{"id":"https://openalex.org/W4220913927","doi":"https://doi.org/10.1080/03610918.2022.2053717","title":"Effect of data preprocessing on ensemble learning for classification in disease diagnosis","display_name":"Effect of data preprocessing on ensemble learning for classification in disease diagnosis","publication_year":2022,"publication_date":"2022-03-24","ids":{"openalex":"https://openalex.org/W4220913927","doi":"https://doi.org/10.1080/03610918.2022.2053717"},"language":"en","primary_location":{"id":"doi:10.1080/03610918.2022.2053717","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2022.2053717","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Statistics - Simulation and Computation","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/A5072268521","display_name":"Y\u00fcksel \u00d6zkan","orcid":"https://orcid.org/0000-0003-0534-1173"},"institutions":[{"id":"https://openalex.org/I41641357","display_name":"Ege University","ror":"https://ror.org/02eaafc18","country_code":"TR","type":"education","lineage":["https://openalex.org/I41641357"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Y\u00fcksel \u00d6zkan","raw_affiliation_strings":["Department of Biostatistics and Medical Informatics, Faculty of Medicine, Ege University, Izmir, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-0534-1173","affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Medical Informatics, Faculty of Medicine, Ege University, Izmir, Turkey","institution_ids":["https://openalex.org/I41641357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002963683","display_name":"Mert Demirarslan","orcid":"https://orcid.org/0000-0001-8848-7340"},"institutions":[{"id":"https://openalex.org/I41641357","display_name":"Ege University","ror":"https://ror.org/02eaafc18","country_code":"TR","type":"education","lineage":["https://openalex.org/I41641357"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mert Demirarslan","raw_affiliation_strings":["Department of Biostatistics and Medical Informatics, Faculty of Medicine, Ege University, Izmir, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-8848-7340","affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Medical Informatics, Faculty of Medicine, Ege University, Izmir, Turkey","institution_ids":["https://openalex.org/I41641357"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080853718","display_name":"Asl\u0131 S\u00fcner","orcid":"https://orcid.org/0000-0002-6872-9901"},"institutions":[{"id":"https://openalex.org/I41641357","display_name":"Ege University","ror":"https://ror.org/02eaafc18","country_code":"TR","type":"education","lineage":["https://openalex.org/I41641357"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Asl\u0131 Suner","raw_affiliation_strings":["Department of Biostatistics and Medical Informatics, Faculty of Medicine, Ege University, Izmir, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-6872-9901","affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Medical Informatics, Faculty of Medicine, Ege University, Izmir, Turkey","institution_ids":["https://openalex.org/I41641357"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5080853718"],"corresponding_institution_ids":["https://openalex.org/I41641357"],"apc_list":null,"apc_paid":null,"fwci":1.0497,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79783317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"53","issue":"4","first_page":"1657","last_page":"1677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9991999864578247,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9976999759674072,"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/boosting","display_name":"Boosting (machine learning)","score":0.8538137674331665},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7859171628952026},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7497053146362305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.713831901550293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6925930380821228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6880485415458679},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.6254383325576782},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5424982905387878},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.5392533540725708},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.46416714787483215},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4570399224758148},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4463620185852051},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38293346762657166},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3285176753997803}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8538137674331665},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7859171628952026},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7497053146362305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.713831901550293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6925930380821228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6880485415458679},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.6254383325576782},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5424982905387878},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.5392533540725708},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.46416714787483215},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4570399224758148},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4463620185852051},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38293346762657166},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3285176753997803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/03610918.2022.2053717","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2022.2053717","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Statistics - Simulation and Computation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1494052777","https://openalex.org/W1525980546","https://openalex.org/W1534477342","https://openalex.org/W1584236903","https://openalex.org/W1666942233","https://openalex.org/W1678356000","https://openalex.org/W1841820628","https://openalex.org/W1970698820","https://openalex.org/W1977098485","https://openalex.org/W1990748933","https://openalex.org/W1996202672","https://openalex.org/W1997894578","https://openalex.org/W2004902747","https://openalex.org/W2010858925","https://openalex.org/W2012035409","https://openalex.org/W2024046085","https://openalex.org/W2034841618","https://openalex.org/W2043175314","https://openalex.org/W2053154970","https://openalex.org/W2053972945","https://openalex.org/W2073883415","https://openalex.org/W2074184525","https://openalex.org/W2074388642","https://openalex.org/W2083780116","https://openalex.org/W2089367555","https://openalex.org/W2113242816","https://openalex.org/W2124491466","https://openalex.org/W2127841934","https://openalex.org/W2139075905","https://openalex.org/W2139986471","https://openalex.org/W2146713522","https://openalex.org/W2148143831","https://openalex.org/W2150780222","https://openalex.org/W2151580670","https://openalex.org/W2152575748","https://openalex.org/W2155653793","https://openalex.org/W2156762605","https://openalex.org/W2164341120","https://openalex.org/W2164788271","https://openalex.org/W2167460663","https://openalex.org/W2324255546","https://openalex.org/W2397616787","https://openalex.org/W2408157549","https://openalex.org/W2500519874","https://openalex.org/W2525984666","https://openalex.org/W2528545823","https://openalex.org/W2551233626","https://openalex.org/W2581465409","https://openalex.org/W2727650337","https://openalex.org/W2738681903","https://openalex.org/W2741016737","https://openalex.org/W2743598054","https://openalex.org/W2765464339","https://openalex.org/W2788531461","https://openalex.org/W2789526227","https://openalex.org/W2793167745","https://openalex.org/W2795165552","https://openalex.org/W2897124762","https://openalex.org/W2911964244","https://openalex.org/W2963899699","https://openalex.org/W2994844380","https://openalex.org/W3099320515","https://openalex.org/W4205701142","https://openalex.org/W4205930639","https://openalex.org/W4234621662","https://openalex.org/W4294214983"],"related_works":["https://openalex.org/W2967733078","https://openalex.org/W3137904399","https://openalex.org/W4310492845","https://openalex.org/W2885778889","https://openalex.org/W2766514146","https://openalex.org/W4289703016","https://openalex.org/W2885516856","https://openalex.org/W4310224730","https://openalex.org/W3094138326","https://openalex.org/W4296079469"],"abstract_inverted_index":{"In":[0,153],"recent":[1],"years,":[2],"supervised":[3],"machine":[4],"learning":[5,20],"methods":[6,21,170],"have":[7],"increased":[8,125],"attention":[9],"to":[10,34,42,52,71],"extracting":[11],"clinically":[12],"relevant":[13],"information":[14],"from":[15],"complex":[16],"health":[17],"data.":[18],"Ensemble":[19],"enable":[22],"the":[23,36,44,68,112,121,130,139,146,150,161],"establishment":[24],"of":[25,46,111,123,132,165],"more":[26],"successful":[27],"models":[28],"by":[29],"training":[30],"multiple":[31,167],"learners":[32],"jointly":[33],"solve":[35],"same":[37],"problem.":[38],"Herein,":[39],"we":[40,80],"aimed":[41],"compare":[43],"performance":[45,107,122,131],"classification":[47],"algorithms":[48,91,100,113,124,134,148],"after":[49,126],"data":[50,127,168],"preprocessing":[51,128,169],"problems":[53],"such":[54],"as":[55,89,103],"missing":[56],"data,":[57],"class":[58,61],"noise,":[59],"and":[60,84,96,108,129,163],"imbalance":[62],"that":[63,120,145],"may":[64],"be":[65],"encountered":[66],"in":[67],"datasets":[69],"used":[70,81,102],"make":[72],"an":[73],"accurate":[74],"disease":[75],"diagnosis.":[76],"To":[77],"this":[78],"end,":[79],"random":[82,87],"forest":[83,88],"weighted":[85],"subspace":[86],"bagging":[90,140],"while":[92],"additive":[93],"logistic":[94],"regression":[95],"gradient":[97],"boosted":[98],"machines":[99],"were":[101,114,149],"boosting":[104,133,147],"algorithms.":[105,141],"The":[106],"running":[109],"time":[110],"also":[115,143],"calculated.":[116],"Our":[117],"findings":[118],"indicated":[119],"yielded":[135],"higher":[136],"results":[137],"than":[138],"We":[142],"observed":[144],"longest-running":[151],"ones.":[152],"conclusion,":[154],"complementing":[155],"existing":[156],"studies,":[157],"our":[158],"work":[159],"highlights":[160],"importance":[162],"effect":[164],"using":[166],"together.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}