A Multifaceted benchmarking of synthetic electronic health record generation models

Synthetic health data have the potential to mitigate privacy concerns when sharing data to support biomedical research and the development of innovative healthcare applications. In this work, the authors introduce a use case oriented benchmarking framework to evaluate data synthesis models through a...

Full description

Bibliographic Details
Main Authors: Chao Yan, Yao Yan, Zhiyu Wan, Ziqi Zhang, Larsson Omberg, Justin Guinney, Sean D. Mooney, Bradley A. Malin
Format: Article
Language:English
Published: Nature Portfolio 2022-12-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-022-35295-1
_version_ 1828169891108093952
author Chao Yan
Yao Yan
Zhiyu Wan
Ziqi Zhang
Larsson Omberg
Justin Guinney
Sean D. Mooney
Bradley A. Malin
author_facet Chao Yan
Yao Yan
Zhiyu Wan
Ziqi Zhang
Larsson Omberg
Justin Guinney
Sean D. Mooney
Bradley A. Malin
author_sort Chao Yan
collection DOAJ
description Synthetic health data have the potential to mitigate privacy concerns when sharing data to support biomedical research and the development of innovative healthcare applications. In this work, the authors introduce a use case oriented benchmarking framework to evaluate data synthesis models through a set of utility and privacy metrics.
first_indexed 2024-04-12T02:59:35Z
format Article
id doaj.art-7f00928d11944926bd2b00764b67250b
institution Directory Open Access Journal
issn 2041-1723
language English
last_indexed 2024-04-12T02:59:35Z
publishDate 2022-12-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj.art-7f00928d11944926bd2b00764b67250b2022-12-22T03:50:42ZengNature PortfolioNature Communications2041-17232022-12-0113111810.1038/s41467-022-35295-1A Multifaceted benchmarking of synthetic electronic health record generation modelsChao Yan0Yao Yan1Zhiyu Wan2Ziqi Zhang3Larsson Omberg4Justin Guinney5Sean D. Mooney6Bradley A. Malin7Department of Biomedical Informatics, Vanderbilt University Medical CenterSage BionetworksDepartment of Biomedical Informatics, Vanderbilt University Medical CenterDepartment of Computer Science, Vanderbilt UniversitySage BionetworksDepartment of Biomedical Informatics and Medical Education, University of WashingtonDepartment of Biomedical Informatics and Medical Education, University of WashingtonDepartment of Biomedical Informatics, Vanderbilt University Medical CenterSynthetic health data have the potential to mitigate privacy concerns when sharing data to support biomedical research and the development of innovative healthcare applications. In this work, the authors introduce a use case oriented benchmarking framework to evaluate data synthesis models through a set of utility and privacy metrics.https://doi.org/10.1038/s41467-022-35295-1
spellingShingle Chao Yan
Yao Yan
Zhiyu Wan
Ziqi Zhang
Larsson Omberg
Justin Guinney
Sean D. Mooney
Bradley A. Malin
A Multifaceted benchmarking of synthetic electronic health record generation models
Nature Communications
title A Multifaceted benchmarking of synthetic electronic health record generation models
title_full A Multifaceted benchmarking of synthetic electronic health record generation models
title_fullStr A Multifaceted benchmarking of synthetic electronic health record generation models
title_full_unstemmed A Multifaceted benchmarking of synthetic electronic health record generation models
title_short A Multifaceted benchmarking of synthetic electronic health record generation models
title_sort multifaceted benchmarking of synthetic electronic health record generation models
url https://doi.org/10.1038/s41467-022-35295-1
work_keys_str_mv AT chaoyan amultifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT yaoyan amultifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT zhiyuwan amultifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT ziqizhang amultifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT larssonomberg amultifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT justinguinney amultifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT seandmooney amultifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT bradleyamalin amultifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT chaoyan multifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT yaoyan multifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT zhiyuwan multifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT ziqizhang multifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT larssonomberg multifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT justinguinney multifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT seandmooney multifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels
AT bradleyamalin multifacetedbenchmarkingofsyntheticelectronichealthrecordgenerationmodels