{"id":"https://openalex.org/W3191709143","doi":"https://doi.org/10.1093/jamia/ocab128","title":"Improving domain adaptation in de-identification of electronic health records through self-training","display_name":"Improving domain adaptation in de-identification of electronic health records through self-training","publication_year":2021,"publication_date":"2021-06-05","ids":{"openalex":"https://openalex.org/W3191709143","doi":"https://doi.org/10.1093/jamia/ocab128","mag":"3191709143","pmid":"https://pubmed.ncbi.nlm.nih.gov/34363664"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocab128","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocab128","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/8449604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052326736","display_name":"S. Matthew Liao","orcid":"https://orcid.org/0000-0001-6579-8656"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Shun Liao","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Ontario, Canada","Donnelly Centre for Cellular and Biomoleular Research, University of Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Donnelly Centre for Cellular and Biomoleular Research, University of Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065231880","display_name":"Jamie Kiros","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148186","display_name":"Google (Canada)","ror":"https://ror.org/04d06q394","country_code":"CA","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969","https://openalex.org/I4210148186"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jamie Kiros","raw_affiliation_strings":["Google, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4210148186"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiyang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148186","display_name":"Google (Canada)","ror":"https://ror.org/04d06q394","country_code":"CA","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969","https://openalex.org/I4210148186"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiyang Chen","raw_affiliation_strings":["Google, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4210148186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009847434","display_name":"Zhaolei Zhang","orcid":"https://orcid.org/0000-0002-7303-6472"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhaolei Zhang","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Ontario, Canada","Donnelly Centre for Cellular and Biomoleular Research, University of Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Donnelly Centre for Cellular and Biomoleular Research, University of Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443189","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0002-3228-9166"},"institutions":[{"id":"https://openalex.org/I4210148186","display_name":"Google (Canada)","ror":"https://ror.org/04d06q394","country_code":"CA","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969","https://openalex.org/I4210148186"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ting Chen","raw_affiliation_strings":["Google, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4210148186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052326736"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":0.8189,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77895078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"28","issue":"10","first_page":"2093","last_page":"2100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.8270999789237976,"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":0.8270999789237976,"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":0.0364999994635582,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.025299999862909317,"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":0.7836648225784302},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6915004253387451},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6570731401443481},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6561074256896973},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6272910237312317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6099732518196106},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5807955861091614},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5482679605484009},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5036510825157166},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4103360176086426},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3611486554145813},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.297954261302948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7836648225784302},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6915004253387451},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6570731401443481},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6561074256896973},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6272910237312317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6099732518196106},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5807955861091614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5482679605484009},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5036510825157166},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4103360176086426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3611486554145813},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.297954261302948},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","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":"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":"D010351","descriptor_name":"Patient Discharge","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010351","descriptor_name":"Patient Discharge","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010351","descriptor_name":"Patient Discharge","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010351","descriptor_name":"Patient Discharge","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},{"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/ocab128","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocab128","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:34363664","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34363664","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:8449604","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8449604","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:8449604","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8449604","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":30,"referenced_works":["https://openalex.org/W1995228216","https://openalex.org/W2015620729","https://openalex.org/W2095705004","https://openalex.org/W2104608657","https://openalex.org/W2160987310","https://openalex.org/W2164695063","https://openalex.org/W2176950688","https://openalex.org/W2186058360","https://openalex.org/W2396881363","https://openalex.org/W2621075239","https://openalex.org/W2622474949","https://openalex.org/W2784499877","https://openalex.org/W2786839164","https://openalex.org/W2787267295","https://openalex.org/W2804649465","https://openalex.org/W2807800730","https://openalex.org/W2896457183","https://openalex.org/W2963341956","https://openalex.org/W2963956191","https://openalex.org/W2979509742","https://openalex.org/W3004506153","https://openalex.org/W3010607409","https://openalex.org/W3027647720","https://openalex.org/W3098949126","https://openalex.org/W6674330103","https://openalex.org/W6686740290","https://openalex.org/W6748200349","https://openalex.org/W6748219368","https://openalex.org/W6755207826","https://openalex.org/W6777997616"],"related_works":["https://openalex.org/W4394775207","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W3203792196","https://openalex.org/W2955455867","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"OBJECTIVE:":[0],"De-identification":[1],"is":[2,37,39,48],"a":[3,54,100,131],"fundamental":[4],"task":[5,238],"in":[6],"electronic":[7,240],"health":[8,13,241],"records":[9],"to":[10,21,25,60,82,103,206,229],"remove":[11],"protected":[12],"information":[14],"entities.":[15],"Deep":[16],"learning":[17,156],"models":[18],"have":[19],"proven":[20],"be":[22],"promising":[23],"tools":[24],"automate":[26],"de-identification":[27,124,237],"processes.":[28],"However,":[29],"when":[30,180],"the":[31,35,42,46,50,72,84,92,105,114,119,138,145,150,160,164,174,190,196,198,202,213,231,236],"target":[32,93,115,146],"domain":[33,44,62,67,85,106,140,232],"(where":[34,45],"model":[36,47,51,73,161],"applied)":[38],"different":[40],"from":[41,91,113,137,144,204],"source":[43,139,165],"trained),":[49],"often":[52],"suffers":[53],"significant":[55],"performance":[56,234],"drop,":[57],"commonly":[58],"referred":[59],"as":[61,189,195],"adaptation":[63,68,107,233],"issue.":[64],"In":[65,77,126,168],"de-identification,":[66],"issues":[69],"can":[70],"make":[71],"vulnerable":[74],"for":[75,217,235,239],"deployment.":[76,184],"this":[78],"work,":[79],"we":[80,129],"aim":[81],"close":[83],"gap":[86],"by":[87,109,176,215],"leveraging":[88,110],"unlabeled":[89,111,142],"data":[90,112,136,143],"domain.":[94,116,147,166],"MATERIALS":[95],"AND":[96],"METHODS:":[97],"We":[98,117,148],"introduce":[99],"self-training":[101,152,227],"framework":[102,153,172,200,228],"address":[104],"issue":[108],"validate":[118],"effectiveness":[120],"on":[121,163],"4":[122],"standard":[123],"datasets.":[125],"each":[127],"experiment,":[128],"use":[130],"pair":[132],"of":[133],"datasets:":[134],"labeled":[135],"and":[141,193,219],"compare":[149],"proposed":[151,171,199],"with":[154,182],"supervised":[155],"that":[157],"directly":[158],"deploys":[159],"trained":[162],"RESULTS:":[167],"summary,":[169],"our":[170],"improves":[173],"F1-score":[175,203,214],"5.38":[177],"(on":[178],"average)":[179],"compared":[181],"direct":[183],"For":[185],"example,":[186],"using":[187],"i2b2-2014":[188],"training":[191],"dataset":[192],"i2b2-2006":[194],"test,":[197],"increases":[201,212],"76.61":[205],"85.41":[207],"(+8.8).":[208],"The":[209],"method":[210],"also":[211],"10.86":[216],"mimic-radiology":[218],"mimic-discharge.":[220],"CONCLUSION:":[221],"Our":[222],"work":[223],"demonstrates":[224],"an":[225],"effective":[226],"boost":[230],"records.":[242]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
