{"id":"https://openalex.org/W4416786152","doi":"https://doi.org/10.1186/s12911-025-03266-3","title":"Augmenting small tabular health data for training prognostic ensemble machine learning models using generative models","display_name":"Augmenting small tabular health data for training prognostic ensemble machine learning models using generative models","publication_year":2025,"publication_date":"2025-11-28","ids":{"openalex":"https://openalex.org/W4416786152","doi":"https://doi.org/10.1186/s12911-025-03266-3","pmid":"https://pubmed.ncbi.nlm.nih.gov/41316099"},"language":"en","primary_location":{"id":"doi:10.1186/s12911-025-03266-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-025-03266-3","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12911-025-03266-3.pdf","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s12911-025-03266-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067657345","display_name":"Dan Liu","orcid":"https://orcid.org/0000-0001-9632-4736"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I2799330578","display_name":"Children's Hospital of Eastern Ontario","ror":"https://ror.org/05nsbhw27","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2799330578"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Dan Liu","raw_affiliation_strings":["Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada","School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada","institution_ids":["https://openalex.org/I2799330578"]},{"raw_affiliation_string":"School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070034467","display_name":"Samer El Kababji","orcid":"https://orcid.org/0000-0002-7642-2280"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I2799330578","display_name":"Children's Hospital of Eastern Ontario","ror":"https://ror.org/05nsbhw27","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2799330578"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Samer El Kababji","raw_affiliation_strings":["Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada","School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada","institution_ids":["https://openalex.org/I2799330578"]},{"raw_affiliation_string":"School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027209386","display_name":"Nicholas Mitsakakis","orcid":"https://orcid.org/0000-0001-9041-9152"},"institutions":[{"id":"https://openalex.org/I2799330578","display_name":"Children's Hospital of Eastern Ontario","ror":"https://ror.org/05nsbhw27","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2799330578"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nicholas Mitsakakis","raw_affiliation_strings":["Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada"],"affiliations":[{"raw_affiliation_string":"Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada","institution_ids":["https://openalex.org/I2799330578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064689966","display_name":"Lisa Pilgram","orcid":"https://orcid.org/0000-0002-1020-0650"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I2799330578","display_name":"Children's Hospital of Eastern Ontario","ror":"https://ror.org/05nsbhw27","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2799330578"]},{"id":"https://openalex.org/I7877124","display_name":"Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/001w7jn25","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I7877124"]}],"countries":["CA","DE"],"is_corresponding":false,"raw_author_name":"Lisa Pilgram","raw_affiliation_strings":["Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada","Department of Nephrology and Medical Intensive Care, Charit\u00e9 - Universitaetsmedizin Berlin, Berlin, Germany","School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada","institution_ids":["https://openalex.org/I2799330578"]},{"raw_affiliation_string":"Department of Nephrology and Medical Intensive Care, Charit\u00e9 - Universitaetsmedizin Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I7877124"]},{"raw_affiliation_string":"School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009290511","display_name":"Thomas D. Walters","orcid":"https://orcid.org/0000-0002-4184-4600"},"institutions":[{"id":"https://openalex.org/I2801317318","display_name":"Hospital for Sick Children","ror":"https://ror.org/057q4rt57","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2801317318"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Thomas D. Walters","raw_affiliation_strings":["Hospital for Sick Children, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Hospital for Sick Children, Toronto, ON, Canada","institution_ids":["https://openalex.org/I2801317318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026335419","display_name":"Mark Clemons","orcid":"https://orcid.org/0000-0001-9392-8219"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I2800722420","display_name":"Ottawa Hospital","ror":"https://ror.org/03c62dg59","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2800722420"]},{"id":"https://openalex.org/I4388482656","display_name":"Ottawa Hospital Research Institute","ror":"https://ror.org/05jtef216","country_code":null,"type":"healthcare","lineage":["https://openalex.org/I153718931","https://openalex.org/I2800722420","https://openalex.org/I4388482656"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mark Clemons","raw_affiliation_strings":["Division of Medical Oncology, Department of Medicine, University of Ottawa, Ottawa, ON, Canada","Ottawa Hospital Research Institute, Ottawa, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Division of Medical Oncology, Department of Medicine, University of Ottawa, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I153718931"]},{"raw_affiliation_string":"Ottawa Hospital Research Institute, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I2800722420","https://openalex.org/I4388482656"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047689900","display_name":"Gregory R. Pond","orcid":"https://orcid.org/0000-0003-1033-0882"},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gregory R. Pond","raw_affiliation_strings":["McMaster University, Hamilton, ON, Canada"],"affiliations":[{"raw_affiliation_string":"McMaster University, Hamilton, ON, Canada","institution_ids":["https://openalex.org/I98251732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116129731","display_name":"Alaa El-Hussuna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alaa El-Hussuna","raw_affiliation_strings":["OpenSourceResearch, Aalborg, Denmark"],"affiliations":[{"raw_affiliation_string":"OpenSourceResearch, Aalborg, Denmark","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070248034","display_name":"Khaled El Emam","orcid":"https://orcid.org/0000-0003-3325-4149"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I2799330578","display_name":"Children's Hospital of Eastern Ontario","ror":"https://ror.org/05nsbhw27","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2799330578"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Khaled El Emam","raw_affiliation_strings":["Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada. kelemam@ehealthinformation.ca","School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada. kelemam@ehealthinformation.ca"],"affiliations":[{"raw_affiliation_string":"Children's Hospital of Eastern Ontario Research Institute, 401 Smyth Road, Ottawa, ON, K1h 8l1, Canada. kelemam@ehealthinformation.ca","institution_ids":["https://openalex.org/I2799330578"]},{"raw_affiliation_string":"School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada. kelemam@ehealthinformation.ca","institution_ids":["https://openalex.org/I153718931"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5067657345"],"corresponding_institution_ids":["https://openalex.org/I153718931","https://openalex.org/I2799330578"],"apc_list":{"value":1570,"currency":"GBP","value_usd":1925},"apc_paid":{"value":1570,"currency":"GBP","value_usd":1925},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20114983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"1","first_page":"435","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.3571999967098236,"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":0.3571999967098236,"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":0.28139999508857727,"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"}},{"id":"https://openalex.org/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.05810000002384186,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/categorical-variable","display_name":"Categorical variable","score":0.6410999894142151},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.5066999793052673},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.42649999260902405},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4253999888896942},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.40880000591278076},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.40720000863075256},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.39959999918937683},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.3984000086784363},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.3831000030040741},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.36570000648498535}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7023000121116638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876000165939331},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6410999894142151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6204000115394592},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.5066999793052673},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.42649999260902405},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.361299991607666},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C153720581","wikidata":"https://www.wikidata.org/wiki/Q5532490","display_name":"Generalized linear mixed model","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C85461838","wikidata":"https://www.wikidata.org/wiki/Q7100785","display_name":"Ordinal data","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s12911-025-03266-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-025-03266-3","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12911-025-03266-3.pdf","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},{"id":"pmid:41316099","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41316099","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":"BMC medical informatics and decision making","raw_type":null},{"id":"pmh:oai:doaj.org/article:bf4eab2943384bb5aabfbb7b4ff2e58c","is_oa":true,"landing_page_url":"https://doaj.org/article/bf4eab2943384bb5aabfbb7b4ff2e58c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Medical Informatics and Decision Making, Vol 25, Iss 1, Pp 1-19 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11468114","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12661835","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12911-025-03266-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-025-03266-3","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12911-025-03266-3.pdf","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416786152.pdf","grobid_xml":"https://content.openalex.org/works/W4416786152.grobid-xml"},"referenced_works_count":117,"referenced_works":["https://openalex.org/W1524416683","https://openalex.org/W1602160603","https://openalex.org/W1966716734","https://openalex.org/W1970723690","https://openalex.org/W1976526581","https://openalex.org/W1982229628","https://openalex.org/W1990700240","https://openalex.org/W2088431433","https://openalex.org/W2112081648","https://openalex.org/W2115709314","https://openalex.org/W2118510964","https://openalex.org/W2118978333","https://openalex.org/W2123998733","https://openalex.org/W2125877832","https://openalex.org/W2141007997","https://openalex.org/W2154039449","https://openalex.org/W2154290668","https://openalex.org/W2156163116","https://openalex.org/W2157963512","https://openalex.org/W2162800060","https://openalex.org/W2296719434","https://openalex.org/W2396881363","https://openalex.org/W2574537113","https://openalex.org/W2593512180","https://openalex.org/W2605102758","https://openalex.org/W2605253636","https://openalex.org/W2786532017","https://openalex.org/W2809949684","https://openalex.org/W2889164652","https://openalex.org/W2889985731","https://openalex.org/W2891179298","https://openalex.org/W2899638272","https://openalex.org/W2900595477","https://openalex.org/W2944052783","https://openalex.org/W2954996726","https://openalex.org/W2958946409","https://openalex.org/W2962718684","https://openalex.org/W2962914239","https://openalex.org/W2963108767","https://openalex.org/W2963459241","https://openalex.org/W2963768110","https://openalex.org/W2963963837","https://openalex.org/W2966525657","https://openalex.org/W2975798518","https://openalex.org/W2978111064","https://openalex.org/W2981390668","https://openalex.org/W2989219518","https://openalex.org/W2998909968","https://openalex.org/W2999603160","https://openalex.org/W3000470572","https://openalex.org/W3011243144","https://openalex.org/W3037824585","https://openalex.org/W3046296398","https://openalex.org/W3083053899","https://openalex.org/W3096891674","https://openalex.org/W3098601872","https://openalex.org/W3104912879","https://openalex.org/W3107178186","https://openalex.org/W3113905359","https://openalex.org/W3114795906","https://openalex.org/W3158157866","https://openalex.org/W3163087324","https://openalex.org/W3165846270","https://openalex.org/W3166908170","https://openalex.org/W3171873561","https://openalex.org/W3174828871","https://openalex.org/W3176226474","https://openalex.org/W3197418972","https://openalex.org/W3199209662","https://openalex.org/W3207033141","https://openalex.org/W3216660278","https://openalex.org/W3217039319","https://openalex.org/W3217680058","https://openalex.org/W4200027480","https://openalex.org/W4221002080","https://openalex.org/W4223540626","https://openalex.org/W4225597912","https://openalex.org/W4246413330","https://openalex.org/W4281646369","https://openalex.org/W4288046750","https://openalex.org/W4296963809","https://openalex.org/W4306722800","https://openalex.org/W4309028162","https://openalex.org/W4309944697","https://openalex.org/W4310583869","https://openalex.org/W4313343845","https://openalex.org/W4319996951","https://openalex.org/W4327909703","https://openalex.org/W4360860566","https://openalex.org/W4367395273","https://openalex.org/W4367693661","https://openalex.org/W4378576258","https://openalex.org/W4382196087","https://openalex.org/W4384663192","https://openalex.org/W4385420510","https://openalex.org/W4386099669","https://openalex.org/W4386648688","https://openalex.org/W4388631083","https://openalex.org/W4392156538","https://openalex.org/W4392302553","https://openalex.org/W4392821079","https://openalex.org/W4393131103","https://openalex.org/W4393236711","https://openalex.org/W4394574292","https://openalex.org/W4396495316","https://openalex.org/W4396742790","https://openalex.org/W4398177119","https://openalex.org/W4399212077","https://openalex.org/W4399362834","https://openalex.org/W4399682166","https://openalex.org/W4404354395","https://openalex.org/W4405544132","https://openalex.org/W4405823654","https://openalex.org/W4406170795","https://openalex.org/W4406852347","https://openalex.org/W4408220952","https://openalex.org/W4410232374"],"related_works":[],"abstract_inverted_index":{"Small":[0],"datasets":[1,20,180,210,273,292,300,335],"are":[2,21,43],"common":[3],"in":[4,240,243,318],"health":[5,52,89,105,330],"research.":[6],"However,":[7],"the":[8,18,68,93,99,113,119,125,127,130,162,173,227,230,236,266,296,350,355,367,387],"generalization":[9],"performance":[10,121,167,208,323,343,369],"of":[11,64,70,95,115,186,269,290,298,320,354,366],"machine":[12,325],"learning":[13,326],"models":[14,86,148,312,327],"is":[15,28,32,59,191,384,396],"suboptimal":[16],"when":[17,378],"training":[19],"small.":[22],"To":[23],"address":[24],"this,":[25],"data":[26,82,90,116,146,238,308,339,391],"augmentation":[27,83,117,187,270,309,368,375,395],"one":[29],"solution":[30],"and":[31,37,58,91,217,252,341,357],"often":[33],"used":[34],"for":[35,50,165,194,209,324,334,370],"imaging":[36],"time":[38],"series":[39],"data,":[40,331],"but":[41,332],"there":[42],"no":[44],"evaluations":[45],"on":[46,78,87,118,135,176,201,271,328],"its":[47],"potential":[48],"benefits":[49],"tabular":[51,88,329],"data.":[53,80],"Augmentation":[54,205,277],"increases":[55,67],"sample":[56,100],"size":[57],"seen":[60],"as":[61,181],"a":[62,109,154,192,195,315,362,371,380],"form":[63],"regularization":[65],"that":[66,211,307,336,389],"diversity":[69,96,289,297,392],"small":[71,178,232,272],"datasets,":[72,106,234],"leading":[73],"them":[74],"to":[75,111,160,250,257,394],"perform":[76],"better":[77,377],"unseen":[79],"Evaluate":[81],"using":[84,310],"generative":[85,223,311],"assess":[92,161],"impact":[94,114,200,268],"versus":[97],"increasing":[98],"size.":[101],"Using":[102],"13":[103],"large":[104],"we":[107],"performed":[108,376],"simulation":[110],"evaluate":[112],"prediction":[120],"(as":[122],"measured":[123],"by":[124],"ROC-AUC,":[126],"area":[128],"under":[129],"receiver":[131],"operating":[132],"characteristic":[133],"curve)":[134],"binary":[136],"classification":[137],"gradient":[138],"boosted":[139],"decision":[140],"tree":[141],"models.":[142],"Four":[143],"different":[144],"synthetic":[145],"generation":[147],"were":[149],"evaluated.":[150],"We":[151,171],"also":[152],"built":[153],"generalized":[155],"linear":[156],"mixed":[157,346],"effect":[158,347],"model":[159,166,224,348],"variable":[163],"importance":[164],"improvements":[168],"from":[169,248,255],"augmentation.":[170],"illustrate":[172],"proposed":[174],"method":[175],"seven":[177,231],"real":[179],"an":[182,241,260],"application.":[183],"A":[184],"comparison":[185],"with":[188,198,259,386],"resampling":[189,282],"(which":[190],"proxy":[193],"larger":[196],"dataset":[197,356],"minimal":[199],"diversity)":[202],"was":[203,279,293],"performed.":[204],"improves":[206],"prognostic":[207],"have":[212,314,361],"higher":[213,280,294],"cardinality":[214],"categorical":[215],"variables":[216],"lower":[218],"baseline":[219,338],"ROC-AUC.":[220],"No":[221],"specific":[222],"consistently":[225],"outperformed":[226],"others.":[228],"For":[229],"application":[233],"augmenting":[235],"existing":[237],"results":[239],"increase":[242],"ROC-AUC":[244,278,284],"between":[245],"4.31%":[246],"(ROC-AUC":[247,254],"0.71":[249],"0.75)":[251],"43.23%":[253],"0.51":[256],"0.73),":[258],"average":[261],"15.55%":[262],"relative":[263],"improvement,":[264],"demonstrating":[265],"nontrivial":[267],"(p":[274,285,301],"=":[275,286,302],"0.0078).":[276],"than":[281,295],"only":[283,333],"0.016).":[287],"The":[288],"augmented":[291],"resampled":[299],"0.046).":[303],"This":[304],"study":[305],"demonstrates":[306],"can":[313,358],"marked":[316],"benefit":[317],"terms":[319],"improved":[321],"predictive":[322,342],"meet":[337],"complexity":[340],"criteria.":[344],"Our":[345],"identified":[349],"most":[351],"influential":[352],"characteristics":[353],"help":[359],"end-users":[360],"more":[363],"realistic":[364],"expectation":[365],"new":[372],"dataset.":[373],"Furthermore,":[374],"having":[379],"smaller":[381],"dataset,":[382],"which":[383],"consistent":[385],"argument":[388],"greater":[390],"due":[393],"beneficial.":[397],"Not":[398],"applicable.":[399]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-11-28T00:00:00"}