Exact power and sample size in clinical trials with two co-primary binary endpoints.

Area of Science:

• Clinical Trials
• Biostatistics
• Medical Research

Background:

• Clinical trials frequently use binary endpoints to assess treatment efficacy.
• Some therapeutic areas necessitate two co-primary binary endpoints for comprehensive treatment benefit evaluation.
• Current methods for two co-primary endpoints often rely on approximations or complex simulations.

Purpose of the Study:

• To develop exact methods for calculating power and sample size in clinical trials with two co-primary binary endpoints.
• To enable the incorporation of correlation between co-primary endpoints for improved trial design.
• To provide a more efficient approach for sample size determination in such trials.

Main Methods:

• Proposed novel methods for calculating exact statistical power and sample size.
• Developed calculations that account for the correlation between two co-primary binary endpoints.
• Validated the methods through numerical investigations across various scenarios.

Main Results:

• The proposed methods accurately incorporate endpoint correlation into sample size calculations.
• Utilizing these methods can significantly reduce the required sample size for clinical trials.
• The calculated exact power closely matches the target power for the determined sample size.

Conclusions:

• The developed exact methods offer a precise and efficient approach for designing clinical trials with two co-primary binary endpoints.
• Accounting for endpoint correlation is crucial for optimizing sample size and trial power.
• These methods are applicable to various statistical tests for binary endpoints and have been demonstrated in a real-world clinical trial application.