Enabling privacy-preserving medication analysis in distributed EHR systems

Abstract

The digitalization of the medical field has resulted in a vast amount of medical data stored in Electronic Health Record (EHR) systems. Among the various valuable applications of EHRs, medication efficacy analysis stands out as a powerful tool for drug development and enhancing patient treatment. This analysis relies on multi-dimensional medical data, encompassing various factors. Currently, medical research is increasingly inclined towards inter-institutional sharing of medical data to enhance the accuracy and reliability of analysis results. However, due to the sensitivity of personal medical data, privacy and security considerations must be taken into account when conducting medical analyses across institutions. In this paper, we present a novel privacy-preserving scheme for distributed medication efficacy analysis. Our work allows for the analysis of multi-dimensional medical data by leveraging the private set intersection protocol and the Paillier cryptosystem. To validate the feasibility of our scheme, we implement it using some real medical datasets. Experimental results demonstrate that our approach offers enhanced security and lower computational and communication overhead compared to the original approach, which solely processes single-dimensional data at a time.