Linked2Safety: A secure linked data medical information space for semantically-interconnecting EHRs advancing patients' safety in medical research

Abstract

Electronic Health Records (EHRs) contain an increasing wealth of medical information. They have the potential to help significantly in advancing medical research, as well as improve health policies, providing society with additional benefits. However, the European healthcare information space is fragmented due to the lack of legal and technical standards, cost effective platforms, and sustainable business models. The vision of Linked2Safety is to advance clinical practice and accelerate medical research, by providing pharmaceutical companies, healthcare professionals and patients with an innovative secure semantic interoperability framework facilitating the efficient and homogenized access to anonymised distributed EHRs in an aggregate form that enables merging multiple data sources into a single analyses. In this paper a first public introduction to the project is provided along with a clear definition of the problems, and proposed architecture. Three usage scenarios are used to demonstrate the potential impact of the outcomes of the project.

Querying phenotype-genotype associations across multiple knowledge bases using Semantic Web technologies

“…Harnessing knowledge from scientific research to produce new drugs and treatment options for patients as well as to enable early detection of adverse events requires innovative interoperability frameworks and business models to support information flow between scientists and research institutions [3,4].…”

On-the-fly generation of multidimensional data cubes for web of things

“…In this approach, authors generate data cubes and store them in RDF format to support data analysis from a single place. In comparison to our work, the approach given in [1] uses a batch mechanism as opposed to real-time transformation of events and generation of data cubes.…”

“…In the paper [1], the authors discuss a system that uses Electronic Health Records (EHR) aggregated from different data sources for advancements on medical research and practice. In this approach, authors generate data cubes and store them in RDF format to support data analysis from a single place.…”

Linked Biomedical Dataspace: Lessons Learned Integrating Data for Drug Discovery

“…Adoption by the actual users is impeded due to their use of a comprehensive ontology instead of a domain-specific model and they have emphasized the need for community-driven annotation and personalization. Linked2Safety [2] and Linked TCGA [29] are pursuing the domain-specific query federation approach towards data integration. However, the scalability of these platforms for integrating newer data sources is yet to be evaluated.…”

“…Health-e-child [5] employs knowledge resources and OLAP-based data normalization tools to build multidimensional semantic spaces from biomedical data collections. Linked2Safety [2], aims to accelerate clinical practice and medical research. Finally, Linked TCGA [29] enables evidence-based personalized prognosis for cancer.…”