The overall technological aim of CARRE project is to show the potential of semantic interlinking of heterogeneous data to construct dynamic personalized models of complex comorbid medical conditions with disease progression pathways and comorbidity trajectories. Also, to show that visual analytics based on such models can support patient understanding of personal complex conditions (projected against ground knowledge and statistical views of similar patient population) and be the basis for shared decision support services for the management of comorbidities.

Major expected technological breakthroughs include:

•  an ontology and schema for the description of comorbidities management (in the case of cardiorenal disease and comorbidities);

• data aggregators for integration of heterogeneous sources of information, such as medical evidence, personal data (including dynamic sensor data), medical information and personal disposition & lifestyle;

•  text analysis tools to semantically annotate  and extract relevant metadata from unstructured sources (medical evidence, social media);

•  generic aggregator technology to harvest semantic information from structured data sources as listed above (e.g. personal sensors, educational content items);

• linked data technologies for semantic data interlinking, and enrichment;

• tools and infrastructure for large scale processing of aggregated data for visual analytics mentioned above;

• data/model driven decision support systems to build shared decision support services for the patient and the medical professional based on the personalized comorbidities model of the patient.