{"id":"https://openalex.org/W7220534382","doi":null,"title":"FIDELITY AND UTILITY OF SYNTHETIC TABULAR HEALTH DATA: A CROSS-PARADIGM BENCHMARKING OF A CORRELATION-PRESERVING STATISTICAL PIPELINE AND A CONDITIONAL GENERATIVE ADVERSARIAL NETWORK","display_name":"FIDELITY AND UTILITY OF SYNTHETIC TABULAR HEALTH DATA: A CROSS-PARADIGM BENCHMARKING OF A CORRELATION-PRESERVING STATISTICAL PIPELINE AND A CONDITIONAL GENERATIVE ADVERSARIAL NETWORK","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7220534382"},"language":"en","primary_location":{"id":"pmh:oai:ojs2.policyresearchjournal.com:article/2106","doi":null,"is_oa":true,"landing_page_url":"https://policyrj.com/1/article/view/2106","pdf_url":"https://policyrj.com/1/article/download/2106/1733","source":{"id":"https://openalex.org/S7407075239","display_name":"Policy Research Journal","issn_l":"3006-7022","issn":["3006-7022","3006-7030"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3006-7022","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://policyrj.com/1/article/download/2106/1733","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157493942","display_name":"Ishrat Fatima","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]},{"id":"https://openalex.org/I160968435","display_name":"University of Sargodha","ror":"https://ror.org/0086rpr26","country_code":"PK","type":"education","lineage":["https://openalex.org/I160968435"]},{"id":"https://openalex.org/I4405286083","display_name":"COMSATS University Islamabad, Lahore Campus","ror":"https://ror.org/012zjsd73","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960","https://openalex.org/I4405286083"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ishrat Fatima","raw_affiliation_strings":["Department of Statistics , COMSATS University Islamabad (CUI) Lahore","Visiting Lecturer , Department of Statistics , University of Sargodha"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , COMSATS University Islamabad (CUI) Lahore","institution_ids":["https://openalex.org/I16076960","https://openalex.org/I4405286083"]},{"raw_affiliation_string":"Visiting Lecturer , Department of Statistics , University of Sargodha","institution_ids":["https://openalex.org/I160968435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155467696","display_name":"Najwa Liaqat","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]},{"id":"https://openalex.org/I4405286083","display_name":"COMSATS University Islamabad, Lahore Campus","ror":"https://ror.org/012zjsd73","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960","https://openalex.org/I4405286083"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Najwa Liaqat","raw_affiliation_strings":["Department of Statistics , Comsats University Islamabad , Lahore Campus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , Comsats University Islamabad , Lahore Campus","institution_ids":["https://openalex.org/I16076960","https://openalex.org/I4405286083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157648476","display_name":"Mahnoor Saeed","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahnoor Saeed","raw_affiliation_strings":["Campus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Campus","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6967758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.23880000412464142,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.23880000412464142,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2249000072479248,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T14509","display_name":"demographic modeling and climate adaptation","score":0.13120000064373016,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synthetic-tabular-data-generation","display_name":"synthetic tabular data generation","score":0.7820000052452087},{"id":"https://openalex.org/keywords/ctgan","display_name":"CTGAN","score":0.7820000052452087},{"id":"https://openalex.org/keywords/conditional-gan","display_name":"conditional generative adversarial networks","score":0.9330000281333923},{"id":"https://openalex.org/keywords/correlation-preservation","display_name":"correlation preservation","score":0.6919999718666077},{"id":"https://openalex.org/keywords/privacy-preserving-data-sharing","display_name":"privacy-preserving data sharing","score":0.5220000147819519},{"id":"https://openalex.org/keywords/health-data","display_name":"health data","score":0.414000004529953},{"id":"https://openalex.org/keywords/mixed-data","display_name":"mixed data","score":0.6759999990463257},{"id":"https://openalex.org/keywords/small-sample-size","display_name":"small sample size","score":0.7099999785423279},{"id":"https://openalex.org/keywords/time-to-event-endpoints","display_name":"time-to-event outcomes","score":0.6790000200271606},{"id":"https://openalex.org/keywords/survival-analysis","display_name":"survival analysis","score":0.515999972820282},{"id":"https://openalex.org/keywords/binary-classification","display_name":"binary classification","score":0.5419999957084656},{"id":"https://openalex.org/keywords/feature-scaling","display_name":"feature scaling","score":0.48500001430511475},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.4819999933242798},{"id":"https://openalex.org/keywords/discretization-artifacts","display_name":"discretization artifacts","score":0.46700000762939453}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7409999966621399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844000220298767},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.582099974155426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5511000156402588},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4390999972820282},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.3732999861240387},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3465000092983246},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C85461838","wikidata":"https://www.wikidata.org/wiki/Q7100785","display_name":"Ordinal data","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ojs2.policyresearchjournal.com:article/2106","doi":null,"is_oa":true,"landing_page_url":"https://policyrj.com/1/article/view/2106","pdf_url":"https://policyrj.com/1/article/download/2106/1733","source":{"id":"https://openalex.org/S7407075239","display_name":"Policy Research Journal","issn_l":"3006-7022","issn":["3006-7022","3006-7030"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3006-7022","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:ojs2.policyresearchjournal.com:article/2106","doi":null,"is_oa":true,"landing_page_url":"https://policyrj.com/1/article/view/2106","pdf_url":"https://policyrj.com/1/article/download/2106/1733","source":{"id":"https://openalex.org/S7407075239","display_name":"Policy Research Journal","issn_l":"3006-7022","issn":["3006-7022","3006-7030"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3006-7022","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.9391000270843506,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220534382.pdf","grobid_xml":"https://content.openalex.org/works/W7220534382.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2139276809","https://openalex.org/W2343877966","https://openalex.org/W2775363893","https://openalex.org/W3012140936","https://openalex.org/W3112354172","https://openalex.org/W3202454134","https://openalex.org/W3215186461","https://openalex.org/W4224022798","https://openalex.org/W4288455572","https://openalex.org/W4288770119","https://openalex.org/W4289520498","https://openalex.org/W4297369397","https://openalex.org/W4321499582","https://openalex.org/W4323353589","https://openalex.org/W4377023976","https://openalex.org/W4379013731","https://openalex.org/W4388000689","https://openalex.org/W4389386858","https://openalex.org/W4390690081","https://openalex.org/W4393261317","https://openalex.org/W4399583736","https://openalex.org/W4399588179","https://openalex.org/W4404517050"],"related_works":["https://openalex.org/W7148492401","https://openalex.org/W7126118292","https://openalex.org/W6991382996","https://openalex.org/W4224022798","https://openalex.org/W4361765033","https://openalex.org/W4315435229","https://openalex.org/W4410716777","https://openalex.org/W3206696332","https://openalex.org/W4388000689","https://openalex.org/W7154494127"],"abstract_inverted_index":{"Background:":[0],"The":[1,135,157,230,270,347,373],"generation":[2,151,332],"of":[3,58,71,356,400,412,422,429,436,443],"synthetic":[4,102,330],"tabular":[5,118],"health":[6,73,103,119,339],"data":[7,104,166,331,369],"has":[8],"emerged":[9],"as":[10],"a":[11,39,61,88,96],"pivotal":[12],"methodology":[13],"for":[14,101,142,162,255,338,378],"statistical":[15,24,99,136,231,295,327,348,405,437],"simulation,":[16,145],"privacy":[17,423],"preservation,":[18],"and":[19,106,126,132,189,200,207,223,263,284,321,328,389,408,426],"methodological":[20],"validation.":[21],"While":[22],"classical":[23,98],"approaches":[25],"offer":[26],"interpretable,":[27],"correlation-preserving":[28],"synthesis":[29],"through":[30,170],"explicit":[31,244],"parametric":[32,148,361],"modeling,":[33],"generative":[34,445],"adversarial":[35],"networks":[36],"(GANs)":[37],"provide":[38],"flexible,":[40],"non-parametric":[41],"alternative":[42],"that":[43,367,432],"learns":[44],"the":[45,54,68,139,294,353,397,404,410,420,427,434,440],"full":[46],"joint":[47,224],"distribution":[48,319],"directly":[49],"from":[50],"empirical":[51,64],"data.":[52],"Despite":[53],"rapidly":[55],"expanding":[56],"application":[57],"both":[59,335],"paradigms,":[60],"rigorous,":[62],"cross-disciplinary":[63],"comparison":[65],"tailored":[66],"to":[67,204,242,288,293],"specific":[69],"challenges":[70],"mixed-type":[72],"datasets":[74,120,379],"with":[75,129,343,380,439],"small-to-moderate":[76],"sample":[77],"sizes":[78],"remains":[79],"absent.":[80],"Aims":[81],"&":[82,215],"Objective:":[83],"This":[84],"study":[85],"evaluates":[86],"whether":[87],"GAN-based":[89,329],"approach":[90,232,272,375],"(CTGAN)":[91],"offers":[92],"demonstrable":[93],"advantages":[94],"over":[95],"modern":[97],"pipeline":[100,137,349],"generation,":[105],"under":[107],"which":[108,297],"practical":[109],"conditions":[110],"each":[111,342],"method":[112,141,296,414],"excels.":[113],"Methodology:":[114],"Six":[115],"publicly":[116],"available":[117],"were":[121],"selected,":[122],"encompassing":[123],"continuous,":[124],"binary,":[125],"time-to-event":[127],"outcomes":[128],"mixed":[130],"continuous":[131],"categorical":[133,184,318],"predictors.":[134],"comprised":[138],"Modgo":[140],"covariate":[143],"matrix":[144,246],"followed":[146],"by":[147],"model-based":[149],"outcome":[150,362],"(linear,":[152],"logistic,":[153],"or":[154,360,385],"Cox":[155],"models).":[156],"CTGAN":[158,271,374],"architecture":[159],"was":[160,168,211],"trained":[161],"1000":[163],"epochs.":[164],"Synthetic":[165],"quality":[167],"assessed":[169],"quantitative":[171],"distributional":[172,441],"similarity":[173],"metrics":[174],"(moments,":[175],"Kullback\u2013Leibler":[176],"divergence,":[177],"Kolmogorov\u2013Smirnov":[178],"statistic,":[179],"Jensen\u2013Shannon":[180],"distance,":[181],"Wasserstein":[182],"distance),":[183],"concordance,":[185],"pairwise":[186,238],"correlation":[187,245,358],"recovery,":[188],"downstream":[190,323],"predictive":[191],"utility":[192],"measured":[193],"via":[194],"mean":[195,275],"squared":[196,276],"error,":[197],"balanced":[198],"accuracy,":[199],"concordance":[201],"index.":[202],"Sensitivity":[203],"variable":[205],"scaling":[206],"training":[208],"epoch":[209],"selection":[210],"systematically":[212],"examined.":[213],"Results":[214],"Findings:":[216],"Both":[217,313],"methods":[218,314,333],"successfully":[219],"reproduced":[220],"univariate":[221],"distributions":[222],"dependence":[225],"structures":[226,359],"across":[227],"all":[228],"datasets.":[229],"demonstrated":[233],"superior":[234],"fidelity":[235],"in":[236,278,291,310,317],"recovering":[237],"linear":[239,279],"correlations,":[240],"attributable":[241],"its":[243],"estimation.":[247],"Consequently,":[248],"it":[249],"yielded":[250],"marginally":[251],"higher":[252],"prediction":[253],"performance":[254],"binary":[256],"classification":[257],"(balanced":[258],"accuracy":[259],"0.85":[260],"vs.":[261,268,282],"0.78)":[262],"survival":[264],"analysis":[265],"(C-index":[266],"0.71":[267],"0.65).":[269],"achieved":[273],"lower":[274],"error":[277],"regression":[280],"(1.02":[281],"2.82)":[283],"exhibited":[285],"pronounced":[286],"robustness":[287],"feature":[289],"scaling,":[290],"contrast":[292],"failed":[298],"catastrophically":[299],"without":[300],"prior":[301],"standardization.":[302],"CTGAN-generated":[303],"densities":[304],"occasionally":[305],"displayed":[306],"discretized":[307],"artifacts,":[308],"particularly":[309],"small":[311],"samples.":[312],"performed":[315],"comparably":[316],"recovery":[320],"overall":[322],"utility.":[324],"Conclusions:":[325],"Classical":[326],"are":[334,392],"viable":[336],"tools":[337],"simulation":[340,406],"studies,":[341],"distinct":[344],"operational":[345],"strengths.":[346],"is":[350,364,371,376],"recommended":[351],"when":[352,386],"precise":[354],"reproduction":[355],"known":[357],"relationships":[363],"critical,":[365],"provided":[366],"rigorous":[368],"preprocessing":[370,388],"undertaken.":[372],"preferable":[377],"complex":[381],"multimodality,":[382],"heavy":[383],"tails,":[384],"minimal":[387],"automated":[390],"implementation":[391],"desired.":[393],"These":[394],"findings":[395],"sanction":[396],"principled":[398],"integration":[399],"AI-based":[401],"generators":[402],"into":[403],"repertoire":[407],"underscore":[409],"importance":[411],"context-dependent":[413],"selection.":[415],"Future":[416],"research":[417],"should":[418],"prioritize":[419],"incorporation":[421],"preservation":[424],"mechanisms":[425],"development":[428],"hybrid":[430],"architectures":[431],"couple":[433],"interpretability":[435],"models":[438],"flexibility":[442],"deep":[444],"networks.":[446]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-06T00:00:00"}