Related Experiment Video
Updated: Jul 14, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
Biomarker-adaptive threshold design: a procedure for evaluating treatment with possible biomarker-defined subset
Wenyu Jiang1, Boris Freidlin, Richard Simon
1Biometric Research Branch, Division of Cancer Treatment and Diagnosis, EPN-8122, National Cancer Institute, Bethesda, MD 20892, USA.
This study introduces a biomarker-adaptive trial design to improve the efficiency of identifying effective anticancer agents in sensitive patient subsets. This method enhances power when only a small group benefits, unlike traditional trials.
Area of Science:
- Biostatistics
- Clinical Trial Design
- Oncology
Background:
- Many targeted cancer therapies benefit only specific patient groups.
- Traditional trials may miss effective agents due to diluted treatment effects in broad populations.
- Biomarkers can identify sensitive subpopulations for targeted therapies.
Purpose of the Study:
- To propose a statistically rigorous biomarker-adaptive threshold Phase III design.
- To address challenges in evaluating targeted therapies with patient subsets.
- To identify sensitive patient populations using continuous or graded biomarkers.
Main Methods:
- Combined overall treatment effect testing with biomarker cut-point establishment and validation.
- Evaluated biomarker-adaptive design performance against traditional designs via simulation.
- Applied the biomarker-adaptive design to a prostate cancer clinical trial dataset.
Main Results:
- The adaptive design maintained power for overall treatment effects in broadly effective treatments.
- Significant efficiency gains were observed with the adaptive design when the sensitive population was small.
- Provided recommendations for sample size and implementation of the adaptive design.
Conclusions:
- A biomarker-defined subset effect test can be integrated into Phase III designs.
- This integration does not compromise the ability to detect overall treatment benefits.
- The proposed design offers a statistically valid approach for targeted therapy evaluation.
Related Concept Videos
Bioequivalence Experimental Study Designs: Repeated Measures, Cross-Over, Carry-Over, and Latin Square Designs
Types 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, controlled...
Therapeutic Drug Monitoring: Drug Analysis Methods
Bioavailability Study Design: Single Versus Multiple Dose Studies
Therapeutic Drug Monitoring: Overview and Classification
Therapeutic Drug Monitoring: Affecting Factors