Architectural Design of a Blockchain-Enabled, Federated Learning Platform for Algorithmic Fairness in Predictive Health Care: Design Science Study
- PMID: 37902833
- PMCID: PMC10644196
- DOI: 10.2196/46547
Architectural Design of a Blockchain-Enabled, Federated Learning Platform for Algorithmic Fairness in Predictive Health Care: Design Science Study
Abstract
Background: Developing effective and generalizable predictive models is critical for disease prediction and clinical decision-making, often requiring diverse samples to mitigate population bias and address algorithmic fairness. However, a major challenge is to retrieve learning models across multiple institutions without bringing in local biases and inequity, while preserving individual patients' privacy at each site.
Objective: This study aims to understand the issues of bias and fairness in the machine learning process used in the predictive health care domain. We proposed a software architecture that integrates federated learning and blockchain to improve fairness, while maintaining acceptable prediction accuracy and minimizing overhead costs.
Methods: We improved existing federated learning platforms by integrating blockchain through an iterative design approach. We used the design science research method, which involves 2 design cycles (federated learning for bias mitigation and decentralized architecture). The design involves a bias-mitigation process within the blockchain-empowered federated learning framework based on a novel architecture. Under this architecture, multiple medical institutions can jointly train predictive models using their privacy-protected data effectively and efficiently and ultimately achieve fairness in decision-making in the health care domain.
Results: We designed and implemented our solution using the Aplos smart contract, microservices, Rahasak blockchain, and Apache Cassandra-based distributed storage. By conducting 20,000 local model training iterations and 1000 federated model training iterations across 5 simulated medical centers as peers in the Rahasak blockchain network, we demonstrated how our solution with an improved fairness mechanism can enhance the accuracy of predictive diagnosis.
Conclusions: Our study identified the technical challenges of prediction biases faced by existing predictive models in the health care domain. To overcome these challenges, we presented an innovative design solution using federated learning and blockchain, along with the adoption of a unique distributed architecture for a fairness-aware system. We have illustrated how this design can address privacy, security, prediction accuracy, and scalability challenges, ultimately improving fairness and equity in the predictive health care domain.
Keywords: bias; blockchain; fairness; federated learning; health care; implementation; privacy; proof of concept; software.
©Xueping Liang, Juan Zhao, Yan Chen, Eranga Bandara, Sachin Shetty. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 30.10.2023.
Conflict of interest statement
Conflicts of Interest: None declared.
Figures
Similar articles
-
Secure and decentralized federated learning framework with non-IID data based on blockchain.Heliyon. 2024 Feb 29;10(5):e27176. doi: 10.1016/j.heliyon.2024.e27176. eCollection 2024 Mar 15. Heliyon. 2024. PMID: 38562497 Free PMC article.
-
Empowering Precision Medicine: Unlocking Revolutionary Insights through Blockchain-Enabled Federated Learning and Electronic Medical Records.Sensors (Basel). 2023 Aug 28;23(17):7476. doi: 10.3390/s23177476. Sensors (Basel). 2023. PMID: 37687931 Free PMC article.
-
Blockchain-Based Federated Learning System: A Survey on Design Choices.Sensors (Basel). 2023 Jun 16;23(12):5658. doi: 10.3390/s23125658. Sensors (Basel). 2023. PMID: 37420824 Free PMC article. Review.
-
A systematic review of privacy-preserving methods deployed with blockchain and federated learning for the telemedicine.Healthc Anal (N Y). 2023 Nov;3:100192. doi: 10.1016/j.health.2023.100192. Epub 2023 May 5. Healthc Anal (N Y). 2023. PMID: 37223223 Free PMC article. Review.
-
Improving Diagnosis Through Digital Pathology: Proof-of-Concept Implementation Using Smart Contracts and Decentralized File Storage.J Med Internet Res. 2022 Mar 28;24(3):e34207. doi: 10.2196/34207. J Med Internet Res. 2022. PMID: 35343905 Free PMC article.
References
-
- Tomašev N, Glorot X, Rae JW, Zielinski M, Askham H, Saraiva A, Mottram A, Meyer C, Ravuri S, Protsyuk I, Connell A, Hughes CO, Karthikesalingam A, Cornebise J, Montgomery H, Rees G, Laing C, Baker CR, Peterson K, Reeves R, Hassabis D, King D, Suleyman M, Back T, Nielson C, Ledsam JR, Mohamed S. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019 Aug;572(7767):116–9. doi: 10.1038/s41586-019-1390-1. https://europepmc.org/abstract/MED/31367026 10.1038/s41586-019-1390-1 - DOI - PMC - PubMed
-
- Zhao J, Feng Q, Wu P, Lupu RA, Wilke RA, Wells QS, Denny JC, Wei W-Q. Learning from longitudinal data in electronic health record and genetic data to improve cardiovascular event prediction. Sci Rep. 2019 Jan 24;9(1):717. doi: 10.1038/s41598-018-36745-x. doi: 10.1038/s41598-018-36745-x.10.1038/s41598-018-36745-x - DOI - DOI - PMC - PubMed
-
- Zhao J, Grabowska ME, Kerchberger VE, Smith JC, Eken HN, Feng Q, Peterson JF, Trent Rosenbloom S, Johnson KB, Wei W-Q. ConceptWAS: a high-throughput method for early identification of COVID-19 presenting symptoms and characteristics from clinical notes. J Biomed Inform. 2021 May;117:103748. doi: 10.1016/j.jbi.2021.103748. https://linkinghub.elsevier.com/retrieve/pii/S1532-0464(21)00077-0 S1532-0464(21)00077-0 - DOI - PMC - PubMed
-
- List of registries. National Institutes of Health. [2022-11-16]. https://www.nih.gov/health-information/nih-clinical-research-trials-you/... .
-
- McLeod A, Dolezel D. Cyber-analytics: modeling factors associated with healthcare data breaches. Decis Support Syst. 2018 Apr;108:57–68. doi: 10.1016/j.dss.2018.02.007. - DOI
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources