Abstract

Disease risk assessment system has great eventuality to alleviate the medical treatment problems for the unborn smart megacity and communities, as it can excavate disease risk factors from a large number of case features, give diagnostic references for doctors, and save medical treatment time for cases. The flourish of disease risk assessment service still faces severe challenges including information privacy and security. Naive Bayesian classification techniques have taken over the task of prediction of disease risk assessment scheme over multi sourced vertical datasets, named CARER. With CARER, the e-healthcare provider can securely train a disease risk predication model over vertically distributed medical data from multiple medical centers and provide privacy-preserving disease risk predication services for users. During the model training and disease risk prediction phases, all sensitive data are operated over cipher texts. Finally, the private information of medical centers, e-healthcare provider, and users can be well protected. This security analysis shows that CARER can resist various known security threats. In addition, we evaluate the performance of CARER with real medical datasets, and the experimental results demonstrate that CARER is efficient and it improves prediction accuracy, privacy, and security compared to the existing methods.