{"id":"https://openalex.org/W2178121026","doi":"https://doi.org/10.18653/v1/w15-2609","title":"Creating a rule based system for text mining of Norwegian breast cancer pathology reports","display_name":"Creating a rule based system for text mining of Norwegian breast cancer pathology reports","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2178121026","doi":"https://doi.org/10.18653/v1/w15-2609","mag":"2178121026"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-2609","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2609","pdf_url":"https://www.aclweb.org/anthology/W15-2609.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth International Workshop on Health Text Mining and Information Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-2609.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028278998","display_name":"Rebecka Weegar","orcid":null},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Rebecka Weegar","raw_affiliation_strings":["Department of Computer and Systems Sciences Stockholm University P.O. Box 7003 164 07 Kista Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Systems Sciences Stockholm University P.O. Box 7003 164 07 Kista Sweden","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010279607","display_name":"Hercules Dalianis","orcid":"https://orcid.org/0000-0003-0165-9926"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hercules Dalianis","raw_affiliation_strings":["Department of Computer and Systems Sciences Stockholm University P.O. Box 7003 164 07 Kista Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Systems Sciences Stockholm University P.O. Box 7003 164 07 Kista Sweden","institution_ids":["https://openalex.org/I161593684"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161593684"],"apc_list":null,"apc_paid":null,"fwci":12.946,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.98655636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/norwegian","display_name":"Norwegian","score":0.7590904235839844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.581238329410553},{"id":"https://openalex.org/keywords/breast-cancer","display_name":"Breast cancer","score":0.5773099064826965},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3601109981536865},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.327602356672287},{"id":"https://openalex.org/keywords/cancer","display_name":"Cancer","score":0.316678524017334},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.2674795389175415},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.1277027428150177},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09878411889076233}],"concepts":[{"id":"https://openalex.org/C63428231","wikidata":"https://www.wikidata.org/wiki/Q9043","display_name":"Norwegian","level":2,"score":0.7590904235839844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.581238329410553},{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.5773099064826965},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3601109981536865},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.327602356672287},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.316678524017334},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2674795389175415},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.1277027428150177},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09878411889076233},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w15-2609","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2609","pdf_url":"https://www.aclweb.org/anthology/W15-2609.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth International Workshop on Health Text Mining and Information Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-2609","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2609","pdf_url":"https://www.aclweb.org/anthology/W15-2609.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth International Workshop on Health Text Mining and Information Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.6700000166893005,"display_name":"Good health and well-being"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314239","display_name":"Netherlands eScience Center","ror":"https://ror.org/00rbjv475"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2178121026.pdf","grobid_xml":"https://content.openalex.org/works/W2178121026.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W68438997","https://openalex.org/W95066055","https://openalex.org/W1939796399","https://openalex.org/W2012560661","https://openalex.org/W2076424959","https://openalex.org/W2145522203","https://openalex.org/W2155863877","https://openalex.org/W2288055910","https://openalex.org/W2418239156"],"related_works":["https://openalex.org/W2061564463","https://openalex.org/W2512753411","https://openalex.org/W2028240842","https://openalex.org/W1972562838","https://openalex.org/W2325410321","https://openalex.org/W4233839983","https://openalex.org/W3101822383","https://openalex.org/W1536194326","https://openalex.org/W3179137071","https://openalex.org/W2425515292"],"abstract_inverted_index":{"National":[0],"cancer":[1,4,52],"registries":[2],"collect":[3],"related":[5],"information":[6,19,37,65],"from":[7,21,38],"multiple":[8],"sources":[9],"and":[10,24,103],"make":[11],"it":[12],"available":[13],"for":[14,33,64],"research.":[15],"Part":[16],"of":[17,30,36,46,71,88,97,101,106],"this":[18,26,72],"originates":[20],"pathology":[22,40,48,91],"reports,":[23],"in":[25],"pre-study":[27],"the":[28,69,80,89],"possibility":[29],"a":[31,60,95,99,114],"system":[32,63,73,115],"automatic":[34],"extraction":[35],"Norwegian":[39],"reports":[41,49],"is":[42,116],"investigated.":[43],"A":[44],"set":[45],"40":[47],"describing":[50],"breast":[51],"tissue":[53],"samples":[54],"has":[55,76,108],"been":[56,77,109],"used":[57],"to":[58,79],"develop":[59],"rule":[61],"based":[62],"extraction.":[66],"To":[67],"validate":[68],"performance":[70],"its":[74],"output":[75],"compared":[78],"data":[81],"produced":[82],"by":[83],"experts":[84],"doing":[85],"manual":[86],"encoding":[87],"same":[90],"reports.":[92],"On":[93],"average,":[94],"precision":[96],"80%,":[98],"recall":[100],"98%":[102],"an":[104],"F-score":[105],"86%":[107],"achieved,":[110],"showing":[111],"that":[112],"such":[113],"indeed":[117],"feasible.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
