@misc{karamiSynEHRgySynthesizingMixedType2024,
	title = {{SynEHRgy}: {Synthesizing} {Mixed}-{Type} {Structured} {Electronic} {Health} {Records} using {Decoder}-{Only} {Transformers}},
	shorttitle = {{SynEHRgy}},
	url = {http://arxiv.org/abs/2411.13428},
	doi = {10.48550/arXiv.2411.13428},
	abstract = {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.},
	urldate = {2026-06-17},
	publisher = {arXiv},
	author = {Karami, Hojjat and Atienza, David and Ionescu, Anisoara},
	month = nov,
	year = {2024},
	note = {arXiv:2411.13428 [cs.LG]},
	keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, preprint},
}