{"id":"https://openalex.org/W4413050125","doi":"https://doi.org/10.3233/shti250924","title":"Evaluation of Synthetic Data Generation Methods for Medical Tabular Data: Representation of Distribution Tails","display_name":"Evaluation of Synthetic Data Generation Methods for Medical Tabular Data: Representation of Distribution Tails","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413050125","doi":"https://doi.org/10.3233/shti250924","pmid":"https://pubmed.ncbi.nlm.nih.gov/40775942"},"language":"en","primary_location":{"id":"doi:10.3233/shti250924","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250924","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti250924","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064722835","display_name":"Ohmi Mohri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109338","display_name":"University of Tokyo Hospital","ror":"https://ror.org/022cvpj02","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210109338"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ohmi Mohri","raw_affiliation_strings":["Department of Healthcare Information Management, The University of Tokyo Hospital"],"raw_orcid":"https://orcid.org/0009-0008-0208-4099","affiliations":[{"raw_affiliation_string":"Department of Healthcare Information Management, The University of Tokyo Hospital","institution_ids":["https://openalex.org/I4210109338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003218088","display_name":"Tomohisa Seki","orcid":"https://orcid.org/0000-0002-4281-135X"},"institutions":[{"id":"https://openalex.org/I4210109338","display_name":"University of Tokyo Hospital","ror":"https://ror.org/022cvpj02","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210109338"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohisa Seki","raw_affiliation_strings":["Department of Healthcare Information Management, The University of Tokyo Hospital"],"raw_orcid":"https://orcid.org/0000-0002-4281-135X","affiliations":[{"raw_affiliation_string":"Department of Healthcare Information Management, The University of Tokyo Hospital","institution_ids":["https://openalex.org/I4210109338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021892377","display_name":"Yoshimasa Kawazoe","orcid":"https://orcid.org/0000-0002-7277-0827"},"institutions":[{"id":"https://openalex.org/I4210109338","display_name":"University of Tokyo Hospital","ror":"https://ror.org/022cvpj02","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210109338"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshimasa Kawazoe","raw_affiliation_strings":["Artificial Intelligence and Digital Twin in Healthcare, Graduate School of Medicine, The University of Tokyo","Department of Healthcare Information Management, The University of Tokyo Hospital"],"raw_orcid":"https://orcid.org/0000-0002-7277-0827","affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Digital Twin in Healthcare, Graduate School of Medicine, The University of Tokyo","institution_ids":[]},{"raw_affiliation_string":"Department of Healthcare Information Management, The University of Tokyo Hospital","institution_ids":["https://openalex.org/I4210109338"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052636056","display_name":"Kazuhiko Ohe","orcid":"https://orcid.org/0000-0002-4296-9536"},"institutions":[{"id":"https://openalex.org/I4210109338","display_name":"University of Tokyo Hospital","ror":"https://ror.org/022cvpj02","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210109338"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiko Ohe","raw_affiliation_strings":["Department of Biomedical Informatics, Graduate School of Medicine, The University of Tokyo","Department of Healthcare Information Management, The University of Tokyo Hospital"],"raw_orcid":"https://orcid.org/0000-0002-4296-9536","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Graduate School of Medicine, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Department of Healthcare Information Management, The University of Tokyo Hospital","institution_ids":["https://openalex.org/I4210109338"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23948443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"329","issue":null,"first_page":"668","last_page":"672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13398","display_name":"Data Analysis with R","score":0.8560000061988831,"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/T13398","display_name":"Data Analysis with R","score":0.8560000061988831,"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/T10862","display_name":"AI in cancer detection","score":0.824999988079071,"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":0.8130999803543091,"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":0.670616865158081},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6448860168457031},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5534124374389648},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5165787935256958},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4432043135166168},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44316643476486206},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41738349199295044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4164649546146393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670616865158081},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6448860168457031},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5534124374389648},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5165787935256958},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4432043135166168},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44316643476486206},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41738349199295044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4164649546146393},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti250924","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250924","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:40775942","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40775942","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":"Studies in health technology and informatics","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.3233/shti250924","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250924","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Synthetic":[0],"data":[1,17,58,72,109],"generation":[2,59,129],"by":[3],"Artificial":[4],"Intelligence":[5],"(AI)":[6],"and":[7,15,21,25,82],"other":[8],"means":[9],"has":[10],"the":[11,46,84,95,101,107,111,116],"potential":[12],"to":[13],"share":[14],"analyze":[16],"while":[18],"preserving":[19],"privacy":[20],"maintaining":[22],"statistical":[23],"characteristics,":[24],"various":[26],"methods":[27,60],"have":[28,62],"been":[29],"developed.":[30],"In":[31],"medical":[32,141],"datasets,":[33],"abnormal":[34],"values":[35,41],"are":[36],"more":[37],"critical":[38],"than":[39,110],"normal":[40],"for":[42],"identifying":[43],"diseases,":[44],"making":[45],"accurate":[47],"representation":[48,85],"of":[49,56,86,103,106,133],"distribution":[50,66,87,104,124],"tails":[51,102,125],"essential.":[52],"However,":[53],"existing":[54],"evaluations":[55],"synthetic":[57,71,140],"often":[61],"not":[63],"focused":[64],"on":[65],"tails.":[67,88],"This":[68],"study":[69],"generated":[70],"from":[73],"actual":[74],"specimen":[75],"test":[76],"results":[77],"at":[78],"a":[79,90],"university":[80],"hospital":[81],"analyzed":[83],"As":[89,123],"result,":[91],"we":[92],"found":[93],"that":[94],"Forest":[96],"Diffusion":[97],"model":[98,114],"better":[99],"represents":[100],"characteristics":[105,135],"original":[108],"Gaussian":[112],"Copula":[113],"or":[115],"Conditional":[117],"generative":[118],"adversarial":[119],"networks":[120],"(CTGAN)":[121],"model.":[122],"vary":[126],"significantly":[127],"across":[128],"methods,":[130],"careful":[131],"consideration":[132],"tail":[134],"is":[136],"crucial":[137],"when":[138],"generating":[139],"data.":[142]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
