{"id":"https://openalex.org/W4413051505","doi":"https://doi.org/10.3233/shti250953","title":"AI Bias and Confounding Risk in Health Feature Engineering for Machine Learning Classification Task","display_name":"AI Bias and Confounding Risk in Health Feature Engineering for Machine Learning Classification Task","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413051505","doi":"https://doi.org/10.3233/shti250953","pmid":"https://pubmed.ncbi.nlm.nih.gov/40775971"},"language":"en","primary_location":{"id":"doi:10.3233/shti250953","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250953","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti250953","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002599099","display_name":"R. Z. Guo","orcid":"https://orcid.org/0000-0002-0742-3343"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ruihua Guo","raw_affiliation_strings":["School of Computer Science, The University of Sydney, NSW, Australia 2008"],"raw_orcid":"https://orcid.org/0000-0002-0742-3343","affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, NSW, Australia 2008","institution_ids":["https://openalex.org/I129604602","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060236637","display_name":"Angus Ritchie","orcid":"https://orcid.org/0000-0002-8164-8786"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Angus Ritchie","raw_affiliation_strings":["Sydney Medical School, The University of Sydney, NSW, Australia 2050"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sydney Medical School, The University of Sydney, NSW, Australia 2050","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ross Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ross Smith","raw_affiliation_strings":["School of Computer Science, The University of Sydney, NSW, Australia 2008"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, NSW, Australia 2008","institution_ids":["https://openalex.org/I129604602","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044521860","display_name":"Yang Lu","orcid":"https://orcid.org/0000-0002-9002-8650"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Lu","raw_affiliation_strings":["School of Public Health, The University of Sydney, NSW, Australia 2050"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Public Health, The University of Sydney, NSW, Australia 2050","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104258328","display_name":"Haeri Min","orcid":"https://orcid.org/0009-0005-0704-5548"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haeri Min","raw_affiliation_strings":["School of Computer Science, The University of Sydney, NSW, Australia 2008"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, NSW, Australia 2008","institution_ids":["https://openalex.org/I129604602","https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003933623","display_name":"Simon Poon","orcid":"https://orcid.org/0000-0003-2726-9109"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Simon K. Poon","raw_affiliation_strings":["School of Computer Science, The University of Sydney, NSW, Australia 2008"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, NSW, Australia 2008","institution_ids":["https://openalex.org/I129604602","https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27074236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"329","issue":null,"first_page":"814","last_page":"819"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.6748999953269958,"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"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.6748999953269958,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.6563000082969666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/confounding","display_name":"Confounding","score":0.7746567726135254},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.6637455224990845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6520815491676331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6187453269958496},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5592557191848755},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5582569241523743},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5441339015960693},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2122015655040741},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1618754267692566},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10642868280410767},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06633073091506958},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06079214811325073}],"concepts":[{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.7746567726135254},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.6637455224990845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6520815491676331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187453269958496},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5592557191848755},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5582569241523743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5441339015960693},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2122015655040741},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1618754267692566},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10642868280410767},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06633073091506958},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06079214811325073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":"D000328","descriptor_name":"Adult","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000328","descriptor_name":"Adult","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002318","descriptor_name":"Cardiovascular Diseases","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D002318","descriptor_name":"Cardiovascular Diseases","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D002318","descriptor_name":"Cardiovascular Diseases","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":true},{"descriptor_ui":"D002318","descriptor_name":"Cardiovascular Diseases","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":true},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","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":"D010359","descriptor_name":"Patient Readmission","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D010359","descriptor_name":"Patient Readmission","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D011247","descriptor_name":"Pregnancy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011247","descriptor_name":"Pregnancy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015986","descriptor_name":"Confounding Factors, Epidemiologic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015986","descriptor_name":"Confounding Factors, Epidemiologic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018570","descriptor_name":"Risk Assessment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D018570","descriptor_name":"Risk Assessment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti250953","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250953","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:40775971","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40775971","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":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/shti250953","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250953","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2994176440","https://openalex.org/W2510575233","https://openalex.org/W3008173435","https://openalex.org/W2750075801","https://openalex.org/W3164948662","https://openalex.org/W4400413234","https://openalex.org/W3153597579","https://openalex.org/W4394398790","https://openalex.org/W4399455186","https://openalex.org/W2963507914"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,8,28,43,63,180,188,197,233],"machine":[3,91],"learning":[4,92],"bring":[5],"unique":[6],"opportunities":[7],"health":[9,24,71],"fields":[10],"but":[11],"also":[12],"pose":[13],"considerable":[14],"challenges.":[15],"Due":[16],"to":[17,36,245],"stringent":[18],"ethical":[19],"considerations":[20],"and":[21,32,40,103,123,128,149,162],"resource":[22],"constraints,":[23],"data":[25,72],"can":[26],"vary":[27],"scope,":[29],"population":[30],"coverage,":[31],"collection":[33],"granularity,":[34],"prone":[35],"different":[37,216],"AI":[38],"bias":[39],"confounding":[41,58,178,223,248],"risks":[42],"the":[44,54,78,114,117,139,141,154,181,189,198,234,251],"performance":[45,62,110,156],"of":[46,60,84,138,222],"a":[47,64,177,215,229,243],"classification":[48],"task.":[49,108],"This":[50],"experimental":[51],"study":[52],"explored":[53],"impact":[55],"on":[56,134,153],"hidden":[57],"risk":[59],"model":[61,155,183],"cardiovascular":[65],"readmission":[66],"prediction":[67],"task":[68],"using":[69,77],"real-life":[70],"from":[73,145,214],"'Data-derived":[74],"Risk":[75],"assessment":[76],"Electronic":[79],"medical":[80],"record":[81],"through":[82],"Application":[83],"Machine":[85],"Learning'":[86],"(DREAM).":[87],"Five":[88],"commonly":[89],"used":[90],"models-k-nearest":[93],"neighbors":[94],"(KNN),":[95],"random":[96],"forest":[97],"(RF),":[98],"decision":[99],"tree":[100],"(DT),":[101],"Catboost":[102],"Xgboost-were":[104],"selected":[105],"for":[106],"this":[107,166],"Model":[109],"was":[111],"assessed":[112],"via":[113],"area":[115],"under":[116,165],"receiver":[118],"operating":[119],"characteristics":[120],"curve":[121],"(AUC)":[122],"F1":[124],"score,":[125],"both":[126],"before":[127],"after":[129],"propensity":[130,238],"score":[131,239],"adjustment.":[132],"Based":[133],"density":[135],"plot":[136],"comparison":[137],"adjustment,":[140],"difference":[142],"mainly":[143],"contributed":[144],"patients":[146,164],"aged":[147],"20":[148],"40.":[150],"High":[151],"fluctuation":[152],"has":[157],"been":[158],"noted":[159],"by":[160],"including":[161],"excluding":[163],"age":[167],"group.":[168],"After":[169],"reasoning,":[170],"high-risk":[171],"pregnant":[172,208],"females":[173],"may":[174,227],"serve":[175],"as":[176],"factor":[179],"original":[182],"generation.":[184],"The":[185],"pregnancy":[186],"rate":[187],"non-readmitted":[190],"group":[191,200],"is":[192],"significantly":[193],"higher":[194],"than":[195],"that":[196],"readmitted":[199],"(x2":[201],"=":[202],"10.2,":[203],"p":[204],"<":[205],"0.001).":[206],"However,":[207],"status":[209],"required":[210],"additional":[211],"information":[212],"query":[213],"hospital":[217],"system.":[218],"Without":[219],"carefully":[220],"consideration":[221],"risks,":[224],"traditional":[225],"pipeline":[226],"generate":[228],"less":[230],"robotic":[231],"classifier":[232],"clinical":[235],"setting.":[236],"Incorporating":[237],"matching":[240],"could":[241],"be":[242],"solution":[244],"randomise":[246],"invisible":[247],"factors":[249],"between":[250],"classes.":[252]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}