Active Learning Pipeline to Identify Candidate Terms for a CDSS Ontology

Xia Jing*, Rohan Goli, Kerthana Komatineni, Shailesh Alluri, Nina Hubig, Hua Min, Yang Gong, Dean F. Sittig, Paul Biondich, David Robinson, Christian Gradhandt Nøhr, Arild Faxvaag, Adam Wright, Timothy Law, Lior Rennert, Ronald Gimbel

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

1 Downloads (Pure)

Abstract

Ontology is essential for achieving health information and information technology application interoperability in the biomedical fields and beyond.
Traditionally, ontology construction is carried out manually by human domain experts (HDE). Here, we explore an active learning approach to automatically
identify candidate terms from publications, with manual verification later as a part of a deep learning model training and learning process. We introduce the overall architecture of the active learning pipeline and present some preliminary results. This work is a critical and complementary component in addition to manually building the ontology, especially during the long-term maintenance stage.
Original languageEnglish
Book seriesStudies in Health Technology and Informatics
Volume316
Pages (from-to)1338-1342
Number of pages5
ISSN0926-9630
DOIs
Publication statusPublished - 22 Aug 2024

Keywords

  • Clinical decision support system ontology
  • active learning
  • deep learning
  • automatic keyphrase identification
  • natural language processing

Fingerprint

Dive into the research topics of 'Active Learning Pipeline to Identify Candidate Terms for a CDSS Ontology'. Together they form a unique fingerprint.

Cite this