{"id":"https://openalex.org/W4401834031","doi":"https://doi.org/10.3233/shti240571","title":"Large Language Models for Synthetic Tabular Health Data: A Benchmark Study","display_name":"Large Language Models for Synthetic Tabular Health Data: A Benchmark Study","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4401834031","doi":"https://doi.org/10.3233/shti240571","pmid":"https://pubmed.ncbi.nlm.nih.gov/39176952"},"language":"en","primary_location":{"id":"doi:10.3233/shti240571","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti240571","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240571","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":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240571","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086979438","display_name":"Marko Miletic","orcid":null},"institutions":[{"id":"https://openalex.org/I130692619","display_name":"Bern University of Applied Sciences","ror":"https://ror.org/02bnkt322","country_code":"CH","type":"education","lineage":["https://openalex.org/I130692619"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marko Miletic","raw_affiliation_strings":["Bern University of Applied Sciences, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bern University of Applied Sciences, Switzerland","institution_ids":["https://openalex.org/I130692619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102842494","display_name":"Murat Sariyar","orcid":"https://orcid.org/0000-0003-3432-2860"},"institutions":[{"id":"https://openalex.org/I130692619","display_name":"Bern University of Applied Sciences","ror":"https://ror.org/02bnkt322","country_code":"CH","type":"education","lineage":["https://openalex.org/I130692619"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Murat Sariyar","raw_affiliation_strings":["Bern University of Applied Sciences, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-3432-2860","affiliations":[{"raw_affiliation_string":"Bern University of Applied Sciences, Switzerland","institution_ids":["https://openalex.org/I130692619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102842494"],"corresponding_institution_ids":["https://openalex.org/I130692619"],"apc_list":null,"apc_paid":null,"fwci":2.119,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.88192781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"316","issue":null,"first_page":"963","last_page":"967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9959999918937683,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9959999918937683,"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/T10028","display_name":"Topic Modeling","score":0.9829000234603882,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7749580144882202},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6053630709648132},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5981466770172119},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5621499419212341},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5528402924537659},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5348600149154663},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5085917711257935},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48783400654792786},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4789448380470276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46478864550590515},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43312591314315796},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.41521745920181274},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41072767972946167},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3529948592185974},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13127267360687256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749580144882202},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6053630709648132},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5981466770172119},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5621499419212341},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5528402924537659},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5348600149154663},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5085917711257935},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48783400654792786},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4789448380470276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46478864550590515},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43312591314315796},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.41521745920181274},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41072767972946167},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3529948592185974},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13127267360687256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","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":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti240571","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti240571","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240571","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:39176952","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39176952","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":null}],"best_oa_location":{"id":"doi:10.3233/shti240571","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti240571","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240571","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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401834031.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W3012140936","https://openalex.org/W3115265188","https://openalex.org/W3118781290","https://openalex.org/W4288296172","https://openalex.org/W4300980427","https://openalex.org/W4306178203","https://openalex.org/W4319793437","https://openalex.org/W4362655426","https://openalex.org/W4387457231","https://openalex.org/W4387839097"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W4231704780","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279"],"abstract_inverted_index":{"Synthetic":[0],"tabular":[1,152],"health":[2],"data":[3,76,153],"plays":[4],"a":[5,68,124],"crucial":[6],"role":[7],"in":[8],"healthcare":[9],"research,":[10],"addressing":[11],"privacy":[12],"regulations":[13],"and":[14,26,40,134,141],"the":[15,30,53,91,99,107,112,128,131,144],"scarcity":[16],"of":[17,52,101,130,147],"publicly":[18],"available":[19],"datasets.":[20],"This":[21],"is":[22],"essential":[23],"for":[24,84,143,150],"diagnostic":[25],"treatment":[27],"advancements.":[28],"Among":[29],"most":[31],"promising":[32],"models":[33,51,105,116,149],"are":[34,77],"transformer-based":[35],"Large":[36],"Language":[37],"Models":[38],"(LLMs)":[39],"Generative":[41],"Adversarial":[42],"Networks":[43],"(GANs).":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,122],"compare":[49],"LLM":[50,55,104,148],"Pythia":[54],"Scaling":[56],"Suite":[57],"with":[58],"varying":[59],"model":[60,71,135],"sizes":[61],"ranging":[62],"from":[63],"14M":[64,114],"to":[65,79,87,119],"1B,":[66],"against":[67],"reference":[69,108],"GAN":[70,109],"(CTGAN).":[72],"The":[73],"generated":[74],"synthetic":[75,151],"used":[78],"train":[80],"random":[81],"forest":[82],"estimators":[83],"classification":[85],"tasks":[86],"make":[88],"predictions":[89],"on":[90],"real-world":[92,145],"data.":[93],"Our":[94],"findings":[95],"indicate":[96],"that":[97],"as":[98],"number":[100],"parameters":[102],"increases,":[103],"outperform":[106],"model.":[110],"Even":[111],"smallest":[113],"parameter":[115],"perform":[117],"comparably":[118],"GANs.":[120],"Moreover,":[121],"observe":[123],"positive":[125],"correlation":[126],"between":[127],"size":[129],"training":[132],"dataset":[133],"performance.":[136],"We":[137],"discuss":[138],"implications,":[139],"challenges,":[140],"considerations":[142],"usage":[146],"generation.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}