{"id":"https://openalex.org/W6908606214","doi":"https://doi.org/10.26190/unsworks/24967","title":"Using machine learning for automated de-identification and clinical coding of free text data in electronic medical records","display_name":"Using machine learning for automated de-identification and clinical coding of free text data in electronic medical records","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W6908606214","doi":"https://doi.org/10.26190/unsworks/24967"},"language":"en","primary_location":{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/101260","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/101260","pdf_url":null,"source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1959.4/101260","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liu, Leibo","orcid":"https://orcid.org/0000-0002-7517-0050"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Leibo","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7517-0050","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.4724999964237213,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.4724999964237213,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.10700000077486038,"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/T10028","display_name":"Topic Modeling","score":0.08829999715089798,"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/medical-classification","display_name":"Medical classification","score":0.5561000108718872},{"id":"https://openalex.org/keywords/text-messaging","display_name":"Text messaging","score":0.5149999856948853},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48989999294281006},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4876999855041504},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.44940000772476196},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.42890000343322754},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.38510000705718994},{"id":"https://openalex.org/keywords/protected-health-information","display_name":"Protected health information","score":0.3686000108718872},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.358599990606308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.646399974822998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6459000110626221},{"id":"https://openalex.org/C154874363","wikidata":"https://www.wikidata.org/wiki/Q3518464","display_name":"Medical classification","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C3018949938","wikidata":"https://www.wikidata.org/wiki/Q17166101","display_name":"Text messaging","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.38510000705718994},{"id":"https://openalex.org/C133652896","wikidata":"https://www.wikidata.org/wiki/Q7251300","display_name":"Protected health information","level":5,"score":0.3686000108718872},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.3555999994277954},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C3018060332","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic medical record","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C63527458","wikidata":"https://www.wikidata.org/wiki/Q5133829","display_name":"Clinical decision support system","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C45827449","wikidata":"https://www.wikidata.org/wiki/Q5270338","display_name":"Diagnosis code","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C2989236134","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Patient care","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/101260","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/101260","pdf_url":null,"source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},{"id":"doi:10.26190/unsworks/24967","is_oa":true,"landing_page_url":"https://doi.org/10.26190/unsworks/24967","pdf_url":null,"source":{"id":"https://openalex.org/S7407053176","display_name":"University of New South Wales","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dissertation"}],"best_oa_location":{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/101260","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/101260","pdf_url":null,"source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4542185366153717}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,82,232,378],"widespread":[1],"adoption":[2],"of":[3,15,26,52,65,74,96,103,131,141,157,177,188,212,221,243,276,318,350,373,394,429],"Electronic":[4],"Medical":[5,298],"Records":[6],"(EMRs)":[7],"in":[8,85,91,145,149,160,279,336],"hospitals":[9],"continues":[10],"to":[11,30,48,125,273,398],"increase":[12],"the":[13,23,27,50,87,94,101,129,155,219,251,307,319,329,334,337,347,361,370,374,383,392,418,427],"amount":[14],"patient":[16,32],"data":[17,54,90,144,269],"that":[18,78,311,417],"are":[19,44,312],"digitally":[20],"stored.":[21],"Although":[22],"primary":[24],"use":[25,162,220],"EMR":[28],"is":[29],"support":[31],"care":[33],"by":[34,167,268],"making":[35],"all":[36,369],"relevant":[37,104],"information":[38,99,105],"accessible,":[39],"governments":[40],"and":[41,63,68,100,127,138,153,199,216,265,271,324,420,440],"health":[42],"organisations":[43],"looking":[45],"for":[46,55,106,135,186,208,228,292,301,333,345,365,436,443],"ways":[47],"unleash":[49],"potential":[51,342],"these":[53,120,158,438],"secondary":[56],"purposes,":[57],"including":[58],"clinical":[59,111,139,421],"research,":[60],"disease":[61],"surveillance":[62],"automation":[64],"healthcare":[66],"processes":[67],"workflows.":[69],"EMRs":[70,92],"include":[71,93],"large":[72,408],"quantities":[73],"free":[75,88,142,189,277],"text":[76,89,143,190,225,278,385,400],"documents":[77],"contain":[79],"valuable":[80],"information.":[81],"greatest":[83],"challenges":[84],"using":[86,174,240,403],"removal":[95],"personally":[97],"identifiable":[98],"extraction":[102],"specific":[107],"tasks":[108,423],"such":[109],"as":[110,147],"coding.":[112,231],"Machine":[113],"learning-based":[114],"automated":[115,136,229],"approaches":[116,159],"can":[117,262,424],"potentially":[118],"address":[119],"challenges.":[121],"This":[122],"thesis":[123],"aims":[124],"explore":[126],"improve":[128],"performance":[130,249],"machine":[132,430],"learning":[133,179,195,245,431],"models":[134,227,397,405],"de-identification":[137,172,187,252,258,275,419],"coding":[140,367,422],"EMRs,":[146],"captured":[148],"hospital":[150],"discharge":[151,308,338,371],"summaries,":[152],"facilitate":[154],"applications":[156],"real-world":[161],"cases.":[163],"It":[164],"does":[165],"so":[166],"1)":[168,236],"implementing":[169,200,437],"an":[170,175,193,241],"end-to-end":[171,238],"framework":[173,239],"ensemble":[176,242],"deep":[178,244],"models;":[180],"2)":[181,254],"developing":[182],"a":[183,201,297,341],"web-based":[184,257],"system":[185,260],"(DEFT)":[191,261],"with":[192,314],"interactive":[194],"loop;":[196],"3)":[197,281],"proposing":[198],"hierarchical":[202],"label-wise":[203,330],"attention":[204,331],"transformer":[205],"model":[206,286],"(HiLAT)":[207,287],"explainable":[209],"International":[210],"Classification":[211],"Diseases":[213],"(ICD)":[214],"coding;":[215],"4)":[217,354],"investigating":[218],"extreme":[222],"multi-label":[223],"long":[224,384,399],"transformer-based":[226,285,357,396,404],"ICD":[230,294,351,366],"key":[233],"findings":[234,415],"include:":[235],"An":[237,355],"base-models":[246],"achieved":[247,288,360],"excellent":[248],"on":[250,296,368,406],"task.":[253],"A":[255,282],"new":[256],"software":[259],"be":[263],"readily":[264],"easily":[266],"adopted":[267],"custodians":[270],"researchers":[272],"perform":[274],"EMRs.":[280],"novel":[283],"domain-specific":[284],"state-of-the-art":[289],"(SOTA)":[290],"results":[291,364],"predicting":[293],"codes":[295],"Information":[299],"Mart":[300],"Intensive":[302],"Care":[303],"(MIMIC-III)":[304],"dataset":[305,376],"comprising":[306],"summaries":[309,372],"(n=12,808)":[310],"coded":[313],"at":[315],"least":[316],"one":[317],"most":[320],"50":[321],"frequent":[322],"diagnosis":[323],"procedure":[325],"codes.":[326],"In":[327],"addition,":[328],"scores":[332],"tokens":[335],"summary":[339],"presented":[340],"explainability":[343],"tool":[344],"checking":[346],"face":[348],"validity":[349],"code":[352],"predictions.":[353],"optimised":[356],"model,":[358],"PLM-ICD,":[359],"latest":[362],"SOTA":[363],"MIMIC-III":[375],"(n=59,652).":[377],"segmentation":[379],"method,":[380],"which":[381],"split":[382],"consecutively":[386],"into":[387],"multiple":[388],"small":[389],"chunks,":[390],"addressed":[391],"problem":[393],"applying":[395],"datasets.":[401],"However,":[402],"extremely":[407],"label":[409],"sets":[410],"needs":[411],"further":[412,444],"research.":[413,445],"These":[414],"demonstrate":[416],"benefit":[425],"from":[426],"application":[428],"approaches,":[432,439],"present":[433],"practical":[434],"tools":[435],"highlight":[441],"priorities":[442]},"counts_by_year":[],"updated_date":"2026-07-13T05:41:17.278356","created_date":"2025-10-10T00:00:00"}