Generating Synthetic Healthcare Records Using Convolutional Generative Adversarial Networks

Torfi, Amirsina; Beyki, Mohammadreza

Generating Synthetic Healthcare Records Using Convolutional Generative Adversarial Networks

dc.contributor.author	Torfi, Amirsina	en
dc.contributor.author	Beyki, Mohammadreza	en
dc.date.accessioned	2019-12-21T00:48:48Z	en
dc.date.available	2019-12-21T00:48:48Z	en
dc.date.issued	2019-12-20	en
dc.description.abstract	Deep learning models have demonstrated high-quality performance in several areas such as image classification and speech processing. However, creating a deep learning model using electronic health record (EHR) data requires addressing particular privacy challenges that make this issue unique to researchers in this domain. This matter focuses attention on generating realistic synthetic data to amplify privacy. Existing methods for artificial data generation suffer from different limitations such as being bound to particular use cases. Furthermore, their generalizability to real-world problems is controversial regarding the uncertainties in defining and measuring key realistic characteristics. Henceforth, there is a need to establish insightful metrics (and to measure the validity of synthetic data), as well as quantitative criteria regarding privacy restrictions. We propose the use of Generative Adversarial Networks to help satisfy requirements for realistic characteristics and acceptable values of privacy metrics simultaneously. The present study makes several unique contributions to synthetic data generation in the healthcare domain. First, utilizing 1-D Convolutional Neural Networks (CNNs), we devise a new approach to capturing the correlation between adjacent diagnosis records. Second, we employ convolutional autoencoders to map the discrete-continuous values. Finally, we devise a new approach to measure the similarity between real and synthetic data, and a means to measure the fidelity of the synthetic data and its associated privacy risks.	en
dc.description.notes	GeneratingSyntheticEHRdataPresentation.zip: The presentation source files, GeneratingSyntheticEHRdataPresentation.pdf: The presentation PDF, GeneratingSyntheticEHRdataReport.zip: The report source files, GeneratingSyntheticEHRdataReport.pdf: The PDF report	en
dc.description.sponsorship	NewWave	en
dc.identifier.uri	http://hdl.handle.net/10919/96186	en
dc.language.iso	en_US	en
dc.publisher	Virginia Tech	en
dc.rights	Creative Commons Attribution-NonCommercial-NoDerivs 3.0 United States	en
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	en
dc.subject	synthetic data	en
dc.subject	generative adversarial networks	en
dc.subject	healthcare	en
dc.subject	convolutional neural networks	en
dc.title	Generating Synthetic Healthcare Records Using Convolutional Generative Adversarial Networks	en
dc.type	Presentation	en
dc.type	Report	en