Retrieval-Reasoning Large Language Model-based Synthetic Clinical Trial Generation

TL;DR

This paper introduces a Retrieval-Reasoning framework using large language models to generate synthetic clinical trial reports, enhancing data availability for clinical research while preserving privacy.

Contribution

It presents a novel retrieval and reasoning-based method for generating realistic synthetic clinical trial data using LLMs, improving outcome prediction models.

Findings

Synthetic trials effectively augment real datasets

Hybrid fine-tuning improves clinical outcome prediction

Synthetic data preserves privacy while supporting research

Abstract

Machine learning (ML) holds great promise for clinical applications but is often hindered by limited access to high-quality data due to privacy concerns, high costs, and long timelines associated with clinical trials. While large language models (LLMs) have demonstrated strong performance in general-purpose generation tasks, their application to synthesizing realistic clinical trials remains underexplored. In this work, we propose a novel Retrieval-Reasoning framework that leverages few-shot prompting with LLMs to generate synthetic clinical trial reports annotated with binary success/failure outcomes. Our approach integrates a retrieval module to ground the generation on relevant trial data and a reasoning module to ensure domain-consistent justifications. Experiments conducted on real clinical trials from the ClinicalTrials.gov database demonstrate that the generated synthetic trials effectively augment real datasets. Fine-tuning a BioBERT classifier on synthetic data, real data, or their combination shows that hybrid fine-tuning leads to improved performance on clinical trial outcome prediction tasks. Our results suggest that LLM-based synthetic data can serve as a powerful tool for privacy-preserving data augmentation in clinical research. The code is available at https://github.com/XuZR3x/Retrieval_Reasoning_Clinical_Trial_Generation.