Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing

• Published in: Circulation Cardiovascular quality and outcomes Vol. 12; no. 7; p. e005122
• Main Authors: Beaulieu-Jones, Brett K., Wu, Zhiwei Steven, Williams, Chris, Lee, Ran, Bhavnani, Sanjeev P., Byrd, James Brian, Greene, Casey S.
• Format: Journal Article
• Language: English
• Published: United States Lippincott Williams & Wilkins 01.07.2019
• Subjects: Antihypertensive Agents - therapeutic use; Blood Pressure - drug effects; Computer Security; Computer Simulation; Confidentiality; Data Collection; Deep Learning; Humans; Hypertension - diagnosis; Hypertension - drug therapy; Hypertension - physiopathology; Information Dissemination - methods; Methods Paper; Randomized Controlled Trials as Topic; Treatment Outcome; blood pressure; deep learning; privacy; machine learning; propensity score
• ISSN: 1941-7713; 1941-7705; 1941-7705
• DOI: 10.1161/CIRCOUTCOMES.118.005122

Data sharing accelerates scientific progress but sharing individual-level data while preserving patient privacy presents a barrier. Using pairs of deep neural networks, we generated simulated, synthetic participants that closely resemble participants of the SPRINT trial (Systolic Blood Pressure Trial). We showed that such paired networks can be trained with differential privacy, a formal privacy framework that limits the likelihood that queries of the synthetic participants' data could identify a real a participant in the trial. Machine learning predictors built on the synthetic population generalize to the original data set. This finding suggests that the synthetic data can be shared with others, enabling them to perform hypothesis-generating analyses as though they had the original trial data. Deep neural networks that generate synthetic participants facilitate secondary analyses and reproducible investigation of clinical data sets by enhancing data sharing while preserving participant privacy.