EUVIMEDDescobrir EUVIMED
Open access

Bayesian adaptive design for covariate‐adaptive historical control information borrowing

Huaqing Jin iD, Mi-Ok Kim iD, Aaron Scheffler, Fei Jiang

Statistics in Medicine · 2023

DOI: 10.1002/sim.9913 ↗

At a glance

Journal article in Statistics in Medicine, 2023. Written by Huaqing Jin and 3 co-authors. Institution: Department of Radiology and Biomedical Imaging, University of California, San Francisco, California. Major MEDLINE topics: Bayes Theorem, Research Design. Cited 2 times so far (Crossref); 40 references. The full text is freely available in PubMed Central. Funded by: NIA NIH HHS, NIH HHS, National Institutes of Health.

ResumoSubjectsDados bibliográficosCiteRelated studies

Abstract (original language)

Interest in incorporating historical data in the clinical trial has increased with the rising cost of conducting clinical trials. The intervention arm for the current trial often requires prospective data to assess a novel treatment, and thus borrowing historical control data commensurate in distribution to current control data is motivated in order to increase the allocation ratio to the current intervention arm. Existing historical control borrowing adaptive designs adjust allocation ratios based on the commensurability assessed through study‐level summary statistics of the response agnostic of the distributions of the trial subject characteristics in the current and historical trials. This can lead to distributional imbalance of the current trial subject characteristics across the treatment arms as well as between current control data and borrowed historical control data. Such covariate imbalance may threaten the internal validity of the current trial by introducing confounding factors that affect study endpoints. In this article, we propose a Bayesian design which borrows and updates the treatment allocation ratios both covariate‐adaptively and commensurate to covariate dependently assessed similarity between the current and historical control data. We employ covariate‐dependent discrepancy parameters which are allowed to grow with the sample size and propose a regularized local regression procedure for the estimation of the parameters. The proposed design also permits the current and the historical controls to be similar to varying degree, depending on the subject level characteristics. We evaluate the proposed design extensively under the settings derived from two placebo‐controlled randomized trials on vertebral fracture risk in post‐menopausal women.

Subjects

MeSH terms (MEDLINE)

Bayes TheoremResearch DesignFemaleHumansComputer SimulationProspective StudiesSample SizeClinical Trials as Topic

Author keywords

Bayesiancovariate-adaptivehigh dimensionalhistorical samplekernel

Authors and institutions

  • Department of Radiology and Biomedical Imaging, University of California, San Francisco, California.
  • Department of Epidemiology and Biostatistics, University of California, San Francisco, California.

ORCID profiles: Huaqing Jin, Mi-Ok Kim

Funding

  • NIA NIH HHS
  • NIH HHS
  • National Institutes of Health
  • National Science Foundation

Cite

APA

Jin, H., Kim, M. O., Scheffler, A., & Jiang, F. (2023). Bayesian adaptive design for covariate‐adaptive historical control information borrowing. Statistics in Medicine. https://doi.org/10.1002/sim.9913

Vancouver

Jin H, Kim MO, Scheffler A, Jiang F. Bayesian adaptive design for covariate‐adaptive historical control information borrowing. Statistics in Medicine. 2023. doi:10.1002/sim.9913

BibTeX
@article{Jin2023,
  author = {Jin, Huaqing and Kim, Mi-Ok and Scheffler, Aaron and Jiang, Fei},
  title = {Bayesian adaptive design for covariate‐adaptive historical control information borrowing},
  journal = {Statistics in Medicine},
  year = {2023},
  doi = {10.1002/sim.9913}
}
Start for free →