Skip to main navigation Skip to search Skip to main content

Natural language-based knowledge extraction in healthcare domain

  • University of Latvia

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

9 Citations (Scopus)

Abstract

There is a growing amount of data in the databases of hospitals. These data could be exploited to alleviate the decision-making process of hospital managers, physicians and researchers. However, these types of end-users often lack the expertise necessary for extracting those data from the database. Several approaches exist in the field of how to allow non-programmers writing queries in a convenient manner, but none of them has yet reached fully satisfactory results. This paper sketches a solution to this problem by introducing means for writing queries in a keywords-containing natural language thus alleviating the query writing process for the end-user. Introducing this approach in the knowledge management system of the organization would greatly benefit the domain experts by allowing them to carry out the decision-making process in a more rapid and less erroneous manner.

Original languageEnglish
Title of host publicationProceedings of 3rd International Conference on Information System and Data Mining, ICISDM 2019
PublisherAssociation for Computing Machinery
Pages138-142
Number of pages5
ISBN (Electronic)9781450366359
DOIs
Publication statusPublished - 6 Apr 2019
Externally publishedYes
Event3rd International Conference on Information System and Data Mining, ICISDM 2019 - Houston, United States
Duration: 6 Apr 20198 Apr 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference3rd International Conference on Information System and Data Mining, ICISDM 2019
Country/TerritoryUnited States
CityHouston
Period6/04/198/04/19

Keywords

  • Containing text

Fingerprint

Dive into the research topics of 'Natural language-based knowledge extraction in healthcare domain'. Together they form a unique fingerprint.

Cite this