{"id":"https://openalex.org/W4410448385","doi":"https://doi.org/10.3233/shti250384","title":"Open-Source Synthetic Data Generation of Clinical Routine Data","display_name":"Open-Source Synthetic Data Generation of Clinical Routine Data","publication_year":2025,"publication_date":"2025-05-15","ids":{"openalex":"https://openalex.org/W4410448385","doi":"https://doi.org/10.3233/shti250384","pmid":"https://pubmed.ncbi.nlm.nih.gov/40380494"},"language":"en","primary_location":{"id":"doi:10.3233/shti250384","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250384","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250384","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://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250384","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117573585","display_name":"Michael Gr\u00f6\u00dfler","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I4210108711","display_name":"University Medical Center Hamburg-Eppendorf","ror":"https://ror.org/01zgy1s35","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I159176309","https://openalex.org/I4210108711"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Gr\u00f6ssler","raw_affiliation_strings":["Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf"],"raw_orcid":"https://orcid.org/0009-0000-5244-0225","affiliations":[{"raw_affiliation_string":"Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I4210108711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039000576","display_name":"Frank \u00dcckert","orcid":"https://orcid.org/0000-0001-8362-5636"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I4210108711","display_name":"University Medical Center Hamburg-Eppendorf","ror":"https://ror.org/01zgy1s35","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I159176309","https://openalex.org/I4210108711"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank \u00dcckert","raw_affiliation_strings":["Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf"],"raw_orcid":"https://orcid.org/0000-0001-8362-5636","affiliations":[{"raw_affiliation_string":"Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I4210108711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024406157","display_name":"Layla Tabea Riemann","orcid":"https://orcid.org/0000-0001-5411-7288"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I4210108711","display_name":"University Medical Center Hamburg-Eppendorf","ror":"https://ror.org/01zgy1s35","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I159176309","https://openalex.org/I4210108711"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Layla Tabea Riemann","raw_affiliation_strings":["Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf"],"raw_orcid":"https://orcid.org/0000-0001-5411-7288","affiliations":[{"raw_affiliation_string":"Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I4210108711"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14115855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"327","issue":null,"first_page":"482","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.973800003528595,"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":0.973800003528595,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.9422000050544739,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13500","display_name":"Probability and Statistical Research","score":0.935699999332428,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8000290393829346},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.5992586612701416},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5918285250663757},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5559954047203064},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5120194554328918},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.44727522134780884},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4058598577976227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18552082777023315},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.0798429548740387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000290393829346},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.5992586612701416},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5918285250663757},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5559954047203064},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5120194554328918},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.44727522134780884},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4058598577976227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18552082777023315},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0798429548740387},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000458","qualifier_name":"organization & administration","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000458","qualifier_name":"organization & administration","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti250384","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250384","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250384","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:40380494","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40380494","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/shti250384","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250384","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250384","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410448385.pdf","grobid_xml":"https://content.openalex.org/works/W4410448385.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W962911587","https://openalex.org/W4200551113","https://openalex.org/W2270762093","https://openalex.org/W4255072332","https://openalex.org/W2028861106","https://openalex.org/W3126834064","https://openalex.org/W3110671107","https://openalex.org/W1754154538","https://openalex.org/W2135768893","https://openalex.org/W3021414116"],"abstract_inverted_index":{"Clinical":[0],"routine":[1,146],"data":[2,26,35,46,60,72,83,91],"is":[3,109],"a":[4,19,28,74,104],"valuable":[5],"resource":[6],"for":[7,61],"research":[8,23,39],"and":[9,86,93,98],"analysis":[10],"in":[11,120],"hospitals.":[12],"Even":[13],"though":[14],"regulations":[15],"allow":[16],"access":[17],"within":[18],"clinical":[20,145],"system,":[21],"decentralized":[22],"with":[24],"up-to-date":[25],"remains":[27],"problem":[29],"limited":[30],"by":[31,41],"privacy":[32,49],"concerns.":[33],"Synthetic":[34],"generation":[36],"can":[37],"elevate":[38],"possibilities":[40],"providing":[42],"statistically":[43],"similar":[44],"cohort":[45],"without":[47],"neglecting":[48],"issues.":[50],"We":[51],"used":[52],"an":[53],"open-source":[54],"software":[55],"package":[56,80],"to":[57,102,131,134],"generate":[58],"synthetic":[59,105],"our":[62],"mixed":[63],"tabular,":[64],"event-based":[65],"electronic":[66],"patient":[67],"records.":[68],"Handling":[69],"these":[70],"specific":[71],"imposes":[73],"rigorous":[75],"challenge":[76],"on":[77,111],"the":[78,82,112,139,143],"chosen":[79],"regarding":[81],"quality,":[84],"complexity,":[85],"overall":[87],"structure.":[88],"After":[89],"preprocessing,":[90],"cleansing,":[92],"division":[94],"we":[95],"combined":[96],"static":[97],"time-series-based":[99],"generative":[100],"algorithms":[101],"create":[103,135],"dataset.":[106],"The":[107],"evaluation":[108],"based":[110],"similarity":[113],"of":[114,142],"marginal":[115],"distributions.":[116],"While":[117],"showing":[118],"potential":[119],"some":[121],"cases":[122],"it":[123],"became":[124],"evident":[125],"that":[126,137],"more":[127],"sophisticated":[128],"work":[129],"has":[130],"be":[132],"done":[133],"datasets":[136],"mimic":[138],"whole":[140],"range":[141],"available":[144],"data.":[147]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
