Privacy-Preserving Medical Data Sharing
Abstract
Patient data that contain demographics, clinical, and genomic information are derived from Electronic Medical Record (EMR) systems and are increasingly disseminated into biomedical research repositories. This is essential to perform large-scale and low-cost biomedical analysis and decision making, but may pose serious privacy threats. Eliminating these threats is necessary to uphold patients' right to privacy and to comply with data sharing policies and legislation, such as the HIPAA privacy rule and the EU Directive 95/46/CE.
In this tutorial, we will first demonstrate the need for privacy-preserving medical data sharing by discussing analysis and mining tasks that disseminated data need to support, as well privacy threats that data sharing entails. Then, we will review privacy-preserving principles and algorithms that have been developed for sharing different types of medical data, including demographics, clinical and genomic data, and discuss a number of key issues, such as how data can be transformed to achieve both utility and privacy and how these two properties can be effectively balanced. In addition, some interesting case studies using data from the US Census and the EMR system of the Vanderbilt University Medical Center will be presented. Following that, we will highlight important open problems and future directions.
Biographies of Authors
Aris Gkoulalas-Divanis is a Research Staff Member in the Information Analytics group at IBM Research-Zurich. Prior to that, he was a postdoctoral researcher in the Health Information Privacy LABoratory (HIPLAB) in Vanderbilt University. Aris received the Diploma from the University of Ioannina, the MS from the University of Minnesota, and the PhD from the University of Thessaly, all in Computer Science. His research interests are in the areas of databases, data mining, privacy-preserving data mining, privacy in medical data, and knowledge hiding.
Grigorios Loukides is an Assistant Professor in the School of Computer Science and Informatics, Cardiff University, and a Royal Academy of Engineering Research Fellow. Prior to that, he was a postdoctoral researcher in the Health Information Privacy LABoratory (HIPLAB), Vanderbilt University. He holds a Diploma from the University of Crete and a Ph.D. from Cardiff University, both in Computer Science. Grigorios' research interests are in privacy-preserving data mining and publishing, and in biomedical informatics.
