{"id":"https://openalex.org/W2135417100","doi":"https://doi.org/10.1136/jamia.1998.0050062","title":"An Experiment Comparing Lexical and Statistical Methods for Extracting MeSH Terms from Clinical Free Text","display_name":"An Experiment Comparing Lexical and Statistical Methods for Extracting MeSH Terms from Clinical Free Text","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W2135417100","doi":"https://doi.org/10.1136/jamia.1998.0050062","mag":"2135417100","pmid":"https://pubmed.ncbi.nlm.nih.gov/9452986"},"language":"en","primary_location":{"id":"doi:10.1136/jamia.1998.0050062","is_oa":true,"landing_page_url":"https://doi.org/10.1136/jamia.1998.0050062","pdf_url":"https://academic.oup.com/jamia/article-pdf/5/1/62/2315318/5-1-62.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/jamia/article-pdf/5/1/62/2315318/5-1-62.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039985406","display_name":"Gregory F. Cooper","orcid":"https://orcid.org/0000-0002-9276-773X"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]},{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I4210134769","display_name":"University of Pittsburgh Medical Center","ror":"https://ror.org/04ehecz88","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210098814","https://openalex.org/I4210134769"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"G. F. Cooper","raw_affiliation_strings":["Center for Biomedical Informatics, University of Pittsburgh, PA 15213-2582, USA. gfc@cbmi.upmc.edu","Division of Biomedical Informatics, Vanderbilt University, Nashville, TN (RAM)","Affiliations of the authors: Center for Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA (GFC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biomedical Informatics, University of Pittsburgh, PA 15213-2582, USA. gfc@cbmi.upmc.edu","institution_ids":["https://openalex.org/I4210134769"]},{"raw_affiliation_string":"Division of Biomedical Informatics, Vanderbilt University, Nashville, TN (RAM)","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Affiliations of the authors: Center for Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA (GFC)","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110236849","display_name":"Rosemary Anne O'Connor Miller","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]},{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. A. Miller","raw_affiliation_strings":["Affiliations of the authors: Center for Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA (GFC); Division of Biomedical Informatics, Vanderbilt University, Nashville, TN (RAM)","Division of Biomedical Informatics, Vanderbilt University, Nashville, TN (RAM)","Affiliations of the authors: Center for Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA (GFC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Affiliations of the authors: Center for Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA (GFC); Division of Biomedical Informatics, Vanderbilt University, Nashville, TN (RAM)","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Division of Biomedical Informatics, Vanderbilt University, Nashville, TN (RAM)","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Affiliations of the authors: Center for Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA (GFC)","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039985406"],"corresponding_institution_ids":["https://openalex.org/I170201317","https://openalex.org/I200719446","https://openalex.org/I4210134769"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":1.629,"has_fulltext":true,"cited_by_count":66,"citation_normalized_percentile":{"value":0.84242794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":"1","first_page":"62","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4758000075817108,"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":0.4758000075817108,"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/T13629","display_name":"Text Readability and Simplification","score":0.07989999651908875,"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/T11894","display_name":"Radiology practices and education","score":0.06360000371932983,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7392721176147461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6953980326652527},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6667343378067017},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.6581454277038574},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.5887041687965393},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5747267007827759},{"id":"https://openalex.org/keywords/text-messaging","display_name":"Text messaging","score":0.5593074560165405},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3907979726791382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33570465445518494},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2178301215171814}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7392721176147461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6953980326652527},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6667343378067017},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.6581454277038574},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.5887041687965393},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5747267007827759},{"id":"https://openalex.org/C3018949938","wikidata":"https://www.wikidata.org/wiki/Q17166101","display_name":"Text messaging","level":2,"score":0.5593074560165405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3907979726791382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33570465445518494},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2178301215171814},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013358","descriptor_name":"Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013358","descriptor_name":"Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013358","descriptor_name":"Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1136/jamia.1998.0050062","is_oa":true,"landing_page_url":"https://doi.org/10.1136/jamia.1998.0050062","pdf_url":"https://academic.oup.com/jamia/article-pdf/5/1/62/2315318/5-1-62.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:9452986","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9452986","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 the American Medical Informatics Association : JAMIA","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:61276","is_oa":true,"landing_page_url":null,"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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:61276","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/61276","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1136/jamia.1998.0050062","is_oa":true,"landing_page_url":"https://doi.org/10.1136/jamia.1998.0050062","pdf_url":"https://academic.oup.com/jamia/article-pdf/5/1/62/2315318/5-1-62.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2319392842","display_name":null,"funder_award_id":"N01-LM-3535","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2135417100.pdf","grobid_xml":"https://content.openalex.org/works/W2135417100.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W3680649","https://openalex.org/W41806421","https://openalex.org/W296703532","https://openalex.org/W335689588","https://openalex.org/W1421211852","https://openalex.org/W1464162502","https://openalex.org/W1504212872","https://openalex.org/W1552325775","https://openalex.org/W1616107618","https://openalex.org/W1829379010","https://openalex.org/W1964261881","https://openalex.org/W1992927493","https://openalex.org/W2027528363","https://openalex.org/W2033266951","https://openalex.org/W2154104658","https://openalex.org/W2162311237","https://openalex.org/W2200682232","https://openalex.org/W2206983297","https://openalex.org/W2281651263","https://openalex.org/W4254165724"],"related_works":["https://openalex.org/W79619734","https://openalex.org/W2010487328","https://openalex.org/W2395081922","https://openalex.org/W2409065517","https://openalex.org/W206173097","https://openalex.org/W1532303244","https://openalex.org/W1557940864","https://openalex.org/W1983449792","https://openalex.org/W1568906437","https://openalex.org/W345154246"],"abstract_inverted_index":{"OBJECTIVE:":[0],"A":[1,254],"primary":[2],"goal":[3],"of":[4,7,44,52,62,103,119,127,182,195,219,230,239,249,260,274,297,304,310],"the":[5,45,77,82,100,111,125,161,179,199,212,231,250,261,295,302,308,316],"University":[6],"Pittsburgh's":[8],"1990-94":[9],"UMLS-sponsored":[10],"effort":[11],"was":[12,177,205],"to":[13,66,94,115,145,190,293,314,319],"develop":[14],"and":[15,22,29,58,84,130,153,245,264,276],"evaluate":[16],"PostDoc":[17,215,275],"(a":[18,24],"lexical":[19],"indexing":[20,26],"system)":[21,27],"Pindex":[23,235,277],"statistical":[25],"comparatively,":[28],"then":[30],"in":[31,68,76,109,160,169,202,280],"combination":[32],"as":[33,40,96,185],"a":[34,42,49,53,60,70,97,131,171,192,217,237],"hybrid":[35,132,255],"system.":[36],"Each":[37,175],"system":[38,176,256],"takes":[39],"input":[41],"portion":[43],"free":[46,180,286],"text":[47,135,181],"from":[48,137,284],"narrative":[50],"part":[51],"patient's":[54],"electronic":[55,112],"medical":[56,113],"record":[57,114,184],"returns":[59],"list":[61,194,318],"suggested":[63],"MeSH":[64,196,222,282,324],"terms":[65,197,223,242,268,283,298,305],"use":[67,309],"formulating":[69],"Medline":[71,173],"search":[72],"that":[73,105,164],"includes":[74],"concepts":[75,159,201,263],"text.":[78,287],"This":[79],"paper":[80],"describes":[81],"systems":[83,104],"reports":[85],"an":[86,186],"evaluation.":[87],"The":[88,122,188,272,288],"intent":[89],"is":[90],"for":[91],"this":[92],"evaluation":[93],"serve":[95],"step":[98],"toward":[99],"eventual":[101],"realization":[102],"assist":[106],"healthcare":[107],"personnel":[108],"using":[110,134],"construct":[116],"patient-specific":[117,172],"searches":[118],"Medline.":[120],"DESIGN:":[121],"authors":[123],"tested":[124],"performances":[126],"PostDoc,":[128],"Pindex,":[129],"system,":[133],"taken":[136],"randomly":[138],"selected":[139],"clinical":[140,162,285],"records,":[141],"which":[142,191,226],"were":[143],"stratified":[144],"include":[146],"six":[147,150,154],"radiology":[148],"reports,":[149,152],"pathology":[151],"discharge":[155],"summaries.":[156],"They":[157],"identified":[158],"records":[163],"might":[165],"conceivably":[166],"be":[167],"used":[168],"performing":[170],"search.":[174],"given":[178],"each":[183],"input.":[187],"extent":[189],"system-derived":[193],"captured":[198,246,257],"relevant":[200,232,251,262,323],"these":[203],"documents":[204],"determined":[206],"based":[207],"on":[208],"blinded":[209],"assessments":[210],"by":[211],"authors.":[213],"RESULTS:":[214],"output":[216,236,265,299,317],"mean":[218,238],"approximately":[220,240,258],"19":[221],"per":[224,243,269],"report,":[225],"included":[227],"about":[228,247,266],"40%":[229],"report":[233,244,252],"concepts.":[234,253],"57":[241],"45%":[248],"66%":[259],"71":[267],"report.":[270],"CONCLUSION:":[271],"outputs":[273],"are":[278],"complementary":[279],"capturing":[281],"results":[289],"suggest":[290],"possible":[291],"approaches":[292],"reduce":[294],"number":[296],"while":[300],"maintaining":[301],"percentage":[303],"captured,":[306],"including":[307],"UMLS":[311],"semantic":[312],"types":[313],"constrain":[315],"contain":[320],"only":[321],"clinically":[322],"terms.":[325]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
