Data linking and integration for health applications
Abstract
Health data is stored in a plethora of heterogeneous databases varying in format, terminology, modality and quality. It is also subject to strong regulatory and jurisdictional restrictions related to data privacy and security. Nevertheless, there are substantial benefits to be obtained in health research and operational activities by linking databases. We will identify some of the issues, and some approaches which might be taken in solving these. A case study will be presented on the use of our particular approach for research on cancer datasets.