{"id":"https://openalex.org/W2408535903","doi":"https://doi.org/10.3233/978-1-60750-791-8-117","title":"Automatic Extraction of Cancer Characteristics from Free-Text Pathology Reports for Cancer Notifications","display_name":"Automatic Extraction of Cancer Characteristics from Free-Text Pathology Reports for Cancer Notifications","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2408535903","doi":"https://doi.org/10.3233/978-1-60750-791-8-117","mag":"2408535903","pmid":"https://pubmed.ncbi.nlm.nih.gov/21893919"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-60750-791-8-117","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-60750-791-8-117","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5023213398","display_name":"Anthony Nguyen","orcid":"https://orcid.org/0000-0002-6215-6954"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I4210141844","display_name":"Australian e-Health Research Centre","ror":"https://ror.org/04ywhbc61","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801244131","https://openalex.org/I2801453606","https://openalex.org/I4210141844","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Nguyen Anthony","raw_affiliation_strings":["The Australian E-Health Research Centre, CSIRO ICT Centre, Brisbane, Australia. anthony.nguyen@csiro.au"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian E-Health Research Centre, CSIRO ICT Centre, Brisbane, Australia. anthony.nguyen@csiro.au","institution_ids":["https://openalex.org/I4210141844","https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054830604","display_name":"Julie Moore","orcid":"https://orcid.org/0000-0001-5110-1635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moore Julie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065944502","display_name":"Michael Lawley","orcid":"https://orcid.org/0000-0001-9508-4769"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lawley Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043970031","display_name":"David Hansen","orcid":"https://orcid.org/0000-0002-2998-4563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hansen David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108378904","display_name":"Shoni Colquist","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Colquist Shoni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5023213398"],"corresponding_institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I4210141844"],"apc_list":null,"apc_paid":null,"fwci":3.7137,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93018217,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"168","issue":null,"first_page":"117","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4999000132083893,"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":0.4999000132083893,"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":0.24729999899864197,"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/T11894","display_name":"Radiology practices and education","score":0.019700000062584877,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/computer-science","display_name":"Computer science","score":0.5661888122558594},{"id":"https://openalex.org/keywords/cancer","display_name":"Cancer","score":0.5660602450370789},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.37437450885772705},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.3345937132835388},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33256906270980835},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.16104239225387573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5661888122558594},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.5660602450370789},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.37437450885772705},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3345937132835388},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33256906270980835},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.16104239225387573}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":false},{"descriptor_ui":"D012042","descriptor_name":"Registries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012042","descriptor_name":"Registries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012042","descriptor_name":"Registries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018563","descriptor_name":"Disease Notification","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018563","descriptor_name":"Disease Notification","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018563","descriptor_name":"Disease Notification","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D039061","descriptor_name":"Systematized Nomenclature of Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039061","descriptor_name":"Systematized Nomenclature of Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039061","descriptor_name":"Systematized Nomenclature of Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-60750-791-8-117","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-60750-791-8-117","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:21893919","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21893919","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3031052312","https://openalex.org/W4389568370","https://openalex.org/W3032375762","https://openalex.org/W1995515455","https://openalex.org/W2080531066","https://openalex.org/W3108674512","https://openalex.org/W1506200166"],"abstract_inverted_index":{"OBJECTIVE:":[0],"To":[1],"develop":[2],"a":[3,90,148,163],"system":[4,86,120],"for":[5,23,64,140,186],"the":[6,24,33,46,59,77,119,153,173,190,197],"automatic":[7],"classification":[8,36],"of":[9,26,49,92,109,136,165,175,201],"Cancer":[10,69,81,160],"Registry":[11,70,82],"notifications":[12,66],"data":[13,166],"from":[14,144,152],"free-text":[15],"pathology":[16,184],"reports.":[17],"METHOD:":[18],"The":[19,85],"underlying":[20],"technology":[21],"used":[22,42,67],"extraction":[25],"cancer":[27,65,183,202],"notification":[28,142,185],"items":[29,143],"is":[30],"based":[31],"on":[32,89,105,192],"symbolic":[34],"rule-based":[35],"methodology,":[37],"whereby":[38],"formal":[39],"semantics":[40],"are":[41],"to":[43,79],"reason":[44],"with":[45,76,126],"systematised":[47],"nomenclature":[48],"medicine":[50],"-":[51],"clinical":[52,194],"terms":[53],"(SNOMED":[54],"CT)":[55],"concepts":[56],"identified":[57],"in":[58],"free":[60],"text.":[61],"Business":[62],"rules":[63],"by":[68],"coding":[71],"staff":[72],"were":[73],"also":[74],"incorporated":[75],"aim":[78],"mimic":[80],"processes.":[83],"RESULTS:":[84],"was":[87],"developed":[88],"corpus":[91],"239":[93],"histology":[94],"and":[95,102,128,131,138,155,178,199],"cytology":[96],"reports":[97,111,125,146],"(with":[98,112],"60%":[99],"notifiable":[100,114,124,145],"reports),":[101],"then":[103],"evaluated":[104],"an":[106,133,180],"independent":[107],"set":[108],"300":[110],"20%":[113],"reports).":[115],"Results":[116],"show":[117],"that":[118,167],"can":[121,188],"reliably":[122],"classify":[123],"96%":[127],"100%":[129],"specificity,":[130],"achieve":[132],"overall":[134],"accuracy":[135],"82%":[137],"74%":[139],"classifying":[141],"at":[147],"unit":[149],"record":[150],"level":[151],"development":[154],"evaluation":[156],"set,":[157],"respectively.":[158],"CONCLUSION:":[159],"Registries":[161],"collect":[162],"multitude":[164],"requires":[168],"manual":[169],"review,":[170],"slowing":[171],"down":[172],"flow":[174],"information.":[176,203],"Extracting":[177],"providing":[179],"automatically":[181],"coded":[182],"review":[187],"lessen":[189],"reliance":[191],"expert":[193],"staff,":[195],"improving":[196],"efficiency":[198],"availability":[200]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}
