Quorum-based model learning on a blockchain hierarchical clinical research network using smart contracts

• Published in: International journal of medical informatics (Shannon, Ireland) Ireland), 2023-01, Vol.169, p.104924-104924, Article 104924
• Main Authors: Kuo, Tsung-Ting, Pham, Anh
• Format: Article
• Language: English
• Subjects: Blockchain Distributed Ledger Technology; Clinical Information System; Data Privacy and Security; Genomics; Humans; Machine Learning; Privacy; Privacy-Preserving Predictive Modeling
• ISSN: 1386-5056; 1872-8243
• DOI: 10.1016/j.ijmedinf.2022.104924

•We developed QuorumChain to address the site-unavailability issue on a blockchain hierarchical network.•We evaluated QuorumChain to demonstrate a more robust model learning protocol by using the quorum mechanism.•QuorumChain can support the deployment of collaborative modeling across institutions to expedite clinical/genomic/biomedical research. Collaborative privacy-preserving modeling across several healthcare institutions allows for the construction of more generalizable predictive models while protecting patient privacy. We aim at addressing the site availability issue on a hierarchical network by designing an immutable/transparent/source-verifiable quorum mechanism. We developed an approach to combine a hierarchical learning algorithm, a novel Proof-of-Quorum (PoQ) consensus protocol, and a design of blockchain smart contracts. We constructed QuorumChain as an example and evaluated the scenarios of site-unavailability during the initialization and/or iteration phases of the modeling process on three healthcare/genomic datasets. When one or more sites would become unavailable, HierarchicalChain could not function, whereas QuorumChain improved predictive correctness significantly (the full Area Under the receiver operating characteristic Curve, or AUC, improved from 0.068 to 0.441, all with p-values