Semantic reconciliation of standard and localized medical terminologies for knowledge interoperability

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The heterogeneous localized concepts of various hospitals reduce interoperability among localized data models of Hospital Information Systems (HIS) and the knowledge bases of clinical decision support systems (CDSS). The leading solution to overcome the interoperability barrier is the reconciliation of standard medical terminologies with localized data models. In this paper, we extend the semantic reconciliation model (SRM) to provide mappings among diverse concepts of localized domain clinical models (DCM) and concepts of standard medical terminologies such as Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT). In the extended SRM, we insert the explicit semantics only into the word vector of the localized DCM concepts instead of the implicit semantics, which enhances the system's accuracy with a lower computational cost. The extended SRM performed well on the datasets of localized DCM and SNOMED CT with a precision of 0.95, a recall of 0.92, and an F-measure of 0.93.

Original languageEnglish
Title of host publicationTHE IMPORTANCE OF HEALTH INFORMATICS IN PUBLIC HEALTH DURING A PANDEMIC
EditorsJohn Mantas, Arie Hasman, Mowafa S. Househ, Parisis Gallos, Emmanouil Zoulias
PublisherIOS Press
Pages461-464
Number of pages4
ISBN (Electronic)9781643680927
DOIs
Publication statusPublished - 2020

Publication series

NameStudies in Health Technology and Informatics
Volume272
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Keywords

  • Semantic reconciliation
  • clinical decision support system
  • health informatics
  • knowledge interoperability
  • ontology matching

Fingerprint

Dive into the research topics of 'Semantic reconciliation of standard and localized medical terminologies for knowledge interoperability'. Together they form a unique fingerprint.

Cite this