Federated and Differentially Private Learning for Electronic Health Records

2019/11/13 by Stephen R. Pfohl, Stephen Pfohl, Andrew M. Dai +4 · 3 citations
Computer Science · Mathematics · Social Sciences · #Access Control and Trust #Cryptography and Data Security #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Privacy-Preserving Technologies in Data #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1911.05861

Machine Learning for Health (ML4H) at NeurIPS 2019 - Extended Abstract

arxiv created 2019/11/13 · openalex publication_date 2019/11/13 · arxiv updated 2019/11/15 · openalex created_date 2019/11/22 · openalex updated_date 2026/07/28

Abstract

The use of collaborative and decentralized machine learning techniques such as federated learning have the potential to enable the development and deployment of clinical risk predictions models in low-resource settings without requiring sensitive data be shared or stored in a central repository. This process necessitates communication of model weights or updates between collaborating entities, but it is unclear to what extent patient privacy is compromised as a result. To gain insight into this question, we study the efficacy of centralized versus federated learning in both private and non-private settings. The clinical prediction tasks we consider are the prediction of prolonged length of stay and in-hospital mortality across thirty one hospitals in the eICU Collaborative Research Database. We find that while it is straightforward to apply differentially private stochastic gradient descent to achieve strong privacy bounds when training in a centralized setting, it is considerably more difficult to do so in the federated setting.

Citations

• Adam: A Method for Stochastic Optimization
• Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach

Cited by

• FedCVD++: Communication-Efficient Federated Learning for Cardiovascular Risk Prediction with Parametric and Non-Parametric Model Optimization
• Federated Learning for Cyber Physical Systems: A Comprehensive Survey
• A Systematic Literature Review on Federated Learning: From A Model Quality Perspective

Related

• Preserving Patient Privacy while Training a Predictive Model of In-hospital Mortality
• Differential Privacy-enabled Federated Learning for Sensitive Health Data
• A Robust Pipeline for Differentially Private Federated Learning on Imbalanced Clinical Data using SMOTETomek and FedProx
• Federated Learning in Healthcare: Model Misconducts, Security, Challenges, Applications, and Future Research Directions -- A Systematic Review
• Federated Learning for Healthcare Informatics