Abstract 142P
Background
In healthcare product development and research, teams invest huge amounts of time to study publications and other relevant sources. There is a need for novel solutions to efficiently and reliably extract information from multiple clinical data sources, in addition to generating new insights which can only be achieved through structuring textual information and accessible intelligent synthesis across multiple relevant data sources. We are developing a cloud-based solution where data from heterogeneous sources is structured, integrated and harmonized, and users can easily leverage the combined database to answer domain-specific questions and generate insights efficiently.
Methods
Knowledge graphs provide us the advantage to leverage relationships in addition to concepts in the context of heterogeneous data. We leveraged graph and NLP (Natural Language Processing) methods to build a domain-specific knowledge graph. We extracted the biomedically-relevant subset of Wikidata and augmented it from the biomedical literature (PubMed), clinical trials (clinicaltrials.gov) and NIH grants.
Results
We generated a rich biomedical knowledge graph including entities and relationships from Wikidata, PubMed, NIH grants and clinical trials, and enabled queries of the combined data source. The graph entities were additionally combined with MESH terminology to uncover similarities between concepts and to display results that enable trends investigation across entities, time horizons, authors, institutions, and funding.
Conclusions
We demonstrate how combining AI innovations in NLP and graph analytics, as well as novel approaches in aggregating and harmonizing disparate sources of biomedical knowledge can act as a novel and promising digital solution with potential to accelerate biomedical insights, answer queries, discover important trends or assist in new hypotheses generation for various biomedical applications such as biomarker and drug discovery.
Legal entity responsible for the study
Roche.
Funding
Roche.
Disclosure
V. Sharma, A. Vladimirova: Financial Interests, Institutional, Full or part-time Employment: Roche. A. Thomas, V. Vettrivel: Financial Interests, Institutional, Funding: John Snow Labs. D. Talby: Financial Interests, Institutional, Full or part-time Employment: John Snow Labs.