Bayesian enhancement two-stage design with error control for phase II clinical trials

Area of Science:

• Clinical Trials
• Biostatistics
• Pharmaceutical Development

Background:

• Phase II clinical trials are crucial for deciding progression to Phase III studies.
• Many drugs fail Phase III despite promising Phase II results, indicating a need for improved trial designs.
• Simon's two-stage design has limitations in strengthening passing criteria for drug efficacy.

Purpose of the Study:

• To introduce the Bayesian enhancement two-stage with error control (BETEC) design for phase II single-arm clinical trials.
• To enhance the decision-making process in early-phase drug development by improving trial stability and evidence strength.
• To provide a more interpretable and balanced alternative to existing trial designs.

Main Methods:

• The BETEC design replaces the highest posterior density (HPD) interval length with the posterior error rate for calibration.
• It computes posterior probabilities of null (H0) and alternative (H1) hypotheses.
• Extensive simulation studies and application to two recent clinical trials were used for comparison.

Main Results:

• The BETEC design achieves a balance between posterior false positive and false negative rates.
• It offers greater transparency and interpretability compared to the BET design's HPD interval length.
• Simulations and case studies demonstrate BETEC's efficiency and effectiveness.

Conclusions:

• The BETEC design provides an efficient and intuitive alternative for implementing phase II single-arm trials.
• It strengthens the criteria for advancing drug development, reducing late-stage failures.
• BETEC offers a practical and interpretable approach for biostatisticians and clinical researchers.