{"id":"https://openalex.org/W2786382696","doi":"https://doi.org/10.1109/ssci.2017.8285286","title":"PHIs (Protected Health Information) identification from free text clinical records based on machine learning","display_name":"PHIs (Protected Health Information) identification from free text clinical records based on machine learning","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2786382696","doi":"https://doi.org/10.1109/ssci.2017.8285286","mag":"2786382696"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2017.8285286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8285286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5112500490","display_name":"Kunal Rajput","orcid":null},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Kunal Rajput","raw_affiliation_strings":["Faculty of ESTEM, University of Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of ESTEM, University of Canberra, Australia","institution_ids":["https://openalex.org/I188329596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083396008","display_name":"Girija Chetty","orcid":"https://orcid.org/0000-0001-6264-8644"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Girija Chetty","raw_affiliation_strings":["Faculty of ESTEM, University of Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of ESTEM, University of Canberra, Australia","institution_ids":["https://openalex.org/I188329596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078446059","display_name":"Rachel Davey","orcid":"https://orcid.org/0000-0002-6117-2872"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rachel Davey","raw_affiliation_strings":["Faculty of Health, University of Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Health, University of Canberra, Australia","institution_ids":["https://openalex.org/I188329596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112500490"],"corresponding_institution_ids":["https://openalex.org/I188329596"],"apc_list":null,"apc_paid":null,"fwci":0.195,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65063266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"16","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9976999759674072,"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/T10582","display_name":"Ethics in Clinical Research","score":0.9793000221252441,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protected-health-information","display_name":"Protected health information","score":0.8682533502578735},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7658851742744446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7617071270942688},{"id":"https://openalex.org/keywords/confidentiality","display_name":"Confidentiality","score":0.7021081447601318},{"id":"https://openalex.org/keywords/patient-confidentiality","display_name":"Patient confidentiality","score":0.6291275024414062},{"id":"https://openalex.org/keywords/informatics","display_name":"Informatics","score":0.5945016145706177},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.5919676423072815},{"id":"https://openalex.org/keywords/health-informatics","display_name":"Health informatics","score":0.5533209443092346},{"id":"https://openalex.org/keywords/text-messaging","display_name":"Text messaging","score":0.53318190574646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4536636471748352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4212518632411957},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4098508358001709},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.3679881691932678},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36087673902511597},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3217923045158386},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1892646849155426},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10615167021751404}],"concepts":[{"id":"https://openalex.org/C133652896","wikidata":"https://www.wikidata.org/wiki/Q7251300","display_name":"Protected health information","level":5,"score":0.8682533502578735},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7658851742744446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617071270942688},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.7021081447601318},{"id":"https://openalex.org/C2909332208","wikidata":"https://www.wikidata.org/wiki/Q2669281","display_name":"Patient confidentiality","level":3,"score":0.6291275024414062},{"id":"https://openalex.org/C191630685","wikidata":"https://www.wikidata.org/wiki/Q4027615","display_name":"Informatics","level":2,"score":0.5945016145706177},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.5919676423072815},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.5533209443092346},{"id":"https://openalex.org/C3018949938","wikidata":"https://www.wikidata.org/wiki/Q17166101","display_name":"Text messaging","level":2,"score":0.53318190574646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4536636471748352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212518632411957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4098508358001709},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.3679881691932678},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36087673902511597},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3217923045158386},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1892646849155426},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10615167021751404},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci.2017.8285286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8285286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1019512417","https://openalex.org/W1600806036","https://openalex.org/W1986398135","https://openalex.org/W1995228216","https://openalex.org/W2000133061","https://openalex.org/W2046020929","https://openalex.org/W2055405704","https://openalex.org/W2109206523","https://openalex.org/W2117273822","https://openalex.org/W2121512846","https://openalex.org/W2132724073","https://openalex.org/W2133362931","https://openalex.org/W2142406320","https://openalex.org/W2159024459","https://openalex.org/W2160987310","https://openalex.org/W2161140849","https://openalex.org/W2190333735","https://openalex.org/W2425617182","https://openalex.org/W6635744232","https://openalex.org/W6717661675"],"related_works":["https://openalex.org/W2974383165","https://openalex.org/W2786382696","https://openalex.org/W2008068951","https://openalex.org/W4281718931","https://openalex.org/W2408088124","https://openalex.org/W2419607224","https://openalex.org/W2052110252","https://openalex.org/W1998390576","https://openalex.org/W4302340031","https://openalex.org/W2294303695"],"abstract_inverted_index":{"To":[0],"preserve":[1],"patient":[2],"confidentiality,":[3],"there":[4],"is":[5,46],"a":[6],"need":[7],"to":[8],"identify":[9],"PHIs":[10,92],"(Protected":[11],"Health":[12],"Information)":[13],"from":[14,93,122],"free":[15,96],"text":[16,17,82,97],"clinical":[18,98],"records,":[19,99],"and":[20,50,67,84,102],"such":[21],"sensitive":[22],"information":[23,62],"must":[24],"either":[25],"be":[26],"removed":[27],"or":[28,56],"replaced.":[29],"Identification":[30],"of":[31,41,59,64,91,109],"the":[32,110,128],"PHI's":[33],"are":[34,63],"normally":[35],"performed":[36],"manually":[37],"on":[38,80],"large":[39],"sets":[40],"structured":[42],"EHR":[43],"databases,":[44],"which":[45],"time-consuming,":[47],"prohibitively":[48],"expensive":[49],"error-prone.":[51],"Hence,":[52],"methods":[53],"for":[54,88,115,124],"automatic":[55,89],"semi-automatic":[57],"identification":[58,90],"personal":[60],"health":[61],"significant":[65],"scientific":[66],"commercial":[68],"interest.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"an":[75],"innovative":[76],"computational":[77],"framework":[78,113],"based":[79],"novel":[81],"mining":[83],"machine":[85],"learning":[86],"algorithms":[87],"massive,":[94],"unstructured":[95],"discharge":[100],"summaries":[101],"other":[103],"care":[104],"documents.":[105],"The":[106],"experimental":[107],"evaluation":[108],"proposed":[111],"algorithmic":[112],"development,":[114],"several":[116],"publicly":[117],"available":[118],"i2b2":[119],"challenge":[120],"datasets":[121],"Informatics":[123],"Integrating":[125],"Biology":[126],"&":[127],"Bedside":[129],"(i2b2)":[130],"shared":[131],"tasks,":[132],"has":[133],"shown":[134],"promising":[135],"outcomes.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
