Hybrid privacy-preserving clinical decision support system in fog–cloud computing

• Published in: Future generation computer systems 2018-01, Vol.78, p.825-837
• Main Authors: Liu, Ximeng, Deng, Robert H., Yang, Yang, Tran, Hieu N., Zhong, Shangping
• Format: Article
• Language: English
• Subjects: Clinical decision support system; Cloud computing; Fog computing; Neural networks; Privacy-preserving
• ISSN: 0167-739X; 1872-7115
• DOI: 10.1016/j.future.2017.03.018

In this paper, we propose a framework for hybrid privacy-preserving clinical decision support system in fog–cloud computing, called HPCS. In HPCS, a fog server uses a lightweight data mining method to securely monitor patients’ health condition in real-time. The newly detected abnormal symptoms can be further sent to the cloud server for high-accuracy prediction in a privacy-preserving way. Specifically, for the fog servers, we design a new secure outsourced inner-product protocol for achieving secure lightweight single-layer neural network. Also, a privacy-preserving piecewise polynomial calculation protocol allows cloud server to securely perform any activation functions in multiple-layer neural network. Moreover, to solve the computation overflow problem, a new protocol called privacy-preserving fraction approximation protocol is designed. We then prove that the HPCS achieves the goal of patient health status monitoring without privacy leakage to unauthorized parties by balancing real-time and high-accurate prediction using simulations. •We propose a hybrid model for real-time and high-accurate secure disease prediction.•We propose a protocol to achieve inner-product calculation over ciphertext in only a single round.•We construct a protocol to calculate non-linear activation function in the neural network.•We construct a secure protocol to overflow problem during the calculation.•Our system can balance the real-time and high-accurate prediction using JAVA simulations.