{"id":"https://openalex.org/W7127176038","doi":"https://doi.org/10.1007/s13721-025-00723-x","title":"Improving medical data quality via synthetic data generation: a review","display_name":"Improving medical data quality via synthetic data generation: a review","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7127176038","doi":"https://doi.org/10.1007/s13721-025-00723-x"},"language":"en","primary_location":{"id":"doi:10.1007/s13721-025-00723-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13721-025-00723-x","pdf_url":null,"source":{"id":"https://openalex.org/S4210178532","display_name":"Network Modeling Analysis in Health Informatics and Bioinformatics","issn_l":"2192-6662","issn":["2192-6662","2192-6670"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310321666","host_organization_name":"Springer Vienna","host_organization_lineage":["https://openalex.org/P4310321666","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Vienna","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":"Network Modeling Analysis in Health Informatics and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s13721-025-00723-x","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079803277","display_name":"Asifa Mehmood Qureshi","orcid":null},"institutions":[{"id":"https://openalex.org/I94876832","display_name":"Dundalk Institute of Technology","ror":"https://ror.org/01800zd49","country_code":"IE","type":"education","lineage":["https://openalex.org/I94876832"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Asifa Mehmood Qureshi","raw_affiliation_strings":["Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland"],"raw_orcid":"https://orcid.org/0009-0002-4312-353X","affiliations":[{"raw_affiliation_string":"Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland","institution_ids":["https://openalex.org/I94876832"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124755070","display_name":"Abhishek Kaushik","orcid":null},"institutions":[{"id":"https://openalex.org/I94876832","display_name":"Dundalk Institute of Technology","ror":"https://ror.org/01800zd49","country_code":"IE","type":"education","lineage":["https://openalex.org/I94876832"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Abhishek Kaushik","raw_affiliation_strings":["Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland","institution_ids":["https://openalex.org/I94876832"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061564649","display_name":"R\u00f3is\u00edn Loughran","orcid":"https://orcid.org/0000-0002-0974-7106"},"institutions":[{"id":"https://openalex.org/I94876832","display_name":"Dundalk Institute of Technology","ror":"https://ror.org/01800zd49","country_code":"IE","type":"education","lineage":["https://openalex.org/I94876832"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"R\u00f3is\u00edn Loughran","raw_affiliation_strings":["Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland","institution_ids":["https://openalex.org/I94876832"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124790129","display_name":"Kevin McDaid","orcid":null},"institutions":[{"id":"https://openalex.org/I94876832","display_name":"Dundalk Institute of Technology","ror":"https://ror.org/01800zd49","country_code":"IE","type":"education","lineage":["https://openalex.org/I94876832"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Kevin McDaid","raw_affiliation_strings":["Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland","institution_ids":["https://openalex.org/I94876832"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124819757","display_name":"Fergal McCaffery","orcid":null},"institutions":[{"id":"https://openalex.org/I94876832","display_name":"Dundalk Institute of Technology","ror":"https://ror.org/01800zd49","country_code":"IE","type":"education","lineage":["https://openalex.org/I94876832"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Fergal McCaffery","raw_affiliation_strings":["Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Regulated Software Research Centre (RSRC), School of Informatics and Creative Arts, Dundalk Institute of Technology, Dublin Road, Dundalk, Co. Louth, A91K584, Ireland","institution_ids":["https://openalex.org/I94876832"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079803277","https://openalex.org/A5124755070"],"corresponding_institution_ids":["https://openalex.org/I94876832"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11669035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"1","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":0.14910000562667847,"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":0.14910000562667847,"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":0.12049999833106995,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.11680000275373459,"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/oversampling","display_name":"Oversampling","score":0.7164999842643738},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.7116000056266785},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6169000267982483},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5267000198364258},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5024999976158142},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4697999954223633},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.45100000500679016},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.39969998598098755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427999973297119},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.7164999842643738},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.7116000056266785},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6169000267982483},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5253999829292297},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4909999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4851999878883362},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4697999954223633},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C2780724565","wikidata":"https://www.wikidata.org/wiki/Q5227256","display_name":"Data classification","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13721-025-00723-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13721-025-00723-x","pdf_url":null,"source":{"id":"https://openalex.org/S4210178532","display_name":"Network Modeling Analysis in Health Informatics and Bioinformatics","issn_l":"2192-6662","issn":["2192-6662","2192-6670"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310321666","host_organization_name":"Springer Vienna","host_organization_lineage":["https://openalex.org/P4310321666","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Vienna","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":"Network Modeling Analysis in Health Informatics and Bioinformatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s13721-025-00723-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13721-025-00723-x","pdf_url":null,"source":{"id":"https://openalex.org/S4210178532","display_name":"Network Modeling Analysis in Health Informatics and Bioinformatics","issn_l":"2192-6662","issn":["2192-6662","2192-6670"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310321666","host_organization_name":"Springer Vienna","host_organization_lineage":["https://openalex.org/P4310321666","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Vienna","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":"Network Modeling Analysis in Health Informatics and Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4341023913","display_name":null,"funder_award_id":"21/FFP-A/9255","funder_id":"https://openalex.org/F8766430056","funder_display_name":"Research Ireland"}],"funders":[{"id":"https://openalex.org/F8766430056","display_name":"Research Ireland","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W935072310","https://openalex.org/W1990165991","https://openalex.org/W2004291985","https://openalex.org/W2141340736","https://openalex.org/W2148143831","https://openalex.org/W2151792436","https://openalex.org/W2165394871","https://openalex.org/W2172165257","https://openalex.org/W2544063074","https://openalex.org/W2910283416","https://openalex.org/W2951635356","https://openalex.org/W2954884160","https://openalex.org/W2991775327","https://openalex.org/W3004493409","https://openalex.org/W3013316335","https://openalex.org/W3014524176","https://openalex.org/W3022206528","https://openalex.org/W3022574011","https://openalex.org/W3033682799","https://openalex.org/W3034578890","https://openalex.org/W3036099941","https://openalex.org/W3036567070","https://openalex.org/W3042297952","https://openalex.org/W3081061369","https://openalex.org/W3089420282","https://openalex.org/W3093212523","https://openalex.org/W3094239814","https://openalex.org/W3107416342","https://openalex.org/W3109072952","https://openalex.org/W3113541070","https://openalex.org/W3118813946","https://openalex.org/W3127988644","https://openalex.org/W3135721250","https://openalex.org/W3155972762","https://openalex.org/W3165292502","https://openalex.org/W3181414820","https://openalex.org/W3198525581","https://openalex.org/W4200472276","https://openalex.org/W4285496636","https://openalex.org/W4289520498","https://openalex.org/W4290012325","https://openalex.org/W4292264211","https://openalex.org/W4294631339","https://openalex.org/W4312826222","https://openalex.org/W4366091323","https://openalex.org/W4367849434","https://openalex.org/W4379094721","https://openalex.org/W4385804865","https://openalex.org/W4386284679","https://openalex.org/W4386958277","https://openalex.org/W4387122051","https://openalex.org/W4387223711","https://openalex.org/W4389306535","https://openalex.org/W4392302553","https://openalex.org/W4393196588","https://openalex.org/W4396220479","https://openalex.org/W4396674388","https://openalex.org/W4400269243","https://openalex.org/W4400438459","https://openalex.org/W4401007481","https://openalex.org/W4407937589","https://openalex.org/W4411143941"],"related_works":[],"abstract_inverted_index":{"Most":[0],"Artificial":[1],"intelligence":[2],"(AI)":[3],"algorithms":[4,29],"are":[5,47,73,181],"trained":[6],"on":[7,32,119,206],"large-scale":[8],"datasets":[9,46],"to":[10,15,21,40,53,86,188,225],"learn":[11],"complex,":[12],"underlying":[13,208],"patterns":[14],"make":[16],"informed":[17],"decisions.":[18],"However,":[19,199],"due":[20],"their":[22,81],"data-intensive":[23],"nature,":[24],"the":[25,33,36,76,90,100,109,164,171,182,193,200,207,212,222],"performance":[26,195],"of":[27,35,61,92,166,196,202,214],"these":[28],"highly":[30],"depends":[31,205],"quality":[34,158,201],"training":[37],"data.":[38],"Due":[39],"strict":[41],"privacy":[42],"regulations,":[43],"large":[44],"medical":[45],"not":[48,71,149],"readily":[49],"available,":[50],"which":[51],"leads":[52],"reduced":[54],"data":[55,68,93,103,111,128,148,152,204,209,216,227],"sizes":[56],"as":[57,59],"well":[58],"under-representation":[60],"some":[62],"classes":[63],"and":[64,114,122,162,178,221],"demographic":[65,168],"groups.":[66],"These":[67],"shortcomings,":[69],"if":[70],"handled,":[72],"replicated":[74],"by":[75,94,159],"AI":[77],"algorithms,":[78],"thus":[79],"compromising":[80],"performance.":[82],"One":[83],"potential":[84],"solution":[85],"this":[87,106,132],"problem":[88],"is":[89],"augmentation":[91],"generating":[95],"synthetic":[96,110,147],"samples":[97],"that":[98,146],"possess":[99],"same":[101],"real-world":[102,215],"properties.":[104],"Therefore,":[105],"study":[107],"explores":[108],"generation":[112,129,210],"process":[113],"pre-existing":[115],"research,":[116],"mainly":[117],"focusing":[118],"statistical,":[120],"probabilistic,":[121],"Machine":[123],"Learning":[124],"(ML)":[125],"based":[126],"tabular":[127],"methods.":[130],"For":[131],"purpose,":[133],"we":[134],"analysed":[135],"high-quality":[136],"peer-reviewed":[137],"articles":[138],"extracted":[139],"from":[140],"different":[141],"databases.":[142],"The":[143],"findings":[144],"show":[145],"only":[150],"increases":[151],"volume":[153],"but":[154],"also":[155],"improves":[156],"its":[157,179],"increasing":[160],"diversity":[161],"enhancing":[163],"representation":[165],"various":[167],"groups":[169],"within":[170],"datasets.":[172],"Synthetic":[173],"Minority":[174],"Oversampling":[175],"Technique":[176],"(SMOTE)":[177],"variants":[180],"commonly":[183],"used":[184,217],"techniques":[185],"with":[186],"up":[187],"12%":[189],"improvement":[190],"reported":[191],"in":[192],"classification":[194],"a":[197],"classifier.":[198],"artificial":[203],"process,":[211],"characteristics":[213],"for":[218],"subsequent":[219],"modelling,":[220],"evaluation":[223],"metrics":[224],"assess":[226],"quality.":[228]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-03T00:00:00"}