A first look at HealthCyberMap medical semantic subject search engine

Maged N Kamel Boulos

Research output: Contribution to journalArticlepeer-review

17 Citations (Scopus)

Abstract

HealthCyberMap (http://healthcybermap.semanticweb.org) is a Semantic Web project that aims at mapping selected parts of health information resources in cyberspace in novel semantic ways to improve their retrieval and navigation. This paper describes HealthCyberMap semantic subject search engine methodology and early prototype which attempt to overcome the limitations of conventional free text search engines. Explicit concepts in resource metadata map onto a brokering domain ontology (a clinical terminology or classification) allowing a Semantic Web search engine to infer implicit meanings (synonyms and semantic relationships) not directly mentioned in either the resource or its metadata. Similarly, user queries would map to the same ontology allowing the search engine to infer the implicit semantics of user queries and use them to optimise retrieval. Related issues of metadata, clinical terminologies and automatic vs. manual indexing of medical Web resources are also discussed, together with future methodological directions, which include the use of a true terminology server as an intelligent broker between user queries and HealthCyberMap pool of resource metadata. A comparative evaluation of the new engine based on relevance metrics is also proposed.

Original languageEnglish
Pages (from-to)33-41
Number of pages9
JournalTechnology and Health Care : Official Journal of the European Society for Engineering and Medicine
Volume12
Issue number1
Publication statusPublished - Dec 2004

Keywords

  • Humans
  • Information Services
  • Information Storage and Retrieval
  • Information Systems
  • Internet
  • Medical Informatics
  • Semantics
  • Unified Medical Language System
  • User-Computer Interface

Fingerprint

Dive into the research topics of 'A first look at HealthCyberMap medical semantic subject search engine'. Together they form a unique fingerprint.

Cite this