{"id":"https://openalex.org/W1988999151","doi":"https://doi.org/10.1145/2808719.2808752","title":"A frequency-filtering strategy of obtaining PHI-free sentences from clinical data repository","display_name":"A frequency-filtering strategy of obtaining PHI-free sentences from clinical data repository","publication_year":2015,"publication_date":"2015-09-09","ids":{"openalex":"https://openalex.org/W1988999151","doi":"https://doi.org/10.1145/2808719.2808752","mag":"1988999151"},"language":"en","primary_location":{"id":"doi:10.1145/2808719.2808752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808719.2808752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics","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/A5103234379","display_name":"Dingcheng Li","orcid":"https://orcid.org/0000-0002-1630-4338"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dingcheng Li","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023661219","display_name":"Majid Rastegar-Mojarad","orcid":"https://orcid.org/0000-0001-6962-3554"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Majid Rastegar-Mojarad","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009338463","display_name":"Ravikumar Komandur Elayavilli","orcid":null},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravikumar Komandur Elayavilli","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080116611","display_name":"Yanshan Wang","orcid":"https://orcid.org/0000-0003-4433-7839"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanshan Wang","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044857258","display_name":"Saeed Mehrabi","orcid":"https://orcid.org/0000-0003-0994-6428"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saeed Mehrabi","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397981","display_name":"Yue Yu","orcid":"https://orcid.org/0000-0002-7620-6078"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Yu","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063986559","display_name":"Sunghwan Sohn","orcid":"https://orcid.org/0000-0001-8256-2602"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunghwan Sohn","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718347","display_name":"Yanpeng Li","orcid":"https://orcid.org/0000-0002-4037-0001"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanpeng Li","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014602642","display_name":"Naveed Afzal","orcid":"https://orcid.org/0000-0001-8878-0256"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naveed Afzal","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101585391","display_name":"Hongfang Liu","orcid":"https://orcid.org/0000-0003-2570-3741"},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongfang Liu","raw_affiliation_strings":["Mayo Clinic, Rochester, Minnesota"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, Minnesota","institution_ids":["https://openalex.org/I1330342723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5103234379"],"corresponding_institution_ids":["https://openalex.org/I1330342723"],"apc_list":null,"apc_paid":null,"fwci":0.5835,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.6769776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"315","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9955999851226807,"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":0.9955999851226807,"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/T10028","display_name":"Topic Modeling","score":0.9948999881744385,"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":0.9815000295639038,"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":0.6329120397567749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4163898825645447},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.404718816280365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33581674098968506},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3233081102371216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6329120397567749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4163898825645447},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.404718816280365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33581674098968506},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3233081102371216}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2808719.2808752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808719.2808752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W45053571","https://openalex.org/W50158085","https://openalex.org/W56293434","https://openalex.org/W169879241","https://openalex.org/W1863940422","https://openalex.org/W1995228216","https://openalex.org/W2002514548","https://openalex.org/W2012466471","https://openalex.org/W2037968453","https://openalex.org/W2046220449","https://openalex.org/W2056208260","https://openalex.org/W2061848042","https://openalex.org/W2069870853","https://openalex.org/W2101374419","https://openalex.org/W2119047901","https://openalex.org/W2119067110","https://openalex.org/W2119738171","https://openalex.org/W2123442489","https://openalex.org/W2128004504","https://openalex.org/W2133362931","https://openalex.org/W2140663467","https://openalex.org/W2141975087","https://openalex.org/W2146089916","https://openalex.org/W2156061936","https://openalex.org/W2158300770","https://openalex.org/W2158645702","https://openalex.org/W2159024459","https://openalex.org/W2159583324","https://openalex.org/W2161880183","https://openalex.org/W2171548451","https://openalex.org/W2186301176","https://openalex.org/W2251991755","https://openalex.org/W2394640408","https://openalex.org/W2476464628","https://openalex.org/W2997209736","https://openalex.org/W4234664880","https://openalex.org/W4255574744","https://openalex.org/W6606851220"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Clinical":[0],"natural":[1],"language":[2],"processing":[3],"(NLP)":[4],"has":[5],"become":[6],"indispensable":[7],"in":[8,131],"the":[9,27,45,61,72,83,101,116,139,156],"secondary":[10],"use":[11,73],"of":[12,29,48,51,63,74,91,124,127,158],"electronic":[13],"medical":[14],"records":[15],"(EMRs).":[16],"However,":[17,44],"it":[18],"is":[19,40,98],"found":[20],"that":[21,103,118],"current":[22],"clinical":[23],"NLP":[24],"tools":[25],"face":[26],"problem":[28,39],"portability":[30],"among":[31,163],"different":[32],"institutes.":[33,164],"An":[34],"ideal":[35],"solution":[36],"to":[37,78,108],"this":[38,57,68],"cross-institutional":[41],"data":[42],"sharing.":[43],"legal":[46],"enforcement":[47],"no":[49,110,148],"revelation":[50],"protected":[52],"health":[53],"information":[54],"(PHI)":[55],"obstructs":[56],"practice":[58],"even":[59],"with":[60,142],"availability":[62],"state-of-the-art":[64],"de-identification":[65],"tools.":[66],"In":[67],"paper,":[69],"we":[70],"investigated":[71],"a":[75,88,121],"frequency-filtering":[76],"approach":[77,97],"extract":[79],"PHI-free":[80],"sentences":[81,104,162],"utilizing":[82],"Enterprise":[84],"Data":[85],"Trust":[86],"(EDT),":[87],"large":[89,122],"collection":[90],"EMRs":[92],"at":[93],"Mayo":[94],"Clinic.":[95],"Our":[96],"based":[99],"on":[100,138],"assumption":[102,113],"appearing":[105],"frequently":[106],"tend":[107],"contain":[109],"PHI.":[111],"This":[112],"originates":[114],"from":[115],"observation":[117],"there":[119],"exist":[120],"number":[123],"redundant":[125],"descriptions":[126],"similar":[128],"patient":[129],"conditions":[130],"EDT.":[132],"Both":[133],"manual":[134],"and":[135],"automatic":[136],"evaluations":[137],"sentence":[140],"set":[141],"frequencies":[143],"higher":[144],"than":[145],"one":[146],"show":[147],"PHI":[149],"are":[150],"found.":[151],"The":[152],"promising":[153],"results":[154],"demonstrate":[155],"potential":[157],"sharing":[159],"highly":[160],"frequent":[161]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}