{"id":"https://openalex.org/W4407613434","doi":"https://doi.org/10.1186/s12911-025-02913-z","title":"De-identification of clinical notes with pseudo-labeling using regular expression rules and pre-trained BERT","display_name":"De-identification of clinical notes with pseudo-labeling using regular expression rules and pre-trained BERT","publication_year":2025,"publication_date":"2025-02-17","ids":{"openalex":"https://openalex.org/W4407613434","doi":"https://doi.org/10.1186/s12911-025-02913-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/39962485"},"language":"en","primary_location":{"id":"doi:10.1186/s12911-025-02913-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-025-02913-z","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/s12911-025-02913-z","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/s12911-025-02913-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004841618","display_name":"Jiyong An","orcid":"https://orcid.org/0000-0001-9546-3654"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jiyong An","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101661306","display_name":"Jiyun Kim","orcid":"https://orcid.org/0009-0007-3189-6849"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiyun Kim","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058961028","display_name":"Leonard Sunwoo","orcid":"https://orcid.org/0000-0003-0374-8658"},"institutions":[{"id":"https://openalex.org/I2803058125","display_name":"Seoul National University Bundang Hospital","ror":"https://ror.org/00cb3km46","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I139264467","https://openalex.org/I2802835388","https://openalex.org/I2803058125"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Leonard Sunwoo","raw_affiliation_strings":["Department of Radiology, Seoul National University Bundang Hospital, Seongnam, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology, Seoul National University Bundang Hospital, Seongnam, South Korea","institution_ids":["https://openalex.org/I2803058125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015725420","display_name":"Hyunyoung Baek","orcid":"https://orcid.org/0000-0003-0810-9396"},"institutions":[{"id":"https://openalex.org/I2803058125","display_name":"Seoul National University Bundang Hospital","ror":"https://ror.org/00cb3km46","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I139264467","https://openalex.org/I2802835388","https://openalex.org/I2803058125"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunyoung Baek","raw_affiliation_strings":["Healthcare ICT Research Center, Office of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Healthcare ICT Research Center, Office of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, South Korea","institution_ids":["https://openalex.org/I2803058125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068195598","display_name":"Sooyoung Yoo","orcid":"https://orcid.org/0000-0001-8620-4925"},"institutions":[{"id":"https://openalex.org/I2803058125","display_name":"Seoul National University Bundang Hospital","ror":"https://ror.org/00cb3km46","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I139264467","https://openalex.org/I2802835388","https://openalex.org/I2803058125"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sooyoung Yoo","raw_affiliation_strings":["Healthcare ICT Research Center, Office of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, South Korea. yoosoo0@snubh.org","Healthcare ICT Research Center, Office of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Healthcare ICT Research Center, Office of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, South Korea. yoosoo0@snubh.org","institution_ids":["https://openalex.org/I2803058125"]},{"raw_affiliation_string":"Healthcare ICT Research Center, Office of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, South Korea","institution_ids":["https://openalex.org/I2803058125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049355350","display_name":"Seunggeun Lee","orcid":"https://orcid.org/0000-0002-8097-3878"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210123907","display_name":"National University College","ror":"https://ror.org/02hs8e066","country_code":"PR","type":"education","lineage":["https://openalex.org/I4210123907"]}],"countries":["KR","PR"],"is_corresponding":false,"raw_author_name":"Seunggeun Lee","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University, Seoul, South Korea. lee7801@snu.ac.kr","Graduate School of Data Science, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University, Seoul, South Korea. lee7801@snu.ac.kr","institution_ids":["https://openalex.org/I4210123907"]},{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5004841618"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":1570,"currency":"GBP","value_usd":1925},"apc_paid":{"value":1570,"currency":"GBP","value_usd":1925},"fwci":1.0242,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73421084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"25","issue":"1","first_page":"82","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.3889999985694885,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.3889999985694885,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.15289999544620514,"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":0.11620000004768372,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7018771171569824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.681104838848114},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6722675561904907},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5810361504554749},{"id":"https://openalex.org/keywords/protected-health-information","display_name":"Protected health information","score":0.5771183371543884},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.556255042552948},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5435807704925537},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5159679055213928},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.49153074622154236},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48555752635002136},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.47487470507621765},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.45495903491973877},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.43752095103263855},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.4288780093193054},{"id":"https://openalex.org/keywords/health-informatics","display_name":"Health informatics","score":0.42883339524269104},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.41577285528182983},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3937995433807373},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2752857208251953},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.2578875422477722},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.13557952642440796},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09188097715377808}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7018771171569824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.681104838848114},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6722675561904907},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5810361504554749},{"id":"https://openalex.org/C133652896","wikidata":"https://www.wikidata.org/wiki/Q7251300","display_name":"Protected health information","level":5,"score":0.5771183371543884},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.556255042552948},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5435807704925537},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5159679055213928},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.49153074622154236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48555752635002136},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.47487470507621765},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.45495903491973877},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.43752095103263855},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.4288780093193054},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.42883339524269104},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41577285528182983},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3937995433807373},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2752857208251953},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2578875422477722},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.13557952642440796},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09188097715377808},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138816342","wikidata":"https://www.wikidata.org/wiki/Q189603","display_name":"Public health","level":2,"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/C185618831","wikidata":"https://www.wikidata.org/wiki/Q1851928","display_name":"Health promotion","level":3,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C147268084","wikidata":"https://www.wikidata.org/wiki/Q5635796","display_name":"HRHIS","level":4,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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":false},{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","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":"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":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":true},{"descriptor_ui":"D056910","descriptor_name":"Republic of Korea","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056910","descriptor_name":"Republic of Korea","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056910","descriptor_name":"Republic of Korea","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056910","descriptor_name":"Republic of Korea","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12911-025-02913-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-025-02913-z","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/s12911-025-02913-z","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},{"id":"pmid:39962485","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39962485","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":"BMC medical informatics and decision making","raw_type":null},{"id":"pmh:oai:doaj.org/article:538cda42d41b4efeb429b778060cf870","is_oa":true,"landing_page_url":"https://doaj.org/article/538cda42d41b4efeb429b778060cf870","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Medical Informatics and Decision Making, Vol 25, Iss 1, Pp 1-10 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11831849","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11831849","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Med Inform Decis Mak","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12911-025-02913-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-025-02913-z","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/s12911-025-02913-z","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2045000886","display_name":null,"funder_award_id":"RS-2023-00222663","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6526468052","display_name":null,"funder_award_id":"2020H1D3A2A03100666","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7480098300","display_name":null,"funder_award_id":"2020H1D3A2A03100666","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7508762746","display_name":null,"funder_award_id":"HI22C0471","funder_id":"https://openalex.org/F4320322107","funder_display_name":"Korea Health Industry Development Institute"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322107","display_name":"Korea Health Industry Development Institute","ror":"https://ror.org/00fdzyk40"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407613434.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2012326946","https://openalex.org/W2045718189","https://openalex.org/W2068402150","https://openalex.org/W2105578014","https://openalex.org/W2155063583","https://openalex.org/W2160987310","https://openalex.org/W2396881363","https://openalex.org/W2911489562","https://openalex.org/W2927032858","https://openalex.org/W2963716420","https://openalex.org/W2970771982","https://openalex.org/W2998445959","https://openalex.org/W3012137864","https://openalex.org/W3017330637","https://openalex.org/W3099008231","https://openalex.org/W4293574676"],"related_works":["https://openalex.org/W4401821554","https://openalex.org/W3180764077","https://openalex.org/W4281560212","https://openalex.org/W4210800588","https://openalex.org/W3116252395","https://openalex.org/W2769084352","https://openalex.org/W4385574021","https://openalex.org/W2887593177","https://openalex.org/W4386322467","https://openalex.org/W2757016069"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"De-identification":[2],"of":[3,48,77,175,219],"clinical":[4,32],"notes":[5,33,67,116,154,190],"is":[6,107,184],"essential":[7],"to":[8,94,109,134],"utilize":[9],"the":[10,45,49,78,114,124,157,173,217],"rich":[11],"information":[12,30],"in":[13,17,27,34,44,209],"unstructured":[14],"text":[15],"data":[16],"medical":[18],"research.":[19],"However,":[20],"only":[21],"limited":[22,98],"work":[23],"has":[24],"been":[25],"done":[26],"removing":[28],"personal":[29],"from":[31,68,172],"Korea.":[35],"Methods":[36],"Our":[37,160],"study":[38],"utilized":[39],"a":[40,104,131,136,203,210],"comprehensive":[41],"dataset":[42,61],"stored":[43],"Note":[46],"table":[47],"OMOP":[50],"Common":[51],"Data":[52],"Model":[53],"at":[54,156],"Seoul":[55],"National":[56],"University":[57],"Bundang":[58],"Hospital.":[59],"This":[60],"includes":[62],"11,181,617":[63],"radiology":[64,150,176],"and":[65,86,99,151,168,196,206],"9,282,477":[66],"various":[69],"other":[70],"departments":[71],"(non-radiology":[72],"reports).":[73],"From":[74],"this,":[75],"0.1%":[76],"reports":[79],"(11,182)":[80],"were":[81],"randomly":[82],"selected":[83],"for":[84],"training":[85],"validation":[87],"purposes.":[88],"We":[89],"used":[90,108],"two":[91],"de-identification":[92,220],"strategies":[93],"improve":[95],"performance":[96,218],"with":[97,141,186],"few":[100],"annotated":[101,117],"data.":[102],"First,":[103],"rule-based":[105,161,204],"approach":[106,133,162,205],"construct":[110],"regular":[111,125],"expressions":[112,126],"on":[113],"1,112":[115],"by":[118,122],"domain":[119],"experts.":[120],"Second,":[121],"using":[123,148],"as":[127],"label-er,":[128],"we":[129],"applied":[130],"semi-supervised":[132,211],"fine-tune":[135],"pre-trained":[137],"Korean":[138],"BERT":[139],"model":[140],"pseudo-labeled":[142,189],"notes.":[143,177],"Results":[144],"Validation":[145],"was":[146],"conducted":[147],"342":[149],"12":[152],"non-radiology":[153],"labeled":[155],"token":[158],"level.":[159],"achieved":[163,191],"97.2%":[164],"precision,":[165,193],"93.7%":[166],"recall,":[167,195],"96.2%":[169],"F1":[170,198],"score":[171],"department":[174],"For":[178],"machine":[179,207],"learning":[180,208],"approach,":[181],"KoBERT-NER":[182],"that":[183,216],"fine-tuned":[185],"32,000":[187],"automatically":[188],"96.5%":[192],"97.6%":[194],"97.1%":[197],"score.":[199],"Conclusion":[200],"By":[201],"combining":[202],"way,":[212],"our":[213],"results":[214],"show":[215],"can":[221],"be":[222],"improved.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-20T08:49:12.498775","created_date":"2025-10-10T00:00:00"}