Futility rules in bioequivalence trials with sequential designs.

Area of Science:

• Pharmacokinetics and Drug Development
• Biostatistics and Clinical Trial Design

Background:

• Regulatory agencies like Health Canada, US FDA, and EMA accept sequential designs for bioequivalence studies if Type I error is controlled at 5%.
• European Medicines Agency guidelines mandate the specification of stopping rules in sequential trial designs.

Purpose of the Study:

• To investigate the impact of different stopping rules on Type I error rates and statistical power in sequential bioequivalence trials.
• To evaluate the effect of futility rules on the performance of two-stage sequential bioequivalence study designs.

Main Methods:

• Conducted extensive trial simulations to assess five distinct futility rules.
• Analyzed the effects of these rules on Type I error rates and power within two-stage sequential bioequivalence trial scenarios.

Main Results:

• Stopping rules can significantly reduce statistical power, particularly under conditions of low initial sample size (Stage 1) and/or high data variability.
• Type I error rates were observed to be less sensitive to the application of various stopping rules compared to power.

Conclusions:

• Implementing specific futility rules in sequential bioequivalence trials can compromise statistical power, potentially hindering compliance with regulatory requirements.
• The use of overly optimistic futility rules may be considered unethical, especially when study variability is unknown beforehand, impacting trial success.
• This research provides the first comprehensive analysis of how futility rules influence Type I errors and power in sequential bioequivalence studies.