Zhu Hui, Liu Xiaoxia, Lu Rongxing, Li Hui
IEEE J Biomed Health Inform. 2017 May;21(3):838-850. doi: 10.1109/JBHI.2016.2548248. Epub 2016 Mar 29.
With the advances of machine learning algorithms and the pervasiveness of network terminals, the online medical prediagnosis system, which can provide the diagnosis of healthcare provider anywhere anytime, has attracted considerable interest recently. However, the flourish of online medical prediagnosis system still faces many challenges including information security and privacy preservation. In this paper, we propose an e fficient and privacy-preserving online medical prediagnosis framework, called eDiag, by using nonlinear kernel support vector machine (SVM). With eDiag, the sensitive personal health information can be processed without privacy disclosure during online prediagnosis service. Specifically, based on an improved expression for the nonlinear SVM, an efficient and privacy-preserving classification scheme is introduced with lightweight multiparty random masking and polynomial aggregation techniques. The encrypted user query is directly operated at the service provider without decryption, and the diagnosis result can only be decrypted by user. Through extensive analysis, we show that eDiag can ensure that users' health information and healthcare provider's prediction model are kept confidential, and has significantly less computation and communication overhead than existing schemes. In addition, performance evaluations via implementing eDiag on smartphone and computer demonstrate eDiag's effectiveness in term of real online environment.
随着机器学习算法的进步和网络终端的普及，能够随时随地为医疗服务提供者提供诊断的在线医学预诊断系统最近引起了广泛关注。然而，在线医学预诊断系统的蓬勃发展仍面临诸多挑战，包括信息安全和隐私保护。在本文中，我们提出了一种高效且保护隐私的在线医学预诊断框架，称为eDiag，它使用非线性核支持向量机（SVM）。借助eDiag，敏感的个人健康信息在在线预诊断服务期间可以在不泄露隐私的情况下进行处理。具体而言，基于非线性SVM的一种改进表达式，引入了一种高效且保护隐私的分类方案，采用轻量级多方随机掩码和多项式聚合技术。加密的用户查询在服务提供商处直接进行操作而无需解密，并且诊断结果只能由用户解密。通过广泛分析，我们表明eDiag可以确保用户的健康信息和医疗服务提供者的预测模型得到保密，并且与现有方案相比具有显著更少的计算和通信开销。此外，通过在智能手机和计算机上实现eDiag进行的性能评估证明了eDiag在实际在线环境方面的有效性。
