Using Large Language Models to Generate Clinical Trial Tables and Figures

TL;DR

This paper investigates the use of large language models to automate the creation of tables, figures, and listings in clinical trial reporting, aiming to reduce manual effort and improve efficiency.

Contribution

It introduces prompt engineering and few-shot transfer learning techniques for LLMs to generate clinical trial TFLs and develops a conversational agent for customized TFL generation.

Findings

LLMs can effectively generate TFLs from clinical trial data with proper prompts.

The approach demonstrates efficiency and potential for automation in clinical trial reporting.

A conversational agent was developed to facilitate user-specific TFL creation.

Abstract

Tables, figures, and listings (TFLs) are essential tools for summarizing clinical trial data. Creation of TFLs for reporting activities is often a time-consuming task encountered routinely during the execution of clinical trials. This study explored the use of large language models (LLMs) to automate the generation of TFLs through prompt engineering and few-shot transfer learning. Using public clinical trial data in ADaM format, our results demonstrated that LLMs can efficiently generate TFLs with prompt instructions, showcasing their potential in this domain. Furthermore, we developed a conservational agent named Clinical Trial TFL Generation Agent: An app that matches user queries to predefined prompts that produce customized programs to generate specific predefined TFLs.