Fixed and Adaptive Parallel Subgroup-Specific Design for Survival Outcomes: Power and Sample Size

Area of Science:

• Clinical Trials
• Biostatistics
• Translational Medicine

Background:

• Biomarker-guided clinical trials are crucial for stratified medicine.
• Planning these trials for adequate statistical power is challenging.
• Existing literature often lacks practical guidance for specific designs.

Purpose of the Study:

• To evaluate the parallel subgroup-specific design for biomarker-guided trials.
• To explore an adaptive version with early stopping for futility or efficacy.
• To provide methods for calculating sample size and power for time-to-event outcomes.

Main Methods:

• Focus on the parallel subgroup-specific design for simultaneous subgroup evaluation.
• Investigate an adaptive design with interim analyses based on event thresholds.
• Calculate required events and patients for sufficient power in each subgroup.
• Explore early stopping probabilities for the adaptive design.
• Implement multiplicity adjustments to control the overall type I error rate.

Main Results:

• Provides event and patient number calculations for ensuring subgroup power.
• Details stopping probabilities for the adaptive design under various scenarios.
• Addresses the challenge of testing multiple hypotheses and interim analyses.

Conclusions:

• The parallel subgroup-specific design offers a framework for evaluating biomarker-guided treatments.
• The adaptive version allows for efficient trial conduct through early stopping.
• Methodological guidance is provided for sample size, power, and multiplicity control in complex trial designs.