CEHR-GPT: Generating Electronic Health Records with Chronological Patient Timelines

TL;DR

This paper introduces CEHR-GPT, a novel method using GPT models trained on patient timelines to generate synthetic EHR data that preserves temporal dependencies and can be formatted for OMOP standards.

Contribution

The work presents a new approach combining CEHR-BERT derived representations with GPT to generate realistic, temporally coherent synthetic EHR sequences in OMOP format.

Findings

Successfully trained GPT on patient timelines

Generated synthetic EHR data with preserved temporal dependencies

Data compatible with OMOP format

Abstract

Synthetic Electronic Health Records (EHR) have emerged as a pivotal tool in advancing healthcare applications and machine learning models, particularly for researchers without direct access to healthcare data. Although existing methods, like rule-based approaches and generative adversarial networks (GANs), generate synthetic data that resembles real-world EHR data, these methods often use a tabular format, disregarding temporal dependencies in patient histories and limiting data replication. Recently, there has been a growing interest in leveraging Generative Pre-trained Transformers (GPT) for EHR data. This enables applications like disease progression analysis, population estimation, counterfactual reasoning, and synthetic data generation. In this work, we focus on synthetic data generation and demonstrate the capability of training a GPT model using a particular patient representation derived from CEHR-BERT, enabling us to generate patient sequences that can be seamlessly converted to the Observational Medical Outcomes Partnership (OMOP) data format.