University of Victoria

Published purpose

Precision medicine is an emerging approach for disease treatment and prevention by delivering personalized care to individual patients taking into consideration their personal circumstance in terms of genetic makeup, environment, and lifestyle. Advancement in precision healthcare is tied to technological advancements, such as big data storage and analysis, sensor technologies, the Internet of Things, etc. Despite the rapid advancement of precision medicine and the considerable promises that it entails, several underlying technological challenges have not yet received the attention they deserve. One such area of great importance is the security and privacy of precision health related data. Specifically, the security and privacy risks of introducing precision health related data, such as the human genome, in patient’s electronic health record (EHR), are not well understood. The purpose of the current project is to develop an Artificial Intelligence-based framework that will take as input precision health related data, such as the human genomic sequence, and produce a different representation that is privacy-proven and can be appended safely to patient’s EHR. This new representation will provide enough information that can be used and analyzed by the different precision health professionals, while not being reversible. The new framework will leverage advances in deep neural network and homomorphic encryption techniques.