{"id":"https://openalex.org/W4407191181","doi":"https://doi.org/10.3390/info16020112","title":"Large Language Models for Electronic Health Record De-Identification in English and German","display_name":"Large Language Models for Electronic Health Record De-Identification in English and German","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407191181","doi":"https://doi.org/10.3390/info16020112"},"language":"en","primary_location":{"id":"doi:10.3390/info16020112","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16020112","pdf_url":"https://www.mdpi.com/2078-2489/16/2/112/pdf","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/16/2/112/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038308708","display_name":"Samuel Sousa","orcid":"https://orcid.org/0000-0001-7196-9095"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Samuel Sousa","raw_affiliation_strings":["Institute of Human-Centred Computing, Graz University of Technology, 8010 Graz, Austria","Know Center Research GmbH, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Human-Centred Computing, Graz University of Technology, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Know Center Research GmbH, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4210088621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049422529","display_name":"Michael Jantscher","orcid":"https://orcid.org/0009-0001-4779-0762"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael Jantscher","raw_affiliation_strings":["Institute of Human-Centred Computing, Graz University of Technology, 8010 Graz, Austria","Know Center Research GmbH, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Human-Centred Computing, Graz University of Technology, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Know Center Research GmbH, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4210088621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102832863","display_name":"Mark Kr\u00f6ll","orcid":"https://orcid.org/0000-0002-8398-5292"},"institutions":[{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Mark Kr\u00f6ll","raw_affiliation_strings":["Know Center Research GmbH, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Know Center Research GmbH, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4210088621"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014398832","display_name":"Roman Kern","orcid":"https://orcid.org/0000-0003-0202-6100"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Roman Kern","raw_affiliation_strings":["Institute of Human-Centred Computing, Graz University of Technology, 8010 Graz, Austria","Know Center Research GmbH, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Human-Centred Computing, Graz University of Technology, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Know Center Research GmbH, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4210088621"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038308708"],"corresponding_institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210088621"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":14.0589,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98405999,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"16","issue":"2","first_page":"112","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9916999936103821,"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":0.9916999936103821,"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":0.9915000200271606,"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/T11719","display_name":"Data Quality and Management","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.8943370580673218},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.705860435962677},{"id":"https://openalex.org/keywords/electronic-health-record","display_name":"Electronic health record","score":0.5079391598701477},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.46279311180114746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4084933400154114},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4040125012397766},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.34263813495635986},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.3394099175930023},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.23328393697738647},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.17148512601852417},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.11832764744758606},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.059537023305892944}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8943370580673218},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.705860435962677},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.5079391598701477},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.46279311180114746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4084933400154114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4040125012397766},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34263813495635986},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.3394099175930023},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.23328393697738647},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.17148512601852417},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.11832764744758606},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.059537023305892944},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info16020112","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16020112","pdf_url":"https://www.mdpi.com/2078-2489/16/2/112/pdf","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9256b0d8bd514d21a683e39e15fedf55","is_oa":true,"landing_page_url":"https://doaj.org/article/9256b0d8bd514d21a683e39e15fedf55","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 16, Iss 2, p 112 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info16020112","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16020112","pdf_url":"https://www.mdpi.com/2078-2489/16/2/112/pdf","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3949093982","display_name":null,"funder_award_id":"COMET","funder_id":"https://openalex.org/F4320323033","funder_display_name":"Bundesministerium f\u00fcr Verkehr, Innovation und Technologie"},{"id":"https://openalex.org/G8994745873","display_name":null,"funder_award_id":"COMET","funder_id":"https://openalex.org/F4320323031","funder_display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft"}],"funders":[{"id":"https://openalex.org/F4320323031","display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft","ror":"https://ror.org/028jc0449"},{"id":"https://openalex.org/F4320323033","display_name":"Bundesministerium f\u00fcr Verkehr, Innovation und Technologie","ror":"https://ror.org/04marky29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407191181.pdf","grobid_xml":"https://content.openalex.org/works/W4407191181.grobid-xml"},"referenced_works_count":86,"referenced_works":["https://openalex.org/W50158085","https://openalex.org/W107524893","https://openalex.org/W992506503","https://openalex.org/W1034374084","https://openalex.org/W1558796178","https://openalex.org/W1565746575","https://openalex.org/W1623072288","https://openalex.org/W1832693441","https://openalex.org/W1863940422","https://openalex.org/W1873763122","https://openalex.org/W2015620729","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2105578014","https://openalex.org/W2128004504","https://openalex.org/W2147880316","https://openalex.org/W2156061936","https://openalex.org/W2157331557","https://openalex.org/W2161880183","https://openalex.org/W2190333735","https://openalex.org/W2404970260","https://openalex.org/W2473418344","https://openalex.org/W2516089573","https://openalex.org/W2535838896","https://openalex.org/W2557515658","https://openalex.org/W2581151820","https://openalex.org/W2621075239","https://openalex.org/W2744160972","https://openalex.org/W2782378770","https://openalex.org/W2791930518","https://openalex.org/W2896457183","https://openalex.org/W2904442979","https://openalex.org/W2944176689","https://openalex.org/W2947819652","https://openalex.org/W2963956191","https://openalex.org/W2970511757","https://openalex.org/W2972132516","https://openalex.org/W2978348882","https://openalex.org/W2989759966","https://openalex.org/W2989885118","https://openalex.org/W2989961484","https://openalex.org/W2991314401","https://openalex.org/W3032302651","https://openalex.org/W3083683925","https://openalex.org/W3083918922","https://openalex.org/W3087011118","https://openalex.org/W3095788424","https://openalex.org/W3123459983","https://openalex.org/W3123552645","https://openalex.org/W3157876196","https://openalex.org/W3160274564","https://openalex.org/W3161588905","https://openalex.org/W3168997536","https://openalex.org/W3169068430","https://openalex.org/W3175122546","https://openalex.org/W3215966579","https://openalex.org/W3216873531","https://openalex.org/W4226116435","https://openalex.org/W4230575913","https://openalex.org/W4239510810","https://openalex.org/W4280635059","https://openalex.org/W4281262808","https://openalex.org/W4292779060","https://openalex.org/W4307079201","https://openalex.org/W4318142182","https://openalex.org/W4319730829","https://openalex.org/W4379232373","https://openalex.org/W4385572634","https://openalex.org/W4386141641","https://openalex.org/W4386741020","https://openalex.org/W4388022708","https://openalex.org/W4389518173","https://openalex.org/W4391913563","https://openalex.org/W4401484139","https://openalex.org/W4402670268","https://openalex.org/W4402671897","https://openalex.org/W4403939330","https://openalex.org/W4404534210","https://openalex.org/W4404782964","https://openalex.org/W6669763840","https://openalex.org/W6739901393","https://openalex.org/W6752600739","https://openalex.org/W6770322699","https://openalex.org/W6778883912","https://openalex.org/W6804231082","https://openalex.org/W6847076894"],"related_works":["https://openalex.org/W2315527029","https://openalex.org/W2065387230","https://openalex.org/W2323937687","https://openalex.org/W648995381","https://openalex.org/W3033791384","https://openalex.org/W2141885522","https://openalex.org/W2776312268","https://openalex.org/W4246315097","https://openalex.org/W346029495","https://openalex.org/W1201259214"],"abstract_inverted_index":{"Electronic":[0],"health":[1,19],"record":[2],"(EHR)":[3],"de-identification":[4,31,89,127],"is":[5,22],"crucial":[6],"for":[7,54,79,91,104],"publishing":[8],"or":[9],"sharing":[10],"medical":[11],"data":[12,39,67],"without":[13,129],"violating":[14],"the":[15,44,52,100,130,135],"patient\u2019s":[16],"privacy.":[17],"Protected":[18],"information":[20],"(PHI)":[21],"abundant":[23],"in":[24,41,82,116],"EHRs,":[25],"and":[26,43,57,84,94,98],"privacy":[27,59],"regulations":[28],"worldwide":[29],"mandate":[30],"before":[32],"downstream":[33],"tasks":[34],"are":[35],"performed.":[36],"The":[37],"ever-growing":[38],"generation":[40],"healthcare":[42],"advent":[45],"of":[46,102,134],"generative":[47],"artificial":[48],"intelligence":[49],"have":[50],"increased":[51],"demand":[53],"de-identified":[55],"EHRs":[56,81,115],"highlighted":[58],"issues":[60],"with":[61,122],"large":[62],"language":[63],"models":[64],"(LLMs),":[65],"especially":[66],"transmission":[68],"to":[69],"cloud-based":[70],"LLMs.":[71,136],"In":[72],"this":[73,105],"study,":[74],"we":[75],"benchmark":[76],"ten":[77],"LLMs":[78,103,112],"de-identifying":[80],"English":[83],"German.":[85],"We":[86],"then":[87],"compare":[88],"performance":[90,128],"in-context":[92,120],"learning":[93,121],"full":[95,132],"model":[96],"fine-tuning":[97,133],"analyze":[99],"limitations":[101],"task.":[106],"Our":[107],"experimental":[108],"evaluation":[109],"shows":[110],"that":[111],"effectively":[113],"de-identify":[114],"both":[117],"languages.":[118],"Moreover,":[119],"a":[123],"one-shot":[124],"setting":[125],"boosts":[126],"costly":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}