Phase II dose-response trials: A simulation study to compare analysis method performance under design considerations.

Area of Science:

• Clinical Trials Methodology
• Biostatistics
• Drug Development

Background:

• Phase II trials are crucial for determining dose-response relationships and selecting doses for Phase III trials.
• Existing analysis methods may not fully optimize dose selection.
• Novel statistical approaches have emerged for dose-finding in early-phase trials.

Purpose of the Study:

• To evaluate and compare the performance of traditional and recent dose-finding analysis methods.
• To provide guidance on selecting appropriate analysis methods for Phase II trials.
• To assess methods under various design options and performance metrics.

Main Methods:

• A simulation study was conducted to assess multiple performance measures.
• One traditional (ANOVA-based) and three recent dose-finding approaches were evaluated.
• Methods were tested across four different design options.
• An example from clinical practice was used for illustration.

Main Results:

• No single analysis method is universally superior across all design options and performance measures.
• Recent dose-finding methods demonstrate advantages over the traditional ANOVA-based approach.
• The choice of analysis method impacts the reliability of dose-response information.

Conclusions:

• Newer analysis methods for Phase II trials are valuable and warrant consideration.
• Careful selection of analysis methods is essential for effective dose-finding.
• Further research may refine guidance for optimal method selection in clinical trial design.