{"id":"https://openalex.org/W1971954596","doi":"https://doi.org/10.1145/2512089.2512101","title":"Document sublanguage clustering to detect medical specialty in cross-institutional clinical texts","display_name":"Document sublanguage clustering to detect medical specialty in cross-institutional clinical texts","publication_year":2013,"publication_date":"2013-10-29","ids":{"openalex":"https://openalex.org/W1971954596","doi":"https://doi.org/10.1145/2512089.2512101","mag":"1971954596","pmid":"https://pubmed.ncbi.nlm.nih.gov/27077137"},"language":"en","primary_location":{"id":"doi:10.1145/2512089.2512101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2512089.2512101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th international workshop on Data and text mining in biomedical informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001036145","display_name":"Kristina Doing-Harris","orcid":"https://orcid.org/0000-0002-9704-8523"},"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":"Kristina Doing-Harris","raw_affiliation_strings":["University of Utah Health Sciences Center, Salt Lake City, UT, USA","University of Utah Health Sciences Center, Salt Lake City, UT, USA;"],"affiliations":[{"raw_affiliation_string":"University of Utah Health Sciences Center, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah Health Sciences Center, Salt Lake City, UT, USA;","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062893408","display_name":"Olga V. Patterson","orcid":"https://orcid.org/0000-0002-8717-5975"},"institutions":[{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olga Patterson","raw_affiliation_strings":["VA SLC Health Care, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"VA SLC Health Care, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I4210089864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033086766","display_name":"Sean Igo","orcid":null},"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":"Sean Igo","raw_affiliation_strings":["University of Utah Health Sciences Center, Salt Lake City, UT, USA","University of Utah Health Sciences Center, Salt Lake City, UT, USA;"],"affiliations":[{"raw_affiliation_string":"University of Utah Health Sciences Center, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah Health Sciences Center, Salt Lake City, UT, USA;","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068166269","display_name":"John F. Hurdle","orcid":"https://orcid.org/0000-0002-1188-7685"},"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":"John Hurdle","raw_affiliation_strings":["University of Utah Health Sciences Center, Salt Lake City, UT, USA","University of Utah Health Sciences Center, Salt Lake City, UT, USA;"],"affiliations":[{"raw_affiliation_string":"University of Utah Health Sciences Center, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah Health Sciences Center, Salt Lake City, UT, USA;","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001036145"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":1.4944,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.8541823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2013","issue":null,"first_page":"9","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7308200001716614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6904959082603455},{"id":"https://openalex.org/keywords/sublanguage","display_name":"Sublanguage","score":0.676314115524292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6076313257217407},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49131670594215393},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47676974534988403},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.4203495383262634},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3902205228805542},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10613542795181274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308200001716614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6904959082603455},{"id":"https://openalex.org/C2776411971","wikidata":"https://www.wikidata.org/wiki/Q17141398","display_name":"Sublanguage","level":2,"score":0.676314115524292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6076313257217407},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49131670594215393},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47676974534988403},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.4203495383262634},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3902205228805542},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10613542795181274},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2512089.2512101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2512089.2512101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th international workshop on Data and text mining in biomedical informatics","raw_type":"proceedings-article"},{"id":"pmid:27077137","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27077137","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":"Proceedings of the ACM ... International Workshop on Data and Text Mining in Biomedical Informatics. ACM International Workshop on Data and Text Mining in Biomedical Informatics","raw_type":null},{"id":"pmh:oai:europepmc.org:3797580","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4827341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W13410520","https://openalex.org/W144923133","https://openalex.org/W177117832","https://openalex.org/W256033851","https://openalex.org/W1237926134","https://openalex.org/W1577356484","https://openalex.org/W2022817031","https://openalex.org/W2031434922","https://openalex.org/W2043433471","https://openalex.org/W2049810512","https://openalex.org/W2054804336","https://openalex.org/W2071105621","https://openalex.org/W2093157872","https://openalex.org/W2120708938","https://openalex.org/W2122402213","https://openalex.org/W2127603354","https://openalex.org/W2148467945","https://openalex.org/W2335231222","https://openalex.org/W2578802954","https://openalex.org/W2984598682","https://openalex.org/W3003665436","https://openalex.org/W3017143921","https://openalex.org/W4388123485","https://openalex.org/W6661396363"],"related_works":["https://openalex.org/W2003127701","https://openalex.org/W2563868050","https://openalex.org/W74549753","https://openalex.org/W1822792362","https://openalex.org/W1513056508","https://openalex.org/W1507779355","https://openalex.org/W2575181596","https://openalex.org/W2138789621","https://openalex.org/W2164861117","https://openalex.org/W2069107439"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"on":[3,56,118],"a":[4,51,71,95,101,123,133],"set":[5],"of":[6,47,85,108,140],"studies":[7],"designed":[8],"to":[9,115,122,156],"identify":[10],"sublanguages":[11,91,178],"in":[12],"documents":[13,112,129,157],"for":[14,78],"domain-specific":[15,48],"processing":[16],"across":[17,92,164,170,182],"institutions.":[18,93,183],"Psychological":[19],"evidence":[20],"indicates":[21],"that":[22,75,151,175],"humans":[23],"use":[24],"context-specific":[25],"linguistic":[26],"information":[27],"when":[28],"they":[29],"read.":[30],"Natural":[31],"Language":[32],"Processing":[33],"(NLP)":[34],"pipelines":[35],"are":[36,59],"successful":[37],"within":[38,145],"specific":[39],"domains":[40],"(i.e.,":[41],"contexts).":[42],"To":[43],"limit":[44],"the":[45,83,106,119,141,146],"number":[46],"NLP":[49,97],"systems,":[50],"natural":[52],"focus":[53],"would":[54],"be":[55,180],"sublanguages.":[57],"Sublanguages":[58],"identified":[60,181],"by":[61,100],"shared":[62],"lexical":[63],"and":[64,68,166],"semantic":[65],"features.[1]":[66],"Patterson":[67],"Hurdle[2]":[69],"developed":[70],"sublanguage":[72],"identification":[73],"system":[74],"functioned":[76],"well":[77],"12":[79],"clinical":[80,96,176],"specialties":[81],"at":[82],"University":[84,107],"Utah.":[86],"The":[87,127,172],"current":[88],"work":[89],"compares":[90],"Using":[94],"pipeline":[98],"augmented":[99],"new":[102,111],"document":[103,167],"corpus":[104],"from":[105],"Pittsburg":[109],"(UPitt),":[110],"were":[113,130],"assigned":[114],"clusters":[116],"based":[117],"minimum":[120],"cosine-distance":[121],"Utah":[124],"cluster":[125],"centroid.":[126],"UPitt":[128],"divided":[131],"into":[132],"nine-group":[134],"specialty":[135,142,177],"corpus.":[136],"Across":[137],"institutions,":[138],"five":[139],"groups":[143],"fell":[144],"expected":[147],"clusters.":[148],"We":[149],"find":[150],"clustering":[152],"encounters":[153],"difficulty":[154],"due":[155],"with":[158],"mixed":[159],"sublanguages;":[160],"naming":[161],"convention":[162],"differences":[163],"institutions;":[165],"types":[168],"used":[169],"specialties.":[171],"findings":[173],"indicate":[174],"can":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}