@Article{info:doi/10.2196/14064,
author="Festag, Sven
and Spreckelsen, Cord",
title="Privacy-Preserving Deep Learning for the Detection of Protected Health Information in Real-World Data: Comparative Evaluation",
journal="JMIR Form Res",
year="2020",
month="May",
day="5",
volume="4",
number="5",
pages="e14064",
keywords="privacy-preserving protocols; neural networks; health informatics; distributed machine learning",
abstract="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. ",
issn="2561-326X",
doi="10.2196/14064",
url="https://formative.jmir.org/2020/5/e14064",
url="https://doi.org/10.2196/14064",
url="http://www.ncbi.nlm.nih.gov/pubmed/32369025"
}