{"id":"https://openalex.org/W3126421551","doi":"https://doi.org/10.1177/1460458221989392","title":"Building a specialized lexicon for breast cancer clinical trial subject eligibility analysis","display_name":"Building a specialized lexicon for breast cancer clinical trial subject eligibility analysis","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3126421551","doi":"https://doi.org/10.1177/1460458221989392","mag":"3126421551","pmid":"https://pubmed.ncbi.nlm.nih.gov/33535885"},"language":"en","primary_location":{"id":"doi:10.1177/1460458221989392","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1460458221989392","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1460458221989392","source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/1460458221989392","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102785623","display_name":"Euisung Jung","orcid":"https://orcid.org/0000-0003-1784-7411"},"institutions":[{"id":"https://openalex.org/I90871651","display_name":"University of Toledo","ror":"https://ror.org/01pbdzh19","country_code":"US","type":"education","lineage":["https://openalex.org/I90871651"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Euisung Jung","raw_affiliation_strings":["Information Operations and Technology Management, John B. and Lillian E. Neff College of Business and Innovation, The University of Toledo, USA"],"raw_orcid":"https://orcid.org/0000-0003-1784-7411","affiliations":[{"raw_affiliation_string":"Information Operations and Technology Management, John B. and Lillian E. Neff College of Business and Innovation, The University of Toledo, USA","institution_ids":["https://openalex.org/I90871651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036018570","display_name":"Hemant Jain","orcid":"https://orcid.org/0000-0001-6184-1565"},"institutions":[{"id":"https://openalex.org/I177097968","display_name":"University of Tennessee at Chattanooga","ror":"https://ror.org/00nqb1v70","country_code":"US","type":"education","lineage":["https://openalex.org/I177097968"]},{"id":"https://openalex.org/I90840245","display_name":"Rollins College","ror":"https://ror.org/009vh5d61","country_code":"US","type":"education","lineage":["https://openalex.org/I90840245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hemant Jain","raw_affiliation_strings":["Gary W. Rollins College of Business, The University of Tennessee at Chattanooga, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gary W. Rollins College of Business, The University of Tennessee at Chattanooga, USA","institution_ids":["https://openalex.org/I177097968","https://openalex.org/I90840245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110260079","display_name":"Atish P. Sinha","orcid":null},"institutions":[{"id":"https://openalex.org/I43579087","display_name":"University of Wisconsin\u2013Milwaukee","ror":"https://ror.org/031q21x57","country_code":"US","type":"education","lineage":["https://openalex.org/I43579087"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atish P Sinha","raw_affiliation_strings":["Lubar School of Business, University of Wisconsin-Milwaukee, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lubar School of Business, University of Wisconsin-Milwaukee, USA","institution_ids":["https://openalex.org/I43579087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085657357","display_name":"Carmelo Gaudioso","orcid":null},"institutions":[{"id":"https://openalex.org/I1292894508","display_name":"Roswell Park Comprehensive Cancer Center","ror":"https://ror.org/0499dwk57","country_code":"US","type":"facility","lineage":["https://openalex.org/I1292894508"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carmelo Gaudioso","raw_affiliation_strings":["Roswell Park Cancer Institute, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roswell Park Cancer Institute, USA","institution_ids":["https://openalex.org/I1292894508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102785623"],"corresponding_institution_ids":["https://openalex.org/I90871651"],"apc_list":{"value":1500,"currency":"USD","value_usd":1500},"apc_paid":{"value":1500,"currency":"USD","value_usd":1500},"fwci":0.5699,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.63421351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"27","issue":"1","first_page":"1460458221989392","last_page":"1460458221989392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9876999855041504,"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":0.9613999724388123,"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":0.7811641693115234},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7721062898635864},{"id":"https://openalex.org/keywords/snomed-ct","display_name":"SNOMED CT","score":0.7395457029342651},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.7002866268157959},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.6722642183303833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5957695841789246},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5929246544837952},{"id":"https://openalex.org/keywords/systematized-nomenclature-of-medicine","display_name":"Systematized Nomenclature of Medicine","score":0.47803980112075806},{"id":"https://openalex.org/keywords/health-informatics","display_name":"Health informatics","score":0.4388817250728607},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41753771901130676},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.3805098533630371},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36255013942718506},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.3392711281776428},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11652204394340515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811641693115234},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7721062898635864},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.7395457029342651},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.7002866268157959},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.6722642183303833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5957695841789246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5929246544837952},{"id":"https://openalex.org/C44681071","wikidata":"https://www.wikidata.org/wiki/Q4048820","display_name":"Systematized Nomenclature of Medicine","level":4,"score":0.47803980112075806},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.4388817250728607},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41753771901130676},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.3805098533630371},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36255013942718506},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.3392711281776428},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11652204394340515},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001943","descriptor_name":"Breast Neoplasms","qualifier_ui":"Q000628","qualifier_name":"therapy","is_major_topic":true},{"descriptor_ui":"D001943","descriptor_name":"Breast Neoplasms","qualifier_ui":"Q000628","qualifier_name":"therapy","is_major_topic":true},{"descriptor_ui":"D001943","descriptor_name":"Breast Neoplasms","qualifier_ui":"Q000628","qualifier_name":"therapy","is_major_topic":true},{"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":"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":"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":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1177/1460458221989392","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1460458221989392","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1460458221989392","source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},{"id":"pmid:33535885","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33535885","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":"Health informatics journal","raw_type":null},{"id":"pmh:oai:doaj.org/article:c8bce1228453445d908ad0768d60f3f6","is_oa":true,"landing_page_url":"https://doaj.org/article/c8bce1228453445d908ad0768d60f3f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Health Informatics Journal, Vol 27 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1177/1460458221989392","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1460458221989392","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1460458221989392","source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W181033957","https://openalex.org/W1489071560","https://openalex.org/W1579838312","https://openalex.org/W1750093058","https://openalex.org/W1892638773","https://openalex.org/W1967985363","https://openalex.org/W1973258251","https://openalex.org/W2001849860","https://openalex.org/W2012560661","https://openalex.org/W2018113873","https://openalex.org/W2030093943","https://openalex.org/W2034562044","https://openalex.org/W2045016337","https://openalex.org/W2054558802","https://openalex.org/W2066578320","https://openalex.org/W2074048861","https://openalex.org/W2079145130","https://openalex.org/W2083782205","https://openalex.org/W2095017581","https://openalex.org/W2100281619","https://openalex.org/W2100676408","https://openalex.org/W2112747875","https://openalex.org/W2114361266","https://openalex.org/W2135781475","https://openalex.org/W2139736061","https://openalex.org/W2156726838","https://openalex.org/W2163918411","https://openalex.org/W2307967803","https://openalex.org/W2328582909","https://openalex.org/W2429026656","https://openalex.org/W2606273705","https://openalex.org/W2623902889","https://openalex.org/W2624698084","https://openalex.org/W2783546159","https://openalex.org/W2799964131","https://openalex.org/W2892244346","https://openalex.org/W2946991228","https://openalex.org/W4231842606","https://openalex.org/W4238453152","https://openalex.org/W4239530551","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2011383762","https://openalex.org/W4327499987","https://openalex.org/W2048414027","https://openalex.org/W3173084154","https://openalex.org/W2940857995","https://openalex.org/W2895883758","https://openalex.org/W2940684586","https://openalex.org/W2809276897","https://openalex.org/W2031891814","https://openalex.org/W353876725"],"abstract_inverted_index":{"A":[0],"natural":[1],"language":[2],"processing":[3,13],"(NLP)":[4],"application":[5],"requires":[6],"sophisticated":[7],"lexical":[8],"resources":[9],"to":[10,31,184],"support":[11],"its":[12],"goals.":[14],"Different":[15],"solutions,":[16],"such":[17],"as":[18,205],"dictionary":[19],"lookup":[20],"and":[21,57,73,95,104,137,162],"MetaMap,":[22],"have":[23],"been":[24,50,68],"proposed":[25],"in":[26,52,60,77,99,200],"the":[27,53,61,71,78,100,111,127,138,196],"healthcare":[28,210],"informatics":[29],"literature":[30],"identify":[32],"disease":[33,41],"terms":[34,132],"with":[35,110],"more":[36],"than":[37],"one":[38],"word":[39],"(multi-gram":[40],"named":[42],"entities).":[43],"Although":[44],"a":[45,89,122,172,206],"lot":[46],"of":[47,55,75,114,129,140,147,175],"work":[48],"has":[49,67],"done":[51,69],"identification":[54],"protein-":[56],"gene-named":[58],"entities":[59],"biomedical":[62],"field,":[63],"not":[64],"much":[65],"research":[66],"on":[70,189],"recognition":[72],"resolution":[74],"terminologies":[76],"clinical":[79,144,185,193],"trial":[80,194],"subject":[81],"eligibility":[82,190],"analysis.":[83],"In":[84],"this":[85,201],"study,":[86],"we":[87],"develop":[88],"specialized":[90,197],"lexicon":[91,153,198],"for":[92,181,208],"improving":[93],"NLP":[94],"text":[96,141,211],"mining":[97,139,212],"analysis":[98],"breast":[101],"cancer":[102],"domain,":[103],"evaluate":[105],"it":[106,109],"by":[107,160,166],"comparing":[108],"Systematized":[112],"Nomenclature":[113],"Medicine":[115],"Clinical":[116],"Terms":[117],"(SNOMED":[118],"CT).":[119],"We":[120],"use":[121],"hybrid":[123],"methodology,":[124],"which":[125,155,170],"combines":[126],"knowledge":[128],"domain":[130],"experts,":[131],"from":[133,142],"multiple":[134],"online":[135],"dictionaries,":[136],"sample":[143],"trials.":[145],"Use":[146],"our":[148],"methodology":[149],"introduces":[150],"4243":[151],"unique":[152],"items,":[154],"increase":[156],"bigram":[157],"entity":[158,164],"match":[159,165],"38.6%":[161],"trigram":[163],"41%.":[167],"Our":[168],"lexicon,":[169],"adds":[171],"significant":[173],"number":[174],"new":[176],"terms,":[177],"is":[178],"very":[179],"useful":[180],"matching":[182],"patients":[183],"trials":[186],"automatically":[187],"based":[188],"matching.":[191],"Beyond":[192],"matching,":[195],"developed":[199],"study":[202],"could":[203],"serve":[204],"foundation":[207],"future":[209],"applications.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
