Related Experiment Video
Updated: Aug 15, 2025
Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
Utility of propensity score-based Bayesian borrowing of external adult data in pediatric trials: A pragmatic
Antara Majumdar1, Rebecca Rothwell2, Gregory Reaman3
1Oncology Biostatistics, GlaxoSmithKline, Collegeville, PA, USA.
Insights
Conducting pediatric cancer trials is difficult due to low patient numbers. This study uses Bayesian methods and propensity score matching to borrow data from adult trials, improving pediatric trial feasibility and assessment.
Area of Science:
- Biostatistics
- Pediatric Oncology
- Clinical Trial Design
Background:
- Pediatric cancer clinical trials face enrollment challenges due to low disease incidence.
- Leveraging external adult trial data can enhance pediatric trial feasibility when appropriate.
- Bayesian analysis offers a method for integrating external adult data into pediatric trial assessments.
Purpose of the Study:
- To investigate methods for effectively borrowing information from external adult cancer trials for pediatric trials.
- To assess the utility of propensity score matching in selecting relevant adult subjects for data borrowing.
- To examine the application of Bayesian mixture and power priors in pediatric trial efficacy assessment using external data.
Main Methods:
- Utilized Bayesian analysis to augment pediatric trial data with external adult trial data.
- Employed propensity score matching to align external adult subjects with pediatric subjects based on clinical covariates.
- Applied propensity score matched mixture and power priors for information borrowing in a pediatric acute lymphoblastic leukemia (ALL) case study.
Main Results:
- Propensity score matching effectively identified clinically relevant adult subjects for data borrowing.
- Bayesian methods, incorporating matched external data, improved the assessment of pediatric trial efficacy.
- Demonstrated the utility of this approach in a case study of pediatric acute lymphoblastic leukemia (ALL).
Conclusions:
- Propensity score matched Bayesian methods enhance the feasibility and statistical power of pediatric cancer trials.
- Borrowing information from carefully selected external adult trials is a viable strategy for pediatric oncology research.
- Considerations for scaling fixed borrowing from external adult data were presented.
Abstract:
A fully powered randomized controlled cancer trial can be challenging to conduct in children because of difficulties in enrollment of pediatric patients due to low disease incidence. One way to improve the feasibility of trials in pediatric patients, when clinically appropriate, is through borrowing information from comparable external adult trials in the same disease. Bayesian analysis of a pediatric trial provides a way of seamlessly augmenting pediatric trial efficacy data with data from external adult trials. However, not all external adult trial subjects may be equally clinically relevant with respect to the baseline disease severity, prognostic factors, co-morbidities, and prior therapy observed in the pediatric trial of interest. The propensity score matching method provides a way of matching the external adult subjects to the pediatric trial subjects on a set of clinically determined baseline covariates, such as baseline disease severity, prognostic factors and prior therapy. The matching then allows Bayesian information borrowing from only the most clinically relevant external adult subjects. Through a case study in pediatric acute lymphoblastic leukemia (ALL), we examine the utility of propensity score matched mixture and power priors in bringing appropriate external adult efficacy information into pediatric trial efficacy assessment, and present considerations for scaling fixed borrowing from external adult data.
Related Concept Videos
01:22Bone Marrow Sampling and Transplants
The transplant begins with high doses of chemotherapy and radiation treatment, which aim to destroy...
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
01:12Analysis of Population Pharmacokinetic Data