{"id":"https://openalex.org/W4417487500","doi":"https://doi.org/10.1016/j.ijmedinf.2025.106225","title":"De-identification of clinical data: A systematic review of free text, image and tabular data approaches","display_name":"De-identification of clinical data: A systematic review of free text, image and tabular data approaches","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W4417487500","doi":"https://doi.org/10.1016/j.ijmedinf.2025.106225","pmid":"https://pubmed.ncbi.nlm.nih.gov/41455387"},"language":"en","primary_location":{"id":"doi:10.1016/j.ijmedinf.2025.106225","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ijmedinf.2025.106225","pdf_url":null,"source":{"id":"https://openalex.org/S53142634","display_name":"International Journal of Medical Informatics","issn_l":"1386-5056","issn":["1386-5056","1872-8243"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Medical Informatics","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.ijmedinf.2025.106225","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017525867","display_name":"Pedro Faustini","orcid":"https://orcid.org/0000-0002-9961-1252"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Pedro Faustini","raw_affiliation_strings":["School of Computing, Macquarie University, Balaclava Rd, Sydney, 2109, NSW, Australia. Electronic address: pedro.faustini@mq.edu.au"],"raw_orcid":"https://orcid.org/0000-0002-9961-1252","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Balaclava Rd, Sydney, 2109, NSW, Australia. Electronic address: pedro.faustini@mq.edu.au","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035107880","display_name":"Annabelle McIver","orcid":"https://orcid.org/0000-0002-2405-9838"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Annabelle McIver","raw_affiliation_strings":["School of Computing, Macquarie University, Balaclava Rd, Sydney, 2109, NSW, Australia. Electronic address: annabelle.mciver@mq.edu.au"],"raw_orcid":"https://orcid.org/0000-0002-2405-9838","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Balaclava Rd, Sydney, 2109, NSW, Australia. Electronic address: annabelle.mciver@mq.edu.au","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ryan Sullivan","orcid":"https://orcid.org/0000-0001-5554-7378"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ryan Sullivan","raw_affiliation_strings":["University of Sydney, City Road, Sydney, 2008, NSW, Australia. Electronic address: ryan.sullivan@sydney.edu.au"],"raw_orcid":"https://orcid.org/0000-0001-5554-7378","affiliations":[{"raw_affiliation_string":"University of Sydney, City Road, Sydney, 2008, NSW, Australia. Electronic address: ryan.sullivan@sydney.edu.au","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022216838","display_name":"Mark Dras","orcid":"https://orcid.org/0000-0001-9908-7182"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mark Dras","raw_affiliation_strings":["School of Computing, Macquarie University, Balaclava Rd, Sydney, 2109, NSW, Australia. Electronic address: mark.dras@mq.edu.au"],"raw_orcid":"https://orcid.org/0000-0001-9908-7182","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Balaclava Rd, Sydney, 2109, NSW, Australia. Electronic address: mark.dras@mq.edu.au","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017525867"],"corresponding_institution_ids":["https://openalex.org/I99043593"],"apc_list":{"value":3210,"currency":"USD","value_usd":3210},"apc_paid":{"value":3210,"currency":"USD","value_usd":3210},"fwci":0.129,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51113586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"208","issue":null,"first_page":"106225","last_page":"106225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.06729999929666519,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.06729999929666519,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.050200000405311584,"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":0.04600000008940697,"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/key","display_name":"Key (lock)","score":0.6165000200271606},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48030000925064087},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.4004000127315521},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.3555999994277954},{"id":"https://openalex.org/keywords/phenomenon","display_name":"Phenomenon","score":0.3425999879837036},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2928999960422516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791100025177002},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5544000267982483},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45419999957084656},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36820000410079956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C50335755","wikidata":"https://www.wikidata.org/wiki/Q483247","display_name":"Phenomenon","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25060001015663147}],"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":"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":"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":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":"D016494","descriptor_name":"Computer Security","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":false},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","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":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},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1016/j.ijmedinf.2025.106225","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ijmedinf.2025.106225","pdf_url":null,"source":{"id":"https://openalex.org/S53142634","display_name":"International Journal of Medical Informatics","issn_l":"1386-5056","issn":["1386-5056","1872-8243"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Medical Informatics","raw_type":"journal-article"},{"id":"pmid:41455387","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41455387","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":"International journal of medical informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.1016/j.ijmedinf.2025.106225","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ijmedinf.2025.106225","pdf_url":null,"source":{"id":"https://openalex.org/S53142634","display_name":"International Journal of Medical Informatics","issn_l":"1386-5056","issn":["1386-5056","1872-8243"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Medical Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4906014721","display_name":"Medical Research Future Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W580350262","https://openalex.org/W992506503","https://openalex.org/W1169821766","https://openalex.org/W1995228216","https://openalex.org/W2014226385","https://openalex.org/W2015620729","https://openalex.org/W2053744708","https://openalex.org/W2064675550","https://openalex.org/W2105578014","https://openalex.org/W2111063183","https://openalex.org/W2111547563","https://openalex.org/W2124216778","https://openalex.org/W2152772232","https://openalex.org/W2160987310","https://openalex.org/W2161880183","https://openalex.org/W2183114698","https://openalex.org/W2190333735","https://openalex.org/W2314398369","https://openalex.org/W2327627395","https://openalex.org/W2396881363","https://openalex.org/W2399899684","https://openalex.org/W2605719883","https://openalex.org/W2609479105","https://openalex.org/W2610743175","https://openalex.org/W2621075239","https://openalex.org/W2622474949","https://openalex.org/W2623375817","https://openalex.org/W2624380710","https://openalex.org/W2729101176","https://openalex.org/W2736476613","https://openalex.org/W2744160972","https://openalex.org/W2800002784","https://openalex.org/W2804603962","https://openalex.org/W2805183640","https://openalex.org/W2919785220","https://openalex.org/W2949308662","https://openalex.org/W2963956191","https://openalex.org/W2990879514","https://openalex.org/W3010607409","https://openalex.org/W3013605954","https://openalex.org/W3017330637","https://openalex.org/W3021380283","https://openalex.org/W3044986852","https://openalex.org/W3083683925","https://openalex.org/W3087011118","https://openalex.org/W3093108616","https://openalex.org/W3095788424","https://openalex.org/W3117568220","https://openalex.org/W3123552645","https://openalex.org/W3140938259","https://openalex.org/W3160540087","https://openalex.org/W3164109169","https://openalex.org/W4210733793","https://openalex.org/W4213082401","https://openalex.org/W4220862305","https://openalex.org/W4283016418","https://openalex.org/W4285293648","https://openalex.org/W4293574676","https://openalex.org/W4300167402","https://openalex.org/W4304810975","https://openalex.org/W4309791331","https://openalex.org/W4320035354","https://openalex.org/W4382279449","https://openalex.org/W4383223222","https://openalex.org/W4389332664","https://openalex.org/W4389377916","https://openalex.org/W4391880762","https://openalex.org/W4392757494","https://openalex.org/W4392757531","https://openalex.org/W4392976136","https://openalex.org/W4394788415","https://openalex.org/W4401387006","https://openalex.org/W4403952035","https://openalex.org/W4404867262"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1],"digitisation":[2],"of":[3,9,53,119,138,175,207,218,245,253,268],"healthcare":[4],"has":[5],"generated":[6],"vast":[7],"amounts":[8],"data":[10,23,140,145,194],"in":[11,141,149,204,224,261],"various":[12],"formats,":[13],"including":[14],"free-text":[15,76],"notes,":[16],"tabular":[17,79,144,193],"records":[18],"and":[19,28,43,81,103,123,146,159,163,195,221,265],"medical":[20,59,77,85,139],"images.":[21,150,209],"This":[22,62],"is":[24],"critical":[25],"for":[26,107,125,233,271],"research":[27],"innovation,":[29],"but":[30],"often":[31,230],"contains":[32],"sensitive":[33,54],"information":[34,55],"that":[35],"must":[36],"be":[37],"de-identified":[38],"to":[39,56,65,75,93,131],"ensure":[40],"patient":[41],"privacy":[42],"regulatory":[44],"compliance.":[45],"Natural":[46],"Language":[47,219],"Processing":[48],"(NLP)":[49],"enables":[50],"automated":[51],"de-identification":[52,72,99,137],"safely":[57],"share":[58],"datasets.":[60,247],"OBJECTIVE:":[61],"study":[63],"aims":[64],"systematically":[66,112],"review":[67],"the":[68,88,153,205,208,243,251,262,266],"literature":[69],"on":[70,156],"NLP-based":[71],"techniques":[73,212],"applied":[74],"reports,":[78],"data,":[80],"burned-in":[82,147],"text":[83,202],"within":[84],"images":[86],"over":[87],"past":[89],"decade.":[90],"It":[91],"seeks":[92],"identify":[94],"state-of-the-art":[95],"methods,":[96],"analyse":[97],"how":[98],"tasks":[100],"are":[101],"assessed,":[102],"find":[104],"existing":[105],"gaps":[106],"future":[108],"research.":[109],"METHODS:":[110],"We":[111,151],"searched":[113],"five":[114],"important":[115],"databases":[116],"(PubMed,":[117],"Web":[118],"Science,":[120],"DBLP,":[121],"ACM":[122],"IEEE)":[124],"articles":[126,154,179],"published":[127],"from":[128],"January":[129],"2015":[130],"December":[132],"2024":[133],"(10":[134],"years)":[135],"about":[136],"free":[142,186],"text,":[143,187],"pixels":[148,206],"filtered":[152],"based":[155],"their":[157],"titles":[158],"abstracts":[160],"against":[161],"inclusion":[162],"exclusion":[164],"criteria,":[165],"followed":[166],"by":[167,242],"a":[168,173,189,196,222],"quality":[169],"filter.":[170],"RESULTS:":[171],"From":[172],"set":[174],"734":[176],"papers,":[177],"83":[178],"were":[180],"deemed":[181],"relevant.":[182],"Most":[183,236],"studies":[184,237],"de-identify":[185,238],"with":[188,192,201,215],"few":[190],"working":[191],"much":[197],"scarcer":[198],"number":[199],"dealing":[200],"embedded":[203],"CONCLUSIONS:":[210],"De-identification":[211],"have":[213],"evolved,":[214],"increased":[216],"use":[217],"Models":[220],"decline":[223],"recurrence-based":[225],"neural":[226],"networks.":[227],"Off-the-shelf":[228],"tools":[229],"require":[231],"customisation":[232],"optimal":[234],"performance.":[235],"English":[239,246],"content,":[240],"supported":[241],"prevalence":[244],"Key":[248],"challenges":[249],"include":[250],"phenomenon":[252],"code-mixing":[254],"(i.e.,":[255],"more":[256],"than":[257],"one":[258],"language":[259],"used":[260],"same":[263],"sentence)":[264],"scarcity":[267],"available":[269],"datasets":[270],"reproducibility.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-19T00:00:00"}
