About

Maintained by
Hui Zhu, Xiaoxia Liu, Rongxing Lu and Hui Li
Xidian University
266 Xinglong Section of Xifeng Road, Xi'an, Shaanxi 710126, China

  Abstract

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.

  System Model

Fig 1.1 System model under consideration

Fig 1.2 Query and response phase in the proposed eDiag framework

  Prototype and user interface

(a) Prototype of eDiag.

(b) User interface of eDiag.apk.

  Computation complexity of SP and user

(a) Computation cost of SP in eDiag.

(b) Computation cost of user in eDiag.

  Performance evaluation

(a) Average running time of SP in eDiag and CDSS.

(b) Average running time of user in eDiag and CDSS.

(c) Query response time in real environment.

  Demo Download

Demo Download:  
Demo File SHA256: 3F0311526FA2BDE00F086F281A969C2B56783979389BF9577219E00CA9B9E231
For Source Code:    zhuhui@xidian.edu.cn