A Healthcare Knowledge Graph-based Approach to Enable Focused Clinical Search

Maulik Kamdar , Will Dowling, Michael Carroll, Cailey Fitzgerald, Sujit Pal, Steve Ross, Katie Scranton, Dru Henke, Mevan Samarasinghe

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review


For the diagnosis, prognosis, and treatment of their patients, clinicians need to search and synthesize accurate, succinct, updated, and trustworthy information, from a broad set of medical literature sources (e.g., patient guidelines, medical textbooks, journals, and synoptic overviews). Advanced technological solutions, which enable search and retrieval of the right excerpts from a corpus of trusted medical literature sources in the right context for clinical questions, are critical for the practice of medicine and patient care. In this talk, we present our research and development on a focused clinical search service that is powered by the Elsevier Healthcare Knowledge Graph, a knowledge platform that is composed of knowledge and data from heterogeneous healthcare sources about diseases, drugs, findings, guidelines, cohorts, journals, and books. The search service parses focused clinical search queries using different features of the healthcare knowledge graph and retrieves relevant, updated, and trusted medical content excerpts from a diverse corpus of medical literature sources. We demonstrate the importance of a scalable healthcare knowledge graph ecosystem and the use of machine learning and knowledge representation methods for focused clinical search.
Original languageAmerican English
Title of host publicationProceedings of the ISWC 2021 Posters, Demos and Industry Tracks: From Novel Ideas to Industrial Practice
Number of pages2
StatePublished - Oct 20 2021
EventInternational Semantic Web Conference 2021 - Virtual
Duration: Oct 24 2021Oct 28 2021


ConferenceInternational Semantic Web Conference 2021
Abbreviated titleISWC 2021
Internet address


Dive into the research topics of 'A Healthcare Knowledge Graph-based Approach to Enable Focused Clinical Search'. Together they form a unique fingerprint.

Cite this