{"id":"https://openalex.org/W4220989182","doi":"https://doi.org/10.1093/jamia/ocac040","title":"CancerBERT: a cancer domain-specific language model for extracting breast cancer phenotypes from electronic health records","display_name":"CancerBERT: a cancer domain-specific language model for extracting breast cancer phenotypes from electronic health records","publication_year":2022,"publication_date":"2022-03-09","ids":{"openalex":"https://openalex.org/W4220989182","doi":"https://doi.org/10.1093/jamia/ocac040","pmid":"https://pubmed.ncbi.nlm.nih.gov/35333345"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocac040","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocac040","pdf_url":"https://academic.oup.com/jamia/article-pdf/29/7/1208/44062229/ocac040.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":"hybrid","oa_url":"https://academic.oup.com/jamia/article-pdf/29/7/1208/44062229/ocac040.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011070394","display_name":"Sicheng Zhou","orcid":"https://orcid.org/0000-0002-9846-1475"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sicheng Zhou","raw_affiliation_strings":["Institute for Health Informatics, University of Minnesota , Minneapolis, Minnesota, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Health Informatics, University of Minnesota , Minneapolis, Minnesota, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332767","display_name":"Nan Wang","orcid":"https://orcid.org/0000-0002-7869-3797"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Wang","raw_affiliation_strings":["School of Statistics, University of Minnesota , Minneapolis, Minnesota, USA"],"affiliations":[{"raw_affiliation_string":"School of Statistics, University of Minnesota , Minneapolis, Minnesota, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406711","display_name":"Liwei Wang","orcid":"https://orcid.org/0000-0001-9970-8604"},"institutions":[{"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":false,"raw_author_name":"Liwei Wang","raw_affiliation_strings":["Department of AI and Informatics Research, Mayo Clinic , Rochester, Minnesota, USA"],"affiliations":[{"raw_affiliation_string":"Department of AI and Informatics Research, Mayo Clinic , Rochester, Minnesota, USA","institution_ids":["https://openalex.org/I4210146710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585391","display_name":"Hongfang Liu","orcid":"https://orcid.org/0000-0003-2570-3741"},"institutions":[{"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":false,"raw_author_name":"Hongfang Liu","raw_affiliation_strings":["Department of AI and Informatics Research, Mayo Clinic , Rochester, Minnesota, USA"],"affiliations":[{"raw_affiliation_string":"Department of AI and Informatics Research, Mayo Clinic , Rochester, Minnesota, USA","institution_ids":["https://openalex.org/I4210146710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100421963","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0001-8258-3585"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Department of Pharmaceutical Care & Health Systems, University of Minnesota , Minneapolis, Minnesota, USA","Institute for Health Informatics, University of Minnesota , Minneapolis, Minnesota, USA"],"affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Care & Health Systems, University of Minnesota , Minneapolis, Minnesota, USA","institution_ids":["https://openalex.org/I130238516"]},{"raw_affiliation_string":"Institute for Health Informatics, University of Minnesota , Minneapolis, Minnesota, USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100421963"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":{"value":3967,"currency":"USD","value_usd":3967},"fwci":9.2711,"has_fulltext":false,"cited_by_count":113,"citation_normalized_percentile":{"value":0.98867918,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"29","issue":"7","first_page":"1208","last_page":"1216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9976999759674072,"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":0.9884999990463257,"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/breast-cancer","display_name":"Breast cancer","score":0.6679424047470093},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6566543579101562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5969827771186829},{"id":"https://openalex.org/keywords/cancer","display_name":"Cancer","score":0.5949957966804504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5664354562759399},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5154641270637512},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4883217513561249},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.4043799638748169},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38064563274383545},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.14853525161743164}],"concepts":[{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.6679424047470093},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6566543579101562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5969827771186829},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.5949957966804504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5664354562759399},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5154641270637512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4883217513561249},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.4043799638748169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38064563274383545},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.14853525161743164},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D001943","descriptor_name":"Breast Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001943","descriptor_name":"Breast Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001943","descriptor_name":"Breast Neoplasms","qualifier_ui":null,"qualifier_name":null,"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":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","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":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","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},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/jamia/ocac040","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocac040","pdf_url":"https://academic.oup.com/jamia/article-pdf/29/7/1208/44062229/ocac040.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:35333345","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35333345","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:9196678","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9196678","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/jamia/ocac040","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocac040","pdf_url":"https://academic.oup.com/jamia/article-pdf/29/7/1208/44062229/ocac040.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/G2635792716","display_name":null,"funder_award_id":"R01AT009457","funder_id":"https://openalex.org/F4320337593","funder_display_name":"National Center for Complementary and Integrative Health"},{"id":"https://openalex.org/G4427315957","display_name":null,"funder_award_id":"UL1TR002494","funder_id":"https://openalex.org/F4320337472","funder_display_name":"National Center for Advancing Translational Sciences"}],"funders":[{"id":"https://openalex.org/F4320334246","display_name":"Clinical and Translational Science Institute, University of Minnesota","ror":null},{"id":"https://openalex.org/F4320337472","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54"},{"id":"https://openalex.org/F4320337593","display_name":"National Center for Complementary and Integrative Health","ror":"https://ror.org/00190t495"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220989182.pdf","grobid_xml":"https://content.openalex.org/works/W4220989182.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W964049080","https://openalex.org/W2154048976","https://openalex.org/W2187089797","https://openalex.org/W2289095709","https://openalex.org/W2418680801","https://openalex.org/W2611254939","https://openalex.org/W2625448454","https://openalex.org/W2762481118","https://openalex.org/W2765488845","https://openalex.org/W2766919434","https://openalex.org/W2797227230","https://openalex.org/W2911489562","https://openalex.org/W2947903144","https://openalex.org/W2949479579","https://openalex.org/W2978511610","https://openalex.org/W2992706359","https://openalex.org/W3085947683","https://openalex.org/W3095092693","https://openalex.org/W3135084718","https://openalex.org/W3169284847","https://openalex.org/W4294170691","https://openalex.org/W6682691769","https://openalex.org/W6716556110","https://openalex.org/W6750111261"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738"],"abstract_inverted_index":{"The":[0,16,37],"CancerBERT":[1,38],"models":[2,32,39],"were":[3],"developed":[4,40],"to":[5],"extract":[6],"the":[7,26,42],"cancer":[8],"phenotypes":[9],"in":[10,33,41],"clinical":[11,34,47],"notes":[12],"and":[13],"pathology":[14],"reports.":[15],"results":[17],"validated":[18],"that":[19],"using":[20],"customized":[21],"vocabulary":[22],"may":[23],"further":[24,45],"improve":[25],"performances":[27],"of":[28],"domain":[29],"specific":[30],"BERT":[31],"NLP":[35],"tasks.":[36],"study":[43],"would":[44],"help":[46],"decision":[48],"support.":[49]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":5}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}
