{"id":"https://openalex.org/W3108322837","doi":"https://doi.org/10.1080/03610918.2020.1850790","title":"Nested cross-validation with ensemble feature selection and classification model for high-dimensional biological data","display_name":"Nested cross-validation with ensemble feature selection and classification model for high-dimensional biological data","publication_year":2020,"publication_date":"2020-11-29","ids":{"openalex":"https://openalex.org/W3108322837","doi":"https://doi.org/10.1080/03610918.2020.1850790","mag":"3108322837"},"language":"en","primary_location":{"id":"doi:10.1080/03610918.2020.1850790","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2020.1850790","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/A5049412020","display_name":"Yi Zhong","orcid":"https://orcid.org/0000-0002-7927-5976"},"institutions":[{"id":"https://openalex.org/I4210128618","display_name":"University of Kansas Medical Center","ror":"https://ror.org/036c9yv20","country_code":"US","type":"funder","lineage":["https://openalex.org/I4210128618"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhong","raw_affiliation_strings":["Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, KS, USA","institution_ids":["https://openalex.org/I4210128618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090752431","display_name":"Prabhakar Chalise","orcid":"https://orcid.org/0000-0001-5581-1220"},"institutions":[{"id":"https://openalex.org/I4210128618","display_name":"University of Kansas Medical Center","ror":"https://ror.org/036c9yv20","country_code":"US","type":"funder","lineage":["https://openalex.org/I4210128618"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prabhakar Chalise","raw_affiliation_strings":["Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, KS, USA","institution_ids":["https://openalex.org/I4210128618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100627154","display_name":"Jianghua He","orcid":"https://orcid.org/0000-0002-9718-1009"},"institutions":[{"id":"https://openalex.org/I4210128618","display_name":"University of Kansas Medical Center","ror":"https://ror.org/036c9yv20","country_code":"US","type":"funder","lineage":["https://openalex.org/I4210128618"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianghua He","raw_affiliation_strings":["Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, KS, USA","institution_ids":["https://openalex.org/I4210128618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5090752431"],"corresponding_institution_ids":["https://openalex.org/I4210128618"],"apc_list":null,"apc_paid":null,"fwci":1.3832,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.81260734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"52","issue":"1","first_page":"110","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9897000193595886,"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/cross-validation","display_name":"Cross-validation","score":0.771152675151825},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7454687356948853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7025893926620483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5869841575622559},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5690805912017822},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.5603398084640503},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5460463166236877},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5348039865493774},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5151704549789429},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4733712077140808},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.467792809009552}],"concepts":[{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.771152675151825},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7454687356948853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025893926620483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5869841575622559},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5690805912017822},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.5603398084640503},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5460463166236877},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5348039865493774},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5151704549789429},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4733712077140808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.467792809009552},{"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":[],"locations_count":1,"locations":[{"id":"doi:10.1080/03610918.2020.1850790","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2020.1850790","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":37,"referenced_works":["https://openalex.org/W1164040328","https://openalex.org/W1493357981","https://openalex.org/W1605688901","https://openalex.org/W1896601755","https://openalex.org/W1961004983","https://openalex.org/W1966701961","https://openalex.org/W1975846642","https://openalex.org/W1984000692","https://openalex.org/W1984459577","https://openalex.org/W1990902703","https://openalex.org/W1993273815","https://openalex.org/W1997313699","https://openalex.org/W2067885219","https://openalex.org/W2091825929","https://openalex.org/W2100805904","https://openalex.org/W2109363337","https://openalex.org/W2115629999","https://openalex.org/W2119387367","https://openalex.org/W2125993116","https://openalex.org/W2139151957","https://openalex.org/W2143481518","https://openalex.org/W2155806188","https://openalex.org/W2159400887","https://openalex.org/W2167055186","https://openalex.org/W2167917621","https://openalex.org/W2173528997","https://openalex.org/W2487087946","https://openalex.org/W2608333569","https://openalex.org/W2611104316","https://openalex.org/W2800581155","https://openalex.org/W2886244096","https://openalex.org/W2899065510","https://openalex.org/W2911964244","https://openalex.org/W3154508156","https://openalex.org/W4239510810","https://openalex.org/W4249247926","https://openalex.org/W4251364655"],"related_works":["https://openalex.org/W816105089","https://openalex.org/W912456583","https://openalex.org/W4386564352","https://openalex.org/W2952668426","https://openalex.org/W4234107176","https://openalex.org/W4309048734","https://openalex.org/W2381029635","https://openalex.org/W1556261580","https://openalex.org/W2389646300","https://openalex.org/W4239059384"],"abstract_inverted_index":{"In":[0,37],"recent":[1],"years,":[2],"application":[3],"of":[4,21,52,98,112,137],"feature":[5,16,92],"selection":[6,17,93],"methods":[7,64],"in":[8,29,94,108],"biological":[9],"datasets":[10],"has":[11,124],"greatly":[12],"increased.":[13],"By":[14],"using":[15,120,131,144],"techniques,":[18],"a":[19,44,81,125],"subset":[20],"relevant":[22],"informative":[23],"features":[24,68],"is":[25,80],"obtained":[26,118],"which":[27],"results":[28,51],"more":[30,45],"interpretable":[31],"model":[32,47,73,107],"improving":[33],"the":[34,50,67,71,91,95,101,105,109,121,132,138],"prediction":[35,127],"accuracy.":[36],"addition,":[38],"ensemble":[39,63],"learning":[40,55],"can":[41],"further":[42],"provide":[43],"robust":[46],"by":[48,119],"combining":[49],"multiple":[53],"statistical":[54],"models.":[56],"We":[57],"propose":[58],"an":[59],"algorithm":[60],"that":[61,130],"uses":[62],"to":[65],"select":[66],"and":[69,83,147],"build":[70],"classification":[72,106,116],"with":[74],"selected":[75],"features.":[76],"Our":[77],"proposed":[78,122,139],"approach":[79],"two-step":[82],"two-layer":[84],"cross-validation":[85],"method.":[86],"The":[87,114,135],"first":[88],"step":[89,103],"performs":[90],"inner":[96],"loop":[97,111],"cross-validation,":[99],"whereas":[100],"second":[102],"builds":[104],"outer":[110],"cross-validation.":[113,134],"final":[115],"model,":[117],"method,":[123],"higher":[126],"accuracy":[128],"than":[129],"standard":[133],"applications":[136],"method":[140],"have":[141],"been":[142],"presented":[143],"both":[145],"simulated":[146],"three":[148],"real":[149],"datasets.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}