{"id":"https://openalex.org/W4416053746","doi":"https://doi.org/10.1093/jamia/ocaf193","title":"Automated detection of stigmatizing language in Electronic Health Records (EHRs) using a multi-stage transfer learning approach","display_name":"Automated detection of stigmatizing language in Electronic Health Records (EHRs) using a multi-stage transfer learning approach","publication_year":2025,"publication_date":"2025-11-09","ids":{"openalex":"https://openalex.org/W4416053746","doi":"https://doi.org/10.1093/jamia/ocaf193","pmid":"https://pubmed.ncbi.nlm.nih.gov/41206907"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocaf193","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocaf193","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://pmc.ncbi.nlm.nih.gov/articles/PMC12844570/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100513132","display_name":"Liyang Xue","orcid":"https://orcid.org/0000-0003-2908-9072"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liyang Xue","raw_affiliation_strings":["Department of Library and Information Science, School of Communication & Information, Rutgers University , New Brunswick, NJ, 08901,","Department of Library and Information Science, School of Communication & Information, Rutgers University, New Brunswick, NJ, 08901, United States"],"raw_orcid":"https://orcid.org/0000-0003-2908-9072","affiliations":[{"raw_affiliation_string":"Department of Library and Information Science, School of Communication & Information, Rutgers University , New Brunswick, NJ, 08901,","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Department of Library and Information Science, School of Communication & Information, Rutgers University, New Brunswick, NJ, 08901, United States","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080412519","display_name":"Aminur Rahman","orcid":"https://orcid.org/0000-0003-1434-3883"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A M Muntasir Rahman","raw_affiliation_strings":["Department of Library and Information Science, School of Communication & Information, Rutgers University , New Brunswick, NJ, 08901,","Department of Library and Information Science, School of Communication & Information, Rutgers University, New Brunswick, NJ, 08901, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Library and Information Science, School of Communication & Information, Rutgers University , New Brunswick, NJ, 08901,","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Department of Library and Information Science, School of Communication & Information, Rutgers University, New Brunswick, NJ, 08901, United States","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027893569","display_name":"Charles Senteio","orcid":"https://orcid.org/0000-0002-0254-3127"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles R Senteio","raw_affiliation_strings":["Department of Library and Information Science, School of Communication & Information, Rutgers University , New Brunswick, NJ, 08901,","Department of Library and Information Science, School of Communication & Information, Rutgers University, New Brunswick, NJ, 08901, United States"],"raw_orcid":"https://orcid.org/0000-0002-0254-3127","affiliations":[{"raw_affiliation_string":"Department of Library and Information Science, School of Communication & Information, Rutgers University , New Brunswick, NJ, 08901,","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Department of Library and Information Science, School of Communication & Information, Rutgers University, New Brunswick, NJ, 08901, United States","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011229206","display_name":"Vivek K. Singh","orcid":"https://orcid.org/0000-0002-8194-2336"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek K Singh","raw_affiliation_strings":["Department of Library and Information Science, School of Communication & Information, Rutgers University , New Brunswick, NJ, 08901,","Department of Library and Information Science, School of Communication & Information, Rutgers University, New Brunswick, NJ, 08901, United States"],"raw_orcid":"https://orcid.org/0000-0002-8194-2336","affiliations":[{"raw_affiliation_string":"Department of Library and Information Science, School of Communication & Information, Rutgers University , New Brunswick, NJ, 08901,","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Department of Library and Information Science, School of Communication & Information, Rutgers University, New Brunswick, NJ, 08901, United States","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100513132"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":3.3146,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93342252,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"33","issue":"2","first_page":"283","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.45969998836517334,"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"}},"topics":[{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.45969998836517334,"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/T10028","display_name":"Topic Modeling","score":0.06639999896287918,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.05590000003576279,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/health-records","display_name":"Health records","score":0.5928999781608582},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.536899983882904},{"id":"https://openalex.org/keywords/electronic-health-record","display_name":"Electronic health record","score":0.44359999895095825},{"id":"https://openalex.org/keywords/health-equity","display_name":"Health equity","score":0.39340001344680786},{"id":"https://openalex.org/keywords/equity","display_name":"Equity (law)","score":0.3806000053882599},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.35010001063346863},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.3314000070095062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6269999742507935},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.5928999781608582},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.536899983882904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5356000065803528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5317000150680542},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.44359999895095825},{"id":"https://openalex.org/C2250968","wikidata":"https://www.wikidata.org/wiki/Q1512929","display_name":"Health equity","level":3,"score":0.39340001344680786},{"id":"https://openalex.org/C199728807","wikidata":"https://www.wikidata.org/wiki/Q2578557","display_name":"Equity (law)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2982795734","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health information","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C168285401","wikidata":"https://www.wikidata.org/wiki/Q1427245","display_name":"Stigma (botany)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3086000084877014},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C3017977704","wikidata":"https://www.wikidata.org/wiki/Q18745135","display_name":"Health data","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.25619998574256897}],"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":"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":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","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":"D057545","descriptor_name":"Social Stigma","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057545","descriptor_name":"Social Stigma","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/jamia/ocaf193","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocaf193","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:41206907","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41206907","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:12844570","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12844570/","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":"pmh:oai:pubmedcentral.nih.gov:12844570","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12844570/","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":34,"referenced_works":["https://openalex.org/W1985892520","https://openalex.org/W2078363695","https://openalex.org/W2114388055","https://openalex.org/W2116191030","https://openalex.org/W2162800060","https://openalex.org/W2789244308","https://openalex.org/W2792485237","https://openalex.org/W2955483668","https://openalex.org/W2963026768","https://openalex.org/W2971258845","https://openalex.org/W2990768863","https://openalex.org/W3034238904","https://openalex.org/W3034255912","https://openalex.org/W3100910918","https://openalex.org/W3126626515","https://openalex.org/W3180412891","https://openalex.org/W3201622928","https://openalex.org/W4205942412","https://openalex.org/W4206020641","https://openalex.org/W4210343882","https://openalex.org/W4281644039","https://openalex.org/W4285391876","https://openalex.org/W4318671461","https://openalex.org/W4319662928","https://openalex.org/W4362716853","https://openalex.org/W4365138453","https://openalex.org/W4366351482","https://openalex.org/W4385570634","https://openalex.org/W4385571720","https://openalex.org/W4390228098","https://openalex.org/W4404447410","https://openalex.org/W4404598813","https://openalex.org/W4404784267","https://openalex.org/W4405807416"],"related_works":[],"abstract_inverted_index":{"OBJECTIVE:":[0],"Stigmatizing":[1],"language":[2,27,64,183,197,233],"(SL)":[3],"in":[4,198,234,242],"Electronic":[5],"Health":[6],"Records":[7],"(EHRs)":[8],"can":[9],"perpetuate":[10],"biases":[11,208],"and":[12,46,56,81,85,90,132,142,217,239],"negatively":[13],"impact":[14],"patient":[15],"care.":[16,244],"This":[17,186,222],"study":[18,187],"introduces":[19],"a":[20,38,225],"novel":[21],"method":[22],"for":[23,79,124,194,230],"automatically":[24],"detecting":[25,195,231],"such":[26],"to":[28,114,122,169],"improve":[29],"healthcare":[30],"documentation":[31],"practices.":[32],"MATERIALS":[33],"AND":[34],"METHODS:":[35],"We":[36],"developed":[37],"multi-stage":[39,201],"transfer":[40,202],"learning":[41,203],"framework":[42,149,176,204,223,229],"integrating":[43],"semantic,":[44],"syntactic,":[45],"task":[47],"adaptation":[48],"using":[49],"three":[50],"datasets:":[51],"hate":[52],"speech,":[53],"clinical":[54,219,243],"phenotypes,":[55],"stigmatizing":[57,63,182,196,232],"language.":[58],"Experiments":[59],"were":[60,88],"conducted":[61],"on":[62,95],"dataset":[65],"which":[66],"consists":[67],"of":[68,99,106,191],"4,129":[69],"de-identified":[70],"EHR":[71],"notes":[72],"(72.7%":[73],"stigmatizing,":[74],"27.3%":[75],"non-stigmatizing),":[76],"split":[77],"80/20":[78],"training":[80],"testing.":[82,127],"Longformer,":[83],"BERT,":[84],"ClinicalBERT":[86],"models":[87,129],"evaluated,":[89],"model":[91],"performance":[92],"was":[93,112],"assessed":[94],"35":[96],"randomized":[97],"subsets":[98],"the":[100,151,189],"test":[101,107,111],"set":[102],"(each":[103],"comprising":[104],"70%":[105],"data).":[108],"The":[109,147,175,200],"Wilcoxon-Mann-Whitney":[110],"used":[113],"evaluate":[115],"statistical":[116],"significance,":[117],"with":[118,154],"Bonferroni":[119,166],"correction":[120,167],"applied":[121],"control":[123],"multiple":[125],"hypothesis":[126],"Baseline":[128],"included":[130],"zero-shot":[131],"few-shot":[133],"GPT-4o,":[134],"Support":[135],"Vector":[136],"Machine,":[137],"Random":[138],"Forest,":[139],"Logistic":[140],"Regression,":[141],"Multinomial":[143],"Naive":[144],"Bayes.":[145],"RESULTS:":[146],"proposed":[148],"achieved":[150],"highest":[152],"accuracy,":[153],"fully":[155],"adapted":[156],"Longformer":[157],"reaching":[158],"89.83%.":[159],"Performance":[160],"improvements":[161],"remained":[162],"statistically":[163,226],"significant":[164],"after":[165],"compared":[168],"all":[170],"baselines":[171],"(p":[172],"<":[173],".05).":[174],"demonstrated":[177],"robust":[178],"gains":[179],"across":[180],"different":[181],"types.":[184],"DISCUSSION:":[185],"underscores":[188],"value":[190],"domain-adaptive":[192],"NLP":[193],"EHRs.":[199],"effectively":[205],"captures":[206],"subtle":[207],"often":[209],"missed":[210],"by":[211],"conventional":[212],"models,":[213],"enabling":[214],"more":[215],"objective":[216],"respectful":[218],"documentation.":[220],"CONCLUSION:":[221],"offers":[224],"validated,":[227],"high-performing":[228],"EHRs,":[235],"supporting":[236],"responsible":[237],"AI":[238],"promoting":[240],"equity":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-11-09T00:00:00"}