Cui Jianfei, Zhu He, Deng Hao, Chen Ziwei, Liu Dianbo
Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90007, United States.
The Hong Kong Polytechnic University, Hong Kong.
J Biomed Inform. 2021 May;117:103735. doi: 10.1016/j.jbi.2021.103735. Epub 2021 Mar 9.
Electrical medical records are restricted and difficult to centralize for machine learning model training due to privacy and regulatory issues. One solution is to train models in a distributed manner that involves many parties in the process. However, sometimes certain parties are not trustable, and in this project, we aim to propose an alternative method to traditional federated learning with central analyzer in order to conduct training in a situation without a trustable central analyzer. The proposed algorithm is called "federated machine learning with anonymous random hybridization (abbreviated as 'FeARH')", using mainly hybridization algorithm to degenerate the integration of connections between medical record data and models' parameters by adding randomization into the parameter sets shared to other parties. Based on our experiment, our new algorithm has similar AUCROC and AUCPR results compared with machine learning in a centralized manner and original federated machine learning.
由于隐私和监管问题，电子病历受到限制且难以集中用于机器学习模型训练。一种解决方案是以分布式方式训练模型，在此过程中涉及多个参与方。然而，有时某些参与方不可信，在本项目中，我们旨在提出一种替代传统带中央分析器的联邦学习的方法，以便在没有可信中央分析器的情况下进行训练。所提出的算法称为“带匿名随机混合的联邦机器学习（简称为‘FeARH’）”，主要使用混合算法，通过在共享给其他参与方的参数集中添加随机化，来弱化病历数据与模型参数之间连接的整合。基于我们的实验，与集中式机器学习和原始联邦机器学习相比，我们的新算法具有相似的AUCROC和AUCPR结果。
