{"id":"https://openalex.org/W2211352316","doi":"https://doi.org/10.1109/bigdata.2015.7363889","title":"Data deidentification in medical transcriptions using regular expressions and machine learning","display_name":"Data deidentification in medical transcriptions using regular expressions and machine learning","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2211352316","doi":"https://doi.org/10.1109/bigdata.2015.7363889","mag":"2211352316"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","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/A5006403617","display_name":"Joshua Seeger","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joshua Seeger","raw_affiliation_strings":["NORC at the University of Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"NORC at the University of Chicago, Chicago, IL","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011178134","display_name":"Aron Culotta","orcid":"https://orcid.org/0000-0003-2660-7575"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aron Culotta","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034379903","display_name":"Jason Keller","orcid":"https://orcid.org/0000-0001-9839-7293"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Keller","raw_affiliation_strings":["NORC at the University of Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"NORC at the University of Chicago, Chicago, IL","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031045273","display_name":"Patrick van Kessel","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick van Kessel","raw_affiliation_strings":["NORC at the University of Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"NORC at the University of Chicago, Chicago, IL","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015043458","display_name":"Michael Jugovich","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Jugovich","raw_affiliation_strings":["NORC at the University of Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"NORC at the University of Chicago, Chicago, IL","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006403617"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.0682208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1322","last_page":"1323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9758999943733215,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9758999943733215,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.97079998254776,"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":0.9588000178337097,"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/computer-science","display_name":"Computer science","score":0.767910897731781},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5694790482521057},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5498669743537903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5474753975868225},{"id":"https://openalex.org/keywords/medical-information","display_name":"Medical information","score":0.4554455280303955},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45067811012268066},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.22922199964523315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767910897731781},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5694790482521057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5498669743537903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5474753975868225},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.4554455280303955},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45067811012268066},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.22922199964523315},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320333059","display_name":"Nutrition Obesity Research Center, University of North Carolina","ror":"https://ror.org/02f0bym65"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3136979370","https://openalex.org/W3204019825"],"abstract_inverted_index":{"A":[0],"system":[1,31],"is":[2,32],"developed":[3,44],"to":[4],"redact":[5],"personally":[6],"identifiable":[7],"information":[8],"(PII)":[9],"through":[10],"a":[11],"combination":[12],"of":[13,27],"entity":[14],"recognition,":[15],"regular":[16],"expressions,":[17],"and":[18,34],"machine":[19],"learning":[20],"with":[21,36],"very":[22],"high":[23],"precision":[24],"from":[25],"millions":[26],"medical":[28,39],"transcriptions.":[29],"This":[30],"trained":[33],"tested":[35],"manually":[37],"redacted":[38],"transcriptions":[40],"using":[41],"an":[42],"internally":[43],"coding":[45],"system,":[46],"providing":[47],"double":[48],"blind":[49],"classification":[50],"capabilities.":[51]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
