{"id":"https://openalex.org/W4416252110","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228958","title":"Beyond Filtering: Leveraging Instance Hardness for Data-Centric Machine Learning in Healthcare","display_name":"Beyond Filtering: Leveraging Instance Hardness for Data-Centric Machine Learning in Healthcare","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252110","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228958"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5067570192","display_name":"Maria Gabriela Valeriano","orcid":"https://orcid.org/0000-0002-3631-156X"},"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":"Maria Gabriela Valeriano","raw_affiliation_strings":["Universidade Estadual de Campinas,Instituto de Computação,Campinas,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Estadual de Campinas,Instituto de Computação,Campinas,Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050014117","display_name":"Carlos Roberto Veiga Kiffer","orcid":"https://orcid.org/0000-0003-1122-0693"},"institutions":[{"id":"https://openalex.org/I4210150618","display_name":"Associa\u00e7\u00e3o Paulista de Medicina","ror":"https://ror.org/03tma2759","country_code":"BR","type":"nonprofit","lineage":["https://openalex.org/I4210150618"]},{"id":"https://openalex.org/I88273585","display_name":"Universidade Federal de S\u00e3o Paulo","ror":"https://ror.org/02k5swt12","country_code":"BR","type":"education","lineage":["https://openalex.org/I88273585"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Carlos Roberto Veiga Kiffer","raw_affiliation_strings":["Universidade Federal de Sâo Paulo,Escola Paulista de Medicina,São Paulo,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Sâo Paulo,Escola Paulista de Medicina,São Paulo,Brazil","institution_ids":["https://openalex.org/I4210150618","https://openalex.org/I88273585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036696970","display_name":"Ana Carolina Lorena","orcid":"https://orcid.org/0000-0002-6140-571X"},"institutions":[{"id":"https://openalex.org/I107428990","display_name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica","ror":"https://ror.org/05vh67662","country_code":"BR","type":"education","lineage":["https://openalex.org/I107428990"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ana Carolina Lorena","raw_affiliation_strings":["Instituto Tecnológico de Aeronáutica,Divisão de Ciência da Computação,São José dos Campos,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Tecnológico de Aeronáutica,Divisão de Ciência da Computação,São José dos Campos,Brazil","institution_ids":["https://openalex.org/I107428990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87527554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.38839998841285706,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.38839998841285706,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.13989999890327454,"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":0.13089999556541443,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8209999799728394},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7394000291824341},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5741999745368958},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4146000146865845},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.39239999651908875},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3549000024795532},{"id":"https://openalex.org/keywords/real-world-data","display_name":"Real world data","score":0.3402999937534332},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.2955000102519989}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8209999799728394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.8116000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7465000152587891},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7394000291824341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013000249862671},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5741999745368958},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C2989086416","wikidata":"https://www.wikidata.org/wiki/Q15067276","display_name":"Healthcare industry","level":3,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2022477494","https://openalex.org/W3005040148","https://openalex.org/W3010919171","https://openalex.org/W3181414820","https://openalex.org/W3200120464","https://openalex.org/W3217256357","https://openalex.org/W4206475336","https://openalex.org/W4283318985","https://openalex.org/W4288758404","https://openalex.org/W4389580951","https://openalex.org/W4400438459","https://openalex.org/W4401215432","https://openalex.org/W4402352651","https://openalex.org/W4402525564","https://openalex.org/W4404291428","https://openalex.org/W4404524215","https://openalex.org/W4406085118"],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1,117],"models":[2,118],"often":[3],"struggle":[4],"to":[5,7,12,25,53,65,113,141],"generalize":[6],"real-world":[8],"healthcare":[9],"settings":[10],"due":[11],"data":[13,40,92,134],"imperfections":[14],"such":[15],"as":[16,145],"noise,":[17],"biases,":[18],"and":[19,67,94,110,122,151],"label":[20],"inconsistencies.":[21],"A":[22],"promising":[23],"approach":[24],"improving":[26],"model":[27,95,152],"robustness":[28],"is":[29],"instance":[30,106,143],"hardness":[31,144],"analysis,":[32],"which":[33],"quantifies":[34],"the":[35,77,88,127],"difficulty":[36],"of":[37,79,133],"classifying":[38],"individual":[39],"points":[41],"in":[42],"a":[43,130,146],"dataset.":[44],"While":[45],"previous":[46],"studies":[47],"have":[48],"explored":[49],"filtering":[50,80,139],"hard":[51,81],"instances":[52,82],"enhance":[54],"predictive":[55],"performance,":[56],"our":[57],"findings":[58],"indicate":[59],"that":[60,115],"this":[61],"strategy":[62],"can":[63],"lead":[64],"overfitting":[66],"reduced":[68],"generalization":[69],"on":[70],"external":[71],"datasets.":[72],"This":[73],"work":[74],"systematically":[75],"evaluates":[76],"effects":[78],"across":[83],"multiple":[84],"healthcare-related":[85],"datasets,":[86],"revealing":[87],"nuanced":[89],"relationship":[90],"between":[91],"complexity":[93],"performance.":[96],"Beyond":[97],"filtering,":[98],"we":[99],"propose":[100],"alternative":[101],"data-centric":[102],"strategies,":[103],"including":[104],"expert-guided":[105],"selection,":[107],"explainability-driven":[108],"insights,":[109],"fairness-aware":[111],"approaches,":[112],"ensure":[114],"machine":[116],"remain":[119],"both":[120],"accurate":[121],"equitable.":[123],"Our":[124],"results":[125],"highlight":[126],"need":[128],"for":[129,148],"holistic":[131],"view":[132],"quality,":[135],"moving":[136],"beyond":[137],"naive":[138],"approaches":[140],"leverage":[142],"tool":[147],"dataset":[149],"refinement":[150],"improvement.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}