{"id":"https://openalex.org/W4410281514","doi":"https://doi.org/10.1177/1088467x251332846","title":"SDM-M-DID: Self-decoding model for medical de-identification","display_name":"SDM-M-DID: Self-decoding model for medical de-identification","publication_year":2025,"publication_date":"2025-05-11","ids":{"openalex":"https://openalex.org/W4410281514","doi":"https://doi.org/10.1177/1088467x251332846"},"language":"en","primary_location":{"id":"doi:10.1177/1088467x251332846","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1088467x251332846","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis: An International Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117512205","display_name":"Bohdan Budiakov","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohdan Budiakov","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0862-6652","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392681","display_name":"Tong Liu","orcid":"https://orcid.org/0000-0003-0485-839X"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tong Liu","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0485-839X","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037869164","display_name":"Junwen Chen","orcid":"https://orcid.org/0000-0003-1355-4128"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwen Chen","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106858369","display_name":"\u0410.\u0418. \u041a\u0430\u0440\u0435\u0432","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Alexey Karev","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-5012-3170","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100392681"],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04449057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":"1","first_page":"127","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9909999966621399,"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":0.9909999966621399,"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":0.9896000027656555,"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":0.986299991607666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6700738072395325},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6548285484313965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4704904556274414},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.18282157182693481},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12724080681800842}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6700738072395325},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6548285484313965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4704904556274414},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.18282157182693481},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12724080681800842},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1088467x251332846","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1088467x251332846","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis: An International Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W992506503","https://openalex.org/W2015620729","https://openalex.org/W2250424592","https://openalex.org/W2250539671","https://openalex.org/W2621075239","https://openalex.org/W2888329843","https://openalex.org/W2951820126","https://openalex.org/W2963854351","https://openalex.org/W2964053384","https://openalex.org/W2981852735","https://openalex.org/W3012211566","https://openalex.org/W3103015934","https://openalex.org/W3114916066","https://openalex.org/W3160137267","https://openalex.org/W3164109169","https://openalex.org/W3166508187","https://openalex.org/W4285180445","https://openalex.org/W4288089799","https://openalex.org/W4385245566","https://openalex.org/W4389040130","https://openalex.org/W4389519530","https://openalex.org/W4399341750","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Information":[0],"leakage":[1],"and":[2,10,38,53,160,211,227,250],"model":[3,80,145],"attacks":[4],"pose":[5],"risks":[6],"in":[7,205,231,242],"the":[8,16,31,50,72,101,121,158,174,177,208,212],"analysis":[9],"exchange":[11],"of":[12,75,112,149,162,176],"medical":[13,22,170],"data,":[14,89],"as":[15],"language":[17,67,142,236],"models":[18,95,237],"used":[19],"to":[20,86,107,125,135,139,172,194,233],"process":[21],"records":[23],"may":[24],"retain":[25],"training":[26],"data.":[27,46],"Traditional":[28],"models,":[29,143],"on":[30,168],"other":[32,66],"hand,":[33],"are":[34],"often":[35],"too":[36],"complicated":[37],"use":[39],"old":[40],"ineffectual":[41],"methods":[42],"for":[43,59],"removing":[44],"personal":[45],"This":[47,69],"can":[48],"compromise":[49],"data\u2019s":[51],"integrity":[52,226],"quality,":[54],"making":[55],"it":[56,116,241],"less":[57,251],"useful":[58],"future":[60],"tasks,":[61],"especially":[62],"when":[63],"combined":[64],"with":[65,120],"models.":[68],"paper":[70],"introduces":[71],"Self-Decoded":[73],"Model":[74],"Medical":[76],"De-identification":[77],"(SDM-M-DID).":[78],"The":[79],"employs":[81],"a":[82,147,185,247],"secure":[83,249],"BERT-based":[84],"encoder":[85],"paraphrase":[87],"sensitive":[88,99],"ensuring":[90],"HIPAA":[91],"compliance.":[92],"Unlike":[93],"traditional":[94],"that":[96,181,219],"only":[97,184,222],"mask":[98],"tokens,":[100,127],"SDM-M-DID":[102,220],"decodes":[103],"its":[104],"own":[105],"embeddings":[106],"generate":[108],"an":[109,154],"internal":[110],"representations":[111,119],"these":[113],"tokens.":[114,164],"Then,":[115],"integrates":[117],"this":[118,217],"pre-trained":[122],"BERT":[123],"dictionary":[124],"rephrase":[126],"preserving":[128],"their":[129],"semantic":[130],"role":[131],"while":[132,245],"altering":[133],"grammar":[134],"prevent":[136],"re-identification.":[137],"Compared":[138],"existing":[140],"large":[141,235],"our":[144],"achieves":[146],"score":[148],"0.8416":[150],"F1":[151],"BERTscore,":[152],"striking":[153],"optimal":[155],"balance":[156],"between":[157,207],"variability":[159],"similarity":[161],"deidentified":[163],"We":[165],"conducted":[166],"experiments":[167],"two":[169],"datasets":[171,210],"demonstrate":[173],"effectiveness":[175],"model.":[178],"Metrics":[179],"show":[180],"there":[182],"is":[183,228],"<mml:math":[186,195],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[187,196],"display=\"inline\"":[188,197],"overflow=\"scroll\">":[189,198],"<mml:mo>\u00b1</mml:mo>":[190,199],"<mml:mn>1</mml:mn>":[191],"</mml:math>":[192,203],"%":[193],"<mml:mn>2</mml:mn>":[200],"<mml:mi":[201],"mathvariant=\"normal\">%</mml:mi>":[202],"difference":[204],"accuracy":[206],"original":[209],"de-identified":[213],"datasets.":[214],"In":[215],"total,":[216],"demonstrates":[218],"not":[221,229],"effectively":[223],"preserves":[224],"data":[225],"inferior":[230],"efficiency":[232],"new":[234],"but":[238],"even":[239],"improves":[240],"some":[243],"cases":[244],"using":[246],"more":[248],"resource-intensive":[252],"technology.":[253]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}