Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes

TL;DR

This paper introduces Asclepius, a clinical large language model trained on synthetic clinical notes derived from biomedical literature, demonstrating that synthetic data can effectively replace real notes for high-performance clinical NLP models.

Contribution

We developed a method to generate synthetic clinical notes from biomedical literature and trained a specialized LLM, showing synthetic data can match real data in clinical NLP tasks.

Findings

Synthetic notes are viable substitutes for real clinical notes.

Asclepius outperforms several baseline models in evaluations.

Resources are publicly available for future research.

Abstract

The development of large language models tailored for handling patients' clinical notes is often hindered by the limited accessibility and usability of these notes due to strict privacy regulations. To address these challenges, we first create synthetic large-scale clinical notes using publicly available case reports extracted from biomedical literature. We then use these synthetic notes to train our specialized clinical large language model, Asclepius. While Asclepius is trained on synthetic data, we assess its potential performance in real-world applications by evaluating it using real clinical notes. We benchmark Asclepius against several other large language models, including GPT-3.5-turbo and other open-source alternatives. To further validate our approach using synthetic notes, we also compare Asclepius with its variants trained on real clinical notes. Our findings convincingly demonstrate that synthetic clinical notes can serve as viable substitutes for real ones when constructing high-performing clinical language models. This conclusion is supported by detailed evaluations conducted by both GPT-4 and medical professionals. All resources including weights, codes, and data used in the development of Asclepius are made publicly accessible for future research. (https://github.com/starmpcc/Asclepius)