Saved in:
Bibliographic Details
Main Authors: Karami, Hojjat, Atienza, David, Ionescu, Anisoara
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.13428
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Generating synthetic Electronic Health Records (EHRs) offers significant potential for data augmentation, privacy-preserving data sharing, and improving machine learning model training. We propose a novel tokenization strategy tailored for structured EHR data, which encompasses diverse data types such as covariates, ICD codes, and irregularly sampled time series. Using a GPT-like decoder-only transformer model, we demonstrate the generation of high-quality synthetic EHRs. Our approach is evaluated using the MIMIC-III dataset, and we benchmark the fidelity, utility, and privacy of the generated data against state-of-the-art models.