Bayesian methods for the incorporation of real world data into the design and analysis of randomized controlled trials

Loading...
Thumbnail Image

Persistent link to this item

Statistics
View Statistics

Journal Title

Journal ISSN

Volume Title

Title

Bayesian methods for the incorporation of real world data into the design and analysis of randomized controlled trials

Published Date

2023-05

Publisher

Type

Thesis or Dissertation

Abstract

Randomized controlled trials (RCTs) are considered the most rigorous form of clinical evidence for regulatory decision making and are the gold-standard for studying causal relationships. Though RCTs have benefits, they also have some drawbacks. One major criticism of RCTs is that they are inefficient, requiring substantial and steadily increasing costs in both time and money. One way to increase efficiency of RCTs would be to leverage external data on one or both trial arms in the design or analysis of the RCT. Though RCTs do not traditionally leverage external data, there are often multiple sources of external data that could be leveraged to improve the efficiency of a RCT, such as previously conducted early phase clinical trials, concurrently conducted observational studies, electronic health records, medicare claims data, and other real world data (RWD) sources. Incorporating these data could lead to desirable properties, such as increasing precision, decreasing necessary sample size, and reducing costs, but this must be done rigorously to avoid undermining the advantages of RCTs. In this dissertation we investigate Bayesian approaches to incorporating external data into the design and analysis of randomized controlled trials. We aim to improve trial efficiency by decreasing necessary trial sample size, improving trial power, alongside improving statistical precision of secondary trial analyses that often are underpowered. In Chapter 2, we introduce a Bayesian approach for incorporating observational data into the analysis of a clinical trial through a Semi-Supervised Mixture distribution and Multisource Exchangeability Model (SS-MIX-MEM). We then apply the SS-MIX-MEM to the context of binary outcomes, when many of the same baseline covariates are measured between the RCT and the observational study, and there is no missingness through an analysis of the INSIGHT FLU-IVIG trial and illustrate how we can gain efficiency by incorporating the data from INSIGHT FLU 003 via the SS-MIX-MEM approach. In Chapter 3, we introduce a trial design that facilitates borrowing during an interim futility analysis using the SS-MIX-MEM approach. We also find the optimal stopping point for this trial design, which aims to leverage external data to improve trial efficiency by stopping ineffective treatments earlier, with fewer trial participants without inflating type 1 error as we only allow early stopping and borrowing in an interim futility analysis. In Chapter 4, we apply the SS-MIX-MEM approach to a secondary analysis of a recently conducted randomized controlled trial, COVID-OUT, borrowing from external N3C data to increase effective trial sample size and power. This analysis focuses on the secondary composite endpoint of emergency department visits and hospitalizations for Covid-19, and all-cause mortality through 28 days, which is a clinically important endpoint to guidelines committees and regulators. In summary, incorporating external RWD into the design and analysis of randomized controlled trials is a promising and exciting area of research that could potentially allow us to leverage the complementary strengths of RWD and RCT data to move clinical research forward.

Keywords

Description

University of Minnesota Ph.D. dissertation.May 2023. Major: Biostatistics. Advisors: Joseph Koopmeiners, Thomas Murray. 1 computer file (PDF); iii, 106 pages.

Related to

Replaces

License

Collections

Series/Report Number

Funding information

Isbn identifier

Doi identifier

Previously Published Citation

Other identifiers

Suggested citation

Haine, Lillian. (2023). Bayesian methods for the incorporation of real world data into the design and analysis of randomized controlled trials. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/258748.

Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.