Skip to content


Bayesian Methods to Borrow Information in Rare Disease Trials

Chair:  Ying Yuan (MD Anderson) and Yong Zang (Indiana)

Speaker: Chenguang Wang, PhD (Regeneron)
Title: Leveraging External Data in Ultra-rare Disease Trials
Therapeutic development for rare diseases presents unique challenges, not least of which is the limited sample size available for clinical trials. This poses significant difficulties for statisticians tasked with designing trials with reasonable study operating characteristics. In this presentation, we will specifically address trials with extremely small sample sizes, often around 20, which is common in ultra-rare diseases. We will explore the following issues related to the use of external data in these trials: 1) the impact of normality approximation on study operating characteristics, 2) the potential for improved covariate balance between current and external data to enhance study operating characteristics, and 3) the performance of various effective sample size evaluation methods in this context. We will use a trial for fibrodysplasia ossificans progressiva as a case study to illustrate these points.

Speaker: Beibei Guo, PhD (Louisianan State University)
Title: Adaptive Hybrid Control Design for Comparative Clinical Trials with Historical Control Data
Abstract: While a randomized controlled trial (RCT) is considered the gold standard for evaluating and estimating the causal effect of a new treatment compared to a control, it often necessitates large sample sizes, making it less suitable for rare diseases. Recognizing this challenge, the FDA has provided guidance on incorporating real-world evidence into drug development. In addressing these considerations, we propose an Adaptive Hybrid Control Causal (AHCC) design. This innovative approach aims to leverage historical control data, thereby reducing the sample size requirements associated with standard RCTs. Simulation studies demonstrate that the AHCC design achieves significant sample size savings when substantial information can be borrowed from historical controls. Importantly, it maintains statistical power even when limited information is available from the historical control dataset.

Speaker: Ying Yuan, PhD (MD Anderson)
Title: BASIC: A Bayesian Adaptive Synthetic-control Design for Phase II Clinical Trials
Abstract: Randomized controlled trials (RCTs) are considered the gold standard for evaluating experimental treatments, but often require large sample sizes. Single-arm trials require smaller sample sizes, but are subject to bias when using historical control data (HCD) for comparative inferences. This talk presents a Bayesian adaptive synthetic control (BASIC) design that exploits HCD to create a hybrid of a single-arm trial and an RCT.BASIC has two stages. In stage 1, a prespecified number of patients are enrolled in a single arm given the experimental treatment. Based on the stage 1 data, applying propensity score matching and Bayesian posterior prediction methods, the usefulness of the HCD for identifying a pseudo-sample of matched synthetic control patients for making comparative inferences is evaluated. If a sufficient number of synthetic controls can be identified, the single arm trial is continued. If not, the trial is switched to an RCT. The performance of BASIC is evaluated by computer simulation. BASIC achieves power and unbiasedness similar to an RCT, but on average requires a much smaller sample size, provided that the HCD patients are sufficiently comparable to the trial patients so that a good number of matched controls can be identified in the HCD. Compared to a single-arm trial, BASIC yields much higher power and much smaller bias.