{"id":"https://openalex.org/W4413050949","doi":"https://doi.org/10.3233/shti251144","title":"Comparing the Accuracy of Deidentification in Japanese Text Using Large Language Models","display_name":"Comparing the Accuracy of Deidentification in Japanese Text Using Large Language Models","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413050949","doi":"https://doi.org/10.3233/shti251144","pmid":"https://pubmed.ncbi.nlm.nih.gov/40776161"},"language":"en","primary_location":{"id":"doi:10.3233/shti251144","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251144","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":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti251144","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030684308","display_name":"Ayako Yagahara","orcid":"https://orcid.org/0000-0003-3364-7719"},"institutions":[{"id":"https://openalex.org/I104234503","display_name":"Hokkaido University of Science","ror":"https://ror.org/05gqsa340","country_code":"JP","type":"education","lineage":["https://openalex.org/I104234503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ayako Yagahara","raw_affiliation_strings":["Department of Radiological Technology, Hokkaido University of Science"],"raw_orcid":"https://orcid.org/0000-0003-3364-7719","affiliations":[{"raw_affiliation_string":"Department of Radiological Technology, Hokkaido University of Science","institution_ids":["https://openalex.org/I104234503"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haluna Mori","orcid":null},"institutions":[{"id":"https://openalex.org/I104234503","display_name":"Hokkaido University of Science","ror":"https://ror.org/05gqsa340","country_code":"JP","type":"education","lineage":["https://openalex.org/I104234503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haluna Mori","raw_affiliation_strings":["Department of Radiological Technology, Hokkaido University of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiological Technology, Hokkaido University of Science","institution_ids":["https://openalex.org/I104234503"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103227082","display_name":"Naoki Nishimoto","orcid":"https://orcid.org/0000-0002-7638-8967"},"institutions":[{"id":"https://openalex.org/I4210141669","display_name":"Hokkaido University Hospital","ror":"https://ror.org/0419drx70","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210141669"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Nishimoto","raw_affiliation_strings":["Data Science Center, HELIOS, Hokkaido University Hospital"],"raw_orcid":"https://orcid.org/0000-0002-7638-8967","affiliations":[{"raw_affiliation_string":"Data Science Center, HELIOS, Hokkaido University Hospital","institution_ids":["https://openalex.org/I4210141669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.3214348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"329","issue":null,"first_page":"1646","last_page":"1647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9804999828338623,"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":0.9804999828338623,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9424999952316284,"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/T11719","display_name":"Data Quality and Management","score":0.9262999892234802,"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/newspaper","display_name":"Newspaper","score":0.805827260017395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6108652353286743},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5551643967628479},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5007915496826172},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4396688938140869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4108719229698181},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.207977294921875}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.805827260017395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6108652353286743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5551643967628479},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5007915496826172},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4396688938140869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4108719229698181},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.207977294921875},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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":"D000095225","descriptor_name":"East Asian People","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000095225","descriptor_name":"East Asian People","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000095225","descriptor_name":"East Asian People","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","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":"D007564","descriptor_name":"Japan","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007564","descriptor_name":"Japan","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007564","descriptor_name":"Japan","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":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":"D010865","descriptor_name":"Pilot Projects","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010865","descriptor_name":"Pilot Projects","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010865","descriptor_name":"Pilot Projects","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":2,"locations":[{"id":"doi:10.3233/shti251144","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251144","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:40776161","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40776161","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":null}],"best_oa_location":{"id":"doi:10.3233/shti251144","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251144","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":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W2100945520","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W644339423","https://openalex.org/W3204019825","https://openalex.org/W2368651715"],"abstract_inverted_index":{"The":[0,68],"purpose":[1],"of":[2,10,39,61,79,105],"this":[3],"study":[4],"is":[5,97],"to":[6,19,35],"evaluate":[7],"the":[8,37,65,74,98,102],"accuracy":[9],"personal":[11,40,84,106],"information":[12,62,107],"extraction":[13,38,66,104],"using":[14],"large":[15],"language":[16],"models":[17],"(LLMs)":[18],"develop":[20],"an":[21],"deidentification":[22],"tool":[23],"for":[24,83,87,92,101],"in-house":[25],"use.":[26],"We":[27],"used":[28],"three":[29,59],"LLMs":[30],"(BERT,":[31],"GPT3.5":[32],"and":[33,44,63,90],"GPT4o-mini)":[34],"target":[36],"names,":[41,43,85,89],"facility":[42,88],"place":[45,93],"names.":[46,94],"As":[47],"a":[48],"pilot":[49],"study,":[50],"we":[51],"analyzed":[52],"20":[53],"Japanese":[54],"newspaper":[55],"articles":[56],"containing":[57],"these":[58],"types":[60],"assessed":[64],"accuracy.":[67],"results":[69],"showed":[70],"that":[71],"BERT":[72,96],"achieved":[73],"highest":[75],"accuracy,":[76],"with":[77],"F1-scores":[78],"0.94":[80],"overall,":[81],"0.99":[82],"0.89":[86],"0.93":[91],"Therefore,":[95],"most":[99],"useful":[100],"automatic":[103],"from":[108],"clinical":[109],"data.":[110]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
