{"id":"https://openalex.org/W2937081623","doi":"https://doi.org/10.1093/jamia/ocz028","title":"A new approach and gold standard toward author disambiguation in MEDLINE","display_name":"A new approach and gold standard toward author disambiguation in MEDLINE","publication_year":2019,"publication_date":"2019-02-27","ids":{"openalex":"https://openalex.org/W2937081623","doi":"https://doi.org/10.1093/jamia/ocz028","mag":"2937081623","pmid":"https://pubmed.ncbi.nlm.nih.gov/30958542"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocz028","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocz028","pdf_url":null,"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":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7647200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022872913","display_name":"Dina Vishnyakova","orcid":"https://orcid.org/0000-0001-9101-5993"},"institutions":[{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Dina Vishnyakova","raw_affiliation_strings":["Roche Pharmaceutical Research and Early Development, pRED Informatics, Roche Innovation Center, Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roche Pharmaceutical Research and Early Development, pRED Informatics, Roche Innovation Center, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002036038","display_name":"Raul Rodriguez\u2010Esteban","orcid":"https://orcid.org/0000-0002-9494-9609"},"institutions":[{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Raul Rodriguez-Esteban","raw_affiliation_strings":["Roche Pharmaceutical Research and Early Development, pRED Informatics, Roche Innovation Center, Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roche Pharmaceutical Research and Early Development, pRED Informatics, Roche Innovation Center, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025307528","display_name":"Fabio Rinaldi","orcid":"https://orcid.org/0000-0001-5718-5462"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabio Rinaldi","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence Research (IDSIA), Manno, Switzerland","Institute of Computational Linguistics, University of Zurich, Switzerland","Swiss Institute of Bioinformatics, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence Research (IDSIA), Manno, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Institute of Computational Linguistics, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Swiss Institute of Bioinformatics, Zurich, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022872913"],"corresponding_institution_ids":["https://openalex.org/I118019719"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":0.8344,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.70815163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"10","first_page":"1037","last_page":"1045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6187999844551086,"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":0.6187999844551086,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.0754999965429306,"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/T14330","display_name":"Library Science and Information Systems","score":0.049300000071525574,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/crowdsourcing","display_name":"Crowdsourcing","score":0.7921792268753052},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7738965749740601},{"id":"https://openalex.org/keywords/gold-standard","display_name":"Gold standard (test)","score":0.705489456653595},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.6599541306495667},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5926516056060791},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5488881468772888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5470163226127625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4731998145580292},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4371252954006195},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1961936354637146},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.12441554665565491}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7921792268753052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738965749740601},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.705489456653595},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.6599541306495667},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5926516056060791},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5488881468772888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5470163226127625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4731998145580292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4371252954006195},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1961936354637146},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.12441554665565491},{"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/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","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":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001319","descriptor_name":"Authorship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001319","descriptor_name":"Authorship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001319","descriptor_name":"Authorship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012015","descriptor_name":"Reference Standards","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012015","descriptor_name":"Reference Standards","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012015","descriptor_name":"Reference Standards","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D063045","descriptor_name":"Crowdsourcing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063045","descriptor_name":"Crowdsourcing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063045","descriptor_name":"Crowdsourcing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/jamia/ocz028","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocz028","pdf_url":null,"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:30958542","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30958542","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:7647200","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7647200","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"},{"id":"pmh:oai:www.zora.uzh.ch:178828","is_oa":false,"landing_page_url":"https://www.zora.uzh.ch/178828","pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Vishnyakova, Dina; Rodriguez-Esteban, Raul; Rinaldi, Fabio (2019). A new approach and gold standard toward author disambiguation in MEDLINE. Journal of the American Medical Informatics Association (JAMIA), 26(10):1037-1045.","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7647200","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7647200","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1539674124","https://openalex.org/W1547987453","https://openalex.org/W1599596048","https://openalex.org/W1964879903","https://openalex.org/W1990976049","https://openalex.org/W2000910146","https://openalex.org/W2026154911","https://openalex.org/W2043014255","https://openalex.org/W2103403573","https://openalex.org/W2133012565","https://openalex.org/W2139531859","https://openalex.org/W2145893390","https://openalex.org/W2156897283","https://openalex.org/W2162337786","https://openalex.org/W2163303745","https://openalex.org/W2196350189","https://openalex.org/W2429565568","https://openalex.org/W2442855540","https://openalex.org/W2468923916","https://openalex.org/W2594541096","https://openalex.org/W2900221602","https://openalex.org/W3082085916","https://openalex.org/W4242819516","https://openalex.org/W4246519874","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114"],"abstract_inverted_index":{"OBJECTIVE:":[0],"Author-centric":[1],"analyses":[2],"of":[3,64,156,174,183,190,214,217,226],"fast-growing":[4],"biomedical":[5],"reference":[6,38,56,243],"databases":[7,244],"are":[8,256],"challenging":[9],"due":[10],"to":[11,47,105,115,152,170,194,241],"author":[12,21,68,123,198,218],"ambiguity.":[13],"This":[14],"problem":[15],"has":[16],"been":[17,130],"mainly":[18],"addressed":[19],"through":[20],"disambiguation":[22,124,199,219],"using":[23],"supervised":[24],"machine-learning":[25,163],"algorithms.":[26,200],"Such":[27],"algorithms,":[28],"however,":[29],"require":[30],"adequately":[31],"designed":[32],"gold":[33,52,135,141,192,206,248],"standards":[34,193],"that":[35,119,126,148,165],"reflect":[36],"the":[37,49,61,65,94,171,180,184,188,215,224,259],"database":[39,57],"properly.":[40],"In":[41],"this":[42,254],"study":[43,255],"we":[44],"used":[45,114,252],"MEDLINE":[46,84,153],"build":[48],"first":[50],"unbiased":[51,205],"standard":[53,142,207,249],"in":[54,67,154,223],"a":[55,74,107,140,210],"and":[58,90,159,186,221,234,250],"improve":[59,121],"over":[60,179],"existing":[62,134],"state":[63,182],"art":[66,185],"disambiguation.":[69],"MATERIALS":[70],"AND":[71,202],"METHODS:":[72],"Following":[73],"new":[75,117,167,227],"corpus":[76,111],"design":[77],"method,":[78],"publication":[79,146],"pairs":[80,147],"randomly":[81],"picked":[82],"from":[83],"were":[85,103],"evaluated":[86],"by":[87],"both":[88],"crowdsourcing":[89],"expert":[91,101],"curators.":[92],"Because":[93],"latter":[95],"showed":[96,176],"higher":[97],"accuracy":[98],"than":[99],"crowdsourcing,":[100],"curators":[102],"tasked":[104],"create":[106],"full":[108],"corpus.":[109],"The":[110,232,247],"was":[112],"then":[113],"explore":[116],"features":[118,168,228],"could":[120],"state-of-the-art":[122],"algorithms":[125],"would":[127],"not":[128],"have":[129],"discoverable":[131],"with":[132],"previously":[133],"standards.":[136],"RESULTS:":[137],"We":[138],"created":[139],"based":[143],"on":[144],"1900":[145],"shows":[149],"close":[150],"similarity":[151],"terms":[155],"chronological":[157],"distribution":[158],"information":[160],"completeness.":[161],"A":[162],"algorithm":[164],"includes":[166],"related":[169],"ethnic":[172],"origin":[173],"authors":[175],"significant":[177],"improvements":[178],"current":[181],"demonstrates":[187],"necessity":[189],"realistic":[191],"further":[195],"develop":[196],"effective":[197],"DISCUSSION":[201],"CONCLUSION:":[203],"An":[204],"can":[208,238],"give":[209],"more":[211],"accurate":[212],"picture":[213],"status":[216],"research":[220],"help":[222],"discovery":[225],"for":[229,253],"machine":[230],"learning.":[231],"principles":[233],"methods":[235],"shown":[236],"here":[237],"be":[239],"applied":[240],"other":[242],"beyond":[245],"MEDLINE.":[246],"code":[251],"available":[257],"at":[258],"following":[260],"repository:":[261],"https://github.com/amorgani/AND/.":[262]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}