Architectural Design of a Blockchain-Enabled, Federated Learning Platform for Algorithmic Fairness in Predictive Health Care: Design Science Study.

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.

A blockchain empowered and privacy preserving digital contact tracing platform.

The spread of the COVID-19 virus continues to increase fatality rates and exhaust the capacity of healthcare providers. Efforts to prevent transmission of the virus among humans remains a high priority. The current efforts to quarantine involve social distancing, monitoring and tracking the infected patients. However, the spread of the virus is too rapid to be contained only by manual and inefficient human contact tracing activities. To address this challenge, we have developed Connect, a blockchain empowered digital contact tracing platform that can leverage information on positive cases and notify people in their immediate proximity which would thereby reduce the rate at which the infection could spread. This would particularly be effective if sufficient people use the platform and benefit from the targeted recommendations. The recommendations would be made in a privacy-preserving fashion and contain the spread of the virus without the need for an extended period of potential lockdown. Connect is an identity wallet platform which will keep user digital identities and user activity trace data on a blockchain platform using Self-Sovereign Identity(SSI) proofs. User activities include the places he/she has travelled, the country of origin he/she came from, travel and dispatch updates from the airport etc. With these activity trace records, Connect platform can easily identify suspected patients who may be infected with the COVID-19 virus and take precautions before spreading it. By storing digital identities and activity trace records on blockchain-based SSI platform, Connect addresses the common issues in centralized cloud-based storage platforms (e.g. lack of data immutability, lack of traceability).