{"id":"https://openalex.org/W1666538313","doi":null,"title":"Part-of-speech tagging for clinical text: wall or bridge between institutions?","display_name":"Part-of-speech tagging for clinical text: wall or bridge between institutions?","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W1666538313","mag":"1666538313","pmid":"https://pubmed.ncbi.nlm.nih.gov/22195091","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3243258"},"language":"en","primary_location":{"id":"pmh:oai:pubmedcentral.nih.gov:3243258","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3243258","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"AMIA Annu Symp Proc","raw_type":"Text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3243258","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111584033","display_name":"Jung-Wei Fan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1343052199","display_name":"Kaiser Permanente","ror":"https://ror.org/00t60zh31","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1343052199"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jung-wei Fan","raw_affiliation_strings":["Kaiser Permanente Southern California, Pasadena, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kaiser Permanente Southern California, Pasadena, CA, USA","institution_ids":["https://openalex.org/I1343052199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026474261","display_name":"Rashmi Prasad","orcid":"https://orcid.org/0000-0002-3870-0630","observed_orcids":["https://orcid.org/0000-0002-3870-0630"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rashmi Prasad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047255374","display_name":"Rommel M Yabut","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rommel M Yabut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065402465","display_name":"Richard M. Loomis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard M Loomis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020362469","display_name":"Daniel S. Zisook","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel S Zisook","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082882378","display_name":"John E. Mattison","orcid":"https://orcid.org/0000-0003-0892-1835","observed_orcids":["https://orcid.org/0000-0003-0892-1835"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John E Mattison","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101682935","display_name":"Yang H. Huang","orcid":"https://orcid.org/0000-0002-9551-4447","observed_orcids":["https://orcid.org/0000-0002-9551-4447","https://orcid.org/0000-0002-7394-0955"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9392,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94149827,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"2011","issue":null,"first_page":"382","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5404999852180481,"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":0.5404999852180481,"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":0.43209999799728394,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.006300000008195639,"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/part-of-speech-tagging","display_name":"part-of-speech tagging","score":1.0},{"id":"https://openalex.org/keywords/clinical-narratives","display_name":"clinical text","score":0.8629999756813049},{"id":"https://openalex.org/keywords/annotation-sharing","display_name":"annotation sharing","score":0.5640000104904175},{"id":"https://openalex.org/keywords/clinical-notes","display_name":"clinical notes","score":0.5040000081062317},{"id":"https://openalex.org/keywords/ctakes","display_name":"cTAKES","score":0.8809999823570251},{"id":"https://openalex.org/keywords/annotation-quality","display_name":"annotation quality","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507742643356323},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7406705617904663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6019004583358765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.594331681728363},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49883508682250977},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43790167570114136},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37794461846351624},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07803294062614441}],"mesh":[{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","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":true}],"locations_count":3,"locations":[{"id":"pmh:oai:pubmedcentral.nih.gov:3243258","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3243258","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"AMIA Annu Symp Proc","raw_type":"Text"},{"id":"pmid:22195091","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22195091","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,"listed_in":[],"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":"AMIA ... Annual Symposium proceedings. AMIA Symposium","raw_type":"Journal Article"},{"id":"mag:1666538313","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22195091","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:3243258","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3243258","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"AMIA Annu Symp Proc","raw_type":"Text"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1275080182","display_name":"Informatics for Integrating Biology & the Bedside (i2b2)","funder_award_id":"U54LM008748","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W17967270","https://openalex.org/W192665053","https://openalex.org/W900993354","https://openalex.org/W1482328859","https://openalex.org/W1511488739","https://openalex.org/W1516896160","https://openalex.org/W1602694398","https://openalex.org/W1632114991","https://openalex.org/W1829379010","https://openalex.org/W1871067837","https://openalex.org/W1967866551","https://openalex.org/W1991277413","https://openalex.org/W2002514548","https://openalex.org/W2007367068","https://openalex.org/W2097960255","https://openalex.org/W2101289003","https://openalex.org/W2127241285","https://openalex.org/W2135843243","https://openalex.org/W2139736061","https://openalex.org/W2146089916","https://openalex.org/W2162461580"],"related_works":["https://openalex.org/W1967866551","https://openalex.org/W2343478324","https://openalex.org/W2151532143","https://openalex.org/W3201805402","https://openalex.org/W2031420872","https://openalex.org/W2251868561","https://openalex.org/W2460715221","https://openalex.org/W2017882693","https://openalex.org/W2165570863","https://openalex.org/W2007367068"],"abstract_inverted_index":{"Part-of-speech":[0],"(POS)":[1],"tagging":[2,65,275,301],"is":[3,27,52],"a":[4,15,72,85,97,128,136],"fundamental":[5],"step":[6],"required":[7],"by":[8,70],"various":[9],"NLP":[10,320],"systems.":[11],"The":[12,116,245],"training":[13,77,215,233],"of":[14,87,102,135,149,251,319],"POS":[16,64,109,118,253,300],"tagger":[17,74,119,129,191],"relies":[18],"on":[19,55,153,162,171,176,185,201,206,220,238,312],"sufficient":[20],"quality":[21],"annotations.":[22],"However,":[23],"the":[24,33,100,124,133,154,165,179,189,197,217,235,249,262,271,299,305],"annotation":[25,47],"process":[26],"both":[28],"knowledge-intensive":[29],"and":[30,49,96,107,113,151,156,204],"time-consuming":[31],"in":[32,123],"clinical":[34,88],"domain.":[35],"A":[36],"promising":[37],"solution":[38],"appears":[39],"to":[40,44,61,126,213,225,231,243],"be":[41,68],"for":[42,277,298,316],"institutions":[43,284],"share":[45],"their":[46],"efforts,":[48],"yet":[50],"there":[51],"little":[53],"research":[54],"associated":[56],"issues.":[57],"We":[58,82,303],"performed":[59],"experiments":[60],"understand":[62],"how":[63],"performance":[66,250],"would":[67],"affected":[69],"using":[71],"pre-trained":[73,192,252,296],"versus":[75],"raw":[76,290],"data":[78,314],"across":[79,261],"different":[80],"institutions.":[81],"manually":[83],"annotated":[84],"set":[86,98],"notes":[89,134,158,203,223,241],"at":[90,141],"Kaiser":[91],"Permanente":[92],"Southern":[93],"California":[94],"(KPSC)":[95],"from":[99,132,267,288,294],"University":[101],"Pittsburg":[103],"Medical":[104],"Center":[105],"(UPMC),":[106],"trained/tested":[108],"taggers":[110,254],"with":[111,193],"intra-":[112],"inter-institution":[114],"settings.":[115],"cTAKES":[117,190],"was":[120,167,181,199],"also":[121,308],"included":[122],"comparison":[125],"represent":[127],"partially":[130],"trained":[131],"third":[137],"institution,":[138],"Mayo":[139,194],"Clinic":[140],"Rochester.":[142],"Intra-institution":[143],"5-fold":[144],"cross-validation":[145],"estimated":[146],"an":[147],"accuracy":[148,166,180,198,219,237,276],"0.953":[150],"0.945":[152],"KPSC":[155,163,186,202,214,222,229],"UPMC":[157,172,177,207,211,232,240],"respectively.":[159],"Trained":[160,174],"purely":[161,175],"notes,":[164,178,196],"0.897":[168],"when":[169,183,258],"tested":[170,184,221,239],"notes.":[173,187,208],"0.904":[182],"Applying":[188],"Clinic's":[195],"0.881":[200],"0.883":[205],"After":[209,227],"adding":[210,228],"annotations":[212,230,266,291],"data,":[216,234],"average":[218,236],"increased":[224,242,274],"0.965.":[226],"0.953.":[244],"results":[246],"indicated:":[247],"first,":[248],"dropped":[255],"about":[256,278],"5%":[257],"applied":[259],"directly":[260],"institutions;":[263],"second,":[264],"mixing":[265],"another":[268],"institution":[269],"following":[270],"same":[272],"guideline":[273],"1%.":[279],"Our":[280],"findings":[281],"suggest":[282],"that":[283],"can":[285],"benefit":[286],"more":[287],"sharing":[289,295,315],"but":[292],"less":[293],"models":[297],"task.":[302],"believe":[304],"study":[306],"could":[307],"provide":[309],"general":[310],"insights":[311],"cross-institution":[313],"other":[317],"types":[318],"tasks.":[321]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}