Privacy Enhancing Technologies for Intelligent Healthcare: Research Challenges and Opportunities

The efficient and secure processing of confidential health data always remained an important challenge for healthcare professionals and policymakers as this information needs to be shared among several parties for both data analytics and improved health treatments. In this regard, Privacy Enhancing Technologies (PETs) have already shown great potential in deploying intelligent healthcare systems for improved prognosis and diagnosis. This article explains important privacy-preserving techniques by focusing on their security models and performance issues. It specifically discusses libraries and tools that can be used to implement a particular PET model. Moreover, a detailed comparison is provided to highlight the strengths and weaknesses of each of the privacy enhancing approaches. It further sheds light on the security requirements of the health sector and summarizes state-of-the-art homomorphic encryption, secure multi-party computation, differential privacy, and trusted execution environment approaches used in the healthcare setting. Finally, important parameters are discussed that must be kept in consideration while choosing an optimal PET. The survey is concluded by presenting some future directions to improve the performance of PETs and their usage in the healthcare domain. To the best of our knowledge, it is the first paper that comprehensively discusses PETs in the context of healthcare.