{"id":"https://openalex.org/W4281717669","doi":"https://doi.org/10.1093/jamia/ocac093","title":"The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression","display_name":"The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281717669","doi":"https://doi.org/10.1093/jamia/ocac093","pmid":"https://pubmed.ncbi.nlm.nih.gov/35686364"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocac093","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocac093","pdf_url":"https://academic.oup.com/jamia/article-pdf/29/9/1525/45444435/ocac093.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://academic.oup.com/jamia/article-pdf/29/9/1525/45444435/ocac093.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001031334","display_name":"Ruben van den Goorbergh","orcid":"https://orcid.org/0000-0003-3229-3015"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]},{"id":"https://openalex.org/I3018483916","display_name":"University Medical Center Utrecht","ror":"https://ror.org/0575yy874","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I3018483916"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ruben van den Goorbergh","raw_affiliation_strings":["Julius Center for Health Sciences and Primary Care, UMC Utrecht, Utrecht University , Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Julius Center for Health Sciences and Primary Care, UMC Utrecht, Utrecht University , Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353","https://openalex.org/I3018483916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067519537","display_name":"Maarten van Smeden","orcid":"https://orcid.org/0000-0002-5529-1541"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]},{"id":"https://openalex.org/I3018483916","display_name":"University Medical Center Utrecht","ror":"https://ror.org/0575yy874","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I3018483916"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten van Smeden","raw_affiliation_strings":["Julius Center for Health Sciences and Primary Care, UMC Utrecht, Utrecht University , Utrecht, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-5529-1541","affiliations":[{"raw_affiliation_string":"Julius Center for Health Sciences and Primary Care, UMC Utrecht, Utrecht University , Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353","https://openalex.org/I3018483916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002144411","display_name":"D. Timmerman","orcid":"https://orcid.org/0000-0002-3707-6645"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dirk Timmerman","raw_affiliation_strings":["Department of Development and Regeneration, KU Leuven , Leuven, Belgium","Department of Obstetrics and Gynecology, University Hospitals Leuven , Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Development and Regeneration, KU Leuven , Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department of Obstetrics and Gynecology, University Hospitals Leuven , Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086320066","display_name":"Ben Van Calster","orcid":"https://orcid.org/0000-0003-1613-7450"},"institutions":[{"id":"https://openalex.org/I2800006345","display_name":"Leiden University Medical Center","ror":"https://ror.org/05xvt9f17","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800006345"]},{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE","NL"],"is_corresponding":true,"raw_author_name":"Ben Van Calster","raw_affiliation_strings":["Department of Biomedical Data Sciences, Leiden University Medical Center , Leiden, The Netherlands","Department of Development and Regeneration, KU Leuven , Leuven, Belgium","EPI-Center, KU Leuven , Leuven, Belgium"],"raw_orcid":"https://orcid.org/0000-0003-1613-7450","affiliations":[{"raw_affiliation_string":"Department of Biomedical Data Sciences, Leiden University Medical Center , Leiden, The Netherlands","institution_ids":["https://openalex.org/I2800006345"]},{"raw_affiliation_string":"Department of Development and Regeneration, KU Leuven , Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"EPI-Center, KU Leuven , Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086320066"],"corresponding_institution_ids":["https://openalex.org/I2800006345","https://openalex.org/I99464096"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":{"value":3967,"currency":"USD","value_usd":3967},"fwci":29.6109,"has_fulltext":true,"cited_by_count":325,"citation_normalized_percentile":{"value":0.9976189,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":"9","first_page":"1525","last_page":"1534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.6111000180244446,"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":0.6111000180244446,"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/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.06390000134706497,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T10862","display_name":"AI in cancer detection","score":0.03869999945163727,"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/undersampling","display_name":"Undersampling","score":0.7273625135421753},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.6638081669807434},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5560224652290344},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.5484750866889954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48233267664909363},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.45350387692451477},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.4378448724746704},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.41826385259628296},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.39118653535842896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38861554861068726},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2998806834220886},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.08146664500236511}],"concepts":[{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.7273625135421753},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.6638081669807434},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5560224652290344},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5484750866889954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48233267664909363},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.45350387692451477},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.4378448724746704},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.41826385259628296},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.39118653535842896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38861554861068726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2998806834220886},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08146664500236511},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","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":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016015","descriptor_name":"Logistic Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016015","descriptor_name":"Logistic Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016015","descriptor_name":"Logistic Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1093/jamia/ocac093","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocac093","pdf_url":"https://academic.oup.com/jamia/article-pdf/29/9/1525/45444435/ocac093.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:35686364","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35686364","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:lirias2repo.kuleuven.be:20.500.12942/701136","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/701136","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Journal Of The American Medical Informatics Association, vol. 29 (9), (1525-1534)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:dspace.library.uu.nl:1874/446782","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/446782","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9382395","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9382395","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/ocac093","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocac093","pdf_url":"https://academic.oup.com/jamia/article-pdf/29/9/1525/45444435/ocac093.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G1969776114","display_name":null,"funder_award_id":"C24M/20/064","funder_id":"https://openalex.org/F4320322308","funder_display_name":"KU Leuven"},{"id":"https://openalex.org/G5747009347","display_name":"Dynamic risk prediction to reduce central line-associated bloodstream infections","funder_award_id":"C24M/20/064","funder_id":"https://openalex.org/F4320327336","funder_display_name":"Vlaamse regering"},{"id":"https://openalex.org/G7822770668","display_name":"The ADNEX risk model for ovarian cancer diagnosis: improving performance across different hospitals and examiners","funder_award_id":"G097322N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281717669.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1513618424","https://openalex.org/W1602160603","https://openalex.org/W1929177037","https://openalex.org/W1970502168","https://openalex.org/W1994682257","https://openalex.org/W2022441134","https://openalex.org/W2041256948","https://openalex.org/W2045030989","https://openalex.org/W2054193584","https://openalex.org/W2060374620","https://openalex.org/W2075159929","https://openalex.org/W2088059023","https://openalex.org/W2097360283","https://openalex.org/W2099878111","https://openalex.org/W2106393550","https://openalex.org/W2113714330","https://openalex.org/W2115709314","https://openalex.org/W2118978333","https://openalex.org/W2148143831","https://openalex.org/W2155653793","https://openalex.org/W2167490420","https://openalex.org/W2225109326","https://openalex.org/W2226880313","https://openalex.org/W2297716127","https://openalex.org/W2338318698","https://openalex.org/W2775363893","https://openalex.org/W2800788706","https://openalex.org/W2807179733","https://openalex.org/W2809949684","https://openalex.org/W2913997948","https://openalex.org/W2981991941","https://openalex.org/W2996480032","https://openalex.org/W3007464329","https://openalex.org/W3012413426","https://openalex.org/W3024192828","https://openalex.org/W3098865414","https://openalex.org/W3207601856","https://openalex.org/W4210545395","https://openalex.org/W4243367342","https://openalex.org/W4294541781","https://openalex.org/W6674629281"],"related_works":["https://openalex.org/W4308469503","https://openalex.org/W32988189","https://openalex.org/W2904737874","https://openalex.org/W4389233021","https://openalex.org/W2399571531","https://openalex.org/W80466363","https://openalex.org/W2947132063","https://openalex.org/W4288337828","https://openalex.org/W4390415670","https://openalex.org/W4287816717"],"abstract_inverted_index":{"OBJECTIVE:":[0],"Methods":[1],"to":[2,54,125,127,180,188],"correct":[3],"class":[4,56,130,154],"imbalance":[5,28,157,217,224],"(imbalance":[6],"between":[7,162,190],"the":[8,25,31,83,93,123,128,143,160,172,195,203,207],"frequency":[9],"of":[10,27,33,72,85,90,112,206],"outcome":[11,94,196],"events":[12],"and":[13,46,64,75,92,164,193],"nonevents)":[14],"are":[15,213],"receiving":[16],"increasing":[17],"interest":[18],"for":[19,103,153],"developing":[20],"prediction":[21,101],"models.":[22,36],"We":[23],"examined":[24],"effect":[26],"correction":[29,152,158,178,225],"on":[30,100],"performance":[32,67],"logistic":[34,49],"regression":[35,50],"MATERIAL":[37],"AND":[38],"METHODS:":[39],"Prediction":[40],"models":[41,149,181],"were":[42,168],"developed":[43,150],"using":[44],"standard":[45],"penalized":[47],"(ridge)":[48],"under":[51,142],"4":[52],"methods":[53,135],"address":[55],"imbalance:":[57],"no":[58],"correction,":[59],"random":[60,62,113,115],"undersampling,":[61,114],"oversampling,":[63,116],"SMOTE.":[65],"Model":[66],"was":[68,131],"evaluated":[69],"in":[70,139,222],"terms":[71],"discrimination,":[73],"calibration,":[74],"classification.":[76],"Using":[77],"Monte":[78],"Carlo":[79],"simulations,":[80],"we":[81],"studied":[82],"impact":[84],"training":[86],"set":[87],"size,":[88],"number":[89],"predictors,":[91],"event":[95],"fraction.":[96],"A":[97],"case":[98],"study":[99],"modeling":[102],"ovarian":[104],"cancer":[105],"diagnosis":[106],"is":[107,218],"presented.":[108],"RESULTS:":[109],"The":[110,198],"use":[111],"or":[117],"SMOTE":[118],"yielded":[119],"poorly":[120],"calibrated":[121],"models:":[122],"probability":[124,173,200],"belong":[126],"minority":[129],"strongly":[132],"overestimated.":[133],"These":[134],"did":[136],"not":[137,219],"result":[138],"higher":[140],"areas":[141],"ROC":[144],"curve":[145],"when":[146],"compared":[147],"with":[148,182,192],"without":[151,185,194],"imbalance.":[155],"Although":[156],"improved":[159],"balance":[161],"sensitivity":[163],"specificity,":[165],"similar":[166],"results":[167],"obtained":[169],"by":[170],"shifting":[171],"threshold":[174],"instead.":[175],"DISCUSSION:":[176],"Imbalance":[177],"led":[179],"strong":[183],"miscalibration":[184],"better":[186],"ability":[187],"distinguish":[189],"patients":[191],"event.":[197],"inaccurate":[199],"estimates":[201],"reduce":[202],"clinical":[204],"utility":[205],"model,":[208],"because":[209],"decisions":[210],"about":[211],"treatment":[212],"ill-informed.":[214],"CONCLUSION:":[215],"Outcome":[216],"a":[220],"problem":[221],"itself,":[223],"may":[226],"even":[227],"worsen":[228],"model":[229],"performance.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":72},{"year":2025,"cited_by_count":99},{"year":2024,"cited_by_count":87},{"year":2023,"cited_by_count":51},{"year":2022,"cited_by_count":16}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}