{"id":"https://openalex.org/W4389543203","doi":"https://doi.org/10.1109/embc40787.2023.10340751","title":"Handling Class Imbalance in Machine Learning-based Prediction Models: A Case Study in Asthma Management","display_name":"Handling Class Imbalance in Machine Learning-based Prediction Models: A Case Study in Asthma Management","publication_year":2023,"publication_date":"2023-07-24","ids":{"openalex":"https://openalex.org/W4389543203","doi":"https://doi.org/10.1109/embc40787.2023.10340751","pmid":"https://pubmed.ncbi.nlm.nih.gov/38083129"},"language":"en","primary_location":{"id":"doi:10.1109/embc40787.2023.10340751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc40787.2023.10340751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5000531950","display_name":"Arif Budiarto","orcid":"https://orcid.org/0000-0001-8875-6694"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]},{"id":"https://openalex.org/I166073570","display_name":"Binus University","ror":"https://ror.org/03zmf4s77","country_code":"ID","type":"education","lineage":["https://openalex.org/I166073570"]}],"countries":["GB","ID"],"is_corresponding":true,"raw_author_name":"Arif Budiarto","raw_affiliation_strings":["University of Edinburgh,Usher Institute,Edinburgh,UK,EH16 4SS","Computer Science Department, School of Computer Science, Bina Nusantara University, Jakarta, Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Usher Institute,Edinburgh,UK,EH16 4SS","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Computer Science Department, School of Computer Science, Bina Nusantara University, Jakarta, Indonesia","institution_ids":["https://openalex.org/I166073570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026215303","display_name":"Aziz Sheikh","orcid":"https://orcid.org/0000-0001-7022-3056"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aziz Sheikh","raw_affiliation_strings":["University of Edinburgh,Usher Institute,Edinburgh,UK,EH16 4SS"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Usher Institute,Edinburgh,UK,EH16 4SS","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080457552","display_name":"Andrew M. Wilson","orcid":"https://orcid.org/0000-0002-5514-4867"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Wilson","raw_affiliation_strings":["University of East Anglia,Norwich Medical School,Norwich,UK,NR4 7TJ"],"affiliations":[{"raw_affiliation_string":"University of East Anglia,Norwich Medical School,Norwich,UK,NR4 7TJ","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052175038","display_name":"David Price","orcid":"https://orcid.org/0000-0002-9728-9992"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]},{"id":"https://openalex.org/I4210118135","display_name":"Observational & Pragmatic Research Institute","ror":"https://ror.org/02gq3ch54","country_code":"SG","type":"other","lineage":["https://openalex.org/I4210118135"]}],"countries":["GB","SG"],"is_corresponding":false,"raw_author_name":"David B Price","raw_affiliation_strings":["Observational and Pragmatic Research Institute,Singapore,Singapore","Centre of Academic Primary Care, Division of Applied Health Sciences, University of Aberdeen, Aberdeen, UK","Observational and Pragmatic Research Institute, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Observational and Pragmatic Research Institute,Singapore,Singapore","institution_ids":["https://openalex.org/I4210118135"]},{"raw_affiliation_string":"Centre of Academic Primary Care, Division of Applied Health Sciences, University of Aberdeen, Aberdeen, UK","institution_ids":["https://openalex.org/I195460627"]},{"raw_affiliation_string":"Observational and Pragmatic Research Institute, Singapore, Singapore","institution_ids":["https://openalex.org/I4210118135"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001914584","display_name":"Syed Ahmar Shah","orcid":"https://orcid.org/0000-0001-5672-0443"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syed Ahmar Shah","raw_affiliation_strings":["University of Edinburgh,Usher Institute,Edinburgh,UK,EH16 4SS"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Usher Institute,Edinburgh,UK,EH16 4SS","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000531950"],"corresponding_institution_ids":["https://openalex.org/I166073570","https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.4314,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85804051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2023","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9930999875068665,"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":0.9930999875068665,"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/T14400","display_name":"Medical Coding and Health Information","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9484999775886536,"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/machine-learning","display_name":"Machine learning","score":0.7927744388580322},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.774134635925293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.676565408706665},{"id":"https://openalex.org/keywords/asthma","display_name":"Asthma","score":0.5975844860076904},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.5945990681648254},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5913211107254028},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.5868047475814819},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5832814574241638},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4992678165435791},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4881199300289154},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4488063156604767},{"id":"https://openalex.org/keywords/asthma-management","display_name":"Asthma management","score":0.42251744866371155},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.29646724462509155}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7927744388580322},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.774134635925293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.676565408706665},{"id":"https://openalex.org/C2776042228","wikidata":"https://www.wikidata.org/wiki/Q35869","display_name":"Asthma","level":2,"score":0.5975844860076904},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.5945990681648254},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5913211107254028},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.5868047475814819},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5832814574241638},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4992678165435791},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4881199300289154},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4488063156604767},{"id":"https://openalex.org/C3018080372","wikidata":"https://www.wikidata.org/wiki/Q35869","display_name":"Asthma management","level":3,"score":0.42251744866371155},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.29646724462509155},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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":"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":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"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":"D008991","descriptor_name":"Monitoring, Physiologic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008991","descriptor_name":"Monitoring, Physiologic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008991","descriptor_name":"Monitoring, Physiologic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008991","descriptor_name":"Monitoring, Physiologic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008991","descriptor_name":"Monitoring, Physiologic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011788","descriptor_name":"Quality of Life","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011788","descriptor_name":"Quality of Life","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011788","descriptor_name":"Quality of Life","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011788","descriptor_name":"Quality of Life","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011788","descriptor_name":"Quality of Life","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":false},{"descriptor_ui":"D016015","descriptor_name":"Logistic Models","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":false},{"descriptor_ui":"D016015","descriptor_name":"Logistic Models","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":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/embc40787.2023.10340751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc40787.2023.10340751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:38083129","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38083129","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":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null},{"id":"pmh:oai:aura.abdn.ac.uk:2164/25744","is_oa":false,"landing_page_url":"https://hdl.handle.net/2164/25744","pdf_url":null,"source":{"id":"https://openalex.org/S4306400966","display_name":"Aberdeen University Research Archive (Aberdeen University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I195460627","host_organization_name":"University of Aberdeen","host_organization_lineage":["https://openalex.org/I195460627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2045256553","https://openalex.org/W2101234009","https://openalex.org/W2103647733","https://openalex.org/W2104933073","https://openalex.org/W2118978333","https://openalex.org/W2132791018","https://openalex.org/W2136132422","https://openalex.org/W2148143831","https://openalex.org/W2295598076","https://openalex.org/W2521200999","https://openalex.org/W2557983321","https://openalex.org/W2806153517","https://openalex.org/W2891512495","https://openalex.org/W2941315734","https://openalex.org/W2963691377","https://openalex.org/W2971644666","https://openalex.org/W3006618054","https://openalex.org/W3044763175","https://openalex.org/W3046382668","https://openalex.org/W3092849554","https://openalex.org/W3123647640","https://openalex.org/W3135623092","https://openalex.org/W3159865429","https://openalex.org/W3164963783","https://openalex.org/W3168662291","https://openalex.org/W4200622207","https://openalex.org/W4224276990","https://openalex.org/W4293713156","https://openalex.org/W4295452670","https://openalex.org/W4307405815","https://openalex.org/W6675354045","https://openalex.org/W6684560594","https://openalex.org/W6777783284"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W2781247653","https://openalex.org/W3196098778","https://openalex.org/W3211250490","https://openalex.org/W4360584310","https://openalex.org/W2981515171","https://openalex.org/W80466363","https://openalex.org/W2924282518","https://openalex.org/W3080872054","https://openalex.org/W3090769163"],"abstract_inverted_index":{"A":[0],"data-driven":[1],"prediction":[2,30,61,126,165,219,238],"tool":[3],"has":[4],"the":[5,57,75,150,163,168,171,184,201,210,216,234,250],"potential":[6],"to":[7,45,141,189,198,221],"provide":[8,241],"early":[9,242],"warning":[10,243],"of":[11,50,59,131,135,203,212,218,252,254],"an":[12],"asthma":[13,17,28,64,71,204,223,237],"attack":[14,29],"and":[15,19,85,99,118,225,227,244],"improve":[16,222],"management":[18,224],"outcomes.":[20],"Most":[21],"previous":[22],"machine":[23],"learning":[24],"(ML)-based":[25],"studies":[26],"for":[27,40,63,79,123,167],"have":[31],"reported":[32],"a":[33,47,229],"severe":[34],"class":[35,52,88,132,137,174,191,213],"imbalance,":[36],"with":[37,128,158,170,256],"major":[38],"implications":[39],"model":[41],"performance.":[42],"We":[43,66,103],"aimed":[44],"undertake":[46],"systematic":[48],"comparison":[49],"several":[51],"imbalance":[53,89,133,175,192,214],"handling":[54,90],"techniques":[55],"in":[56,108,153,200,215],"context":[58,202,217],"risk":[60],"models":[62,112],"prognosis.":[65],"used":[67],"data":[68],"from":[69,74,139],"9,835":[70],"patients":[72,255],"extracted":[73],"Medical":[76],"Information":[77],"Mart":[78],"Intensive":[80],"Care":[81],"(MIMIC)":[82],"IV":[83],"database":[84],"deployed":[86],"five":[87],"methods":[91,152],"based":[92],"on":[93],"synthetic":[94],"minority":[95],"oversampling":[96,199],"technique":[97,147],"(SMOTE)":[98],"cost":[100,144,159,185],"function":[101,145,160,186],"customisation.":[102],"then":[104],"compared":[105,197],"their":[106],"performances":[107],"improving":[109,249],"two-class":[110],"classifier":[111],"developed":[113],"using":[114],"logistic":[115],"regression":[116],"(LR)":[117],"extreme":[119,173],"gradient":[120],"boosting":[121],"(XGBoost)":[122],"three":[124],"different":[125],"tasks":[127],"varying":[129],"severity":[130],"(proportion":[134],"majority":[136],"ranging":[138],"90.86%":[140],"98.98%).":[142],"The":[143],"customisation":[146,161],"substantially":[148,194],"outperformed":[149],"SMOTE-based":[151],"all":[154],"tasks.":[155],"XGBoost":[156],"combined":[157],"achieved":[162],"highest":[164],"performance":[166,196],"outcome":[169],"most":[172],"ratio":[176],"(AUC":[177],"=":[178],"0.72).":[179],"Our":[180],"findings":[181],"suggest":[182],"that":[183,232],"customisation-based":[187],"approach":[188],"tackle":[190],"provides":[193,228],"better":[195],"management.Clinical":[205],"Relevance-":[206],"This":[207],"study":[208],"underscores":[209],"challenge":[211],"tools":[220,239],"outcomes":[226],"methodological":[230],"solution":[231],"addresses":[233],"challenge.":[235],"Accurate":[236],"can":[240],"potentially":[245],"prevent":[246],"deterioration":[247],"thereby":[248],"quality":[251],"life":[253],"asthma.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}