{"id":"https://openalex.org/W1968534217","doi":"https://doi.org/10.1145/1882992.1883019","title":"An evaluation of feature sets and sampling techniques for de-identification of medical records","display_name":"An evaluation of feature sets and sampling techniques for de-identification of medical records","publication_year":2010,"publication_date":"2010-11-11","ids":{"openalex":"https://openalex.org/W1968534217","doi":"https://doi.org/10.1145/1882992.1883019","mag":"1968534217"},"language":"en","primary_location":{"id":"doi:10.1145/1882992.1883019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882992.1883019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM International Health Informatics Symposium","raw_type":"proceedings-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/A5027865441","display_name":"James Gardner","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"James Gardner","raw_affiliation_strings":["Emory University, Atlanta, GA, USA","Emory University, atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Emory University, atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078394535","display_name":"Li Xiong","orcid":"https://orcid.org/0000-0001-7354-0428"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Xiong","raw_affiliation_strings":["Emory University, Atlanta, GA, USA","Emory University, atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Emory University, atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704639","display_name":"Fusheng Wang","orcid":"https://orcid.org/0000-0002-9369-9361"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fusheng Wang","raw_affiliation_strings":["Emory University, Atlanta, GA, USA","Emory University, atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Emory University, atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105024689","display_name":"Andrew Post","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Post","raw_affiliation_strings":["Emory University, Atlanta, GA, USA","Emory University, atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Emory University, atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072946826","display_name":"Joel Saltz","orcid":"https://orcid.org/0000-0002-3451-2165"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joel Saltz","raw_affiliation_strings":["Emory University, Atlanta, GA, USA","Emory University, atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Emory University, atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033155973","display_name":"Tyrone Grandison","orcid":"https://orcid.org/0000-0003-1989-3913"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyrone Grandison","raw_affiliation_strings":["IBM Services Research, Hawthorne, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Services Research, Hawthorne, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027865441"],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":null,"apc_paid":null,"fwci":3.716,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92953082,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9961000084877014,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9961000084877014,"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":0.9933000206947327,"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":0.9909999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7188540697097778},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6655873656272888},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6505628824234009},{"id":"https://openalex.org/keywords/health-informatics","display_name":"Health informatics","score":0.5750975608825684},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5462973713874817},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5319360494613647},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5007107257843018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4111667573451996},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.391341894865036},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37056320905685425},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.18825140595436096},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.13215097784996033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188540697097778},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6655873656272888},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6505628824234009},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.5750975608825684},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5462973713874817},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5319360494613647},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5007107257843018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4111667573451996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.391341894865036},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37056320905685425},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.18825140595436096},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.13215097784996033},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1882992.1883019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882992.1883019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM International Health Informatics Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.3","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.3","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mathcs.emory.edu/~lxiong/research/pub/ihi2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W19235523","https://openalex.org/W1558796178","https://openalex.org/W1863940422","https://openalex.org/W1995228216","https://openalex.org/W2007894602","https://openalex.org/W2012466471","https://openalex.org/W2021641767","https://openalex.org/W2051434435","https://openalex.org/W2128004504","https://openalex.org/W2140663467","https://openalex.org/W2142261479","https://openalex.org/W2147880316","https://openalex.org/W2160987310","https://openalex.org/W2162800060","https://openalex.org/W2169730138","https://openalex.org/W2503315106","https://openalex.org/W4231748293"],"related_works":["https://openalex.org/W3008173435","https://openalex.org/W3200179079","https://openalex.org/W4293072910","https://openalex.org/W2968586400","https://openalex.org/W2963749793","https://openalex.org/W2942650110","https://openalex.org/W3017600792","https://openalex.org/W2950010088","https://openalex.org/W4311106677","https://openalex.org/W4306175410"],"abstract_inverted_index":{"De-identification":[0],"of":[1,6,21,61,68,85,92,102],"text":[2],"medical":[3,22],"records":[4],"is":[5,78],"critical":[7],"importance":[8],"in":[9,14,72],"any":[10],"health":[11],"informatics":[12],"system":[13,54],"order":[15],"to":[16,48,80],"facilitate":[17],"research":[18],"and":[19,52,66,89,94,111],"sharing":[20],"records.":[23],"While":[24],"statistical":[25],"learning":[26],"based":[27],"techniques":[28],"have":[29],"shown":[30],"promising":[31],"results":[32],"for":[33,46],"de-identification":[34],"purposes,":[35],"few":[36],"such":[37],"systems":[38],"are":[39],"publicly":[40],"available.":[41],"It":[42],"remains":[43],"a":[44,58],"challenge":[45],"practitioners":[47],"build":[49],"an":[50],"accurate":[51],"efficient":[53],"as":[55],"it":[56],"involves":[57],"significant":[59],"amount":[60],"feature":[62,87],"engineering,":[63],"i.e.":[64],"creation":[65],"examination":[67],"new":[69],"features":[70],"used":[71],"the":[73,83,98],"system.":[74],"A":[75],"comprehensive":[76],"evaluation":[77],"needed":[79],"thoroughly":[81],"understand":[82],"effects":[84],"different":[86],"sets":[88],"potential":[90],"impacts":[91],"sampling":[93],"their":[95],"trade-offs":[96],"between":[97],"often":[99],"conflicting":[100],"goals":[101],"precision":[103],"(or":[104,109],"positive":[105],"predictive":[106],"value),":[107],"recall":[108],"sensitivity),":[110],"efficiency.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}