{"id":"https://openalex.org/W2184534773","doi":"https://doi.org/10.1093/jamia/ocv010","title":"Expert guided natural language processing using one-class classification","display_name":"Expert guided natural language processing using one-class classification","publication_year":2015,"publication_date":"2015-06-10","ids":{"openalex":"https://openalex.org/W2184534773","doi":"https://doi.org/10.1093/jamia/ocv010","mag":"2184534773","pmid":"https://pubmed.ncbi.nlm.nih.gov/26063744"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocv010","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocv010","pdf_url":"https://academic.oup.com/jamia/article-pdf/22/5/962/5091786/ocv010.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/jamia/article-pdf/22/5/962/5091786/ocv010.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001663845","display_name":"Erel Joffe","orcid":"https://orcid.org/0000-0002-7883-289X"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erel Joffe","raw_affiliation_strings":["Department of Hematology and Bone Marrow Transplantation, Tel Aviv Medical Center, Tel Aviv Israel","School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Hematology and Bone Marrow Transplantation, Tel Aviv Medical Center, Tel Aviv Israel","institution_ids":[]},{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Texas","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023114465","display_name":"Emily J Pettigrew","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily J Pettigrew","raw_affiliation_strings":["Department of Computer Science, Rice University, Houston, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069247158","display_name":"Jorge R Herskovic","orcid":"https://orcid.org/0000-0002-0167-5646"},"institutions":[{"id":"https://openalex.org/I1343551460","display_name":"The University of Texas MD Anderson Cancer Center","ror":"https://ror.org/04twxam07","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1343551460"]},{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jorge R Herskovic","raw_affiliation_strings":["School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Texas","The University of Texas, M.D. Anderson Cancer Center, Houston, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Texas","institution_ids":["https://openalex.org/I919571938"]},{"raw_affiliation_string":"The University of Texas, M.D. Anderson Cancer Center, Houston, Texas","institution_ids":["https://openalex.org/I1343551460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075106196","display_name":"Charles F Bearden","orcid":null},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles F Bearden","raw_affiliation_strings":["School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Texas","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075275684","display_name":"Elmer V. Bernstam","orcid":"https://orcid.org/0000-0001-7643-791X"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elmer V Bernstam","raw_affiliation_strings":["Department of Internal Medicine, Medical School, The University of Texas Health Science Center at Houston, Houston, Texas","School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, Medical School, The University of Texas Health Science Center at Houston, Houston, Texas","institution_ids":["https://openalex.org/I919571938"]},{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Texas","institution_ids":["https://openalex.org/I919571938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":3.1162,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92904483,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"22","issue":"5","first_page":"962","last_page":"966"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.33090001344680786,"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/T10862","display_name":"AI in cancer detection","score":0.33090001344680786,"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":0.10109999775886536,"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":0.0877000018954277,"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/support-vector-machine","display_name":"Support vector machine","score":0.8040652275085449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8001431226730347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7549622058868408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6252599954605103},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5933156609535217},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5156506299972534},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.514372706413269},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3835042119026184},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3777388334274292}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.8040652275085449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8001431226730347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549622058868408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6252599954605103},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5933156609535217},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5156506299972534},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.514372706413269},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3835042119026184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3777388334274292},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D001943","descriptor_name":"Breast Neoplasms","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D001943","descriptor_name":"Breast Neoplasms","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D001943","descriptor_name":"Breast Neoplasms","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","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":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","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":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1093/jamia/ocv010","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocv010","pdf_url":"https://academic.oup.com/jamia/article-pdf/22/5/962/5091786/ocv010.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:26063744","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26063744","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 the American Medical Informatics Association : JAMIA","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.987.441","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.987.441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jamia.oxfordjournals.org/content/jaminfo/early/2015/06/09/jamia.ocv010.full.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.990.9275","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.990.9275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jamia.oxfordjournals.org/content/jaminfo/22/5/962.full.pdf","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:4986669","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4986669","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/jamia/ocv010","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocv010","pdf_url":"https://academic.oup.com/jamia/article-pdf/22/5/962/5091786/ocv010.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W104901463","https://openalex.org/W1480287196","https://openalex.org/W1561370360","https://openalex.org/W1983078185","https://openalex.org/W1986563448","https://openalex.org/W2023299139","https://openalex.org/W2023450550","https://openalex.org/W2056234582","https://openalex.org/W2071038402","https://openalex.org/W2098162425","https://openalex.org/W2112119668","https://openalex.org/W2117592999","https://openalex.org/W2127613611","https://openalex.org/W2132870739","https://openalex.org/W2142047467","https://openalex.org/W2153332911","https://openalex.org/W2159985898","https://openalex.org/W2288946185","https://openalex.org/W3104422614","https://openalex.org/W4231476871","https://openalex.org/W6604308541","https://openalex.org/W6682762504","https://openalex.org/W6695979358","https://openalex.org/W6813049668"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W1980100242","https://openalex.org/W2530420969","https://openalex.org/W2051187167","https://openalex.org/W4315815996"],"abstract_inverted_index":{"INTRODUCTION:":[0],"Automatically":[1],"identifying":[2],"specific":[3],"phenotypes":[4],"in":[5],"free-text":[6],"clinical":[7,16],"notes":[8,88,96,116,182,250],"is":[9],"critically":[10],"important":[11],"for":[12,31,102,143,186,209,226],"the":[13,21,37,48,62,109,210,227,261],"reuse":[14],"of":[15,39,50,64,111,151,160,260],"data.":[17],"In":[18],"this":[19],"study,":[20],"authors":[22,75],"combine":[23],"expert-guided":[24],"feature":[25,51],"(text)":[26],"selection":[27,52],"with":[28,67,155,257],"one-class":[29,40,77],"classification":[30,41],"text":[32,57,127,237],"processing.":[33],"OBJECTIVES:":[34],"To":[35],"compare":[36,108],"performance":[38,110,136,201],"to":[42,46,60,69,86,107,122,131,177,216,253],"traditional":[43],"binary":[44],"classification;":[45],"evaluate":[47],"utility":[49],"based":[53],"on":[54,114,125,147,165,172,180,191,234,245],"expert-selected":[55,126,235],"salient":[56],"(snippets);":[58],"and":[59,82,99,146],"determine":[61],"robustness":[63],"these":[65],"models":[66,112,123],"respects":[68],"irrelevant":[70],"surrounding":[71],"text.":[72],"METHODS:":[73],"The":[74],"trained":[76,113,124,171,179,233,244],"support":[78],"vector":[79],"machines":[80],"(1C-SVMs)":[81],"two-class":[83],"SVMs":[84],"(2C-SVMs)":[85],"identify":[87],"discussing":[89],"breast":[90,103,132,157],"cancer.":[91],"Manually":[92],"annotated":[93],"visit":[94],"summary":[95],"(88":[97],"positive":[98,119,262],"88":[100],"negative":[101,121],"cancer)":[104],"were":[105],"used":[106],"whole":[115,181,249],"labeled":[117],"as":[118],"or":[120,248],"sections":[128,238],"(snippets)":[129],"relevant":[130,236],"cancer":[133,158],"status.":[134],"Model":[135],"was":[137],"evaluated":[138,190],"using":[139],"a":[140,148,156,166,192,198],"70:30":[141],"split":[142],"20":[144],"iterations":[145],"realistic":[149,193],"dataset":[150],"10":[152],"000":[153],"records":[154],"prevalence":[159,259],"1.4%.":[161],"RESULTS:":[162],"When":[163,189],"tested":[164],"balanced":[167],"experimental":[168],"dataset,":[169,195],"1C-SVMs":[170,196,232],"snippets":[173,247],"had":[174,197],"comparable":[175],"results":[176],"2C-SVMs":[178,242],"(F":[183,202],"=":[184,203,207,220,224],"0.92":[185],"both":[187],"approaches).":[188],"imbalanced":[194,255],"considerably":[199],"superior":[200],"0.61":[204],"vs.":[205,222],"F":[206],"0.17":[208],"best":[211,228],"performing":[212,229],"model)":[213],"attributable":[214],"mainly":[215],"improved":[217],"precision":[218],"(p":[219],".88":[221],"p":[223],".09":[225],"model).":[230],"CONCLUSIONS:":[231],"perform":[239],"better":[240],"than":[241],"classifiers":[243],"either":[246],"when":[251],"applied":[252],"realistically":[254],"data":[256],"low":[258],"class.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}