|
Abstract:
|
Shiny is a library that allows statistical programmers to develop web applications within the realm of R, either building from existing base code or starting off from scratch. In the Office of Biostatistics at FDA's Center for Drug Evaluation and Research (CDER), the development of standardized, interactive clinical review tools has begun. Routine analyses, visualizations, and other programming tasks are currently being implemented in the Shiny framework. This approach supports the office goals of increasing efficiency in clinical reviews and lightening the workload of reviewers. Examples of the Shiny apps that are under development and in use include applying statistical procedures for multiplicity adjustments, producing visualizations for patient-reported outcomes data, and generating subgroup forest plots. To establish a firm foundation for Shiny in CDER, a working group has recently been formed with members across different offices to collaborate on promoting and developing "fit for purpose" tools using Shiny. This poster will describe the approach of working toward this firm foundation and the process of developing Shiny apps in a regulatory setting.
|
