Knowledge graphs for enhancing transparency in health data ecosystems1

Abstract

Tailoring personalized treatments demands the analysis of a patient’s characteristics, which may be scattered over a wide variety of sources. These features include family history, life habits, comorbidities, and potential treatment side effects. Moreover, the analysis of the services visited the most by a patient before a new diagnosis, as well as the type of requested tests, may uncover patterns that contribute to earlier disease detection and treatment effectiveness. Built on knowledge-driven ecosystems, we devise DE4LungCancer, a health data ecosystem of data sources for lung cancer. In this data ecosystem, knowledge extracted from heterogeneous sources, e.g., clinical records, scientific publications, and pharmacological data, is integrated into knowledge graphs. Ontologies describe the meaning of the combined data, and mapping rules enable the declarative definition of the transformation and integration processes. DE4LungCancer is assessed regarding the methods followed for data quality assessment and curation. Lastly, the role of controlled vocabularies and ontologies in health data management is discussed, as well as their impact on transparent knowledge extraction and analytics. This paper presents the lessons learned in the DE4LungCancer development. It demonstrates the transparency level supported by the proposed knowledge-driven ecosystem, in the context of the lung cancer pilots of the EU H2020-funded project BigMedilytic, the ERA PerMed funded project P4-LUCAT, and the EU H2020 projects CLARIFY and iASiS.

Empowering the SDM-RDFizer tool for scaling up to complex knowledge graph creation pipelines1

“…This section illustrates the problem of defining a KG using a declarative approach where mapping rules are specified in RML. In this example, we focus on a portion of a DIS that defines a biomedical KG [2,52,64,65], e.g., the one created in the context of the EU H2020 projects iASiS 5 and CLARIFY 6 . The data sources, referred to as SDM-Genomic-Datasets [33] vary in size, with 100k, 1M, and 5M rows, and each dataset has a different percentage of data duplicate rate (25% or 75%).…”

“…SDM-RDFizer has been incorporated into a knowledge-driven framework to overcome challenges related to interoperability and data quality in lung cancer data. This framework provides a foundation for addressing clinical research questions in lung cancer (Fotis et al [2] and Torrente et al [62]).…”

“…These scenarios are exemplified by the testbeds proposed in the Knowledge Graph Construction Workshop 2023 Challenge at ESWC 2023 [63] and are characterized by parameters reported by Chaves-Fraga et al [15]. These complex use cases span different domains, such as biomedicine [2,52,59] and energy [37], where the declarative definition of KGs facilitates the smooth integration of large amounts of heterogeneous data, potentially duplicated across different data sources. As a result, SDM-RDFizer v4.5.6 is empowered to scale up data collection, processing, and integration towards efficient KG creation.…”