Aligning Federated Learning with Existing Trust Structures in Health Care Systems

Patient-centered health care information systems (PHSs) on peer-to-peer (P2P) networks (e.g., decentralized personal health records) enable storing data locally at the edge to enhance data sovereignty and resilience to single points of failure. Nonetheless, these systems raise concerns on trust and adoption in medical workflow due to non-alignment to current health care processes and stakeholders’ needs. The distributed nature of the data makes it more challenging to train and deploy machine learning models (using traditional methods) at the edge, for instance, for disease prediction. Federated learning (FL) has been proposed as a possible solution to these limitations. However, the P2P PHS architecture challenges current FL solutions because they use centralized engines (or random entities that could pose privacy concerns) for model update aggregation. Consequently, we propose a novel conceptual FL framework, CareNetFL, that is suitable for P2P PHS multi-tier and hybrid architecture and leverages existing trust structures in health care systems to ensure scalability, trust, and security. Entrusted parties (practitioners’ nodes) are used in CareNetFL to aggregate local model updates in the network hierarchy for their patients instead of random entities that could actively become malicious. Involving practitioners in their patients’ FL model training increases trust and eases access to medical data. The proposed concepts mitigate communication latency and improve FL performance through patient–practitioner clustering, reducing skewed and imbalanced data distributions and system heterogeneity challenges of FL at the edge. The framework also ensures end-to-end security and accountability through leveraging identity-based systems and privacy-preserving techniques that only guarantee security during training.

[1]  Arindom Chakraborty,et al.  Blockchain Application in Healthcare Systems: A Review , 2023, Syst..

[2]  Michael G. Rabbat,et al.  Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning , 2022, ICLR.

[3]  Imrana Abdullahi Yari,et al.  Federated Learning for Healthcare: Systematic Review and Architecture Proposal , 2022, ACM Trans. Intell. Syst. Technol..

[4]  D. Asch,et al.  Consumer Willingness to Share Personal Digital Information for Health-Related Uses , 2022, JAMA network open.

[5]  O. Spjuth,et al.  Scalable federated machine learning with FEDn , 2021, 2022 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid).

[6]  Sin Kit Lo,et al.  Architectural Patterns for the Design of Federated Learning Systems , 2021, J. Syst. Softw..

[7]  Nicolas Papernot,et al.  When the Curious Abandon Honesty: Federated Learning Is Not Private , 2021, 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P).

[8]  Feng Lyu,et al.  SHARE: Shaping Data Distribution at Edge for Communication-Efficient Hierarchical Federated Learning , 2021, 2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS).

[9]  Enhong Chen,et al.  Hierarchical Personalized Federated Learning for User Modeling , 2021, WWW.

[10]  Bjoern M. Eskofier,et al.  Online at Will: A Novel Protocol for Mutual Authentication in Peer-to-Peer Networks for Patient-Centered Health Care Information Systems , 2021, HICSS.

[11]  A. Sunyaev,et al.  Security Engineering of Patient-Centered Health Care Information Systems in Peer-to-Peer Environments: Systematic Review , 2020, Journal of medical Internet research.

[12]  J. Bosch,et al.  Federated Learning Systems: Architecture Alternatives , 2020, 2020 27th Asia-Pacific Software Engineering Conference (APSEC).

[13]  Micah J. Sheller,et al.  The future of digital health with federated learning. , 2020, NPJ digital medicine.

[14]  Oliver Hohlfeld,et al.  Corona-warn-app: tracing the start of the official COVID-19 exposure notification app for germany , 2020, SIGCOMM Posters and Demos.

[15]  Hyunghoon Cho,et al.  Contact Tracing Mobile Apps for COVID-19: Privacy Considerations and Related Trade-offs , 2020, ArXiv.

[16]  Micah J. Sheller,et al.  The future of digital health with federated learning , 2020, npj Digital Medicine.

[17]  Peter B. Walker,et al.  Federated Learning for Healthcare Informatics , 2019, Journal of Healthcare Informatics Research.

[18]  Xin Qin,et al.  FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare , 2019, IEEE Intelligent Systems.

[19]  S. H. Song,et al.  Client-Edge-Cloud Hierarchical Federated Learning , 2019, ICC 2020 - 2020 IEEE International Conference on Communications (ICC).

[20]  Yun Yang,et al.  Comparison and Modelling of Country-level Microblog User and Activity in Cyber-physical-social Systems Using Weibo and Twitter Data , 2019, ACM Trans. Intell. Syst. Technol..

[21]  Nassir Navab,et al.  BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning , 2019, ArXiv.

[22]  Hubert Eichner,et al.  Towards Federated Learning at Scale: System Design , 2019, SysML.

[23]  Nigel Shadbolt,et al.  Common Barriers to the Use of Patient-Generated Data Across Clinical Settings , 2018, CHI.

[24]  Carmela Troncoso,et al.  Systematizing Decentralization and Privacy: Lessons from 15 Years of Research and Deployments , 2017, Proc. Priv. Enhancing Technol..

[25]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[26]  Susan S. Woods,et al.  Outcomes From Health Information Exchange: Systematic Review and Future Research Needs , 2015, JMIR medical informatics.

[27]  Ali Sunyaev,et al.  Secure provision of patient-centered health information technology services in public networks—leveraging security and privacy features provided by the German nationwide health information technology infrastructure , 2014, Electron. Mark..

[28]  S. Woolf,et al.  A vision for patient-centered health information systems. , 2011, JAMA.

[29]  Beng Chin Ooi,et al.  Architecture of Peer-to-Peer Systems , 2010 .

[30]  Beng Chin Ooi,et al.  Peer-to-Peer Computing - Principles and Applications , 2009 .

[31]  Antoine Geissbühler,et al.  Design of a Patient-Centered, Multi-Institutional Healthcare Information Network Using Peer-to-peer Communication in a Highly Distributed Architecture , 2004, MedInfo.

[32]  LAURA DE BOEL,et al.  The Final European Union General Data Protection Regulation , 2022 .