An Adversorial Approach to Enable Re-Use of Machine Learning Models and Collaborative Research Efforts Using Synthetic Unstructured Free-Text Medical Data.

Autor:	Kasthurirathne SN; Center for Biomedical Informatics, Regenstrief Institute, Indianapolis, Indiana, USA.; Richard M. Fairbanks School of Public Health, Indiana University, Indianapolis, Indiana, USA., Dexter G; Center for Biomedical Informatics, Regenstrief Institute, Indianapolis, Indiana, USA., Grannis SJ; Center for Biomedical Informatics, Regenstrief Institute, Indianapolis, Indiana, USA.; School of Medicine, Indiana University, Indianapolis, IN, USA.
Jazyk:	angličtina
Zdroj:	Studies in health technology and informatics [Stud Health Technol Inform] 2019 Aug 21; Vol. 264, pp. 1510-1511.
DOI:	10.3233/SHTI190509
Abstrakt:	We leverage Generative Adversarial Networks (GAN) to produce synthetic free-text medical data with low re-identification risk, and apply these to replicate machine learning solutions. We trained GAN models to generate free-text cancer pathology reports. Decision models were trained using synthetic datasets reported performance metrics that were statistically similar to models trained using original test data. Our results further the use of GANs to generate synthetic data for collaborative research and re-use of machine learning models.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu