{"id":"https://openalex.org/W2154290668","doi":"https://doi.org/10.1186/1758-2946-6-10","title":"Cross-validation pitfalls when selecting and assessing regression and classification models","display_name":"Cross-validation pitfalls when selecting and assessing regression and classification models","publication_year":2014,"publication_date":"2014-03-29","ids":{"openalex":"https://openalex.org/W2154290668","doi":"https://doi.org/10.1186/1758-2946-6-10","mag":"2154290668","pmid":"https://pubmed.ncbi.nlm.nih.gov/24678909"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-6-10","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-6-10","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-6-10","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-6-10","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073226546","display_name":"Damjan Krstaji\u0107","orcid":"https://orcid.org/0000-0002-7381-8570"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Damjan Krstajic","raw_affiliation_strings":["Clinical Persona Inc, 932 Mouton Circle, East Palo Alto, CA, 94303, USA. damjan.krstajic@rcc.org.rs","Laboratory for Molecular Biomedicine, Institute of Molecular Genetics and Genetic Engineering, University of Belgrade, Vojvode Stepe 444a, 11010, Beograd, Serbia. damjan.krstajic@rcc.org.rs","Research Centre for Cheminformatics, Jasenova 7, 11030, Beograd, Serbia. damjan.krstajic@rcc.org.rs","Research Centre for Cheminformatics, Jasenova 7, 11030, Beograd, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clinical Persona Inc, 932 Mouton Circle, East Palo Alto, CA, 94303, USA. damjan.krstajic@rcc.org.rs","institution_ids":[]},{"raw_affiliation_string":"Laboratory for Molecular Biomedicine, Institute of Molecular Genetics and Genetic Engineering, University of Belgrade, Vojvode Stepe 444a, 11010, Beograd, Serbia. damjan.krstajic@rcc.org.rs","institution_ids":[]},{"raw_affiliation_string":"Research Centre for Cheminformatics, Jasenova 7, 11030, Beograd, Serbia. damjan.krstajic@rcc.org.rs","institution_ids":[]},{"raw_affiliation_string":"Research Centre for Cheminformatics, Jasenova 7, 11030, Beograd, Serbia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046069907","display_name":"Ljubomir Buturovi\u0107","orcid":"https://orcid.org/0000-0003-1732-4338"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ljubomir J Buturovic","raw_affiliation_strings":["Clinical Persona Inc, 932 Mouton Circle, East Palo Alto, CA, 94303, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clinical Persona Inc, 932 Mouton Circle, East Palo Alto, CA, 94303, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056129485","display_name":"David E. Leahy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162142","display_name":"Redx Pharma (United Kingdom)","ror":"https://ror.org/04wysdg63","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210162142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David E Leahy","raw_affiliation_strings":["Molplex Pharmaceuticals, Alderly Park, Macclesfield, SK10 4TF, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molplex Pharmaceuticals, Alderly Park, Macclesfield, SK10 4TF, UK","institution_ids":["https://openalex.org/I4210162142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103067787","display_name":"Simon Thomas","orcid":"https://orcid.org/0000-0002-1761-2623"},"institutions":[{"id":"https://openalex.org/I4210093855","display_name":"C4X Discovery (United Kingdom)","ror":"https://ror.org/00hfwa053","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210093855"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Thomas","raw_affiliation_strings":["Cyprotex Discovery Ltd, 15 Beech Lane, Macclesfield, SK10 2DR, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cyprotex Discovery Ltd, 15 Beech Lane, Macclesfield, SK10 2DR, UK","institution_ids":["https://openalex.org/I4210093855"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073226546"],"corresponding_institution_ids":[],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":30.8859,"has_fulltext":true,"cited_by_count":1040,"citation_normalized_percentile":{"value":0.99709518,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"6","issue":"1","first_page":"10","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.30079999566078186,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.30079999566078186,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0640999972820282,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.05999999865889549,"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/computer-science","display_name":"Computer science","score":0.6685812473297119},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49042221903800964},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.47659415006637573},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.45718854665756226},{"id":"https://openalex.org/keywords/model-validation","display_name":"Model validation","score":0.4158143103122711},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.41218698024749756},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33074408769607544},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31717196106910706},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2343347668647766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1164340078830719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6685812473297119},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49042221903800964},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.47659415006637573},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.45718854665756226},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.4158143103122711},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.41218698024749756},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33074408769607544},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31717196106910706},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2343347668647766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1164340078830719}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/1758-2946-6-10","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-6-10","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-6-10","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:24678909","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24678909","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":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:3994246","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3994246","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1758-2946-6-10","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-6-10","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-6-10","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2154290668.pdf","grobid_xml":"https://content.openalex.org/works/W2154290668.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1594031697","https://openalex.org/W1680392829","https://openalex.org/W1942197703","https://openalex.org/W1966508716","https://openalex.org/W1971104901","https://openalex.org/W1977340881","https://openalex.org/W1981251392","https://openalex.org/W1981552604","https://openalex.org/W1988712483","https://openalex.org/W2012540065","https://openalex.org/W2032481853","https://openalex.org/W2050297026","https://openalex.org/W2080951248","https://openalex.org/W2092372160","https://openalex.org/W2097360283","https://openalex.org/W2097998348","https://openalex.org/W2107956883","https://openalex.org/W2111814036","https://openalex.org/W2112081648","https://openalex.org/W2141007997","https://openalex.org/W2143684265","https://openalex.org/W2153635508","https://openalex.org/W2157397778","https://openalex.org/W2170744043","https://openalex.org/W2171074980","https://openalex.org/W2174230067","https://openalex.org/W2787894218","https://openalex.org/W2796308790","https://openalex.org/W3085162807","https://openalex.org/W3100970744","https://openalex.org/W3104887532","https://openalex.org/W4294541781"],"related_works":["https://openalex.org/W816105089","https://openalex.org/W2100523380","https://openalex.org/W4318240167","https://openalex.org/W31220157","https://openalex.org/W2312753042","https://openalex.org/W4289356671","https://openalex.org/W3048572280","https://openalex.org/W2389155397","https://openalex.org/W2165884543","https://openalex.org/W3186837933"],"abstract_inverted_index":{"BACKGROUND:":[0],"We":[1,73,132,177],"address":[2],"the":[3,58,124,128,145,150,157,179,192],"problem":[4],"of":[5,30,57,68,135,144,152,156,181,194],"selecting":[6,169,185],"and":[7,10,40,47,89,91,106,116,119,170,173],"assessing":[8,171,199],"classification":[9,88,172],"regression":[11,174],"models":[12,20],"using":[13,123],"cross-validation.":[14],"Current":[15],"state-of-the-art":[16],"methods":[17,60],"can":[18],"yield":[19],"with":[21],"high":[22],"variance,":[23],"rendering":[24],"them":[25],"unsuitable":[26],"for":[27,79,84,99,122],"a":[28,94,200],"number":[29],"practical":[31],"applications":[32],"including":[33],"QSAR.":[34],"In":[35],"this":[36],"paper":[37],"we":[38,92,109],"describe":[39,74],"evaluate":[41],"best":[42],"practices":[43],"which":[44,64,148],"improve":[45],"reliability":[46],"increase":[48],"confidence":[49],"in":[50,75,87,127,159],"selected":[51],"models.":[52,175],"A":[53],"key":[54],"operational":[55],"component":[56],"proposed":[59],"is":[61,149],"cloud":[62],"computing":[63],"enables":[65],"routine":[66],"use":[67],"previously":[69],"infeasible":[70],"approaches.":[71],"METHODS:":[72],"detail":[76],"an":[77,186],"algorithm":[78,98],"repeated":[80,95,125],"grid-search":[81,114,126],"V-fold":[82,160],"cross-validation":[83,97,115,183,197],"parameter":[85,107],"tuning":[86,108],"regression,":[90],"define":[93,110],"nested":[96,196],"model":[100],"assessment.":[101],"As":[102],"regards":[103],"variable":[104],"selection":[105],"two":[111],"algorithms":[112,137],"(repeated":[113],"double":[117],"cross-validation),":[118],"provide":[120],"arguments":[121],"general":[129],"case.":[130],"RESULTS:":[131],"show":[133],"results":[134],"our":[136],"on":[138],"seven":[139],"QSAR":[140],"datasets.":[141],"The":[142],"variation":[143],"prediction":[146,201],"performance,":[147],"result":[151],"choosing":[153],"different":[154],"splits":[155],"dataset":[158],"cross-validation,":[161],"needs":[162],"to":[163],"be":[164],"taken":[165],"into":[166],"account":[167],"when":[168,184,198],"CONCLUSIONS:":[176],"demonstrate":[178],"importance":[180,193],"repeating":[182,195],"optimal":[187],"model,":[188],"as":[189,191],"well":[190],"error.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":48},{"year":2025,"cited_by_count":128},{"year":2024,"cited_by_count":139},{"year":2023,"cited_by_count":142},{"year":2022,"cited_by_count":150},{"year":2021,"cited_by_count":133},{"year":2020,"cited_by_count":108},{"year":2019,"cited_by_count":59},{"year":2018,"cited_by_count":60},{"year":2017,"cited_by_count":29},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":21},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}