{"id":"https://openalex.org/W3083683925","doi":"https://doi.org/10.1186/s40537-020-00351-4","title":"Survey on RNN and CRF models for de-identification of medical free text","display_name":"Survey on RNN and CRF models for de-identification of medical free text","publication_year":2020,"publication_date":"2020-09-04","ids":{"openalex":"https://openalex.org/W3083683925","doi":"https://doi.org/10.1186/s40537-020-00351-4","mag":"3083683925"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-020-00351-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-020-00351-4","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00351-4","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00351-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004094853","display_name":"Joffrey L. Leevy","orcid":"https://orcid.org/0000-0002-7079-7540"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joffrey L. Leevy","raw_affiliation_strings":["Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA"],"raw_orcid":"https://orcid.org/0000-0002-7079-7540","affiliations":[{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089170562","display_name":"Taghi M. Khoshgoftaar","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taghi M. Khoshgoftaar","raw_affiliation_strings":["Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073869382","display_name":"Flavio Villanustre","orcid":"https://orcid.org/0000-0003-4373-4250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Flavio Villanustre","raw_affiliation_strings":["LexisNexis Business Information Solutions, 245 Peachtree Center Avenue, Atlanta, GA, 30303, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LexisNexis Business Information Solutions, 245 Peachtree Center Avenue, Atlanta, GA, 30303, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004094853"],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":3.3973,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.93825264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"7","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9962000250816345,"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":0.9962000250816345,"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":0.995199978351593,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9894000291824341,"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/overfitting","display_name":"Overfitting","score":0.9056581258773804},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.8278640508651733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7837547063827515},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7015196084976196},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6901366710662842},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6132130026817322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6128720641136169},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.4122858941555023},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3361290693283081},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.1084887683391571}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9056581258773804},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8278640508651733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837547063827515},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7015196084976196},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6901366710662842},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6132130026817322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6128720641136169},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.4122858941555023},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3361290693283081},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.1084887683391571},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-020-00351-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-020-00351-4","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00351-4","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a09ca30997834f4aa4b24c4abb792ff6","is_oa":true,"landing_page_url":"https://doaj.org/article/a09ca30997834f4aa4b24c4abb792ff6","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 7, Iss 1, Pp 1-22 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-020-00351-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-020-00351-4","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00351-4","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5416735113","display_name":"MRI: Acquisition of Big Data Training and Research Laboratory","funder_award_id":"1427536","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6293531692","display_name":null,"funder_award_id":"CNS-1427536","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310801","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387"},{"id":"https://openalex.org/F4320317380","display_name":"Universidad del Atl\u00e1ntico","ror":"https://ror.org/05mm1w714"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3083683925.pdf","grobid_xml":"https://content.openalex.org/works/W3083683925.grobid-xml"},"referenced_works_count":90,"referenced_works":["https://openalex.org/W27189800","https://openalex.org/W28412257","https://openalex.org/W45053571","https://openalex.org/W114517082","https://openalex.org/W189514790","https://openalex.org/W298172948","https://openalex.org/W1485981043","https://openalex.org/W1499864241","https://openalex.org/W1966106237","https://openalex.org/W1981276685","https://openalex.org/W1995228216","https://openalex.org/W2015620729","https://openalex.org/W2016648380","https://openalex.org/W2020648356","https://openalex.org/W2028138594","https://openalex.org/W2046788142","https://openalex.org/W2051434435","https://openalex.org/W2065784179","https://openalex.org/W2079735306","https://openalex.org/W2082907066","https://openalex.org/W2095178814","https://openalex.org/W2099419573","https://openalex.org/W2100184389","https://openalex.org/W2100796029","https://openalex.org/W2110485445","https://openalex.org/W2111362445","https://openalex.org/W2123442489","https://openalex.org/W2124216778","https://openalex.org/W2124290836","https://openalex.org/W2129999749","https://openalex.org/W2146302296","https://openalex.org/W2147880316","https://openalex.org/W2153848201","https://openalex.org/W2154137718","https://openalex.org/W2160134066","https://openalex.org/W2183114698","https://openalex.org/W2190333735","https://openalex.org/W2251316980","https://openalex.org/W2293634267","https://openalex.org/W2296283641","https://openalex.org/W2313711614","https://openalex.org/W2314398369","https://openalex.org/W2318802957","https://openalex.org/W2396881363","https://openalex.org/W2414426089","https://openalex.org/W2488984245","https://openalex.org/W2563832757","https://openalex.org/W2565017937","https://openalex.org/W2589634835","https://openalex.org/W2593437763","https://openalex.org/W2610743175","https://openalex.org/W2621075239","https://openalex.org/W2622474949","https://openalex.org/W2624380710","https://openalex.org/W2744160972","https://openalex.org/W2767787532","https://openalex.org/W2785531515","https://openalex.org/W2787267295","https://openalex.org/W2804603962","https://openalex.org/W2892826221","https://openalex.org/W2894037224","https://openalex.org/W2898933544","https://openalex.org/W2899434936","https://openalex.org/W2913340405","https://openalex.org/W2942069880","https://openalex.org/W2944851425","https://openalex.org/W2953405390","https://openalex.org/W2963366932","https://openalex.org/W2963625095","https://openalex.org/W2963816430","https://openalex.org/W2963956191","https://openalex.org/W2964248614","https://openalex.org/W2966632508","https://openalex.org/W2974576727","https://openalex.org/W2980895577","https://openalex.org/W2984506903","https://openalex.org/W2987767100","https://openalex.org/W2989759966","https://openalex.org/W2990019189","https://openalex.org/W2990612605","https://openalex.org/W2993961432","https://openalex.org/W2997026866","https://openalex.org/W3004133200","https://openalex.org/W3004506153","https://openalex.org/W3039774111","https://openalex.org/W4206192903","https://openalex.org/W4232473632","https://openalex.org/W4235730433","https://openalex.org/W4285719527","https://openalex.org/W6600763685"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W4297676672","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Abstract":[0],"The":[1,87],"increasing":[2],"reliance":[3],"on":[4,51],"electronic":[5],"health":[6,81],"record":[7],"(EHR)":[8],"in":[9],"areas":[10],"such":[11],"as":[12,41],"medical":[13],"research":[14,171],"should":[15,174],"be":[16,30,138,175],"addressed":[17],"by":[18],"using":[19],"ample":[20],"safeguards":[21],"for":[22,76,177],"patient":[23],"privacy.":[24],"These":[25],"records":[26],"often":[27],"tend":[28],"to":[29,47],"big":[31],"data,":[32],"and":[33,61,72,110,132,156],"given":[34],"that":[35,173],"a":[36],"significant":[37],"portion":[38],"is":[39],"stored":[40],"free":[42,53,85],"(unstructured)":[43],"text,":[44],"we":[45,167],"decided":[46],"examine":[48],"relevant":[49],"work":[50,92],"automated":[52],"text":[54],"de-identification":[55,143],"with":[56],"recurrent":[57],"neural":[58],"network":[59],"(RNN)":[60],"conditional":[62],"random":[63],"field":[64],"(CRF)":[65],"approaches.":[66],"Both":[67],"methods":[68],"involve":[69],"machine":[70],"learning":[71],"are":[73,145],"widely":[74],"used":[75,146],"the":[77],"removal":[78],"of":[79,89,153],"protected":[80],"information":[82],"(PHI)":[83],"from":[84],"text.":[86],"outcome":[88],"our":[90,164],"survey":[91],"produced":[93],"several":[94],"informative":[95],"findings.":[96],"Firstly,":[97],"RNN":[98],"models,":[99],"particularly":[100],"long":[101],"short-term":[102],"memory":[103],"(LSTM)":[104],"algorithms,":[105],"generally":[106],"outperformed":[107],"CRF":[108,133],"models":[109,125],"also":[111,168],"other":[112],"systems,":[113],"namely":[114],"rule-based":[115],"algorithms.":[116],"Secondly,":[117],"hybrid":[118],"or":[119],"ensemble":[120],"systems":[121],"containing":[122],"joint":[123],"LSTM-CRF":[124],"showed":[126],"no":[127],"advantage":[128],"over":[129],"individual":[130],"LSTM":[131],"models.":[134],"Thirdly,":[135],"overfitting":[136],"may":[137],"an":[139],"issue":[140],"when":[141],"customized":[142],"datasets":[144],"during":[147,158],"model":[148],"training.":[149],"Finally,":[150],"statistical":[151],"validation":[152],"performance":[154],"scores":[155],"diversity":[157],"experimentation":[159],"were":[160],"largely":[161],"ignored.":[162],"In":[163],"comprehensive":[165],"survey,":[166],"identify":[169],"major":[170],"gaps":[172],"considered":[176],"future":[178],"work.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}