Federated Machine Learning, Privacy-Enhancing Technologies, and Data Protection Laws in Medical Research: Scoping Review

Abstract

Background The collection, storage, and analysis of large data sets are relevant in many sectors. Especially in the medical field, the processing of patient data promises great progress in personalized health care. However, it is strictly regulated, such as by the General Data Protection Regulation (GDPR). These regulations mandate strict data security and data protection and, thus, create major challenges for collecting and using large data sets. Technologies such as federated learning (FL), especially paired with differential privacy (DP) and secure multiparty computation (SMPC), aim to solve these challenges. Objective This scoping review aimed to summarize the current discussion on the legal questions and concerns related to FL systems in medical research. We were particularly interested in whether and to what extent FL applications and training processes are compliant with the GDPR data protection law and whether the use of the aforementioned privacy-enhancing technologies (DP and SMPC) affects this legal compliance. We placed special emphasis on the consequences for medical research and development. Methods We performed a scoping review according to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews). We reviewed articles on Beck-Online, SSRN, ScienceDirect, arXiv, and Google Scholar published in German or English between 2016 and 2022. We examined 4 questions: whether local and global models are “personal data” as per the GDPR; what the “roles” as defined by the GDPR of various parties in FL are; who controls the data at various stages of the training process; and how, if at all, the use of privacy-enhancing technologies affects these findings. Results We identified and summarized the findings of 56 relevant publications on FL. Local and likely also global models constitute personal data according to the GDPR. FL strengthens data protection but is still vulnerable to a number of attacks and the possibility of data leakage. These concerns can be successfully addressed through the privacy-enhancing technologies SMPC and DP. Conclusions Combining FL with SMPC and DP is necessary to fulfill the legal data protection requirements (GDPR) in medical research dealing with personal data. Even though some technical and legal challenges remain, for example, the possibility of successful attacks on the system, combining FL with SMPC and DP creates enough security to satisfy the legal requirements of the GDPR. This combination thereby provides an attractive technical solution for health institutions willing to collaborate without exposing their data to risk. From a legal perspective, the combination provides enough built-in security measures to satisfy data protection requirements, and from a technical perspective, the combination provides secure systems with comparable performance with centralized machine learning applications.

Digital Transformation in Toxicology: Improving Communication and Efficiency in Risk Assessment

“…One of the significant challenges of digital transformation in toxicology is data privacy and security . As the amount of data generated by toxicological studies increases, it becomes crucial to ensure that sensitive information is protected from unauthorized access or breaches.…”

mHealth Systems Need a Privacy-by-Design Approach: Commentary on “Federated Machine Learning, Privacy-Enhancing Technologies, and Data Protection Laws in Medical Research: Scoping Review”

“…Brauneck et al [ 1 ] correctly point out that FL alone does not sufficiently protect user privacy. This is well known.…”

“…It is therefore important for system designers to have a broad understanding of available tools. Moreover, old and new tools need to be examined from a legal perspective just as Brauneck et al [ 1 ] have done for FL, DP, and SMPC. This is challenging because technology and the law are both undergoing changes.…”

“…Brauneck et al [ 1 ] do not mention private synthetic data generation as a PET, but I believe that private synthetic data has tremendous potential for enabling data-driven innovation in health care without sacrificing privacy. The use case the authors considered is one where a data processing workflow (eg, FL) needs to be modified to ensure that it satisfies DP.…”

“…Brauneck et al [ 1 ] should be congratulated for reviewing privacy-enhancing technologies (PETs) from a legal standpoint. The right to privacy is a fundamental human right, the importance of which in the current digital age cannot be overstated.…”