MedSyn: LLM-based Synthetic Medical Text Generation Framework

TL;DR

This paper introduces MedSyn, a framework that generates synthetic medical texts using large language models and a Medical Knowledge Graph, improving ICD code prediction accuracy and providing a large open-source dataset for Russian clinical notes.

Contribution

MedSyn is a novel framework combining LLMs with a Medical Knowledge Graph to generate realistic synthetic clinical notes for healthcare research.

Findings

Synthetic data improved ICD code prediction accuracy by up to 17.8%.

Created the largest open-source Russian clinical notes dataset with over 41,000 samples.

Demonstrated the utility of synthetic data in real-world medical applications.

Abstract

Generating synthetic text addresses the challenge of data availability in privacy-sensitive domains such as healthcare. This study explores the applicability of synthetic data in real-world medical settings. We introduce MedSyn, a novel medical text generation framework that integrates large language models with a Medical Knowledge Graph (MKG). We use MKG to sample prior medical information for the prompt and generate synthetic clinical notes with GPT-4 and fine-tuned LLaMA models. We assess the benefit of synthetic data through application in the ICD code prediction task. Our research indicates that synthetic data can increase the classification accuracy of vital and challenging codes by up to 17.8% compared to settings without synthetic data. Furthermore, to provide new data for further research in the healthcare domain, we present the largest open-source synthetic dataset of clinical notes for the Russian language, comprising over 41k samples covering 219 ICD-10 codes.