{"id":"https://openalex.org/W7161819537","doi":"https://doi.org/10.48550/arxiv.2605.19214","title":"Worst-Group Equalized Odds Regularization for Multi-Attribute Fair Medical Image Classification","display_name":"Worst-Group Equalized Odds Regularization for Multi-Attribute Fair Medical Image Classification","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161819537","doi":"https://doi.org/10.48550/arxiv.2605.19214"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.19214","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012268461","display_name":"Nikhil Cherian Kurian","orcid":"https://orcid.org/0000-0003-1713-0736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kurian, Nikhil Cherian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136522421","display_name":"Victor Caquilpan Parra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parra, Victor Caquilpan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092732210","display_name":"Abin Shoby","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shoby, Abin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024354532","display_name":"Luke Whitbread","orcid":"https://orcid.org/0000-0001-9960-5592"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Whitbread, Luke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068274591","display_name":"Lauren Oakden\u2010Rayner","orcid":"https://orcid.org/0000-0001-5471-5202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oakden-Rayner, Lauren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092173408","display_name":"Robert Vandersluis","orcid":"https://orcid.org/0009-0003-7197-104X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vandersluis, Robert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007707507","display_name":"Jessica Schrouff","orcid":"https://orcid.org/0000-0003-4992-3183"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schrouff, Jessica","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136563603","display_name":"Lyle John Palmer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Palmer, Lyle J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004220534","display_name":"Mark Jenkinson","orcid":"https://orcid.org/0000-0001-6043-0166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jenkinson, Mark","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.24690000712871552,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.24690000712871552,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.18930000066757202,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.07050000131130219,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7161999940872192},{"id":"https://openalex.org/keywords/odds","display_name":"Odds","score":0.6600000262260437},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6047000288963318},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46880000829696655},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.45989999175071716},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4000000059604645},{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.39410001039505005},{"id":"https://openalex.org/keywords/odds-ratio","display_name":"Odds ratio","score":0.33469998836517334}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7161999940872192},{"id":"https://openalex.org/C143095724","wikidata":"https://www.wikidata.org/wiki/Q515895","display_name":"Odds","level":3,"score":0.6600000262260437},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5407999753952026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5099999904632568},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.451200008392334},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3504999876022339},{"id":"https://openalex.org/C156957248","wikidata":"https://www.wikidata.org/wiki/Q1862216","display_name":"Odds ratio","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C544519230","wikidata":"https://www.wikidata.org/wiki/Q32566","display_name":"Computed tomography","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C39847760","wikidata":"https://www.wikidata.org/wiki/Q1385465","display_name":"Extreme point","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2782000005245209},{"id":"https://openalex.org/C2781415353","wikidata":"https://www.wikidata.org/wiki/Q5196602","display_name":"Cut-point","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.19214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8408119678497314}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diagnostic":[0],"performance":[1,178],"in":[2,55,62,156,165],"medical":[3,153],"AI":[4],"varies":[5],"systematically":[6],"across":[7,80,142],"demographic":[8,82,120,144],"groups,":[9],"yet":[10],"subgroup":[11],"AUC":[12],"can":[13,53],"mask":[14],"clinically":[15],"important":[16],"disparities.":[17],"At":[18,110],"a":[19,87,136],"fixed":[20],"inference-time":[21],"operating":[22,77],"point,":[23],"some":[24],"groups":[25],"may":[26],"exhibit":[27,128],"over-diagnostic":[28],"behaviour,":[29],"characterized":[30],"by":[31,66,118],"elevated":[32],"true":[33,45,102],"and":[34,46,71,79,104,125,134,168],"false":[35,47,105],"positive":[36,48,103,106],"rates,":[37],"while":[38,58,179],"others":[39],"show":[40],"under-diagnostic":[41],"patterns":[42],"with":[43,171],"reduced":[44],"rates.":[49],"These":[50],"opposing":[51],"tendencies":[52],"cancel":[54],"aggregate":[56],"AUCs":[57],"producing":[59],"meaningful":[60],"inequities":[61],"clinical":[63],"decision-making.":[64],"Motivated":[65],"the":[67,76,101,113,129],"need":[68],"to":[69],"assess":[70],"mitigate":[72],"such":[73],"disparities":[74,164],"at":[75,108],"point":[78],"multiple":[81,143],"attributes":[83,121],"simultaneously,":[84],"we":[85],"propose":[86],"worst-group":[88],"equalized-odds":[89],"margin":[90,132],"regularizer.":[91],"The":[92],"proposed":[93],"regularizer":[94],"explicitly":[95],"targets":[96],"subgroup-level":[97],"deviations":[98,133],"on":[99,174],"both":[100],"sides":[107],"inference.":[109],"each":[111],"update,":[112],"method":[114,161],"identifies":[115],"subgroups":[116],"defined":[117],"explicit":[119,148],"(e.g.,":[122],"age,":[123],"sex,":[124],"race)":[126],"that":[127],"most":[130],"extreme":[131],"applies":[135],"unified":[137],"penalty,":[138],"enabling":[139],"fairness":[140],"optimization":[141],"axes":[145],"without":[146],"requiring":[147],"intersectional":[149],"constraints.":[150],"Across":[151],"two":[152],"imaging":[154],"datasets":[155],"realistic":[157],"multi-label":[158],"settings,":[159],"our":[160],"consistently":[162],"reduces":[163],"Equalized":[166,169],"Odds":[167],"Opportunity":[170],"minimal":[172],"impact":[173],"AUC,":[175],"preserving":[176],"diagnostic":[177],"improving":[180],"fairness.":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-21T00:00:00"}