Data-Driven
Open Access DepositedTwo-Stage Adaptive Design and Patient Enrichment for Different Types of Outcomes with Continuous Biomarkers
Downloadable Content
We propose a Two-Stage Biomarker Adaptive Patient Enrichment Design(2SB-APED), an adaptive trial design that selectively recruits a biomarkerdefined subgroup expected to benefit most from treatment. The design refines the patient population to optimize power while controlling type I errors. 2SB-APED is implemented for continuous, binary, and survival outcomes, with an interim decision rule to determine whether to continue with all patients or enrich recruitment with biomarker-positive patients. It includes an early stopping rule for futility. Generalized Additive Models (GAMs) are used for flexible, data-driven estimation without strict parametric assumptions [1, 2]. Through simulation studies, we show that when a biomarker subgroup exists, 2SB-APED achieves higher power and more efficient patient recruitment than nonadaptive designs. We illustrate its application in two clinical trials
the IR-DME study (continuous and binary outcomes) and the GBSG trial (survival outcomes) [3, 4, 5]. Results confirm that 2SB-APED improves statistical efficiency while enhancing treatment benefits for biomarker subgroups.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.