{"id":"https://openalex.org/W2757523618","doi":"https://doi.org/10.1155/2017/7847531","title":"Correcting Classifiers for Sample Selection Bias in Two-Phase Case-Control Studies","display_name":"Correcting Classifiers for Sample Selection Bias in Two-Phase Case-Control Studies","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2757523618","doi":"https://doi.org/10.1155/2017/7847531","mag":"2757523618","pmid":"https://pubmed.ncbi.nlm.nih.gov/29312464"},"language":"en","primary_location":{"id":"doi:10.1155/2017/7847531","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2017/7847531","pdf_url":"http://downloads.hindawi.com/journals/cmmm/2017/7847531.pdf","source":{"id":"https://openalex.org/S36980176","display_name":"Computational and Mathematical Methods in Medicine","issn_l":"1748-670X","issn":["1748-670X","1748-6718"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational and Mathematical Methods in Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://downloads.hindawi.com/journals/cmmm/2017/7847531.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017566256","display_name":"Norbert Krautenbacher","orcid":"https://orcid.org/0000-0002-7704-1543"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Norbert Krautenbacher","raw_affiliation_strings":["Department of Mathematics, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Institute of Computational Biology, Helmholtz Zentrum M\u00fcnchen, German Research Center for Environmental Health, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7704-1543","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute of Computational Biology, Helmholtz Zentrum M\u00fcnchen, German Research Center for Environmental Health, Munich, Germany","institution_ids":["https://openalex.org/I3018134672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083128670","display_name":"Fabian J. Theis","orcid":"https://orcid.org/0000-0002-2419-1943"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian J. Theis","raw_affiliation_strings":["Department of Mathematics, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Institute of Computational Biology, Helmholtz Zentrum M\u00fcnchen, German Research Center for Environmental Health, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute of Computational Biology, Helmholtz Zentrum M\u00fcnchen, German Research Center for Environmental Health, Munich, Germany","institution_ids":["https://openalex.org/I3018134672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063476572","display_name":"Christiane Fuchs","orcid":"https://orcid.org/0000-0003-3565-8315"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christiane Fuchs","raw_affiliation_strings":["Department of Mathematics, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Institute of Computational Biology, Helmholtz Zentrum M\u00fcnchen, German Research Center for Environmental Health, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3565-8315","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute of Computational Biology, Helmholtz Zentrum M\u00fcnchen, German Research Center for Environmental Health, Munich, Germany","institution_ids":["https://openalex.org/I3018134672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063476572"],"corresponding_institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I62916508"],"apc_list":{"value":2550,"currency":"USD","value_usd":2550},"apc_paid":{"value":2550,"currency":"USD","value_usd":2550},"fwci":1.0588,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81213228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2017","issue":null,"first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9933000206947327,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.8861569762229919},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.674799919128418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6452414989471436},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.6128682494163513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5636807680130005},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.5349057912826538},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5211910605430603},{"id":"https://openalex.org/keywords/bootstrap-aggregating","display_name":"Bootstrap aggregating","score":0.4909856617450714},{"id":"https://openalex.org/keywords/random-subspace-method","display_name":"Random subspace method","score":0.47399985790252686},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4737050235271454},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.420514315366745},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3951442241668701},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3035368323326111},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.2509441375732422}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8861569762229919},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.674799919128418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6452414989471436},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.6128682494163513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5636807680130005},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.5349057912826538},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5211910605430603},{"id":"https://openalex.org/C162040801","wikidata":"https://www.wikidata.org/wiki/Q799897","display_name":"Bootstrap aggregating","level":2,"score":0.4909856617450714},{"id":"https://openalex.org/C106135958","wikidata":"https://www.wikidata.org/wiki/Q7291993","display_name":"Random subspace method","level":3,"score":0.47399985790252686},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4737050235271454},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.420514315366745},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3951442241668701},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3035368323326111},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2509441375732422},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006505","descriptor_name":"Hepatitis","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D006505","descriptor_name":"Hepatitis","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D006505","descriptor_name":"Hepatitis","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D006505","descriptor_name":"Hepatitis","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":false},{"descriptor_ui":"D006505","descriptor_name":"Hepatitis","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":false},{"descriptor_ui":"D006505","descriptor_name":"Hepatitis","qualifier_ui":"Q000453","qualifier_name":"epidemiology","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":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015983","descriptor_name":"Selection Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015983","descriptor_name":"Selection Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015983","descriptor_name":"Selection Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016022","descriptor_name":"Case-Control Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016022","descriptor_name":"Case-Control Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016022","descriptor_name":"Case-Control Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":7,"locations":[{"id":"doi:10.1155/2017/7847531","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2017/7847531","pdf_url":"http://downloads.hindawi.com/journals/cmmm/2017/7847531.pdf","source":{"id":"https://openalex.org/S36980176","display_name":"Computational and Mathematical Methods in Medicine","issn_l":"1748-670X","issn":["1748-670X","1748-6718"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational and Mathematical Methods in Medicine","raw_type":"journal-article"},{"id":"pmid:29312464","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29312464","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":"Computational and mathematical methods in medicine","raw_type":null},{"id":"pmh:oai:push-zb.helmholtz-munich.de:51843","is_oa":true,"landing_page_url":"https://push-zb.helmholtz-munich.de/frontdoor.php?source_opus=51843","pdf_url":"https://push-zb.helmholtz-munich.de/deliver.php?id=19725","source":{"id":"https://openalex.org/S7407055352","display_name":"PuSH - Publication Server of Helmholtz Zentrum M\u00fcnchen","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Comput. Math. Methods Med. 2017:7847531 (2017)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:europepmc.org:4669154","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5632994","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:6fbc7e43bbd44f3b94e15047dceb303c","is_oa":false,"landing_page_url":"https://doaj.org/article/6fbc7e43bbd44f3b94e15047dceb303c","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational and Mathematical Methods in Medicine, Vol 2017 (2017)","raw_type":"article"},{"id":"pmh:oai:opus-zb.helmholtz-muenchen.de:51843","is_oa":true,"landing_page_url":"https://push-zb.helmholtz-muenchen.de/frontdoor.php?source_opus=51843","pdf_url":null,"source":{"id":"https://openalex.org/S4377196115","display_name":"Site cant be reached","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Comput. Math. Methods Med. 2017:7847531 (2017)","raw_type":null},{"id":"pmh:oai:pub.uni-bielefeld.de:2934011","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2934011","pdf_url":null,"source":{"id":"https://openalex.org/S4306401624","display_name":"Publikationen an der Universit\u00e4t Bielefeld (Universit\u00e4t Bielefeld)","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Krautenbacher N, Theis FJ, Fuchs C. Correcting Classifiers for Sample Selection Bias in Two-Phase Case-Control Studies. <em>Computational and Mathematical Methods in Medicine</em>. 2017;2017: 7847531.","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1155/2017/7847531","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2017/7847531","pdf_url":"http://downloads.hindawi.com/journals/cmmm/2017/7847531.pdf","source":{"id":"https://openalex.org/S36980176","display_name":"Computational and Mathematical Methods in Medicine","issn_l":"1748-670X","issn":["1748-670X","1748-6718"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational and Mathematical Methods in Medicine","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7705551220","display_name":null,"funder_award_id":"Subproject A17","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2757523618.pdf","grobid_xml":"https://content.openalex.org/works/W2757523618.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1531879651","https://openalex.org/W1551135786","https://openalex.org/W1853837125","https://openalex.org/W1918432791","https://openalex.org/W2006617902","https://openalex.org/W2065883168","https://openalex.org/W2094159667","https://openalex.org/W2099375483","https://openalex.org/W2118444937","https://openalex.org/W2124652275","https://openalex.org/W2132862423","https://openalex.org/W2136018575","https://openalex.org/W2139122730","https://openalex.org/W2145126338","https://openalex.org/W2148143831","https://openalex.org/W2155221388","https://openalex.org/W2157395790","https://openalex.org/W2158698691","https://openalex.org/W2165139489","https://openalex.org/W2215128562","https://openalex.org/W2328176404","https://openalex.org/W2798198804","https://openalex.org/W2911964244","https://openalex.org/W3102027041","https://openalex.org/W3125937743","https://openalex.org/W4233471163","https://openalex.org/W4235424165","https://openalex.org/W4243220370","https://openalex.org/W4249409719"],"related_works":["https://openalex.org/W3022501507","https://openalex.org/W4205824301","https://openalex.org/W3188632291","https://openalex.org/W2023639956","https://openalex.org/W1981866886","https://openalex.org/W2046975922","https://openalex.org/W2052615004","https://openalex.org/W1760344465","https://openalex.org/W2599507641","https://openalex.org/W2017396468"],"abstract_inverted_index":{"Epidemiological":[0],"studies":[1],"often":[2],"utilize":[3],"stratified":[4],"data":[5,92],"in":[6,20,66,202],"which":[7,62,67],"rare":[8],"outcomes":[9],"or":[10],"exposures":[11],"are":[12,195],"artificially":[13],"enriched.":[14],"This":[15],"design":[16],"can":[17],"increase":[18],"precision":[19],"association":[21],"tests":[22],"but":[23,41],"distorts":[24],"predictions":[25],"when":[26,178],"applying":[27],"classifiers":[28,180],"on":[29,54,117,181],"nonstratified":[30],"data.":[31,121],"Several":[32],"methods":[33,72,87,147,177],"correct":[34],"for":[35,47,74,107,159,174],"this":[36],"so-called":[37],"sample":[38],"selection":[39],"bias,":[40],"their":[42],"performance":[43],"remains":[44],"unclear":[45],"especially":[46,78],"machine":[48,75],"learning":[49,76],"classifiers.":[50,168],"With":[51],"an":[52],"emphasis":[53],"two-phase":[55],"case-control":[56],"studies,":[57],"we":[58,171],"aim":[59],"to":[60,64,70,88],"assess":[61],"corrections":[63],"perform":[65,148],"setting":[68],"and":[69,93,99,111,116,119,146,157,166],"obtain":[71],"suitable":[73],"techniques,":[77],"the":[79,90,108,126,132,163,203],"random":[80,109,127,164,185],"forest.":[81],"We":[82,103,150,198],"propose":[83],"two":[84],"new":[85],"resampling-based":[86],"resemble":[89],"original":[91],"covariance":[94],"structure:":[95],"stochastic":[96],"inverse-probability":[97,101,134],"oversampling":[98],"parametric":[100,133],"bagging.":[102],"compare":[104],"all":[105],"techniques":[106],"forest":[110,128,165],"other":[112,140,167],"classifiers,":[113,141],"both":[114],"theoretically":[115],"simulated":[118],"real":[120],"Empirical":[122],"results":[123],"show":[124],"that":[125],"profits":[129],"from":[130],"only":[131],"bagging":[135],"proposed":[136],"by":[137],"us.":[138],"For":[139,184],"correction":[142,176],"is":[143],"mostly":[144],"advantageous,":[145],"uniformly.":[149],"discuss":[151],"consequences":[152],"of":[153],"inappropriate":[154],"distribution":[155,193],"assumptions":[156,194],"reason":[158],"different":[160],"behaviors":[161],"between":[162],"In":[169],"conclusion,":[170],"provide":[172,199],"guidance":[173],"choosing":[175],"training":[179],"biased":[182],"samples.":[183],"forests,":[186],"our":[187,200],"method":[188],"outperforms":[189],"state-of-the-art":[190],"procedures":[191],"if":[192],"roughly":[196],"fulfilled.":[197],"implementation":[201],"R":[204],"package":[205],"sambia":[206],".":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}