{"id":"https://openalex.org/W4417472989","doi":"https://doi.org/10.1109/sipaim67325.2025.11283167","title":"Beyond Accuracy: Evaluating Fairness in Deep Learning Models for Chest X-ray Classification","display_name":"Beyond Accuracy: Evaluating Fairness in Deep Learning Models for Chest X-ray Classification","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W4417472989","doi":"https://doi.org/10.1109/sipaim67325.2025.11283167"},"language":null,"primary_location":{"id":"doi:10.1109/sipaim67325.2025.11283167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sipaim67325.2025.11283167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 21st International Symposium on Biomedical Image Processing and Analysis (SIPAIM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Let\u00edcia Lopes Mendes Da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Let\u00edcia Lopes Mendes Da Silva","raw_affiliation_strings":["Universidade Estadual de Campinas,School of Electrical and Computer Engineering,SP,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Estadual de Campinas,School of Electrical and Computer Engineering,SP,Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046393559","display_name":"Diedre Carmo","orcid":"https://orcid.org/0000-0002-5922-9120"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Diedre Santos Do Carmo","raw_affiliation_strings":["Universidade Estadual de Campinas,School of Electrical and Computer Engineering,SP,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Estadual de Campinas,School of Electrical and Computer Engineering,SP,Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017698959","display_name":"Let\u00edcia Rittner","orcid":"https://orcid.org/0000-0001-8182-5554"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Let\u00edcia Rittner","raw_affiliation_strings":["Universidade Estadual de Campinas,School of Electrical and Computer Engineering,SP,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Estadual de Campinas,School of Electrical and Computer Engineering,SP,Brazil","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181391015"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5408103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.8095999956130981,"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"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.8095999956130981,"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"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.06989999860525131,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02449999935925007,"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/deep-learning","display_name":"Deep learning","score":0.5579000115394592},{"id":"https://openalex.org/keywords/equity","display_name":"Equity (law)","score":0.4912000000476837},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4706999957561493},{"id":"https://openalex.org/keywords/fairness-measure","display_name":"Fairness measure","score":0.28450000286102295},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2685999870300293}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.588100016117096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5688999891281128},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C199728807","wikidata":"https://www.wikidata.org/wiki/Q2578557","display_name":"Equity (law)","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47450000047683716},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2937000095844269},{"id":"https://openalex.org/C11867375","wikidata":"https://www.wikidata.org/wiki/Q5430671","display_name":"Fairness measure","level":4,"score":0.28450000286102295},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sipaim67325.2025.11283167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sipaim67325.2025.11283167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 21st International Symposium on Biomedical Image Processing and Analysis (SIPAIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2911410812","https://openalex.org/W2963466845","https://openalex.org/W2995225687","https://openalex.org/W3110181119","https://openalex.org/W3181414820","https://openalex.org/W4200191097","https://openalex.org/W4205164650","https://openalex.org/W4290033826","https://openalex.org/W4291021452","https://openalex.org/W4403021352","https://openalex.org/W4405304237","https://openalex.org/W4408865267"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)":[2],"models":[3,33,57,175],"have":[4],"achieved":[5],"remarkable":[6],"results":[7,119],"in":[8,23,64,124,159],"chest":[9,65],"X-ray":[10],"classification.":[11],"However,":[12],"concerns":[13],"remain":[14],"regarding":[15],"their":[16],"fairness":[17,53,94,107,169],"across":[18,81,112],"demographic":[19],"subgroups":[20],"and":[21,71,79,83,116,132,173],"variations":[22],"image":[24,135],"acquisition.":[25],"Evaluations":[26],"that":[27,34,143],"overlook":[28],"these":[29],"attributes":[30],"may":[31],"favor":[32],"perform":[35],"well":[36,87],"overall":[37],"but":[38],"exhibit":[39],"biased":[40],"behavior,":[41],"potentially":[42],"harming":[43],"underrepresented":[44],"subgroups.":[45],"In":[46],"this":[47,98],"study,":[48],"we":[49,74,100],"conduct":[50],"a":[51],"systematic":[52],"evaluation":[54,103],"of":[55],"DL":[56],"trained":[58],"to":[59,129,167],"detect":[60],"14":[61],"clinical":[62,177],"findings":[63,163],"radiographs.":[66],"Using":[67],"three":[68],"public":[69],"datasets":[70],"EfficientNet-Based":[72],"architectures,":[73],"assess":[75],"both":[76],"model":[77,151],"performance":[78,144],"equity":[80],"sex":[82],"age":[84,131],"groups,":[85],"as":[86,88],"different":[89,113],"radiographic":[90],"views,":[91],"using":[92],"specialized":[93],"metrics.":[95],"To":[96],"support":[97],"analysis,":[99],"developed":[101],"an":[102],"framework":[104],"for":[105,176],"multi-label":[106],"auditing,":[108],"enabling":[109],"direct":[110],"comparison":[111],"models,":[114],"classes,":[115],"attributes.":[117],"Our":[118],"reveal":[120],"notable":[121],"biases":[122],"even":[123],"top-performing":[125],"classifiers,":[126],"particularly":[127],"related":[128],"patient":[130],"positioning":[133],"during":[134],"acquisition,":[136],"with":[137,157],"class-dependent":[138],"bias":[139],"patterns.":[140],"This":[141],"demonstrates":[142],"metrics":[145],"alone":[146],"do":[147],"not":[148],"fully":[149],"characterize":[150],"behavior":[152],"or":[153],"the":[154,165],"risks":[155],"associated":[156],"deployment":[158],"real-world":[160],"scenarios.":[161],"These":[162],"highlight":[164],"need":[166],"incorporate":[168],"considerations":[170],"when":[171],"developing":[172],"selecting":[174],"use.":[178]},"counts_by_year":[],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-12-18T00:00:00"}