Bayesian adaptive N‐of‐1 trials for estimating population and individual treatment effects

Abstract

This article proposes a novel adaptive design algorithm that can be used to find optimal treatment allocations in N-of-1 clinical trials. This new methodology uses two Laplace approximations to provide a computationally efficient estimate of population and individual random effects within a repeated measures, adaptive design framework. Given the efficiency of this approach, it is also adopted for treatment selection to target the collection of data for the precise estimation of treatment effects. To evaluate this approach, we consider both a simulated and motivating N-of-1 clinical trial from the literature. For each trial, our methods were compared with the multiarmed bandit approach and a randomized N-of-1 trial design in terms of identifying the best treatment for each patient and the information gained about the model parameters. The results show that our new approach selects designs that are highly efficient in achieving each of these objectives. As such, we propose our Laplace-based algorithm as an efficient approach for designing adaptive N-of-1 trials.

What research methodologies could make a difference in disability?

“…Adaptive design can also apply to N-of-1 trials to estimate treatment effects in individuals and populations. 3 Bayesian rather than frequentist statistics can be used in all these designs to make the most of prior information and update our beliefs in the event of new data. 4 We must listen to the voices of individuals with developmental neurodisability as they call for dramatic improvements in research.…”

Controlled evaLuation of Angiotensin Receptor Blockers for COVID-19 respIraTorY disease (CLARITY): statistical analysis plan for a randomised controlled Bayesian adaptive sample size trial

“…Accordingly, a fast approach to form an approximation of the posterior distribution is needed. Consequently, the Laplace approximation [ 31 ] will be adopted, as has been used previously for a similar purpose [ 32 , 33 ]. Based on this posterior, an indicator function is evaluated to determine whether treatment effectiveness would be concluded at the pre-specified level of evidence ( Δ =0.975), if the outcomes from all enrolled participants were ascertained (line 6).…”

Controlled evaLuation of Angiotensin Receptor Blockers for COVID-19 respIraTorY disease (CLARITY): Statistical analysis plan for a randomised controlled Bayesian adaptive sample size trial

“…Accordingly, a fast approach to form an approximation of the posterior distribution is needed. Consequently, the Laplace approximation [17] will be adopted, as has been used previously for a similar purpose [23,30]. Based on this posterior, an indicator function is evaluated to determine whether treatment effectiveness would be concluded at the pre-specified level of evidence (∆ = 0.975), if the outcomes from all enrolled participants were ascertained (line 6).…”