{"id":"https://openalex.org/W79002519","doi":null,"title":"An effective general purpose approach for automated biomedical document classification.","display_name":"An effective general purpose approach for automated biomedical document classification.","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W79002519","mag":"79002519","pmid":"https://pubmed.ncbi.nlm.nih.gov/17238323","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/1839342"},"language":"en","primary_location":{"id":"pmh:oai:europepmc.org:1818033","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1839342","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1839342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062561557","display_name":"Aaron Michael Cohen","orcid":"https://orcid.org/0000-0002-4610-9912","observed_orcids":["https://orcid.org/0000-0002-4610-9912"]},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aaron M Cohen","raw_affiliation_strings":["Oregon Health & Science University, Portland, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon Health & Science University, Portland, OR, USA","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062561557"],"corresponding_institution_ids":["https://openalex.org/I165690674"],"apc_list":null,"apc_paid":null,"fwci":3.182,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.91050198,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9872999787330627,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9872999787330627,"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":0.010300000198185444,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.00019999999494757503,"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/biomedical-text-classification","display_name":"biomedical text classification","score":0.9810000061988831},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.5899999737739563},{"id":"https://openalex.org/keywords/cost-sensitive-classification","display_name":"cost-sensitive classification","score":0.6809999942779541},{"id":"https://openalex.org/keywords/chi-square-feature-selection","display_name":"chi-square feature selection","score":0.8820000290870667},{"id":"https://openalex.org/keywords/rejection-sampling","display_name":"rejection sampling","score":0.9089999794960022},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.8759999871253967},{"id":"https://openalex.org/keywords/voting-classifier","display_name":"voting classifier","score":0.5820000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893962860107422},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.7352148294448853},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6603125333786011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5862351059913635},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5572152733802795},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5482070446014404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5217524170875549},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.46349382400512695},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4457222521305084},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4425325095653534},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3695988059043884},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.13257744908332825},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","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":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001330","descriptor_name":"Electronic Data Processing","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":true},{"descriptor_ui":"D008491","descriptor_name":"Medical Informatics Applications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016009","descriptor_name":"Chi-Square Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"pmh:oai:europepmc.org:1818033","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1839342","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:1839342","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1839342","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AMIA Annu Symp Proc","raw_type":"Text"},{"id":"pmid:17238323","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17238323","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,"listed_in":[],"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":"AMIA ... Annual Symposium proceedings. AMIA Symposium","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.137.9499","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.137.9499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://medir.ohsu.edu/~cohenaa/biomedical_document_classification_cohen-20060626c.pdf","raw_type":"text"},{"id":"mag:79002519","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17238323","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":{"id":"pmh:oai:europepmc.org:1818033","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1839342","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W168362576","https://openalex.org/W297499026","https://openalex.org/W2122305935","https://openalex.org/W2142261479","https://openalex.org/W2149684865","https://openalex.org/W2154703852","https://openalex.org/W2917056928"],"related_works":["https://openalex.org/W3110717416","https://openalex.org/W395088103","https://openalex.org/W4306661594","https://openalex.org/W2359099235","https://openalex.org/W7098312105","https://openalex.org/W4406199060","https://openalex.org/W2941179688","https://openalex.org/W1967376701","https://openalex.org/W2143352929","https://openalex.org/W2146724934"],"abstract_inverted_index":{"Automated":[0],"document":[1],"classification":[2,110],"can":[3],"be":[4],"a":[5,43,83,104,116],"valuable":[6],"tool":[7],"for":[8,51,121],"biomedical":[9,47,108,123],"tasks":[10],"that":[11,21],"involve":[12],"large":[13],"amounts":[14],"of":[15,45,74,82,106],"text.":[16,124],"However,":[17],"in":[18],"biomedicine,":[19],"documents":[20],"have":[22],"the":[23,60,89],"desired":[24],"properties":[25],"are":[26,32,56],"often":[27],"rare,":[28],"and":[29,41,62,71,99],"special":[30],"methods":[31],"usually":[33],"required":[34],"to":[35],"address":[36],"this":[37],"issue.":[38],"We":[39],"propose":[40],"evaluate":[42],"method":[44,66,114],"classifying":[46,122],"text":[48,109],"documents,":[49],"optimizing":[50],"utility":[52],"when":[53],"misclassification":[54],"costs":[55],"highly":[57],"asymmetric":[58],"between":[59],"positive":[61],"negative":[63],"classes.":[64],"The":[65,113],"uses":[67],"chi-square":[68],"feature":[69],"selection":[70],"several":[72],"iterations":[73],"cost":[75],"proportionate":[76],"rejection":[77],"sampling":[78],"followed":[79],"by":[80],"application":[81],"support":[84],"vector":[85],"machine":[86],"(SVM),":[87],"combining":[88],"resulting":[90],"classifier":[91],"results":[92],"with":[93],"voting.":[94],"It":[95],"is":[96,115],"straightforward,":[97],"fast,":[98],"achieves":[100],"competitive":[101],"performance":[102],"on":[103],"set":[105],"standardized":[107],"evaluation":[111],"tasks.":[112],"good":[117],"general":[118],"purpose":[119],"approach":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}