Patient-centric Pragmatic Subgroup Analyses in Clinical Trials based on The Desirability of Outcome Ranking (DOOR)

This dissertation investigates the application of the Desirability of Outcome Ranking(DOOR) for subgroup analysis in clinical trials, focusing on patient-centric benefit-risk assessment. Employing both novel and established statistical methods, this study addresses the challenges of analyzing ordinal outcomes and enhancing the understanding of treatment effects across diverse patient subgroups. Through a series of simulation studies and applications to real-world data, this study demonstrates how DOOR-based analyses can improve the clarity and applicability of clinical trial results. Key contributions include the development of a statistical test designed to detect treatment effect heterogeneity between subgroups, accompanied by a comprehensive evaluation of this test through simulation studies. The dissertation also evaluated both model-free and model-based analysis methods in simulated clinical settings and provided closed-form confidence intervals for the DOOR outcome based on these models. This research aims to contribute insights into subgroup analysis based on the DOOR outcome that can impact the benefit-risk assessments and provide a deeper understanding of how treatments can be precisely tailored to meet individual patient needs, thereby enhancing clinical outcomes and advancing personalized medicine.

Author

• Dai, Weixiao

Language

• English

Date created

• 2024

Type of Work

• Dissertation

License

• All rights reserved

Rights statement

• In Copyright

GW Unit

• Biostatistics (CCAS/SPHHS)

Degree

• Ph.D.

Advisor

• Hamasaki, Toshimitsu
• Evans, Scott

Committee Member(s)

• Gao, Guoqing

Persistent URL

•  https://scholarspace.library.gwu.edu/etd/9306t0217