%0 Journal Article
%@ 2561-326X
%I JMIR Publications
%V 4
%N 5
%P e14064
%T Privacy-Preserving Deep Learning for the Detection of Protected Health Information in Real-World Data: Comparative Evaluation
%A Festag,Sven
%A Spreckelsen,Cord
%+ Institute of Medical Statistics, Computer and Data Sciences, Jena University Hospital, Bachstraße 18, Jena, , Germany, 49 3641 9 398360, Cord.Spreckelsen@med.uni-jena.de
%K privacy-preserving protocols
%K neural networks
%K health informatics
%K distributed machine learning
%D 2020
%7 5.5.2020
%9 Original Paper
%J JMIR Form Res
%G English
%X Background: Collaborative privacy-preserving training methods allow for the integration of locally stored private data sets into machine learning approaches while ensuring confidentiality and nondisclosure. Objective: In this work we assess the performance of a state-of-the-art neural network approach for the detection of protected health information in texts trained in a collaborative privacy-preserving way. Methods: The training adopts distributed selective stochastic gradient descent (ie, it works by exchanging local learning results achieved on private data sets). Five networks were trained on separated real-world clinical data sets by using the privacy-protecting protocol. In total, the data sets contain 1304 real longitudinal patient records for 296 patients. Results: These networks reached a mean F1 value of 0.955. The gold standard centralized training that is based on the union of all sets and does not take data security into consideration reaches a final value of 0.962. Conclusions: Using real-world clinical data, our study shows that detection of protected health information can be secured by collaborative privacy-preserving training. In general, the approach shows the feasibility of deep learning on distributed and confidential clinical data while ensuring data protection. 
%M 32369025
%R 10.2196/14064
%U https://formative.jmir.org/2020/5/e14064
%U https://doi.org/10.2196/14064
%U http://www.ncbi.nlm.nih.gov/pubmed/32369025