@inbook{3c6ae4a4742a48c89d720d87edebe3f6,
  title     = "Identifying disease-centric subdomains in very large medical ontologies: A case-study on breast cancer concepts in SNOMED CT. Or: Finding 2500 out of 300.000",
  abstract  = "Modern medical vocabularies can contain up to hundreds of thousands of concepts. In any particular use-case only a small fraction of these will be needed. In this paper we first define two notions of a disease-centric subdomain of a large ontology. We then explore two methods for identifying disease-centric subdomains of such large medical vocabularies. The first method is based on lexically querying the ontology with an iteratively extended set of seed queries. The second method is based on manual mapping between concepts from a medical guideline document and ontology concepts. Both methods include concept-expansion over subsumption and equality relations. We use both methods to determine a breast-cancer-centric subdomain of the SNOMED CT ontology. Our experiments show that the two methods produce a considerable overlap, but they also yield a large degree of complementarity, with interesting differences between the sets of concepts that they return. Analysis of the results reveals strengths and weaknesses of the different methods.",
  keywords  = "Disease related concepts, Identifying ontology subdomain, Mapping medical terminologies, Medical guidelines, Ontology subsetting, Seed queries",
  author    = "Krystyna Milian and Zharko Aleksovski and Richard Vdovjak and {Ten Teije}, Annette and {Van Harmelen}, Frank",
  year      = "2010",
  doi       = "10.1007/978-3-642-11808-1_5",
  isbn      = "3642118070",
  volume    = "5943 LNAI",
  series    = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
  pages     = "50--63",
  booktitle = "Knowledge Representation for Health-Care: Data, Processes and Guidelines, AIME 2009, Workshop KR4HC 2009, Revised Selected and Invited Papers",
}

{"_id":"zBSvRhPqzXG5RwDSW","bibbaseid":"milian-aleksovski-vdovjak-tenteije-vanharmelen-identifyingdiseasecentricsubdomainsinverylargemedicalontologiesacasestudyonbreastcancerconceptsinsnomedctorfinding2500outof300000-2010","downloads":0,"creationDate":"2017-10-10T08:05:28.772Z","title":"Identifying disease-centric subdomains in very large medical ontologies: A case-study on breast cancer concepts in SNOMED CT. Or: Finding 2500 out of 300.000","author_short":["Milian, K.","Aleksovski, Z.","Vdovjak, R.","Ten Teije, A.","Van Harmelen, F."],"year":2010,"bibtype":"inbook","biburl":"https://raw.githubusercontent.com/KRRVU/website/master/publications/krr.bib","bibdata":{"bibtype":"inbook","type":"inbook","title":"Identifying disease-centric subdomains in very large medical ontologies: A case-study on breast cancer concepts in SNOMED CT. Or: Finding 2500 out of 300.000","abstract":"Modern medical vocabularies can contain up to hundreds of thousands of concepts. In any particular use-case only a small fraction of these will be needed. In this paper we first define two notions of a disease-centric subdomain of a large ontology. We then explore two methods for identifying disease-centric subdomains of such large medical vocabularies. The first method is based on lexically querying the ontology with an iteratively extended set of seed queries. The second method is based on manual mapping between concepts from a medical guideline document and ontology concepts. Both methods include concept-expansion over subsumption and equality relations. We use both methods to determine a breast-cancer-centric subdomain of the SNOMED CT ontology. Our experiments show that the two methods produce a considerable overlap, but they also yield a large degree of complementarity, with interesting differences between the sets of concepts that they return. Analysis of the results reveals strengths and weaknesses of the different methods.","keywords":"Disease related concepts, Identifying ontology subdomain, Mapping medical terminologies, Medical guidelines, Ontology subsetting, Seed queries","author":[{"firstnames":["Krystyna"],"propositions":[],"lastnames":["Milian"],"suffixes":[]},{"firstnames":["Zharko"],"propositions":[],"lastnames":["Aleksovski"],"suffixes":[]},{"firstnames":["Richard"],"propositions":[],"lastnames":["Vdovjak"],"suffixes":[]},{"propositions":[],"lastnames":["Ten Teije"],"firstnames":["Annette"],"suffixes":[]},{"propositions":[],"lastnames":["Van Harmelen"],"firstnames":["Frank"],"suffixes":[]}],"year":"2010","doi":"10.1007/978-3-642-11808-1_5","isbn":"3642118070","volume":"5943 LNAI","series":"Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)","pages":"50–63","booktitle":"Knowledge Representation for Health-Care: Data, Processes and Guidelines, AIME 2009, Workshop KR4HC 2009, Revised Selected and Invited Papers","bibtex":"@inbook{3c6ae4a4742a48c89d720d87edebe3f6,\n title = \"Identifying disease-centric subdomains in very large medical ontologies: A case-study on breast cancer concepts in SNOMED CT. Or: Finding 2500 out of 300.000\",\n abstract = \"Modern medical vocabularies can contain up to hundreds of thousands of concepts. In any particular use-case only a small fraction of these will be needed. In this paper we first define two notions of a disease-centric subdomain of a large ontology. We then explore two methods for identifying disease-centric subdomains of such large medical vocabularies. The first method is based on lexically querying the ontology with an iteratively extended set of seed queries. The second method is based on manual mapping between concepts from a medical guideline document and ontology concepts. Both methods include concept-expansion over subsumption and equality relations. We use both methods to determine a breast-cancer-centric subdomain of the SNOMED CT ontology. Our experiments show that the two methods produce a considerable overlap, but they also yield a large degree of complementarity, with interesting differences between the sets of concepts that they return. Analysis of the results reveals strengths and weaknesses of the different methods.\",\n keywords = \"Disease related concepts, Identifying ontology subdomain, Mapping medical terminologies, Medical guidelines, Ontology subsetting, Seed queries\",\n author = \"Krystyna Milian and Zharko Aleksovski and Richard Vdovjak and {Ten Teije}, Annette and {Van Harmelen}, Frank\",\n year = \"2010\",\n doi = \"10.1007/978-3-642-11808-1_5\",\n isbn = \"3642118070\",\n volume = \"5943 LNAI\",\n series = \"Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)\",\n pages = \"50--63\",\n booktitle = \"Knowledge Representation for Health-Care: Data, Processes and Guidelines, AIME 2009, Workshop KR4HC 2009, Revised Selected and Invited Papers\",\n}\n\n\n","author_short":["Milian, K.","Aleksovski, Z.","Vdovjak, R.","Ten Teije, A.","Van Harmelen, F."],"key":"3c6ae4a4742a48c89d720d87edebe3f6","id":"3c6ae4a4742a48c89d720d87edebe3f6","bibbaseid":"milian-aleksovski-vdovjak-tenteije-vanharmelen-identifyingdiseasecentricsubdomainsinverylargemedicalontologiesacasestudyonbreastcancerconceptsinsnomedctorfinding2500outof300000-2010","role":"author","urls":{},"keyword":["Disease related concepts","Identifying ontology subdomain","Mapping medical terminologies","Medical guidelines","Ontology subsetting","Seed queries"],"metadata":{"authorlinks":{}},"downloads":0},"search_terms":["identifying","disease","centric","subdomains","very","large","medical","ontologies","case","study","breast","cancer","concepts","snomed","finding","2500","out","300","000","milian","aleksovski","vdovjak","ten teije","van harmelen"],"keywords":["disease related concepts","identifying ontology subdomain","mapping medical terminologies","medical guidelines","ontology subsetting","seed queries"],"authorIDs":[],"dataSources":["H6xuGqu5uQ6rXhdJ4","dJmTXpbSWWjnxatYT"]}