A two-stage design with two co-primary endpoints

Area of Science:

• Clinical Trials Methodology
• Biostatistics
• Oncology Drug Development

Background:

• Two-stage designs are standard in phase II oncology trials to avoid ineffective drugs.
• Current designs typically focus on a single efficacy endpoint, often response rate.
• Controlling Type I and II errors is crucial when multiple endpoints are involved.

Purpose of the Study:

• To propose a method for extending two-stage oncology trial designs to accommodate two co-primary efficacy endpoints.
• To develop a simultaneous search for stopping boundaries that control overall Type I (α) and Type II (β) errors.
• To provide a framework for selecting optimal designs based on objective functions.

Main Methods:

• Utilizing binomial distribution to define stopping boundaries for two hypotheses.
• Simultaneously searching for boundaries that satisfy predefined α and β error constraints.
• Employing simulation studies to validate the proposed methodology and design characteristics.
• Illustrating the application with a metastatic breast cancer trial example incorporating response rate and quality of life.

Main Results:

• A novel method for designing two-stage oncology trials with two co-primary endpoints was developed.
• The method allows for simultaneous optimization of stopping rules while controlling overall error rates.
• Simulation results confirm the validity and efficiency of the proposed approach.

Conclusions:

• The proposed design is a practical extension of the Simon Two-Stage Design for phase II oncology trials.
• This methodology is suitable for trials with two independent co-primary efficacy endpoints.
• The approach facilitates more robust trial designs when multiple efficacy measures are critical.