Generative Adversarial Networks for Creating Synthetic Free-Text Medical Data: A Proposal for Collaborative Research and Re-use of Machine Learning Models.

Autor:	Kasthurirathne SN; Regenstrief Institute, Indianapolis, IN, USA.; Indiana University School of Medicine, Indianapolis, IN, USA., Dexter G; Purdue University, Indianapolis, IN, USA., Grannis SJ; Regenstrief Institute, Indianapolis, IN, USA.; Indiana University School of Medicine, Indianapolis, IN, USA.
Jazyk:	angličtina
Zdroj:	AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science [AMIA Jt Summits Transl Sci Proc] 2021 May 17; Vol. 2021, pp. 335-344. Date of Electronic Publication: 2021 May 17 (Print Publication: 2021).
Abstrakt:	Restrictions in sharing Patient Health Identifiers (PHI) limit cross-organizational re-use of free-text medical data. We leverage Generative Adversarial Networks (GAN) to produce synthetic unstructured free-text medical data with low re-identification risk, and assess the suitability of these datasets to replicate machine learning models. We trained GAN models using unstructured free-text laboratory messages pertaining to salmonella, and identified the most accurate models for creating synthetic datasets that reflect the informational characteristics of the original dataset. Natural Language Generation metrics comparing the real and synthetic datasets demonstrated high similarity. Decision models generated using these datasets reported high performance metrics. There was no statistically significant difference in performance measures reported by models trained using real and synthetic datasets. Our results inform the use of GAN models to generate synthetic unstructured free-text data with limited re-identification risk, and use of this data to enable collaborative research and re-use of machine learning models. (©2021 AMIA - All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu