{"id":"https://openalex.org/W2989605948","doi":"https://doi.org/10.3233/shti190520","title":"Using Enriched Samples for Semi-Automated Vocabulary Expansion to Identify Rare Events in Clinical Text: Sexual Orientation as a Use Case","display_name":"Using Enriched Samples for Semi-Automated Vocabulary Expansion to Identify Rare Events in Clinical Text: Sexual Orientation as a Use Case","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2989605948","doi":"https://doi.org/10.3233/shti190520","mag":"2989605948","pmid":"https://pubmed.ncbi.nlm.nih.gov/31438217"},"language":"en","primary_location":{"id":"doi:10.3233/shti190520","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190520","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti190520","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067620656","display_name":"Kristine E. Lynch","orcid":"https://orcid.org/0000-0002-2221-2421"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lynch Kristine E.","raw_affiliation_strings":["Department of Internal Medicine, Division of Epidemiology, University of Utah, Salt Lake City, UT, USA","VA Informatics and Computing Infrastructure, Department of Veterans Affairs, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, Division of Epidemiology, University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Informatics and Computing Infrastructure, Department of Veterans Affairs, Salt Lake City, UT, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080489523","display_name":"Patrick R. Alba","orcid":"https://orcid.org/0000-0002-5176-5447"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alba Patrick","raw_affiliation_strings":["Department of Internal Medicine, Division of Epidemiology, University of Utah, Salt Lake City, UT, USA","VA Informatics and Computing Infrastructure, Department of Veterans Affairs, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, Division of Epidemiology, University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Informatics and Computing Infrastructure, Department of Veterans Affairs, Salt Lake City, UT, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119361","display_name":"Benjamin Viernes","orcid":"https://orcid.org/0000-0003-1973-9043"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viernes Benjamin","raw_affiliation_strings":["Department of Internal Medicine, Division of Epidemiology, University of Utah, Salt Lake City, UT, USA","VA Informatics and Computing Infrastructure, Department of Veterans Affairs, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, Division of Epidemiology, University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Informatics and Computing Infrastructure, Department of Veterans Affairs, Salt Lake City, UT, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037435182","display_name":"Scott L. DuVall","orcid":"https://orcid.org/0000-0002-4898-3865"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DuVall Scott L.","raw_affiliation_strings":["Department of Internal Medicine, Division of Epidemiology, University of Utah, Salt Lake City, UT, USA","VA Informatics and Computing Infrastructure, Department of Veterans Affairs, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, Division of Epidemiology, University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Informatics and Computing Infrastructure, Department of Veterans Affairs, Salt Lake City, UT, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067620656"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":1.3136,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84475223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"264","issue":null,"first_page":"1532","last_page":"1533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.859025239944458},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.7669600248336792},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.757209300994873},{"id":"https://openalex.org/keywords/sexual-orientation","display_name":"Sexual orientation","score":0.7073260545730591},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.681309700012207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6356821656227112},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.587862491607666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.514162540435791},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4526233673095703},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28312569856643677},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26989126205444336},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10906589031219482},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07685971260070801},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07452869415283203}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.859025239944458},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.7669600248336792},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.757209300994873},{"id":"https://openalex.org/C2777997956","wikidata":"https://www.wikidata.org/wiki/Q17888","display_name":"Sexual orientation","level":2,"score":0.7073260545730591},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.681309700012207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6356821656227112},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.587862491607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.514162540435791},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4526233673095703},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28312569856643677},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26989126205444336},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10906589031219482},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07685971260070801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07452869415283203},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005783","descriptor_name":"Gender Identity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005783","descriptor_name":"Gender Identity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005783","descriptor_name":"Gender Identity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014825","descriptor_name":"Vocabulary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014825","descriptor_name":"Vocabulary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014825","descriptor_name":"Vocabulary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti190520","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190520","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:31438217","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31438217","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/shti190520","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190520","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W3195005284","https://openalex.org/W2391730868","https://openalex.org/W4394659737","https://openalex.org/W2759814045","https://openalex.org/W2118055728","https://openalex.org/W4399756845","https://openalex.org/W2736760277","https://openalex.org/W4386940087","https://openalex.org/W4386931226"],"abstract_inverted_index":{"We":[0,51],"demonstrate":[1],"the":[2,54],"utility":[3],"of":[4,13,47],"concept":[5],"lexicon":[6],"expansion":[7],"and":[8,15,40],"evaluation":[9],"using":[10],"enriched":[11],"samples":[12],"patients":[14],"documents":[16],"with":[17],"sexual":[18,70],"orientation":[19,71],"as":[20],"a":[21,60],"use":[22,53],"case":[23],"for":[24],"rare":[25],"event":[26],"detection":[27],"in":[28],"electronic":[29],"medical":[30],"records.":[31],"Using":[32],"this":[33],"approach,":[34],"we":[35],"found":[36],"7":[37],"additional":[38],"words":[39],"21":[41],"misspellings":[42],"beyond":[43],"our":[44],"initial":[45],"set":[46],"five":[48],"seed":[49],"words.":[50],"can":[52],"expanded":[55],"vocabulary":[56],"to":[57,66],"further":[58],"develop":[59],"full":[61],"natural":[62],"language":[63],"processing":[64],"system":[65],"identify":[67],"instances":[68],"where":[69],"is":[72],"documented.":[73]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-02-25T21:11:00.739837","created_date":"2025-10-10T00:00:00"}
