An Efficient Privacy-preserving Recommender System for e-Healthcare systems

The significant growth of medical data has necessitated the development of secure health-care recommender systems to assist people with their health-being effectively. Unfortunately, there is still a considerable gap between the performance of secure recommender systems and normal versions. In this work, we develop a privacy-preserving health-care recommendation algorithm to reduce that gap. The main strength of our contribution lies in providing a highly efficient solution, while the sensitive medical data are kept confidential. Our studies show that the runtime of our protocol is 81,5% faster than the existing implementation for small bit-lengths, and even more so for large bit-lengths.