Interactive and Instant: GenAI-driven Creation of Clinical Trial Applications

Abstract

Building exploratory analysis dashboards for clinical trials traditionally requires considerable expertise, extensive time, and deep familiarity with specialized frameworks such as R/Shiny and teal . In this talk, we share our experience exploring how Generative AI can significantly streamline this process. We will present a tool we developed, powered by Claude Code, that enables biostatisticians and clinical researchers to effortlessly create and immediately preview R/Shiny applications tailored for exploratory clinical data analysis using teal . Throughout our journey, we experimented with various GenAI-driven solutions, including code editors integrated with AI assistance tools (e.g., GitHub Copilot), and approaches leveraging MCP servers. Our current implementation is an interactive AI-powered chat interface designed to simplify the application-building experience, providing users with immediate application previews, and reducing both development complexity and the learning curve associated with the teal package. We will demonstrate how GenAI-driven solutions can empower users with limited programming backgrounds to rapidly build effective exploratory analysis dashboards, discuss challenges encountered, and highlight insights gained through our iterative development process.

Type
Publication
Presented at genAI Day 2025

Related