An efficient and privacy-Preserving pre-clinical guide scheme for mobile eHealthcare

Abstract

With the increasing popularity of pervasive devices such as smartphones and Internet-of-Things devices, mobile e-Healthcare has become a research trend in recent years. Disease risk prediction using big data analytics techniques is one popular e-Healthcare research focus, and one associated research challenge is ensuring the privacy of user and patient data. In this paper, we propose a new efficient and privacy-preserving pre-clinical guidance scheme (hereafter referred to as PGuide) for mobile eHealthcare, designed to offer both self-diagnosis and hospital recommendation services to users in a privacy-preserving way. To provide users the capability to present a detailed health profile for accurate disease risk prediction, we introduce a privacy-preserving comparison protocol (PPCP) in PGuide, which will improve the accuracy of disease risk prediction. We also employ a single-attribute encryption technique to devise a privacy-preserving hospital recommendation service in PGuide, which can further guide users to choose a hospital appropriate for their visit after conducting a self-diagnosis. We then prove that PGuide can achieve the privacy-preservation requirements in both self-diagnosis and hospitals recommendation services. We also conduct a number of experiments, which demonstrate the efficiency of PGuide, in terms of computational cost and communication overhead.