SynEHRgy: Synthesizing Mixed-Type Structured Electronic Health Records using Decoder-Only Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909397478801408 |
|---|---|
| author | Karami, Hojjat Atienza, David Ionescu, Anisoara |
| author_facet | Karami, Hojjat Atienza, David Ionescu, Anisoara |
| 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13428 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SynEHRgy: Synthesizing Mixed-Type Structured Electronic Health Records using Decoder-Only Transformers Karami, Hojjat Atienza, David Ionescu, Anisoara Machine Learning Artificial Intelligence 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. |
| title | SynEHRgy: Synthesizing Mixed-Type Structured Electronic Health Records using Decoder-Only Transformers |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2411.13428 |