Cancer immunotherapy trial design with delayed treatment effect.

Area of Science:

• Clinical Trials
• Biostatistics
• Cancer Research

Background:

• Cancer immunotherapy trials face challenges with delayed treatment effects, violating proportional hazards assumptions.
• Traditional log-rank tests lose statistical power when delayed effects are ignored.
• Existing piecewise weighted log-rank tests have inaccurate sample size formulas, especially for small hazard ratios or unbalanced designs.

Purpose of the Study:

• To develop a new, accurate sample size formula for cancer immunotherapy trials accounting for delayed treatment effects.
• To address the limitations of existing methods in sample size estimation for both balanced and unbalanced trial designs.

Main Methods:

• Derived a novel sample size formula based on a fixed alternative hypothesis for the delayed treatment effect model.
• Conducted simulation studies to evaluate the accuracy of the new formula compared to existing methods.

Main Results:

• The new sample size formula provides accurate estimations for balanced trial designs.
• The formula also accurately estimates sample sizes for unbalanced trial designs, unlike previous methods.
• Improved statistical power in cancer immunotherapy trial designs is achievable with accurate sample size calculations.

Conclusions:

• The proposed sample size formula offers a more reliable approach for designing cancer immunotherapy trials with delayed treatment effects.
• Accurate sample size determination is crucial for maintaining statistical power and ensuring the validity of trial outcomes.
• This work contributes to more efficient and effective clinical trial design in oncology.