Implementation of a two-group likelihood time-to-event continual reassessment method using SAS

Area of Science:

• Clinical Trials Methodology
• Biostatistics
• Pharmacometrics

Background:

• Model-based methods, including the continual reassessment method (CRM) and time-to-event CRM (TITE-CRM), offer advanced approaches for complex clinical trials.
• Addressing patient heterogeneity is crucial in trial design, impacting inclusion/exclusion criteria and overall study outcomes.
• Current statistical software for these methods primarily supports single-sample estimations, limiting practical implementation for complex trial designs.

Purpose of the Study:

• To develop and present a SAS program designed for two-group dose-finding studies.
• To facilitate the practical implementation of the time-to-event continual reassessment method (TITE-CRM) in clinical trial design.
• To provide a tool that accounts for patient heterogeneity in dose-finding trials.

Main Methods:

• Development of a SAS program utilizing TITE-CRM and likelihood estimation for two-group trials.
• Implementation of macros within the SAS program to aid in trial planning and execution.
• Demonstration of the program's utility through examples, including sample size estimation.

Main Results:

• The developed SAS program effectively accommodates two-group study designs using TITE-CRM.
• The program includes macros that streamline the planning and implementation phases of dose-finding trials.
• Examples illustrate the program's capability in guiding sample size determination for trials with patient heterogeneity.

Conclusions:

• The SAS program serves as a valuable resource for researchers designing dose-finding studies.
• It enables the incorporation of patient heterogeneity into trial design and conduct.
• The program facilitates the application of advanced statistical methods in real-world clinical trial settings.