Cautionary note on regional consistency evaluation in multiregional clinical trials with binary outcomes

Area of Science:

• Clinical Trials
• Biostatistics
• Drug Development

Background:

• Multiregional clinical trials (MRCTs) are crucial for global drug approvals.
• Determining appropriate regional sample sizes in MRCTs presents a significant statistical challenge.
• Existing methods for calculating regional consistency probabilities are primarily designed for continuous outcomes.

Purpose of the Study:

• To evaluate the accuracy of existing formulas for regional consistency probability in MRCTs with binary outcomes.
• To develop and validate novel formulas for accurate regional consistency probability calculations in binary outcome MRCTs.
• To provide a practical tool for sample size determination in MRCTs, particularly for binary endpoints.

Main Methods:

• Simulation studies were conducted to assess the performance of existing and proposed formulas.
• The accuracy of formulas was evaluated based on their ability to predict regional consistency probabilities.
• The proposed formulas were applied to a real-world MRCT case study.

Main Results:

• Existing closed-form formulas were found to be inaccurate for binary outcomes, even with large sample sizes.
• The newly developed alternative formulas demonstrated high accuracy in predicting regional consistency probabilities.
• The proposed formulas offer a reliable method for sample size calculations in binary outcome MRCTs.

Conclusions:

• Current statistical formulas for regional consistency are not suitable for binary outcomes in MRCTs.
• The developed alternative formulas provide accurate sample size estimations for binary outcome MRCTs.
• These findings are critical for optimizing MRCT design and ensuring successful global drug development.