Please use this identifier to cite or link to this item: https://ahro.austin.org.au/austinjspui/handle/1/19959
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKhor, Richard C-
dc.contributor.authorNguyen, Anthony-
dc.contributor.authorO'Dwyer, John-
dc.contributor.authorKothari, Gargi-
dc.contributor.authorSia, Joseph-
dc.contributor.authorChang, David-
dc.contributor.authorNg, Sweet Ping-
dc.contributor.authorDuchesne, Gillian M-
dc.contributor.authorForoudi, Farshad-
dc.date2018-10-23-
dc.date.accessioned2018-12-17T00:56:00Z-
dc.date.available2018-12-17T00:56:00Z-
dc.date.issued2019-01-
dc.identifier.citationInternational journal of medical informatics 2019; 121: 53-57en_US
dc.identifier.urihttps://ahro.austin.org.au/austinjspui/handle/1/19959-
dc.description.abstractTo implement a system for unsupervised extraction of tumor stage and prognostic data in patients with genitourinary cancers using clinicopathological and radiology text. A corpus of 1054 electronic notes (clinician notes, radiology reports and pathology reports) was annotated for tumor stage, prostate specific antigen (PSA) and Gleason grade. Annotations from five clinicians were reconciled to form a gold standard dataset. A training dataset of 386 documents was sequestered. The Medtex algorithm was adapted using the training dataset. Adapted Medtex equaled or exceeded human performance in most annotations, except for implicit M stage (F-measure of 0.69 vs 0.84) and PSA (0.92 vs 0.96). Overall Medtex performed with an F-measure of 0.86 compared to human annotations of 0.92. There was significant inter-observer variability when comparing human annotators to the gold standard. The Medtex algorithm performed similarly to human annotators for extracting stage and prognostic data from varied clinical texts.en_US
dc.language.isoeng-
dc.subjectElectronic medical recorden_US
dc.subjectGenitourinary cancersen_US
dc.subjectNatural language processingen_US
dc.subjectText miningen_US
dc.subjectTumor stagingen_US
dc.titleExtracting tumour prognostic factors from a diverse electronic record dataset in genito-urinary oncology.en_US
dc.typeJournal Articleen_US
dc.identifier.journaltitleInternational journal of medical informaticsen_US
dc.identifier.affiliationUniversity of Melbourne, Sir Peter MacCallum Department of Oncology, Melbourne, Australiaen_US
dc.identifier.affiliationThe Australian e-Health Research Centre, CSIRO, Brisbane, Australiaen_US
dc.identifier.affiliationRadiation Oncologyen_US
dc.identifier.affiliationDepartment of Biochemistry, Monash University, Melbourne, Australiaen_US
dc.identifier.affiliationPeter MacCallum Cancer Centre, Department of Radiation Oncology, Melbourne, Australiaen_US
dc.identifier.affiliationDepartment of Medical Radiations, Monash University, Melbourne, Australiaen_US
dc.identifier.affiliationDepartment of Cancer Medicine, Latrobe University, Melbourne, Australiaen_US
dc.identifier.doi10.1016/j.ijmedinf.2018.10.008en_US
dc.type.contentTexten_US
dc.identifier.orcid0000-0001-8387-0965en_US
dc.identifier.pubmedid30545489-
dc.type.austinJournal Article-
local.name.researcherForoudi, Farshad
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
item.fulltextNo Fulltext-
item.grantfulltextnone-
item.languageiso639-1en-
item.openairetypeJournal Article-
crisitem.author.deptRadiation Oncology-
crisitem.author.deptOlivia Newton-John Cancer Wellness and Research Centre-
crisitem.author.deptOlivia Newton-John Cancer Wellness and Research Centre-
crisitem.author.deptRadiation Oncology-
Appears in Collections:Journal articles
Show simple item record

Page view(s)

18
checked on Mar 28, 2024

Google ScholarTM

Check


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.