{"id":"https://openalex.org/W3012137864","doi":"https://doi.org/10.1145/3368555.3384455","title":"Deidentification of free-text medical records using pre-trained bidirectional transformers","display_name":"Deidentification of free-text medical records using pre-trained bidirectional transformers","publication_year":2020,"publication_date":"2020-03-20","ids":{"openalex":"https://openalex.org/W3012137864","doi":"https://doi.org/10.1145/3368555.3384455","mag":"3012137864","pmid":"https://pubmed.ncbi.nlm.nih.gov/34350426"},"language":"en","primary_location":{"id":"doi:10.1145/3368555.3384455","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368555.3384455","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368555.3384455","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on Health, Inference, and Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3368555.3384455","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003528274","display_name":"Alistair E. W. Johnson","orcid":"https://orcid.org/0000-0002-8735-3014"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alistair E. W. Johnson","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058544968","display_name":"Lucas Bulgarelli","orcid":"https://orcid.org/0000-0001-5456-2170"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucas Bulgarelli","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086791063","display_name":"Tom Pollard","orcid":"https://orcid.org/0000-0002-5676-7898"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom J. Pollard","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003528274"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.4243,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.89631377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"2020","issue":null,"first_page":"214","last_page":"221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9912999868392944,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9912999868392944,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.991100013256073,"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/T10350","display_name":"Electronic Health Records Systems","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.8114957809448242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7190361618995667},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.4770047962665558},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.45748817920684814},{"id":"https://openalex.org/keywords/patient-data","display_name":"Patient data","score":0.4364742636680603},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4333048164844513},{"id":"https://openalex.org/keywords/clinical-practice","display_name":"Clinical Practice","score":0.42362940311431885},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3583541512489319},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.23058104515075684},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.1592797040939331},{"id":"https://openalex.org/keywords/family-medicine","display_name":"Family medicine","score":0.11404773592948914},{"id":"https://openalex.org/keywords/alternative-medicine","display_name":"Alternative medicine","score":0.09799322485923767}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.8114957809448242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190361618995667},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.4770047962665558},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.45748817920684814},{"id":"https://openalex.org/C3018822202","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Patient data","level":2,"score":0.4364742636680603},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4333048164844513},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.42362940311431885},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3583541512489319},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.23058104515075684},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.1592797040939331},{"id":"https://openalex.org/C512399662","wikidata":"https://www.wikidata.org/wiki/Q3505712","display_name":"Family medicine","level":1,"score":0.11404773592948914},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.09799322485923767},{"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/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3368555.3384455","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368555.3384455","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368555.3384455","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on Health, Inference, and Learning","raw_type":"proceedings-article"},{"id":"pmid:34350426","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34350426","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":"Proceedings of the ACM Conference on Health, Inference, and Learning","raw_type":null},{"id":"pmh:oai:dspace.mit.edu:1721.1/146118","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/146118","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM|ACM Conference on Health, Inference, and Learning","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"pmh:oai:pubmedcentral.nih.gov:8330601","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8330601","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc ACM Conf Health Inference Learn (2020)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3368555.3384455","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368555.3384455","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368555.3384455","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on Health, Inference, and Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3012137864.pdf","grobid_xml":"https://content.openalex.org/works/W3012137864.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1034374084","https://openalex.org/W1995228216","https://openalex.org/W2117539524","https://openalex.org/W2160987310","https://openalex.org/W2161880183","https://openalex.org/W2183114698","https://openalex.org/W2190333735","https://openalex.org/W2396881363","https://openalex.org/W2484962737","https://openalex.org/W2525778437","https://openalex.org/W2605961855","https://openalex.org/W2621075239","https://openalex.org/W2622474949","https://openalex.org/W2624380710","https://openalex.org/W2626778328","https://openalex.org/W2783186845","https://openalex.org/W2807251972","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2919101625","https://openalex.org/W2950813464","https://openalex.org/W2963738950","https://openalex.org/W2963956191","https://openalex.org/W2970771982","https://openalex.org/W2970971581","https://openalex.org/W2979826702","https://openalex.org/W2980282514","https://openalex.org/W2986266667","https://openalex.org/W2996428491","https://openalex.org/W3010607409","https://openalex.org/W3012137864","https://openalex.org/W3119509555","https://openalex.org/W4256295604"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W2319837024","https://openalex.org/W2343500026","https://openalex.org/W2390627310","https://openalex.org/W2413664130","https://openalex.org/W4304208754","https://openalex.org/W2191601217"],"abstract_inverted_index":{"The":[0],"ability":[1],"of":[2,15,47,73,139,155,173,191,196,198,202],"caregivers":[3],"and":[4,18,36,76,102,149,170,200],"investigators":[5],"to":[6,12,22,28,40,125,206],"share":[7],"patient":[8,42,74,92,104],"data":[9,55,93,105],"is":[10,25,50,59,94,106,210],"fundamental":[11],"many":[13,61],"areas":[14],"clinical":[16,156],"practice":[17,78],"biomedical":[19],"research.":[20],"Prior":[21],"sharing,":[23],"it":[24],"often":[26,95,107],"necessary":[27],"remove":[29],"identifiers":[30,63],"such":[31],"as":[32],"names,":[33],"contact":[34],"details,":[35],"dates":[37],"in":[38,77,119,129,134,186],"order":[39],"protect":[41],"privacy.":[43],"Deidentification,":[44],"the":[45,137,174,189],"process":[46],"removing":[48],"identifiers,":[49],"challenging,":[51],"however.":[52],"High-quality":[53],"annotated":[54],"for":[56,153,214],"developing":[57],"models":[58],"scarce;":[60],"target":[62],"are":[64,70],"highly":[65],"heterogenous":[66],"(for":[67],"example,":[68],"there":[69],"uncountable":[71],"variations":[72],"names);":[75],"anything":[79],"less":[80],"than":[81],"perfect":[82],"sensitivity":[83],"may":[84],"be":[85,100],"considered":[86],"a":[87,90,110,160],"failure.":[88],"As":[89],"result,":[91],"withheld":[96],"when":[97,109],"sharing":[98],"would":[99,113],"beneficial,":[101],"identifiable":[103],"divulged":[108],"deidentified":[111],"version":[112],"suffice.":[114],"In":[115,144],"recent":[116],"years,":[117],"advances":[118],"machine":[120],"learning":[121],"methods":[122],"have":[123],"led":[124],"rapid":[126],"performance":[127,176],"improvements":[128],"natural":[130],"language":[131,142],"processing":[132],"tasks,":[133],"particular":[135],"with":[136],"advent":[138],"large-scale":[140],"pretrained":[141],"models.":[143,180],"this":[145],"paper":[146],"we":[147,182],"develop":[148,207],"evaluate":[150],"an":[151],"approach":[152],"deidentification":[154],"notes":[157],"based":[158],"on":[159],"bidirectional":[161],"transformer":[162],"model.":[163],"We":[164],"propose":[165],"human":[166],"interpretable":[167],"evaluation":[168],"measures":[169],"demonstrate":[171],"state":[172],"art":[175],"against":[177],"modern":[178],"baseline":[179],"Finally,":[181],"highlight":[183],"current":[184],"challenges":[185],"deidentification,":[187],"including":[188],"absence":[190],"clear":[192],"annotation":[193],"guidelines,":[194],"lack":[195],"portability":[197],"models,":[199],"paucity":[201],"training":[203],"data.":[204],"Code":[205],"our":[208],"model":[209],"open":[211],"source,":[212],"allowing":[213],"broad":[215],"reuse.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}