{"id":"https://openalex.org/W7161963961","doi":"https://doi.org/10.3233/shti260440","title":"The SURROGATOR Framework for Context-Aware Surrogation of Privacy Sensitive Information in Medical Text","display_name":"The SURROGATOR Framework for Context-Aware Surrogation of Privacy Sensitive Information in Medical Text","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7161963961","doi":"https://doi.org/10.3233/shti260440","pmid":"https://pubmed.ncbi.nlm.nih.gov/42175112"},"language":"en","primary_location":{"id":"doi:10.3233/shti260440","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti260440","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti260440","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042587817","display_name":"Christina Lohr","orcid":"https://orcid.org/0000-0001-9889-162X"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christina Lohr","raw_affiliation_strings":["Institute for Medical Informatics, Statistics and Epidemiology (IMISE), University Leipzig, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9889-162X","affiliations":[{"raw_affiliation_string":"Institute for Medical Informatics, Statistics and Epidemiology (IMISE), University Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116858851","display_name":"Marvin Seiferling","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I4210159254","display_name":"Klaus Tschira Foundation","ror":"https://ror.org/052jep661","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210159254"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marvin Seiferling","raw_affiliation_strings":["Klaus Tschira Institute for Integrative Computational Cardiology, University Hospital Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Klaus Tschira Institute for Integrative Computational Cardiology, University Hospital Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I2802164966","https://openalex.org/I4210159254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031301838","display_name":"Philipp Wiesenbach","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I4210159254","display_name":"Klaus Tschira Foundation","ror":"https://ror.org/052jep661","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210159254"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Wiesenbach","raw_affiliation_strings":["Klaus Tschira Institute for Integrative Computational Cardiology, University Hospital Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Klaus Tschira Institute for Integrative Computational Cardiology, University Hospital Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I2802164966","https://openalex.org/I4210159254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103019022","display_name":"Jakob Faller","orcid":"https://orcid.org/0009-0002-8875-5426"},"institutions":[{"id":"https://openalex.org/I4210088053","display_name":"Universit\u00e4tsklinikum Erlangen","ror":"https://ror.org/0030f2a11","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210088053"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jakob Faller","raw_affiliation_strings":["Medical Center for Information and Communication Technology, University Hospital Erlangen, Germany"],"raw_orcid":"https://orcid.org/0009-0002-8875-5426","affiliations":[{"raw_affiliation_string":"Medical Center for Information and Communication Technology, University Hospital Erlangen, Germany","institution_ids":["https://openalex.org/I4210088053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083154676","display_name":"Christoph Dieterich","orcid":"https://orcid.org/0000-0001-9468-6311"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I4210127591","display_name":"German Centre for Cardiovascular Research","ror":"https://ror.org/031t5w623","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127591","https://openalex.org/I4405256427"]},{"id":"https://openalex.org/I4210159254","display_name":"Klaus Tschira Foundation","ror":"https://ror.org/052jep661","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210159254"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Dieterich","raw_affiliation_strings":["Klaus Tschira Institute for Integrative Computational Cardiology, University Hospital Heidelberg, Germany","Partner Site Heidelberg/Mannheim, German Centre for Cardiovascular Research (DZHK), Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9468-6311","affiliations":[{"raw_affiliation_string":"Klaus Tschira Institute for Integrative Computational Cardiology, University Hospital Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I2802164966","https://openalex.org/I4210159254"]},{"raw_affiliation_string":"Partner Site Heidelberg/Mannheim, German Centre for Cardiovascular Research (DZHK), Heidelberg, Germany","institution_ids":["https://openalex.org/I4210127591"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67174344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"336","issue":null,"first_page":"1405","last_page":"1409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.27489998936653137,"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/T10028","display_name":"Topic Modeling","score":0.27489998936653137,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.18449999392032623,"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/T10350","display_name":"Electronic Health Records Systems","score":0.09920000284910202,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.692300021648407},{"id":"https://openalex.org/keywords/medical-information","display_name":"Medical information","score":0.4799000024795532},{"id":"https://openalex.org/keywords/information-sensitivity","display_name":"Information sensitivity","score":0.47850000858306885},{"id":"https://openalex.org/keywords/personally-identifiable-information","display_name":"Personally identifiable information","score":0.4578000009059906},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.4505000114440918},{"id":"https://openalex.org/keywords/information-sharing","display_name":"Information sharing","score":0.4424999952316284},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.4361000061035156},{"id":"https://openalex.org/keywords/confidentiality","display_name":"Confidentiality","score":0.36309999227523804},{"id":"https://openalex.org/keywords/privacy-protection","display_name":"Privacy protection","score":0.34459999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385999798774719},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.692300021648407},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45809999108314514},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.4505000114440918},{"id":"https://openalex.org/C2776854237","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information sharing","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C3018822202","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Patient data","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C3018060332","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic medical record","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C2910417920","wikidata":"https://www.wikidata.org/wiki/Q4116434","display_name":"Patient privacy","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2522999942302704}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003219","descriptor_name":"Confidentiality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003219","descriptor_name":"Confidentiality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003219","descriptor_name":"Confidentiality","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":"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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","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":"Q000458","qualifier_name":"organization & administration","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000458","qualifier_name":"organization & administration","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti260440","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti260440","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:42175112","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42175112","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":"Studies in health technology and informatics","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.3233/shti260440","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti260440","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7480941414833069,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Clinical":[0],"text":[1,30,69],"cannot":[2],"be":[3],"shared":[4],"freely":[5],"due":[6],"to":[7,28,93],"data":[8,56,105],"protection":[9],"regulations.":[10],"This":[11],"paper":[12],"introduces":[13],"SURROGATOR,":[14],"an":[15,86],"open-source":[16],"framework":[17],"that":[18,98],"replaces":[19],"personal":[20],"identifiable":[21],"information":[22],"with":[23,58,66],"fictitious,":[24],"high-fidelity":[25],"synthetic":[26,51],"surrogates":[27],"maintain":[29],"utility":[31],"for":[32,111],"human":[33],"and":[34,46,104],"artificial":[35],"intelligence.":[36],"We":[37,96],"focus":[38],"on":[39,49],"the":[40,67,112],"automated":[41],"replacement":[42],"of":[43,71,88,115],"names,":[44],"dates,":[45],"locations.":[47],"Evaluation":[48],"a":[50,76,80,108],"clinical":[52,116],"corpus":[53],"demonstrated":[54],"high":[55],"utility,":[57,106],"named":[59],"entity":[60],"recognition":[61],"performance":[62],"remaining":[63],"en":[64],"par":[65],"original":[68],"(F1-score":[70],"0.70":[72],"vs.":[73],"0.73).":[74],"Furthermore,":[75],"re-identification":[77],"attack":[78],"using":[79],"large":[81],"language":[82],"model":[83],"resulted":[84],"in":[85,118],"accuracy":[87],"50.8%,":[89],"which":[90],"is":[91],"equivalent":[92],"random":[94],"chance.":[95],"conclude":[97],"SURROGATOR":[99],"effectively":[100],"balances":[101],"patient":[102],"privacy":[103],"providing":[107],"robust":[109],"solution":[110],"secure":[113],"sharing":[114],"documents":[117],"medical":[119],"research.":[120]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-05-22T00:00:00"}
