{"id":"https://openalex.org/W4366084291","doi":"https://doi.org/10.1177/14604582231164696","title":"Programming techniques for improving rule readability for rule-based information extraction natural language processing pipelines of unstructured and semi-structured medical texts","display_name":"Programming techniques for improving rule readability for rule-based information extraction natural language processing pipelines of unstructured and semi-structured medical texts","publication_year":2023,"publication_date":"2023-04-01","ids":{"openalex":"https://openalex.org/W4366084291","doi":"https://doi.org/10.1177/14604582231164696","pmid":"https://pubmed.ncbi.nlm.nih.gov/37068028"},"language":"en","primary_location":{"id":"doi:10.1177/14604582231164696","is_oa":true,"landing_page_url":"https://doi.org/10.1177/14604582231164696","pdf_url":null,"source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1355-4743","issn":["1355-4743","1460-4582","1741-2811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1177/14604582231164696","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046265823","display_name":"Nektarios Ladas","orcid":"https://orcid.org/0000-0001-5918-8384"},"institutions":[{"id":"https://openalex.org/I34809795","display_name":"Medizinische Hochschule Hannover","ror":"https://ror.org/00f2yqf98","country_code":"DE","type":"education","lineage":["https://openalex.org/I34809795"]},{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nektarios Ladas","raw_affiliation_strings":["Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5918-8384","affiliations":[{"raw_affiliation_string":"Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany","institution_ids":["https://openalex.org/I34809795","https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006643663","display_name":"Florian Borchert","orcid":"https://orcid.org/0000-0003-1079-6500"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Borchert","raw_affiliation_strings":["Hasso-Plattner-Institut Fur Digital Engineering gGmbH, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut Fur Digital Engineering gGmbH, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024391853","display_name":"Stefan Franz","orcid":null},"institutions":[{"id":"https://openalex.org/I34809795","display_name":"Medizinische Hochschule Hannover","ror":"https://ror.org/00f2yqf98","country_code":"DE","type":"education","lineage":["https://openalex.org/I34809795"]},{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Franz","raw_affiliation_strings":["Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany","institution_ids":["https://openalex.org/I34809795","https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074328465","display_name":"Alina Rehberg","orcid":null},"institutions":[{"id":"https://openalex.org/I34809795","display_name":"Medizinische Hochschule Hannover","ror":"https://ror.org/00f2yqf98","country_code":"DE","type":"education","lineage":["https://openalex.org/I34809795"]},{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alina Rehberg","raw_affiliation_strings":["Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany","institution_ids":["https://openalex.org/I34809795","https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087447108","display_name":"Natalia Strauch","orcid":null},"institutions":[{"id":"https://openalex.org/I34809795","display_name":"Medizinische Hochschule Hannover","ror":"https://ror.org/00f2yqf98","country_code":"DE","type":"education","lineage":["https://openalex.org/I34809795"]},{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Natalia Strauch","raw_affiliation_strings":["Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany","institution_ids":["https://openalex.org/I34809795","https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109152386","display_name":"Kim Katrin Sommer","orcid":null},"institutions":[{"id":"https://openalex.org/I34809795","display_name":"Medizinische Hochschule Hannover","ror":"https://ror.org/00f2yqf98","country_code":"DE","type":"education","lineage":["https://openalex.org/I34809795"]},{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kim Katrin Sommer","raw_affiliation_strings":["Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany","institution_ids":["https://openalex.org/I34809795","https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024392920","display_name":"Michael Marschollek","orcid":"https://orcid.org/0000-0002-5921-3073"},"institutions":[{"id":"https://openalex.org/I34809795","display_name":"Medizinische Hochschule Hannover","ror":"https://ror.org/00f2yqf98","country_code":"DE","type":"education","lineage":["https://openalex.org/I34809795"]},{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Marschollek","raw_affiliation_strings":["Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany","institution_ids":["https://openalex.org/I34809795","https://openalex.org/I94509681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030870582","display_name":"Matthias Gietzelt","orcid":"https://orcid.org/0000-0002-3796-3367"},"institutions":[{"id":"https://openalex.org/I34809795","display_name":"Medizinische Hochschule Hannover","ror":"https://ror.org/00f2yqf98","country_code":"DE","type":"education","lineage":["https://openalex.org/I34809795"]},{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Gietzelt","raw_affiliation_strings":["Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Hannover, Germany","institution_ids":["https://openalex.org/I34809795","https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046265823"],"corresponding_institution_ids":["https://openalex.org/I34809795","https://openalex.org/I94509681"],"apc_list":{"value":1500,"currency":"USD","value_usd":1500},"apc_paid":{"value":1500,"currency":"USD","value_usd":1500},"fwci":0.7862,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76456367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"29","issue":"2","first_page":"14604582231164696","last_page":"14604582231164696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.8087000250816345,"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/T13629","display_name":"Text Readability and Simplification","score":0.8087000250816345,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.12809999287128448,"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":0.00860000029206276,"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/computer-science","display_name":"Computer science","score":0.8478896617889404},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.7845828533172607},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6446066498756409},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6272035837173462},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.6247928738594055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5769461393356323},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5515895485877991},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4486536681652069},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43727195262908936},{"id":"https://openalex.org/keywords/rule-based-system","display_name":"Rule-based system","score":0.4333036541938782},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.43310368061065674},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40706637501716614},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36674565076828003},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.299572229385376},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.24620983004570007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478896617889404},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.7845828533172607},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6446066498756409},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6272035837173462},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.6247928738594055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5769461393356323},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5515895485877991},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4486536681652069},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43727195262908936},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.4333036541938782},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.43310368061065674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40706637501716614},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36674565076828003},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.299572229385376},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.24620983004570007}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D032882","descriptor_name":"Comprehension","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D032882","descriptor_name":"Comprehension","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D032882","descriptor_name":"Comprehension","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1177/14604582231164696","is_oa":true,"landing_page_url":"https://doi.org/10.1177/14604582231164696","pdf_url":null,"source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1355-4743","issn":["1355-4743","1460-4582","1741-2811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},{"id":"pmid:37068028","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37068028","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":"Health informatics journal","raw_type":null},{"id":"pmh:oai:doaj.org/article:f4744e803c4a4793b1af3e2a61fe5147","is_oa":true,"landing_page_url":"https://doaj.org/article/f4744e803c4a4793b1af3e2a61fe5147","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Health Informatics Journal, Vol 29 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1177/14604582231164696","is_oa":true,"landing_page_url":"https://doi.org/10.1177/14604582231164696","pdf_url":null,"source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1355-4743","issn":["1355-4743","1460-4582","1741-2811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W86894687","https://openalex.org/W1536690700","https://openalex.org/W2058858020","https://openalex.org/W2096797897","https://openalex.org/W2103260577","https://openalex.org/W2106950427","https://openalex.org/W2108454922","https://openalex.org/W2116667392","https://openalex.org/W2123442489","https://openalex.org/W2138373060","https://openalex.org/W2510014353","https://openalex.org/W2551573137","https://openalex.org/W2883427794","https://openalex.org/W2898155085","https://openalex.org/W2955138751","https://openalex.org/W2968339949","https://openalex.org/W2981089724","https://openalex.org/W2999135213","https://openalex.org/W3011594683","https://openalex.org/W3093341832","https://openalex.org/W3141847762","https://openalex.org/W3145100113","https://openalex.org/W4213347664","https://openalex.org/W4242338205"],"related_works":["https://openalex.org/W1788528807","https://openalex.org/W2020540721","https://openalex.org/W4385489363","https://openalex.org/W2725657302","https://openalex.org/W1872130062","https://openalex.org/W2393978999","https://openalex.org/W2293457016","https://openalex.org/W4362731990","https://openalex.org/W159132833","https://openalex.org/W4366084291"],"abstract_inverted_index":{"BACKGROUND:":[0],"Extraction":[1],"of":[2,14,25,55,58,108,114,153,206,218,224,234,238,241,292,308,311],"medical":[3,15],"terms":[4],"and":[5,11,21,64,68,94,99,124,135,156,169,195,216,226,250,266,277,295,315,330,339,347],"their":[6],"corresponding":[7],"values":[8,54],"from":[9,62,166],"semi-structured":[10,65,225],"unstructured":[12,63,227],"texts":[13],"reports":[16,67],"can":[17,30,121,297,323],"be":[18,122,299,324],"a":[19,38,73,78,190,319],"time-consuming":[20],"error-prone":[22],"process.":[23],"Methods":[24],"natural":[26],"language":[27,255,314],"processing":[28],"(NLP)":[29],"help":[31,107],"define":[32],"an":[33,49,332],"extraction":[34,118,183,338],"pipeline":[35,51],"for":[36,77,181,198,213,259,327,335,340],"accomplishing":[37],"structured":[39,74],"format":[40],"transformation":[41],"strategy.":[42],"OBJECTIVES:":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,173,186,209],"build":[48],"NLP":[50,348],"to":[52,72,129,139,344],"extract":[53,145],"the":[56,97,106,112,127,133,199,204,211,214,219,232,239,251,261,290,309,312,316,337,342],"classification":[57,155],"malignant":[59],"tumors":[60],"(TNM)":[61],"pathology":[66],"import":[69,137],"them":[70,138,188],"further":[71],"data":[75,152,170,223],"source":[76],"clinical":[79],"study.":[80],"Our":[81],"research":[82],"interest":[83],"is":[84],"not":[85],"focused":[86],"on":[87,96,163],"standard":[88],"performance":[89],"metrics":[90],"like":[91],"precision,":[92],"recall,":[93],"F-measure":[95],"test":[98,222],"validation":[100],"data.":[101],"We":[102,230,288],"discuss":[103,289],"how":[104,296],"with":[105,150,246],"software":[109],"programming":[110,141,217,245,302,313],"techniques":[111],"readability":[113,237,294],"rule-based":[115],"(RB)":[116],"information":[117],"(IE)":[119],"pipelines":[120,161],"improved,":[123],"therefore":[125],"minimize":[126],"time":[128,212,258],"correct":[130],"or":[131],"update":[132],"rules,":[134,242],"efficiently":[136],"another":[140],"language.":[142],"METHODS:":[143],"The":[144,257],"rules":[146,263,272,343],"were":[147,280],"manually":[148],"programmed":[149],"training":[151],"TNM":[154],"tested":[157],"in":[158,178,189,264,273,282,284],"two":[159],"separate":[160],"based":[162],"design":[164],"specifications":[165],"domain":[167],"experts":[168],"curators.":[171],"Firstly":[172],"implemented":[174],"each":[175,182],"rule":[176],"directly":[177],"one":[179],"line":[180],"item.":[184],"Secondly,":[185],"reprogrammed":[187,281],"readable":[191,262,320],"fashion":[192],"through":[193,221,236,243],"decomposition":[194],"intention-revealing":[196,278],"names":[197],"variable":[200],"declaration.":[201],"To":[202],"measure":[203,210],"impact":[205],"both":[207],"methods":[208],"fine-tuning":[215],"extractions":[220],"texts.":[228],"RESULTS:":[229],"analyze":[231],"benefits":[233],"improving":[235],"writing":[240],"parallel":[244],"regular":[247],"expressions":[248],"(REGEX),":[249],"Apache":[252],"Uima":[253],"Ruta":[254],"(AURL).":[256],"correcting":[260],"AURL":[265,283],"REGEX":[267,274],"was":[268],"significantly":[269],"reduced.":[270],"Complicated":[271],"are":[275],"decomposed":[276],"declarations":[279],"5":[285],"min.":[286],"CONCLUSION:":[287],"importance":[291],"factor":[293],"it":[298],"improved":[300],"when":[301],"RB":[303],"text":[304],"IE":[305],"pipelines.":[306,349],"Independent":[307],"features":[310],"tools":[317],"applied,":[318],"coding":[321],"strategy":[322],"proven":[325],"beneficial":[326],"future":[328],"maintenance":[329],"offer":[331],"interpretable":[333],"solution":[334],"understanding":[336],"transferring":[341],"other":[345],"domains":[346]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
