Optimal two-stage designs for phase II clinical trials

Area of Science:

• Clinical Trials
• Biostatistics
• Pharmacology

Background:

• Phase II clinical trials aim to assess drug efficacy for further development.
• Multi-institutional trials require manageable designs, often limiting complex multi-stage approaches.
• Evaluating new drug regimens necessitates robust statistical methodologies.

Purpose of the Study:

• To present optimal two-stage clinical trial designs for phase II studies.
• To minimize expected sample size under low drug activity, subject to Type I and Type II error constraints.
• To determine designs that minimize the maximum sample size (minimax designs).

Main Methods:

• Development of two-stage clinical trial designs.
• Optimization criteria: minimizing expected sample size and maximum sample size.
• Tabulation of optimal and minimax designs for various parameters.
• Application to pilot studies with toxicity endpoints.

Main Results:

• Tabulated optimal two-stage designs that minimize expected sample size.
• Tabulated minimax two-stage designs that minimize maximum sample size.
• Designs are presented for a range of statistical parameters.

Conclusions:

• The presented two-stage designs offer efficient methods for phase II clinical trials.
• These designs are suitable for multi-institutional settings and pilot studies.
• The methodology provides a framework for optimizing sample size and controlling errors in early drug development.