{"id":"https://openalex.org/W4413050570","doi":"https://doi.org/10.3233/shti250965","title":"Large Language Model Empowered Privacy-Protected Framework for PHI Annotation in Clinical Notes","display_name":"Large Language Model Empowered Privacy-Protected Framework for PHI Annotation in Clinical Notes","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413050570","doi":"https://doi.org/10.3233/shti250965","pmid":"https://pubmed.ncbi.nlm.nih.gov/40775983"},"language":"en","primary_location":{"id":"doi:10.3233/shti250965","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250965","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/shti250965","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067651547","display_name":"Guanchen Wu","orcid":"https://orcid.org/0000-0002-5579-1052"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanchen Wu","raw_affiliation_strings":["Department of Computer Science, Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101260049","display_name":"Linzhi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linzhi Zheng","raw_affiliation_strings":["Department of Computer Science, University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007293006","display_name":"Han Xie","orcid":"https://orcid.org/0000-0001-7633-5040"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Xie","raw_affiliation_strings":["Department of Computer Science, Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085283385","display_name":"Zhen Xiang","orcid":"https://orcid.org/0000-0002-4284-2041"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Xiang","raw_affiliation_strings":["School of Computing, University of Georgia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Georgia","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103935473","display_name":"Jiaying Lu","orcid":"https://orcid.org/0000-0003-4449-325X"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaying Lu","raw_affiliation_strings":["Nell Hodgson Woodruff School of Nursing, Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nell Hodgson Woodruff School of Nursing, Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014913295","display_name":"Darren Liu","orcid":"https://orcid.org/0000-0003-0301-4080"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darren Liu","raw_affiliation_strings":["Nell Hodgson Woodruff School of Nursing, Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nell Hodgson Woodruff School of Nursing, Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108959844","display_name":"Delgersuren Bold","orcid":"https://orcid.org/0000-0002-2983-571X"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Delgersuren Bold","raw_affiliation_strings":["Nell Hodgson Woodruff School of Nursing, Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nell Hodgson Woodruff School of Nursing, Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374364","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-7500-8355"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Department of Computer Science, University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Hu","raw_affiliation_strings":["Nell Hodgson Woodruff School of Nursing, Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nell Hodgson Woodruff School of Nursing, Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006897094","display_name":"Carl Yang","orcid":"https://orcid.org/0000-0001-9145-4531"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Yang","raw_affiliation_strings":["Department of Computer Science, Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.363,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92029533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"329","issue":null,"first_page":"876","last_page":"880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9679999947547913,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9679999947547913,"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":0.9229999780654907,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9211000204086304,"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/generalizability-theory","display_name":"Generalizability theory","score":0.865382194519043},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8052672147750854},{"id":"https://openalex.org/keywords/confidentiality","display_name":"Confidentiality","score":0.7764061689376831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7093583941459656},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.666655957698822},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4888002574443817},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.47340402007102966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4141681492328644},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.3765389323234558},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34301263093948364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3414609432220459},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.34139978885650635},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3213874101638794},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1453712284564972},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1310829520225525},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.11311772465705872}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.865382194519043},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8052672147750854},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.7764061689376831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7093583941459656},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.666655957698822},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4888002574443817},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.47340402007102966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4141681492328644},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3765389323234558},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34301263093948364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3414609432220459},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.34139978885650635},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3213874101638794},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1453712284564972},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1310829520225525},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.11311772465705872},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000068241","descriptor_name":"Personally Identifiable Information","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068241","descriptor_name":"Personally Identifiable Information","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":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"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/shti250965","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250965","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:40775983","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40775983","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/shti250965","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250965","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W126325116"],"abstract_inverted_index":{"De-identifying":[0],"private":[1],"information":[2],"in":[3],"medical":[4],"records":[5],"is":[6],"crucial":[7],"to":[8,54],"prevent":[9],"confidentiality":[10],"breaches.":[11],"Rule-based":[12],"and":[13,19,34,77,87],"learning-based":[14],"methods":[15],"struggle":[16],"with":[17,51,69],"generalizability":[18],"require":[20],"large":[21],"annotated":[22],"datasets,":[23],"while":[24],"LLMs":[25,53,67],"offer":[26],"better":[27],"language":[28],"comprehension":[29],"but":[30],"face":[31],"privacy":[32,75],"risks":[33],"high":[35,78],"computational":[36],"costs.":[37],"We":[38],"propose":[39],"LPPA,":[40],"an":[41],"LLM-empowered":[42],"Privacy-protected":[43],"PHI":[44,79],"Annotation":[45],"framework,":[46],"which":[47],"uses":[48],"few-shot":[49],"learning":[50],"pre-trained":[52],"generate":[55],"synthetic":[56,70],"clinical":[57],"notes,":[58,71],"reducing":[59],"the":[60],"need":[61],"for":[62],"extensive":[63],"datasets.":[64],"By":[65],"fine-tuning":[66],"locally":[68],"LPPA":[72],"ensures":[73],"strong":[74],"protection":[76],"annotation":[80],"accuracy.":[81],"Experiments":[82],"confirm":[83],"its":[84],"effectiveness,":[85],"efficiency,":[86],"scalability.":[88]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}