{"id":"https://openalex.org/W2183913575","doi":"https://doi.org/10.2390/biecoll-jib-2011-177","title":"Evaluating the effect of unbalanced data in biomedical document classification","display_name":"Evaluating the effect of unbalanced data in biomedical document classification","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2183913575","doi":"https://doi.org/10.2390/biecoll-jib-2011-177","mag":"2183913575","pmid":"https://pubmed.ncbi.nlm.nih.gov/21926440"},"language":"en","primary_location":{"id":"pmid:21926440","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21926440","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":"Journal of integrative bioinformatics","raw_type":null},"type":"article","indexed_in":["datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2390/biecoll-jib-2011-177","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052333506","display_name":"Rosal\u00eda Laza","orcid":"https://orcid.org/0000-0002-1889-1337"},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Laza, Rosalia","raw_affiliation_strings":["ESEI, Escuela Superior de Ingenier\u00eda Inform\u00e1tica, University of Vigo, Edificio Polit\u00e9cnico, Campus Universitario As Lagoas s/n, 32004, Ourense, Spain. rlaza@uvigo.es"],"affiliations":[{"raw_affiliation_string":"ESEI, Escuela Superior de Ingenier\u00eda Inform\u00e1tica, University of Vigo, Edificio Polit\u00e9cnico, Campus Universitario As Lagoas s/n, 32004, Ourense, Spain. rlaza@uvigo.es","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065363539","display_name":"Reyes Pav\u00f3n","orcid":"https://orcid.org/0000-0002-4247-973X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavon, Reyes","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026022133","display_name":"Miguel Reboiro\u2010Jato","orcid":"https://orcid.org/0000-0001-8749-2703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reboiro-Jato, Miguel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048392452","display_name":"Florentino Fdez\u2010Riverola","orcid":"https://orcid.org/0000-0002-3943-8013"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fdez-Riverola, Florentino","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052333506"],"corresponding_institution_ids":["https://openalex.org/I6289922"],"apc_list":null,"apc_paid":null,"fwci":3.07,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92325577,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":"3","first_page":"177","last_page":"177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991000294685364,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991000294685364,"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":0.9904000163078308,"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":0.9779999852180481,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8725723028182983},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.713617205619812},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5169369578361511},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.49024826288223267},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.4766548275947571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4724070429801941},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43737804889678955},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40742480754852295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8725723028182983},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.713617205619812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5169369578361511},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.49024826288223267},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.4766548275947571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724070429801941},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43737804889678955},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40742480754852295}],"mesh":[{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","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":3,"locations":[{"id":"pmid:21926440","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21926440","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":"Journal of integrative bioinformatics","raw_type":null},{"id":"pmh:oai:biecoll.ub.uni-bielefeld.de:5193","is_oa":false,"landing_page_url":"http://biecoll.ub.uni-bielefeld.de/volltexte/2011/5193/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://journal.imbio.de/article.php?aid=177","raw_type":"Journal Article"},{"id":"doi:10.2390/biecoll-jib-2011-177","is_oa":true,"landing_page_url":"https://doi.org/10.2390/biecoll-jib-2011-177","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.2390/biecoll-jib-2011-177","is_oa":true,"landing_page_url":"https://doi.org/10.2390/biecoll-jib-2011-177","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W5447123","https://openalex.org/W35304842","https://openalex.org/W85350352","https://openalex.org/W118267201","https://openalex.org/W167016754","https://openalex.org/W1503432700","https://openalex.org/W1588282782","https://openalex.org/W1941659294","https://openalex.org/W2008906462","https://openalex.org/W2019858993","https://openalex.org/W2058165281","https://openalex.org/W2058732827","https://openalex.org/W2097553584","https://openalex.org/W2099550922","https://openalex.org/W2114453188","https://openalex.org/W2119191234","https://openalex.org/W2131547811","https://openalex.org/W2131557422","https://openalex.org/W2134546032","https://openalex.org/W2136903812","https://openalex.org/W2151872900","https://openalex.org/W2170654002","https://openalex.org/W2171629518","https://openalex.org/W2175779775","https://openalex.org/W3103913776"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W2623427976","https://openalex.org/W41957589","https://openalex.org/W3200179079","https://openalex.org/W4249229055","https://openalex.org/W2981904269","https://openalex.org/W2556319748","https://openalex.org/W2147947227","https://openalex.org/W3154094704","https://openalex.org/W3201534795"],"abstract_inverted_index":{"Nowadays,":[0],"document":[1],"classification":[2,41,157],"has":[3],"become":[4],"an":[5,149],"interesting":[6],"research":[7],"field.":[8],"Partly,":[9],"this":[10,31,62,89],"is":[11,24,66,134,187],"due":[12],"to":[13,26,39,153,189],"the":[14,81,93,102,110,156],"increasing":[15],"availability":[16],"of":[17,57,74,83,95,104,112,158],"biomedical":[18],"information":[19],"in":[20,70],"digital":[21],"form":[22],"which":[23,106],"necessary":[25],"catalogue":[27],"and":[28,77,130,179,193],"organize.":[29],"In":[30,88],"context,":[32],"machine":[33],"learning":[34],"techniques":[35,195],"are":[36,86,107,121],"usually":[37],"applied":[38],"text":[40,52],"by":[42,109],"using":[43,161],"a":[44,51,55,67,96,135,162],"general":[45],"inductive":[46],"process":[47],"that":[48,119,131,184],"automatically":[49],"builds":[50],"classifier":[53,164,186],"from":[54],"set":[56],"pre-classified":[58],"documents.":[59],"Related":[60],"with":[61,170],"domain,":[63],"imbalanced":[64],"data":[65],"well-known":[68],"problem":[69],"many":[71],"practical":[72],"applications":[73],"knowledge":[75],"discovery":[76],"its":[78,198],"effects":[79],"on":[80],"performance":[82],"standard":[84],"classifiers":[85],"remarkable.":[87],"paper,":[90],"we":[91,147],"investigate":[92,154],"application":[94],"Bayesian":[97],"Network":[98],"(BN)":[99],"model":[100],"for":[101,123,138],"triage":[103],"documents,":[105],"represented":[108],"association":[111],"different":[113,143],"MeSH":[114,128,132],"terms.":[115],"Our":[116],"results":[117],"show":[118],"BNs":[120],"adequate":[122],"describing":[124],"conditional":[125],"independencies":[126],"between":[127],"terms":[129],"ontology":[133],"valuable":[136],"resource":[137],"representing":[139],"Medline":[140,159],"documents":[141,160],"at":[142],"abstraction":[144],"levels.":[145],"Moreover,":[146],"perform":[148],"extensive":[150],"experimental":[151],"evaluation":[152,174],"if":[155],"BN":[163,185],"poses":[165],"additional":[166],"challenges":[167],"when":[168],"dealing":[169],"class-imbalanced":[171],"prediction.":[172],"The":[173],"involves":[175],"two":[176],"methods,":[177],"under-sampling":[178],"cost-sensitive":[180],"learning.":[181],"We":[182],"conclude":[183],"sensitive":[188],"both":[190],"balancing":[191],"strategies":[192],"existing":[194],"can":[196],"improve":[197],"overall":[199],"performance.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}