combined water, sanitation, hygiene and nutritional interventions in rural Bangladesh and Kenya: the WASH Benefits study design and rationale

“…We chose the effect size for diarrhoea based on earlier WASH efficacy studies 111. The control arm is double sized because it will be used in multiple hypothesis tests and, given available information, a 2:1 allocation ratio is close to the optimal allocation that minimises the variance for the six tests planned under our first hypothesis, below 112 113. Online supplementary appendix 4 includes the detailed assumptions used in the calculations.…”

Optimum treatment allocation rules under a variance heterogeneity model

“…An early application of continuous design theory to clinical trial is to finding optimal rules for patient assignment in a sequential trial [3]. Interest continues to this day to apply optimal design ideas to find allocation schemes in different settings, that includes optimal design for study with a placebo and several treatment groups [4,5,6]. In what is to follow, we apply optimal design theory to design a randomized trial whose objectives are to compare a continuous outcome from treatment groups, with possibly different emphasis in each comparison, and the variance of the outcome varies across the groups.…”

Uncovering noisy social signals: Using optimization methods from experimental physics to study social phenomena

“…Examples include, but are not limited to, determining the value of continuous treatments in economic decision experiments (offered prices, product features, etc. [39]), determining optimal dosages of medical treatments, determining optimal values of health promotion feedback (see [40]), or choosing the speed at which stimuli are displayed in reaction tasks such that effects are magnified (such as [41]). Note that LiF can be used not only to position treatments during experiments but can also be of use in practical applications [23].…”