{"id":"https://openalex.org/W7135093388","doi":"https://doi.org/10.1111/exsy.70234","title":"Data Resampling and Feature Selection in Diabetes Prediction","display_name":"Data Resampling and Feature Selection in Diabetes Prediction","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135093388","doi":"https://doi.org/10.1111/exsy.70234"},"language":"en","primary_location":{"id":"doi:10.1111/exsy.70234","is_oa":false,"landing_page_url":"https://doi.org/10.1111/exsy.70234","pdf_url":null,"source":{"id":"https://openalex.org/S72232612","display_name":"Expert Systems","issn_l":"0266-4720","issn":["0266-4720","1468-0394"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems","raw_type":"journal-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":"https://openalex.org/A5042349899","display_name":"Angela Shin\u2010Yu Lien","orcid":"https://orcid.org/0000-0002-5711-8072"},"institutions":[{"id":"https://openalex.org/I173093425","display_name":"Chang Gung University","ror":"https://ror.org/00d80zx46","country_code":"TW","type":"education","lineage":["https://openalex.org/I173093425"]},{"id":"https://openalex.org/I3020100970","display_name":"Chang Gung Memorial Hospital","ror":"https://ror.org/02verss31","country_code":"TW","type":"healthcare","lineage":["https://openalex.org/I3020100970"]},{"id":"https://openalex.org/I4210116208","display_name":"Linkou Chang Gung Memorial Hospital","ror":"https://ror.org/02dnn6q67","country_code":"TW","type":"healthcare","lineage":["https://openalex.org/I3020100970","https://openalex.org/I4210116208"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Angela Shin\u2010Yu Lien","raw_affiliation_strings":["Division of Endocrinology and Metabolism, Department of Internal Medicine Chang Gung Memorial Hospital at Linkou  Taoyuan Taiwan","School of Nursing, College of Medicine Chang Gung University  Taoyuan Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-5711-8072","affiliations":[{"raw_affiliation_string":"Division of Endocrinology and Metabolism, Department of Internal Medicine Chang Gung Memorial Hospital at Linkou  Taoyuan Taiwan","institution_ids":["https://openalex.org/I4210116208","https://openalex.org/I3020100970"]},{"raw_affiliation_string":"School of Nursing, College of Medicine Chang Gung University  Taoyuan Taiwan","institution_ids":["https://openalex.org/I173093425"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128901487","display_name":"Ting\u2010Syuan Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I173093425","display_name":"Chang Gung University","ror":"https://ror.org/00d80zx46","country_code":"TW","type":"education","lineage":["https://openalex.org/I173093425"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ting\u2010Syuan Yeh","raw_affiliation_strings":["Department of Information Management Chang Gung University  Taoyuan Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Management Chang Gung University  Taoyuan Taiwan","institution_ids":["https://openalex.org/I173093425"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005466635","display_name":"Chien\u2010Hsiung Huang","orcid":"https://orcid.org/0000-0002-8207-3582"},"institutions":[{"id":"https://openalex.org/I173093425","display_name":"Chang Gung University","ror":"https://ror.org/00d80zx46","country_code":"TW","type":"education","lineage":["https://openalex.org/I173093425"]},{"id":"https://openalex.org/I3020100970","display_name":"Chang Gung Memorial Hospital","ror":"https://ror.org/02verss31","country_code":"TW","type":"healthcare","lineage":["https://openalex.org/I3020100970"]},{"id":"https://openalex.org/I4210116208","display_name":"Linkou Chang Gung Memorial Hospital","ror":"https://ror.org/02dnn6q67","country_code":"TW","type":"healthcare","lineage":["https://openalex.org/I3020100970","https://openalex.org/I4210116208"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien\u2010Hsiung Huang","raw_affiliation_strings":["Department of Emergency Medicine Chang Gung Memorial Hospital at Linkou  Taoyuan Taiwan","Graduate Institute of Management Chang Gung University  Taoyuan Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Emergency Medicine Chang Gung Memorial Hospital at Linkou  Taoyuan Taiwan","institution_ids":["https://openalex.org/I4210116208","https://openalex.org/I3020100970"]},{"raw_affiliation_string":"Graduate Institute of Management Chang Gung University  Taoyuan Taiwan","institution_ids":["https://openalex.org/I173093425"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010914146","display_name":"Wei\u2010Chao Lin","orcid":"https://orcid.org/0000-0002-5803-513X"},"institutions":[{"id":"https://openalex.org/I173093425","display_name":"Chang Gung University","ror":"https://ror.org/00d80zx46","country_code":"TW","type":"education","lineage":["https://openalex.org/I173093425"]},{"id":"https://openalex.org/I3020100970","display_name":"Chang Gung Memorial Hospital","ror":"https://ror.org/02verss31","country_code":"TW","type":"healthcare","lineage":["https://openalex.org/I3020100970"]},{"id":"https://openalex.org/I4210116208","display_name":"Linkou Chang Gung Memorial Hospital","ror":"https://ror.org/02dnn6q67","country_code":"TW","type":"healthcare","lineage":["https://openalex.org/I3020100970","https://openalex.org/I4210116208"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Wei\u2010Chao Lin","raw_affiliation_strings":["Department of Digital Financial Technology Chang Gung University  Taoyuan Taiwan","Department of Emergency Medicine Chang Gung Memorial Hospital at Linkou  Taoyuan Taiwan","Department of Information Management Chang Gung University  Taoyuan Taiwan","Graduate Institute of Management Chang Gung University  Taoyuan Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-5803-513X","affiliations":[{"raw_affiliation_string":"Department of Digital Financial Technology Chang Gung University  Taoyuan Taiwan","institution_ids":["https://openalex.org/I173093425"]},{"raw_affiliation_string":"Department of Emergency Medicine Chang Gung Memorial Hospital at Linkou  Taoyuan Taiwan","institution_ids":["https://openalex.org/I4210116208","https://openalex.org/I3020100970"]},{"raw_affiliation_string":"Department of Information Management Chang Gung University  Taoyuan Taiwan","institution_ids":["https://openalex.org/I173093425"]},{"raw_affiliation_string":"Graduate Institute of Management Chang Gung University  Taoyuan Taiwan","institution_ids":["https://openalex.org/I173093425"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010914146"],"corresponding_institution_ids":["https://openalex.org/I173093425","https://openalex.org/I3020100970","https://openalex.org/I4210116208"],"apc_list":{"value":3860,"currency":"USD","value_usd":3860},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54478256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.7860999703407288,"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"}},"topics":[{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.7860999703407288,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.03550000116229057,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.02800000086426735,"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/resampling","display_name":"Resampling","score":0.8810999989509583},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.8708000183105469},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7972999811172485},{"id":"https://openalex.org/keywords/undersampling","display_name":"Undersampling","score":0.7231000065803528},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6101999878883362},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5598000288009644},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5181999802589417},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47589999437332153},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4731000065803528}],"concepts":[{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.8810999989509583},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8708000183105469},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7972999811172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7710000276565552},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.7231000065803528},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6101999878883362},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5598000288009644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587999820709229},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5181999802589417},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.478300005197525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47589999437332153},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46459999680519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4162999987602234},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1111/exsy.70234","is_oa":false,"landing_page_url":"https://doi.org/10.1111/exsy.70234","pdf_url":null,"source":{"id":"https://openalex.org/S72232612","display_name":"Expert Systems","issn_l":"0266-4720","issn":["0266-4720","1468-0394"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2632634862","display_name":null,"funder_award_id":"BMRPH13","funder_id":"https://openalex.org/F4320313619","funder_display_name":"Chang Gung Memorial Hospital"},{"id":"https://openalex.org/G4272131961","display_name":null,"funder_award_id":"MOST\u2010109\u20102314\u2010B\u2010182\u2010048","funder_id":"https://openalex.org/F4320309618","funder_display_name":"Ministry of Science and Technology"},{"id":"https://openalex.org/G5348871170","display_name":null,"funder_award_id":"CMRPD1M0781","funder_id":"https://openalex.org/F4320313619","funder_display_name":"Chang Gung Memorial Hospital"},{"id":"https://openalex.org/G5478351436","display_name":null,"funder_award_id":"MOST 111\u20102410\u2010H\u2010182\u2010015\u2010MY3","funder_id":"https://openalex.org/F4320309618","funder_display_name":"Ministry of Science and Technology"},{"id":"https://openalex.org/G5502486382","display_name":null,"funder_award_id":"BMRPJ25","funder_id":"https://openalex.org/F4320313619","funder_display_name":"Chang Gung Memorial Hospital"}],"funders":[{"id":"https://openalex.org/F4320309618","display_name":"Ministry of Science and Technology","ror":"https://ror.org/02b207r52"},{"id":"https://openalex.org/F4320313619","display_name":"Chang Gung Memorial Hospital","ror":"https://ror.org/02verss31"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2015452969","https://openalex.org/W2099454382","https://openalex.org/W2118978333","https://openalex.org/W2119387367","https://openalex.org/W2131414141","https://openalex.org/W2138776277","https://openalex.org/W2164330572","https://openalex.org/W2167101736","https://openalex.org/W2334028018","https://openalex.org/W2562319768","https://openalex.org/W2569214105","https://openalex.org/W2592842236","https://openalex.org/W2612292012","https://openalex.org/W2612634114","https://openalex.org/W2738681903","https://openalex.org/W2749850822","https://openalex.org/W2800788706","https://openalex.org/W2807027008","https://openalex.org/W2897056982","https://openalex.org/W2899434936","https://openalex.org/W2900329012","https://openalex.org/W2921196390","https://openalex.org/W2978392610","https://openalex.org/W2996982661","https://openalex.org/W3006252432","https://openalex.org/W3006492268","https://openalex.org/W3008233702","https://openalex.org/W3022911566","https://openalex.org/W3034893840","https://openalex.org/W3037763840","https://openalex.org/W3081255334","https://openalex.org/W3130449168","https://openalex.org/W3186962463","https://openalex.org/W3201252053","https://openalex.org/W4211253314","https://openalex.org/W4223646140","https://openalex.org/W4281702443"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"Diabetes":[1],"prediction":[2,23,124,232],"aims":[3],"to":[4,62,89],"identify":[5],"people":[6],"at":[7],"high":[8],"risk":[9],"of":[10,34,43,76,85,93,97,129,175],"developing":[11],"diabetes":[12,22,100],"in":[13,18,99],"the":[14,20,32,35,44,72,81,91,103,127,134,161,173,199,205,215,219,231],"early":[15],"stage.":[16],"However,":[17,66,217],"practice,":[19],"collected":[21],"datasets":[24,158],"are":[25,165],"usually":[26],"class":[27,37],"imbalanced,":[28],"which":[29,204],"means":[30],"that":[31,42,160,230],"size":[33],"diabetic":[36],"is":[38,88,137,194],"much":[39],"smaller":[40],"than":[41,198,237],"nondiabetic":[45],"class.":[46],"To":[47],"address":[48],"this,":[49],"data":[50,77,136,191,223,241],"resampling,":[51],"including":[52],"under,":[53],"over":[54,155],"and":[55,150,172,177,185,190,212,222],"hybrid":[56,152,206],"sampling":[57,153,207],"methods,":[58],"can":[59],"be":[60],"used":[61],"rebalance":[63],"class\u2010imbalanced":[64],"datasets.":[65],"related":[67,157],"studies":[68],"have":[69],"considered":[70],"only":[71],"first":[73,82,189],"two":[74,148],"types":[75,96],"resampling":[78,192,224,242],"methods.":[79],"Therefore,":[80,126],"research":[83],"objective":[84],"this":[86],"paper":[87],"examine":[90],"performances":[92],"these":[94],"three":[95,146,163],"methods":[98,154,164],"prediction.":[101],"On":[102],"other":[104,200],"hand,":[105],"conducting":[106],"feature":[107,131,181,220],"selection":[108,132,182,221],"by":[109,144,183],"selecting":[110],"some":[111],"representative":[112],"features":[113],"from":[114],"a":[115,195],"given":[116],"training":[117],"set":[118],"has":[119],"shown":[120],"potential":[121],"for":[122],"improving":[123],"performance.":[125],"effect":[128],"performing":[130,180],"on":[133,240],"resampled":[135],"further":[138],"investigated.":[139],"The":[140],"experimental":[141],"results":[142],"obtained":[143],"comparing":[145],"undersampling,":[147],"oversampling":[149,167],"four":[151],"six":[156],"show":[159],"top":[162],"random":[166,169],"(ROS),":[168],"undersampling":[170],"(RUS)":[171],"combination":[174,201],"ROS":[176],"RUS.":[178],"Moreover,":[179],"classification":[184],"regression":[186],"tree":[187],"(CART)":[188],"second":[193],"better":[196,235],"choice":[197],"orders,":[202],"among":[203],"method":[208],"using":[209],"Tomek":[210],"links":[211],"SMOTE":[213],"performs":[214],"best.":[216],"applying":[218],"steps":[225],"does":[226],"not":[227],"necessarily":[228],"mean":[229],"model":[233],"provides":[234],"performance":[236],"models":[238],"based":[239],"alone.":[243]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-13T00:00:00"}