Bayesian semiparametric<scp>meta‐analytic‐predictive</scp>prior for historical control borrowing in clinical trials

Hupf, Bradley; Bunn, Veronica; Lin, Jianchang; Dong, Cheng

doi:10.1002/sim.8970

Cited by 24 publications

(15 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Schmidli et al 10 proposed a robust MAP, in which the robustness is achieved by adding an extra weakly informative component to the prior. Hupf et al 11 proposed to use a Dirichlet process mixture to adaptively borrow the information from historical data.…”

Section: Introductionmentioning

confidence: 99%

A novel power prior approach for borrowing historical control data in clinical trials

Shi

Liu

2023

Stat Methods Med Res

View full text Add to dashboard Cite

There has been an increased interest in borrowing information from historical control data to improve the statistical power for hypothesis testing, therefore reducing the required sample sizes in clinical trials. To account for the heterogeneity between the historical and current trials, power priors are often considered to discount the information borrowed from the historical data. However, it can be challenging to choose a fixed power prior parameter in the application. The modified power prior approach, which defines a random power parameter with initial prior to control the amount of historical information borrowed, may not directly account for heterogeneity between the trials. In this paper, we propose a novel approach to pick a power prior based on some direct measures of distributional differences between historical control data and current control data under normal assumptions. Simulations are conducted to investigate the performance of the proposed approach compared with current approaches (e.g. commensurate prior, meta-analytic-predictive, and modified power prior). The results show that the proposed power prior improves the study power while controlling the type I error within a tolerable limit when the distribution of the historical control data is similar to that of the current control data. The method is developed for both superiority and non-inferiority trials and is illustrated with an example from vaccine clinical trials.

show abstract

Section: Introductionmentioning

confidence: 99%

A novel power prior approach for borrowing historical control data in clinical trials

Shi

Liu

2023

Stat Methods Med Res

View full text Add to dashboard Cite

show abstract

“…Bunn et al [ 18 ] show that such models require fewer assumptions than other more commonly used methods and allow more reliable data-driven decision-making in basket trials. Hupf et al [ 19 ] further extend these flexible Bayesian borrowing strategies to incorporate historical or real-world data.…”

Section: Case Studiesmentioning

confidence: 99%

Machine Learning and Artificial Intelligence in Pharmaceutical Research and Development: a Review

Kolluri

Lin

Liu

et al. 2022

AAPS J

Self Cite

130

View full text Add to dashboard Cite

Graphical abstract Over the past decade, artificial intelligence (AI) and machine learning (ML) have become the breakthrough technology most anticipated to have a transformative effect on pharmaceutical research and development (R&D). This is partially driven by revolutionary advances in computational technology and the parallel dissipation of previous constraints to the collection/processing of large volumes of data. Meanwhile, the cost of bringing new drugs to market and to patients has become prohibitively expensive. Recognizing these headwinds, AI/ML techniques are appealing to the pharmaceutical industry due to their automated nature, predictive capabilities, and the consequent expected increase in efficiency. ML approaches have been used in drug discovery over the past 15–20 years with increasing sophistication. The most recent aspect of drug development where positive disruption from AI/ML is starting to occur, is in clinical trial design, conduct, and analysis. The COVID-19 pandemic may further accelerate utilization of AI/ML in clinical trials due to an increased reliance on digital technology in clinical trial conduct. As we move towards a world where there is a growing integration of AI/ML into R&D, it is critical to get past the related buzz-words and noise. It is equally important to recognize that the scientific method is not obsolete when making inferences about data. Doing so will help in separating hope from hype and lead to informed decision-making on the optimal use of AI/ML in drug development. This manuscript aims to demystify key concepts, present use-cases and finally offer insights and a balanced view on the optimal use of AI/ML methods in R&D.

show abstract

“…By relaxing the parametric assumption on the random effects, the BaSe-MAP prior adaptively learn the relationship between the historical data and current control data while still being able to discount the historical data in case of prior-data conflict. The full BaSe-MAP prior for binary endpoint proposed by Hupf et al 19 is given by:…”

Section: Base-map Prior For Time-to-event Endpointsmentioning

confidence: 99%

BEATS: Bayesian hybrid design with flexible sample size adaptation for time‐to‐event endpoints

Bi,

Liu,

Lin

et al. 2023

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

As the roles of historical trials and real‐world evidence in drug development have substantially increased, several approaches have been proposed to leverage external data and improve the design of clinical trials. While most of these approaches focus on methodology development for borrowing information during the analysis stage, there is a risk of inadequate or absent enrollment of concurrent control due to misspecification of heterogeneity from external data, which can result in unreliable estimates of treatment effect. In this study, we introduce a Bayesian hybrid design with flexible sample size adaptation (BEATS) that allows for adaptive borrowing of external data based on the level of heterogeneity to augment the control arm during both the design and interim analysis stages. Moreover, BEATS extends the Bayesian semiparametric meta‐analytic predictive prior (BaSe‐MAP) to incorporate time‐to‐event endpoints, enabling optimal borrowing performance. Initially, BEATS calibrates the expected sample size and initial randomization ratio based on heterogeneity among the external data. During the interim analysis, flexible sample size adaptation is performed to address conflicts between the concurrent and historical control, while also conducting futility analysis. At the final analysis, estimation is provided by incorporating the calibrated amount of external data. Therefore, our proposed design allows for an approximation of an ideal randomized controlled trial with an equal randomization ratio while controlling the size of the concurrent control to benefit patients and accelerate drug development. BEATS also offers optimal power and robust estimation through flexible sample size adaptation when conflicts arise between the concurrent control and external data.

show abstract

Bayesian semiparametricmeta‐analytic‐predictiveprior for historical control borrowing in clinical trials

Cited by 24 publications

References 38 publications

A novel power prior approach for borrowing historical control data in clinical trials

A novel power prior approach for borrowing historical control data in clinical trials

Machine Learning and Artificial Intelligence in Pharmaceutical Research and Development: a Review

BEATS: Bayesian hybrid design with flexible sample size adaptation for time‐to‐event endpoints

Contact Info

Product

Resources

About