drugdevelopR: Planning of phase II/III drug development programs with optimal sample size allocation and Go/No-go decision rules in R

Abstract

Sample size determination is crucial in phase II/III drug development programs, impacting the likelihood of meeting program objectives. Within a utility-based framework, methods for optimal designs were developed recently, i.e., optimal go/no-go decision rules (whether to stop or to proceed to phase III) and optimal sample sizes minimizing the cost while maximizing the chances of achieving the program objective. These approaches can accommodate diverse scenarios like multiple phase III trials, arms, or endpoints. To facilitate the usability, the drugdevelopR R package and R Shiny applications were implemented. A sophisticated quality validation concept consisting of measures for archiving, versioning, bug reporting, and code documentation was developed, assuring reliable results.