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. 

In this project, we propose a generic machine learning with encryption (MLE) framework, which we used to build an ML model that predicts cancer from one of the most recent comprehensive genomics

datasets in the field. Our framework achieves high prediction accuracy while maintaining the privacy of the patients’ genomic data. To facilitate the validation, reproduction, and extension of this work, we provide an open-source repository that contains the design and implementation of the framework, all the ML experiments and code, and the final predictive model deployed to a free cloud service.