Minimizing the maximum expected sample size in two-stage Phase II clinical trials with continuous outcomes

Area of Science:

• Clinical Trials Methodology
• Biostatistics
• Pharmaceutical Research

Background:

• Two-stage designs are standard for Phase II clinical trials.
• Existing optimal designs minimize expected sample size at the null value but can be inefficient if the true effect varies.
• This can lead to poor performance and wasted resources in early-phase drug development.

Purpose of the Study:

• To introduce a novel two-stage design for continuous treatment responses.
• To minimize the maximum expected sample size across all possible treatment effects.
• To provide a more robust and efficient design for Phase II trials.

Main Methods:

• Development of a new two-stage trial design.
• Focus on continuous treatment response data.
• Minimization of the maximum expected sample size as the primary optimization criterion.
• Comparison with a standard optimal two-stage design.

Main Results:

• The proposed design effectively minimizes the maximum expected sample size.
• It demonstrates robust performance across a wider range of true treatment effects.
• The new design exhibits superior expected sample size properties compared to the previously used optimal design.

Conclusions:

• The novel two-stage design offers improved efficiency and reliability for Phase II trials.
• It is particularly advantageous when the true treatment effect is uncertain.
• This approach enhances resource allocation in early-phase clinical studies.