A Bayesian adaptive design for multi-dose, randomized, placebo-controlled phase I/II trials

Area of Science:

• Clinical Trials
• Biostatistics
• Pharmacology

Background:

• Traditional randomized controlled trials (RCTs) often require separate phases for dose safety and efficacy evaluation.
• This can lead to prolonged trial durations and larger sample sizes.
• Optimizing dose-finding is crucial for efficient drug development.

Purpose of the Study:

• To introduce and evaluate a novel adaptive randomized controlled trial design.
• To assess the efficiency and statistical properties of this design compared to conventional approaches.
• To facilitate simultaneous dose escalation and cohort expansion for improved drug development.

Main Methods:

• The proposed design integrates dose escalation and cohort expansion iteratively.
• Adaptive cohort expansion decisions are guided by Bayesian rules based on interim dose-placebo comparisons.
• Simulations were used to evaluate operating characteristics across various toxicity and efficacy scenarios.

Main Results:

• The adaptive design demonstrated a reduction in total sample size compared to conventional methods.
• Sample size reduction was more significant when tested doses were ineffective.
• The design effectively controlled the false positive error rate and maintained adequate statistical power.

Conclusions:

• The proposed adaptive design optimizes dose-finding by removing ineffective doses and reducing sample size.
• This approach maintains statistical power for detecting treatment effects.
• The design has been implemented in an ongoing study, with simulation software available.