Towards a knowledge federation of linked patient registries

Rare disease patient registries are now an essential tool for all clinical stakeholders. These systems' features aim to improve patient treatments by collecting comprehensive electronic patient records. Understanding these data is a vital step towards personalized medicine. Yet, the growing number of disease-specific patient registries brings new challenges for life sciences developers. These systems are closed data silos, with independent formats and data models. As they were built with security and privacy in mind, available tools lack comprehensive data access mechanisms, thus making data sharing a complex process. However, exchanging knowledge is essential to a better understanding of studied diseases. To tackle these challenges we introduce a semantic web-based architecture to connect distributed and heterogeneous registries. This enables the federation of knowledge between multiple independent environments. The semantic web paradigm enhances the ways we deal with data, optimising how we can create, infer and publish knowledge. Hence, we adopt these modern standards to deploy patient registry add ons. These can extract anonymised data and elevate them to a knowledge-oriented format, common to all registries. The outcome is a unique semantic layer, connecting miscellaneous registries, which we access using federated querying. Ultimately, this strategy empowers an holistic view through connected registries, enabling state-of-the-art semantic data sharing and access.