Department of Information Systems and Business Analytics, Florida International University, Miami, FL, United States.
American Heart Association, Dallas, TX, United States.
J Med Internet Res. 2023 Oct 30;25:e46547. doi: 10.2196/46547.
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.
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.
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.
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.
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.
开发有效且可推广的预测模型对于疾病预测和临床决策至关重要，通常需要多样化的样本来减轻人群偏差并解决算法公平性问题。然而，一个主要的挑战是在不引入本地偏差和不公平性的情况下，从多个机构中检索学习模型，同时保护每个站点中个体患者的隐私。
本研究旨在了解机器学习过程在预测性医疗保健领域中存在的偏差和公平性问题。我们提出了一种软件架构，该架构集成了联邦学习和区块链，以提高公平性，同时保持可接受的预测准确性并最小化开销成本。
我们通过迭代设计方法改进了现有的联邦学习平台，通过集成区块链来实现。我们使用了设计科学研究方法，该方法涉及 2 个设计周期（联邦学习以减轻偏差和去中心化架构）。该设计涉及基于新颖架构的基于区块链的联邦学习框架中的偏差缓解过程。在这种架构下，多个医疗机构可以使用其受保护的隐私数据有效地共同训练预测模型，并最终在医疗保健领域实现决策公平。
我们使用 Aplos 智能合约、微服务、Rahasak 区块链和基于 Apache Cassandra 的分布式存储来设计和实现我们的解决方案。通过在 Rahasak 区块链网络中的 5 个模拟医疗中心作为对等方进行 20000 次本地模型训练迭代和 1000 次联邦模型训练迭代，我们展示了具有改进公平性机制的解决方案如何提高预测诊断的准确性。
我们的研究确定了医疗保健领域现有预测模型面临的预测偏差的技术挑战。为了克服这些挑战，我们提出了一种使用联邦学习和区块链的创新设计解决方案，并采用了一种独特的分布式架构来实现公平意识系统。我们已经说明了这种设计如何解决隐私、安全、预测准确性和可扩展性方面的挑战，最终提高预测性医疗保健领域的公平性和公正性。
