Generating sequential electronic health records using dual adversarial autoencoder

Recent studies on electronic health records (EHRs) started to learn deep generative models and synthesize a huge amount of realistic records, in order to address significant privacy issues surrounding the EHR. However, most of them only focus on structured records about patients' independent vi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of the American Medical Informatics Association : JAMIA Ročník 27; číslo 9; s. 1411
Hlavní autoři: Lee, Dongha, Yu, Hwanjo, Jiang, Xiaoqian, Rogith, Deevakar, Gudala, Meghana, Tejani, Mubeen, Zhang, Qiuchen, Xiong, Li
Médium: Journal Article
Jazyk:angličtina
Vydáno: England 01.09.2020
Témata:
Computer Simulation
Confidentiality
Electronic Health Records
Humans
Machine Learning
Neural Networks, Computer
Software
sequential data generation
generative autoencoder
generative adversarial networks (GANs)
electornic health records (EHRs)
differential privacy
ISSN:1527-974X, 1527-974X
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Recent studies on electronic health records (EHRs) started to learn deep generative models and synthesize a huge amount of realistic records, in order to address significant privacy issues surrounding the EHR. However, most of them only focus on structured records about patients' independent visits, rather than on chronological clinical records. In this article, we aim to learn and synthesize realistic sequences of EHRs based on the generative autoencoder. We propose a dual adversarial autoencoder (DAAE), which learns set-valued sequences of medical entities, by combining a recurrent autoencoder with 2 generative adversarial networks (GANs). DAAE improves the mode coverage and quality of generated sequences by adversarially learning both the continuous latent distribution and the discrete data distribution. Using the MIMIC-III (Medical Information Mart for Intensive Care-III) and UT Physicians clinical databases, we evaluated the performances of DAAE in terms of predictive modeling, plausibility, and privacy preservation. Our generated sequences of EHRs showed the comparable performances to real data for a predictive modeling task, and achieved the best score in plausibility evaluation conducted by medical experts among all baseline models. In addition, differentially private optimization of our model enables to generate synthetic sequences without increasing the privacy leakage of patients' data. DAAE can effectively synthesize sequential EHRs by addressing its main challenges: the synthetic records should be realistic enough not to be distinguished from the real records, and they should cover all the training patients to reproduce the performance of specific downstream tasks.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1527-974X
1527-974X
DOI:10.1093/jamia/ocaa119