{"id":"https://openalex.org/W4403446297","doi":"https://doi.org/10.1109/access.2024.3482192","title":"Empirical Study of Feature Selection Methods in Regression for Large-Scale Healthcare Data: A Case Study on Estimating Dental Expenditures","display_name":"Empirical Study of Feature Selection Methods in Regression for Large-Scale Healthcare Data: A Case Study on Estimating Dental Expenditures","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403446297","doi":"https://doi.org/10.1109/access.2024.3482192"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3482192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3482192","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3482192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087138085","display_name":"Veena Mayya","orcid":"https://orcid.org/0000-0002-8091-5053"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Veena Mayya","raw_affiliation_strings":["Center for Decision Support Systems and Informatics, School of Global Health Management and Informatics, University of Central Florida, Orlando, FL, USA","School of Global Health Management and Informatics, Center for Decision Support Systems and Informatics, University of Central Florida, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0002-8091-5053","affiliations":[{"raw_affiliation_string":"Center for Decision Support Systems and Informatics, School of Global Health Management and Informatics, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"School of Global Health Management and Informatics, Center for Decision Support Systems and Informatics, University of Central Florida, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000885736","display_name":"Christian King","orcid":"https://orcid.org/0000-0003-1157-5734"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian King","raw_affiliation_strings":["Center for Decision Support Systems and Informatics, School of Global Health Management and Informatics, University of Central Florida, Orlando, FL, USA","School of Global Health Management and Informatics, Center for Decision Support Systems and Informatics, University of Central Florida, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0003-1157-5734","affiliations":[{"raw_affiliation_string":"Center for Decision Support Systems and Informatics, School of Global Health Management and Informatics, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"School of Global Health Management and Informatics, Center for Decision Support Systems and Informatics, University of Central Florida, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849422","display_name":"Giang T. Vu","orcid":"https://orcid.org/0000-0003-1159-6973"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giang T. Vu","raw_affiliation_strings":["Center for Decision Support Systems and Informatics, School of Global Health Management and Informatics, University of Central Florida, Orlando, FL, USA","School of Global Health Management and Informatics, Center for Decision Support Systems and Informatics, University of Central Florida, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0003-1159-6973","affiliations":[{"raw_affiliation_string":"Center for Decision Support Systems and Informatics, School of Global Health Management and Informatics, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"School of Global Health Management and Informatics, Center for Decision Support Systems and Informatics, University of Central Florida, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102810707","display_name":"Varadraj P. Gurupur","orcid":"https://orcid.org/0000-0003-1596-9298"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Varadraj Gurupur","raw_affiliation_strings":["Center for Decision Support Systems and Informatics, School of Global Health Management and Informatics, University of Central Florida, Orlando, FL, USA","School of Global Health Management and Informatics, Center for Decision Support Systems and Informatics, University of Central Florida, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0003-1596-9298","affiliations":[{"raw_affiliation_string":"Center for Decision Support Systems and Informatics, School of Global Health Management and Informatics, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"School of Global Health Management and Informatics, Center for Decision Support Systems and Informatics, University of Central Florida, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":4.5703,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.95148209,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"153564","last_page":"153579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14484","display_name":"Technology and Data Analysis","score":0.41100001335144043,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14484","display_name":"Technology and Data Analysis","score":0.41100001335144043,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12647","display_name":"Traditional Chinese Medicine Studies","score":0.40689998865127563,"subfield":{"id":"https://openalex.org/subfields/2707","display_name":"Complementary and alternative medicine"},"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/feature-selection","display_name":"Feature selection","score":0.7439284920692444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.63739413022995},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6215364336967468},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5696282386779785},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.5526936650276184},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.5185856819152832},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47634175419807434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4547138214111328},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4540362060070038},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.431564062833786},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42326247692108154},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.41913846135139465},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3664420545101166},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3494299650192261},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17425984144210815}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7439284920692444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.63739413022995},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6215364336967468},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5696282386779785},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.5526936650276184},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.5185856819152832},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47634175419807434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4547138214111328},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4540362060070038},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.431564062833786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42326247692108154},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.41913846135139465},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3664420545101166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3494299650192261},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17425984144210815},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3482192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3482192","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:500680133f6e4736a7c38b33a921d7c0","is_oa":true,"landing_page_url":"https://doaj.org/article/500680133f6e4736a7c38b33a921d7c0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 153564-153579 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3482192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3482192","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1967192683","https://openalex.org/W2011301426","https://openalex.org/W2036887984","https://openalex.org/W2072026441","https://openalex.org/W2087686509","https://openalex.org/W2125847307","https://openalex.org/W2135458935","https://openalex.org/W2143426320","https://openalex.org/W2152195021","https://openalex.org/W2169245194","https://openalex.org/W2295598076","https://openalex.org/W2342249984","https://openalex.org/W2468622493","https://openalex.org/W2516809705","https://openalex.org/W2772592523","https://openalex.org/W2794866761","https://openalex.org/W2928048063","https://openalex.org/W2963042850","https://openalex.org/W2997591727","https://openalex.org/W3011631149","https://openalex.org/W3034245077","https://openalex.org/W3035509652","https://openalex.org/W3035965352","https://openalex.org/W3045004532","https://openalex.org/W3046595277","https://openalex.org/W3110336092","https://openalex.org/W3115324092","https://openalex.org/W3137665052","https://openalex.org/W3158456519","https://openalex.org/W3160301105","https://openalex.org/W3198244247","https://openalex.org/W3198990261","https://openalex.org/W3210865164","https://openalex.org/W4210494754","https://openalex.org/W4220997467","https://openalex.org/W4252660591","https://openalex.org/W4283593236","https://openalex.org/W4285133390","https://openalex.org/W4292402161","https://openalex.org/W4294151673","https://openalex.org/W4294691580","https://openalex.org/W4295886337","https://openalex.org/W4304806670","https://openalex.org/W4304889692","https://openalex.org/W4306731729","https://openalex.org/W4307498319","https://openalex.org/W4312247183","https://openalex.org/W4312822299","https://openalex.org/W4321502669","https://openalex.org/W4366679782","https://openalex.org/W4376640984","https://openalex.org/W4381249462","https://openalex.org/W4384080487","https://openalex.org/W4384923081","https://openalex.org/W4385482819","https://openalex.org/W4386634564","https://openalex.org/W4386951748","https://openalex.org/W4387546264","https://openalex.org/W4387717664","https://openalex.org/W4388145374","https://openalex.org/W4388288681","https://openalex.org/W4388819569","https://openalex.org/W4388972579","https://openalex.org/W4389104743","https://openalex.org/W4389161223","https://openalex.org/W4389231539","https://openalex.org/W4390969301","https://openalex.org/W4391547558","https://openalex.org/W4391661550","https://openalex.org/W4391849992","https://openalex.org/W4392513858","https://openalex.org/W4392667149","https://openalex.org/W4392854411","https://openalex.org/W4392882189","https://openalex.org/W4393254990","https://openalex.org/W4394063683","https://openalex.org/W4394841027","https://openalex.org/W4399146432","https://openalex.org/W4399526810","https://openalex.org/W4399939200","https://openalex.org/W6601034125","https://openalex.org/W6607717118","https://openalex.org/W6737947904","https://openalex.org/W6750729320","https://openalex.org/W6809356829","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W4386564352","https://openalex.org/W2952668426","https://openalex.org/W31220157","https://openalex.org/W2312753042","https://openalex.org/W4289356671","https://openalex.org/W2389155397","https://openalex.org/W2165884543","https://openalex.org/W3186837933","https://openalex.org/W2368989808","https://openalex.org/W1969346022"],"abstract_inverted_index":{"The":[0,109,141],"complexity":[1],"and":[2,27,47,97,167],"high":[3],"dimensionality":[4],"of":[5,21,57,114,116,180,198,211],"healthcare":[6],"data":[7],"present":[8],"substantial":[9],"challenges":[10],"in":[11,112],"building":[12],"machine":[13],"learning":[14],"(ML)":[15],"models,":[16],"given":[17],"the":[18,63,87,106,129,134,138,145,163,184,196,199,209],"large":[19],"number":[20],"variables":[22],"such":[23,38,160],"as":[24,39,161],"patient":[25],"demographics":[26],"medical":[28],"history.":[29],"Effective":[30],"feature":[31,58,99,107,124,172],"selection":[32,59,100,125,173],"is":[33,119,148],"crucial":[34],"to":[35,61,85,104,183,194,207],"address":[36],"issues":[37],"increased":[40],"computational":[41],"resource,":[42],"longer":[43],"training":[44],"times,":[45],"overfitting,":[46],"reduced":[48,155],"model":[49,176],"interpretability,":[50],"etc.":[51],"This":[52],"study":[53],"evaluates":[54],"a":[55,122],"range":[56],"methods":[60],"identify":[62],"most":[64],"impactful":[65],"features":[66,136,213],"for":[67,150,165],"predicting":[68,215],"dental":[69,216],"expenditures":[70],"using":[71,121],"publicly":[72],"available":[73],"Medical":[74],"Expenditure":[75],"Panel":[76],"Survey":[77],"(MEPS)":[78],"data.":[79],"Sixteen":[80],"ML":[81,201],"models":[82],"are":[83,102,205],"assessed":[84],"determine":[86],"top":[88],"performing":[89],"model,":[90,202],"after":[91],"which":[92],"state-of-the-art":[93],"filter,":[94],"wrapper,":[95],"embedded,":[96],"hybrid":[98,123],"techniques":[101],"applied":[103],"optimize":[105],"set.":[108],"highest":[110],"performance,":[111,177],"terms":[113],"coefficient":[115],"determination":[117],"($R^{2}$),":[118],"achieved":[120,187],"method":[126],"that":[127,144],"combines":[128],"mutual":[130],"information":[131],"filter":[132],"with":[133,154,188],"embedded":[135],"from":[137],"CatBoost":[139],"regressor.":[140],"results":[142],"indicate":[143],"proposed":[146],"system":[147],"suitable":[149],"real-time":[151],"deployment":[152],"even":[153],"features,":[156],"providing":[157],"potential":[158],"benefits":[159],"minimizing":[162],"need":[164],"irrelevant":[166],"difficult-to-obtain":[168],"features.":[169,192],"Moreover,":[170],"automated":[171],"significantly":[174],"enhances":[175],"yielding":[178],"a$R^{2}$score":[179],"0.86,":[181],"compared":[182],"score":[185],"0.73":[186],"carefully":[189],"selected":[190],"manual":[191],"Additionally,":[193],"enhance":[195],"interpretability":[197],"top-performing":[200],"explanatory":[203],"visualizations":[204],"employed":[206],"examine":[208],"influence":[210],"key":[212],"on":[214],"expenditures.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}