{"id":"https://openalex.org/W2104254426","doi":"https://doi.org/10.1186/2041-1480-4-3","title":"Pooling annotated corpora for clinical concept extraction","display_name":"Pooling annotated corpora for clinical concept extraction","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2104254426","doi":"https://doi.org/10.1186/2041-1480-4-3","mag":"2104254426","pmid":"https://pubmed.ncbi.nlm.nih.gov/23294871"},"language":"en","primary_location":{"id":"doi:10.1186/2041-1480-4-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-4-3","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-4-3","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-4-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041082275","display_name":"Kavishwar B. Wagholikar","orcid":"https://orcid.org/0000-0002-6219-861X"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]},{"id":"https://openalex.org/I4210125099","display_name":"Mayo Clinic in Arizona","ror":"https://ror.org/03jp40720","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"]},{"id":"https://openalex.org/I4210146710","display_name":"Mayo Clinic in Florida","ror":"https://ror.org/03zzw1w08","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210146710"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kavishwar B Wagholikar","raw_affiliation_strings":["Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, MN, USA. wagholikar.kavishwar@mayo.edu","Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, MN, USA. wagholikar.kavishwar@mayo.edu","institution_ids":["https://openalex.org/I1330342723","https://openalex.org/I4210125099","https://openalex.org/I4210146710"]},{"raw_affiliation_string":"Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, USA","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028161578","display_name":"Manabu Torii","orcid":"https://orcid.org/0000-0002-4825-0696"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manabu Torii","raw_affiliation_strings":["Department of Radiology, Georgetown University Medical Center, Washington, DC, USA","Dept. of Radiology, Georgetown University Medical Center, Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology, Georgetown University Medical Center, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670","https://openalex.org/I2799903593"]},{"raw_affiliation_string":"Dept. of Radiology, Georgetown University Medical Center, Washington, USA","institution_ids":["https://openalex.org/I184565670","https://openalex.org/I2799903593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056672185","display_name":"Siddhartha Jonnalagadda","orcid":"https://orcid.org/0000-0003-3299-6052"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha R Jonnalagadda","raw_affiliation_strings":["Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, MN, USA","Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, MN, USA","institution_ids":["https://openalex.org/I1330342723"]},{"raw_affiliation_string":"Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, USA","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051769953","display_name":"Hongfang Liu","orcid":"https://orcid.org/0000-0003-2529-7341"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongfang Liu","raw_affiliation_strings":["Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, MN, USA","Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, MN, USA","institution_ids":["https://openalex.org/I1330342723"]},{"raw_affiliation_string":"Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, USA","institution_ids":["https://openalex.org/I1330342723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041082275"],"corresponding_institution_ids":["https://openalex.org/I1330342723","https://openalex.org/I4210125099","https://openalex.org/I4210146710"],"apc_list":{"value":1340,"currency":"USD","value_usd":1340},"apc_paid":{"value":1340,"currency":"USD","value_usd":1340},"fwci":1.6508,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.83620994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4","issue":"1","first_page":"3","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6776999831199646,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6776999831199646,"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":0.08309999853372574,"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":0.02879999950528145,"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":0.8572515249252319},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.797114372253418},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4929232597351074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47882774472236633},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4743548631668091},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45763635635375977},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32464277744293213},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10397407412528992},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08303248882293701}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8572515249252319},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.797114372253418},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4929232597351074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47882774472236633},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4743548631668091},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45763635635375977},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32464277744293213},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10397407412528992},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08303248882293701}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/2041-1480-4-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-4-3","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-4-3","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},{"id":"pmid:23294871","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23294871","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":"Journal of biomedical semantics","raw_type":null},{"id":"pmh:oai:europepmc.org:2601638","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3599895","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/2041-1480-4-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-4-3","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-4-3","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G2858025007","display_name":null,"funder_award_id":"R01 LM009959","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G5387631503","display_name":"CAREER:  Natural Language Processing for Biological Knowledge Management","funder_award_id":"0845523","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7647588643","display_name":null,"funder_award_id":"K99 LM011389","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G7999594839","display_name":null,"funder_award_id":"R01 GM102282","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G8744663245","display_name":null,"funder_award_id":"U54LM008748","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309644","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2104254426.pdf","grobid_xml":"https://content.openalex.org/works/W2104254426.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W16586333","https://openalex.org/W23757268","https://openalex.org/W192665053","https://openalex.org/W1529842856","https://openalex.org/W1552325775","https://openalex.org/W1563275488","https://openalex.org/W1666538313","https://openalex.org/W1977748891","https://openalex.org/W2002514548","https://openalex.org/W2032237293","https://openalex.org/W2061848042","https://openalex.org/W2109206523","https://openalex.org/W2111437636","https://openalex.org/W2114039834","https://openalex.org/W2114388055","https://openalex.org/W2120253533","https://openalex.org/W2122402213","https://openalex.org/W2131887446","https://openalex.org/W2145383760","https://openalex.org/W2146089916","https://openalex.org/W2152228269","https://openalex.org/W2154333659","https://openalex.org/W2159583324","https://openalex.org/W2160987310","https://openalex.org/W2168041406","https://openalex.org/W2416328342","https://openalex.org/W2568020214","https://openalex.org/W2912090181","https://openalex.org/W2912915691","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,80,91,166,198],"availability":[2],"of":[3,10,77,103,107,136,151,160,168,195,200,211,215,220,230,255,277,314],"annotated":[4,83,137,175,256,291],"corpora":[5,38,62,81,138,288],"has":[6],"facilitated":[7],"the":[8,29,57,149,152,161,180,185,193,231,251,263,274,315,321],"application":[9],"machine":[11,49,112],"learning":[12,113],"algorithms":[13],"to":[14,35,72,188,227,240,305],"concept":[15,119,300],"extraction":[16],"from":[17,39,63],"clinical":[18],"notes.":[19],"However,":[20],"high":[21],"expenditure":[22],"and":[23,68,111,118,157,218,222,253,308],"labor":[24],"are":[25,281],"required":[26],"for":[27,47,75,84,114,133],"creating":[28],"annotations.":[30],"A":[31],"potential":[32,275],"alternative":[33],"is":[34,203],"reuse":[36,135,254],"existing":[37,97,306],"other":[40],"institutions":[41],"by":[42,60,303],"pooling":[43,61,145,201,252],"with":[44,88,243,292],"local":[45,153,221],"corpora,":[46,202,257],"training":[48,181],"taggers.":[50],"In":[51],"this":[52,285],"paper":[53],"we":[54,258],"have":[55],"investigated":[56],"latter":[58],"approach":[59],"2010":[64],"i2b2/VA":[65],"NLP":[66,264],"challenge":[67],"Mayo":[69],"Clinic":[70],"Rochester,":[71],"evaluate":[73],"taggers":[74,92],"recognition":[76],"medical":[78,85],"problems.":[79],"were":[82,93,164,177],"problems,":[86],"but":[87],"different":[89,247],"guidelines.":[90],"constructed":[94],"using":[95],"an":[96],"tagging":[98,110],"system":[99],"MedTagger":[100],"that":[101,123,144,191,260,272,280,296],"consisted":[102],"dictionary":[104],"lookup,":[105],"part":[106],"speech":[108],"(POS)":[109],"named":[115],"entity":[116],"prediction":[117],"extraction.":[120],"We":[121,142,183],"hope":[122],"our":[124],"current":[125],"work":[126],"will":[127],"be":[128,241,290,318],"a":[129,268,293],"useful":[130],"case":[131],"study":[132],"facilitating":[134],"across":[139],"institutions.":[140],"RESULTS:":[141],"found":[143],"was":[146,155],"effective":[147],"when":[148],"size":[150,219],"corpus":[154],"small":[156],"after":[158],"some":[159,229],"guideline":[162,232,271,278],"differences":[163,233,279],"reconciled.":[165],"benefits":[167],"pooling,":[169],"however,":[170],"diminished":[171],"as":[172,312],"more":[173],"locally":[174],"documents":[176],"included":[178],"in":[179,284],"data.":[182],"examined":[184],"annotation":[186,212,270,322],"guidelines":[187],"identify":[189],"factors":[190],"determine":[192],"effect":[194],"pooling.":[196,236],"CONCLUSIONS:":[197],"effectiveness":[199],"dependent":[204],"on":[205,246,299],"several":[206],"factors,":[207],"which":[208],"include":[209],"compatibility":[210],"guidelines,":[213],"distribution":[214],"report":[216,316],"types":[217],"foreign":[223],"corpora.":[224,248],"Simple":[225],"methods":[226],"rectify":[228],"can":[234],"facilitate":[235,250],"Our":[237],"findings":[238],"need":[239],"confirmed":[242],"further":[244],"studies":[245],"To":[249],"suggest":[259],"-":[261],"i)":[262],"community":[265],"should":[266,289,317],"develop":[267],"standard":[269],"addresses":[273],"areas":[276],"partly":[282],"identified":[283],"paper;":[286],"ii)":[287],"two-pass":[294],"method":[295],"focuses":[297],"first":[298],"recognition,":[301],"followed":[302],"normalization":[304],"ontologies;":[307],"iii)":[309],"metadata":[310],"such":[311],"type":[313],"created":[319],"during":[320],"process.":[323]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}