{"id":"https://openalex.org/W1481556729","doi":null,"title":"Generalizability and comparison of automatic clinical text de-identification methods and resources.","display_name":"Generalizability and comparison of automatic clinical text de-identification methods and resources.","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1481556729","mag":"1481556729","pmid":"https://pubmed.ncbi.nlm.nih.gov/23304289","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3540471"},"language":"en","primary_location":{"id":"pmh:oai:pubmedcentral.nih.gov:3540471","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3540471","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,"listed_in":[],"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":"AMIA Annu Symp Proc","raw_type":"Text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3540471","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110232320","display_name":"\u00d3scar Ferr\u00e1ndez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"\u00d3scar Ferr\u00e1ndez","raw_affiliation_strings":["Department of Biomedical Informatics, University of Utah, Salt Lake City, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008552631","display_name":"Brett R. South","orcid":"https://orcid.org/0000-0003-1178-0711","observed_orcids":["https://orcid.org/0000-0003-1178-0711"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brett R South","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113710224","display_name":"Shuying Shen","orcid":"https://orcid.org/0009-0006-0817-0719","observed_orcids":["https://orcid.org/0009-0006-0817-0719"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuying Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040206439","display_name":"Jeff Friedlin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"F Jeff Friedlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078072232","display_name":"Matthew H. Samore","orcid":"https://orcid.org/0000-0002-4862-9196","observed_orcids":["https://orcid.org/0000-0002-4862-9196"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew H Samore","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"St\u00e9phane M Meystre","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"St\u00e9phane M Meystre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1608,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79454005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"2012","issue":null,"first_page":"199","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9491999745368958,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9491999745368958,"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/T14029","display_name":"Thoreau and American Literature","score":0.015699999406933784,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.0052999998442828655,"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/personal-health-information","display_name":"personal health data","score":0.6029999852180481},{"id":"https://openalex.org/keywords/patient-privacy","display_name":"patient privacy","score":0.6069999933242798},{"id":"https://openalex.org/keywords/generalizability","display_name":"generalizability","score":0.6539999842643738},{"id":"https://openalex.org/keywords/model-transportability","display_name":"model portability","score":0.7599999904632568},{"id":"https://openalex.org/keywords/mist","display_name":"mist","score":0.9169999957084656},{"id":"https://openalex.org/keywords/hides","display_name":"hides","score":0.9950000047683716},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"precision and recall","score":0.44999998807907104},{"id":"https://openalex.org/keywords/health-informatics","display_name":"health informatics","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7793293595314026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71860671043396},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6922774314880371},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6852163672447205},{"id":"https://openalex.org/C133652896","wikidata":"https://www.wikidata.org/wiki/Q7251300","display_name":"Protected health information","level":5,"score":0.6362674832344055},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6315505504608154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607754111289978},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.5666834712028503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4807269871234894},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.430469274520874},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.42851829528808594},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4192241430282593},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38965585827827454},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3567746579647064},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.26333773136138916},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10384353995323181},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014493","descriptor_name":"United States Department of Veterans Affairs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020408","descriptor_name":"Health Insurance Portability and Accountability Act","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}],"locations_count":3,"locations":[{"id":"pmh:oai:pubmedcentral.nih.gov:3540471","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3540471","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,"listed_in":[],"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":"AMIA Annu Symp Proc","raw_type":"Text"},{"id":"pmid:23304289","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23304289","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,"listed_in":[],"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":"AMIA ... Annual Symposium proceedings. AMIA Symposium","raw_type":"Comparative Study"},{"id":"mag:1481556729","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23304289","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:3540471","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3540471","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,"listed_in":[],"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":"AMIA Annu Symp Proc","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.6240000128746033,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W50158085","https://openalex.org/W1863940422","https://openalex.org/W1995228216","https://openalex.org/W2012466471","https://openalex.org/W2015620729","https://openalex.org/W2068882115","https://openalex.org/W2096765155","https://openalex.org/W2118585731","https://openalex.org/W2140663467","https://openalex.org/W2146089916","https://openalex.org/W2153635508","https://openalex.org/W2156061936","https://openalex.org/W2160987310","https://openalex.org/W2161880183","https://openalex.org/W2181718862"],"related_works":["https://openalex.org/W2158645702","https://openalex.org/W2065784179","https://openalex.org/W2251316980","https://openalex.org/W3030919230","https://openalex.org/W2105141860","https://openalex.org/W4389814305","https://openalex.org/W2574739597","https://openalex.org/W4391223857","https://openalex.org/W4414979271","https://openalex.org/W4412819847"],"abstract_inverted_index":{"In":[0],"this":[1,51],"paper,":[2],"we":[3],"present":[4],"an":[5],"evaluation":[6],"of":[7,73],"the":[8,24,59,69,74,125],"hybrid":[9],"best-of-breed":[10],"automated":[11],"VHA":[12,25,56],"(Veteran's":[13],"Health":[14],"Administration)":[15],"clinical":[16,46],"text":[17,38],"de-identification":[18,62],"system,":[19],"nicknamed":[20],"BoB,":[21],"developed":[22],"within":[23],"Consortium":[26],"for":[27,50,96,124],"Healthcare":[28],"Informatics":[29],"Research.":[30],"We":[31],"also":[32,91],"evaluate":[33],"two":[34],"available":[35],"machine":[36],"learning-based":[37],"de-identifications":[39],"systems:":[40],"MIST":[41,101],"and":[42,58,71,90,102,115],"HIDE.":[43],"Two":[44],"different":[45,78],"corpora":[47],"were":[48],"used":[49],"evaluation:":[52],"a":[53],"manually":[54],"annotated":[55],"corpus,":[57],"2006":[60],"i2b2":[61],"challenge":[63],"corpus.":[64],"These":[65],"experiments":[66],"focus":[67],"on":[68],"generalizability":[70],"portability":[72],"classification":[75],"models":[76],"across":[77],"document":[79,99],"sources.":[80],"BoB":[81],"demonstrated":[82],"good":[83],"recall":[84,118],"(92.6%),":[85],"satisfactorily":[86],"prioritizing":[87],"patient":[88],"privacy,":[89],"achieved":[92],"competitive":[93,106],"precision":[94,113],"(83.6%)":[95],"preserving":[97],"subsequent":[98],"interpretability.":[100],"HIDE":[103],"reached":[104],"very":[105],"results,":[107],"in":[108],"most":[109,126],"cases":[110],"with":[111],"high":[112],"(92.6%":[114],"93.6%),":[116],"although":[117],"was":[119],"sometimes":[120],"lower":[121],"than":[122],"desired":[123],"sensitive":[127],"PHI":[128],"categories.":[129]},"counts_by_year":[{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
