Medical data privacy and disease prediction using advance encryption and machine learning approach

Abstract

Medical information of a patient is one of the most sensitive and private data and should be collected and stored in such a way that it doesn’t violate patient’s privacy. To achieve it, various different schemes have been proposed in the past.One of the main drawbacks of these proposed systems is time efficiency of data upload and retrieval which is mainly limited by the cryptographic algorithms used in these systems. In this paper, we proposea system that drastically improves efficiency without compromising on privacy with the help of Elliptic-curve cryptography (ECC). Furthermore, we run machine learning algorithm on the stored data for disease prediction. We use UCI heart disease patient data set which is publicly available to train the proposed system. Our proposed model found performing better compared to the surveyed systems.