{"id":"https://openalex.org/W3103102495","doi":"https://doi.org/10.1038/s41746-020-00353-9","title":"Generating high-fidelity synthetic patient data for assessing machine learning healthcare software","display_name":"Generating high-fidelity synthetic patient data for assessing machine learning healthcare software","publication_year":2020,"publication_date":"2020-11-09","ids":{"openalex":"https://openalex.org/W3103102495","doi":"https://doi.org/10.1038/s41746-020-00353-9","mag":"3103102495","pmid":"https://pubmed.ncbi.nlm.nih.gov/33299100"},"language":"en","primary_location":{"id":"doi:10.1038/s41746-020-00353-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-020-00353-9","pdf_url":"https://www.nature.com/articles/s41746-020-00353-9.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"npj Digital Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41746-020-00353-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004397914","display_name":"Allan Tucker","orcid":"https://orcid.org/0000-0001-5105-3506"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Allan Tucker","raw_affiliation_strings":["Department of Computer Science, Brunel University London, London, UK. allan.tucker@brunel.ac.uk","Department of Computer Science, Brunel University London, London, UK"],"raw_orcid":"https://orcid.org/0000-0001-5105-3506","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brunel University London, London, UK. allan.tucker@brunel.ac.uk","institution_ids":["https://openalex.org/I59433898"]},{"raw_affiliation_string":"Department of Computer Science, Brunel University London, London, UK","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028448798","display_name":"Zhenchen Wang","orcid":"https://orcid.org/0000-0003-4710-0298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenchen Wang","raw_affiliation_strings":["CPRD, Medicines & Healthcare Products Regulatory Agency, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CPRD, Medicines & Healthcare Products Regulatory Agency, London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063594087","display_name":"Ylenia Rotalinti","orcid":"https://orcid.org/0000-0001-9828-6200"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ylenia Rotalinti","raw_affiliation_strings":["Biomedical Informatics Laboratory, University of Pavia, Pavia, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Laboratory, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080758722","display_name":"Puja Myles","orcid":"https://orcid.org/0000-0002-8976-890X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Puja Myles","raw_affiliation_strings":["CPRD, Medicines & Healthcare Products Regulatory Agency, London, UK"],"raw_orcid":"https://orcid.org/0000-0002-8976-890X","affiliations":[{"raw_affiliation_string":"CPRD, Medicines & Healthcare Products Regulatory Agency, London, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004397914"],"corresponding_institution_ids":["https://openalex.org/I59433898"],"apc_list":{"value":3060,"currency":"USD","value_usd":3060},"apc_paid":{"value":3060,"currency":"USD","value_usd":3060},"fwci":14.4047,"has_fulltext":true,"cited_by_count":215,"citation_normalized_percentile":{"value":0.99160961,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"3","issue":"1","first_page":"147","last_page":"147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9929999709129333,"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":0.9929999709129333,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9914000034332275,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9830999970436096,"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":0.760978102684021},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6746358275413513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5643008351325989},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5355894565582275},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5335401296615601},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5186007022857666},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4647706151008606},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4460832476615906},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43693289160728455},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.4110249876976013},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3941747844219208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760978102684021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6746358275413513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5643008351325989},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5355894565582275},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5335401296615601},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5186007022857666},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4647706151008606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4460832476615906},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43693289160728455},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.4110249876976013},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3941747844219208},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1038/s41746-020-00353-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-020-00353-9","pdf_url":"https://www.nature.com/articles/s41746-020-00353-9.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"npj Digital Medicine","raw_type":"journal-article"},{"id":"pmid:33299100","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33299100","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":"NPJ digital medicine","raw_type":null},{"id":"pmh:oai:bura.brunel.ac.uk:2438/21683","is_oa":true,"landing_page_url":"https://bura.brunel.ac.uk/handle/2438/21683","pdf_url":null,"source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"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":"","raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:393faecb6a464df29677635072a0df65","is_oa":true,"landing_page_url":"https://doaj.org/article/393faecb6a464df29677635072a0df65","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"npj Digital Medicine, Vol 3, Iss 1, Pp 1-13 (2020)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7653933","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7653933","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"NPJ Digit Med","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1038/s41746-020-00353-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-020-00353-9","pdf_url":"https://www.nature.com/articles/s41746-020-00353-9.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"npj Digital Medicine","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307418","display_name":"Pioneer Fund","ror":"https://ror.org/01mrzcs29"},{"id":"https://openalex.org/F4320312933","display_name":"Department for Business, Energy and Industrial Strategy, UK Government","ror":"https://ror.org/019ya6433"},{"id":"https://openalex.org/F4320335087","display_name":"Innovate UK","ror":"https://ror.org/05ar5fy68"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3103102495.pdf","grobid_xml":"https://content.openalex.org/works/W3103102495.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W234640303","https://openalex.org/W1484010841","https://openalex.org/W1523680690","https://openalex.org/W1871050032","https://openalex.org/W1985389985","https://openalex.org/W1988814833","https://openalex.org/W1991365922","https://openalex.org/W2002970973","https://openalex.org/W2017665047","https://openalex.org/W2037836788","https://openalex.org/W2049633694","https://openalex.org/W2055838663","https://openalex.org/W2064582039","https://openalex.org/W2094155635","https://openalex.org/W2100697007","https://openalex.org/W2104661533","https://openalex.org/W2115744219","https://openalex.org/W2118597903","https://openalex.org/W2119047901","https://openalex.org/W2125838338","https://openalex.org/W2125865219","https://openalex.org/W2143978441","https://openalex.org/W2148143831","https://openalex.org/W2154039449","https://openalex.org/W2156754463","https://openalex.org/W2165157425","https://openalex.org/W2168175751","https://openalex.org/W2173497437","https://openalex.org/W2187599255","https://openalex.org/W2204978804","https://openalex.org/W2282821441","https://openalex.org/W2322371438","https://openalex.org/W2565167788","https://openalex.org/W2582721310","https://openalex.org/W2589644515","https://openalex.org/W2600165045","https://openalex.org/W2803749461","https://openalex.org/W2808404826","https://openalex.org/W2883252565","https://openalex.org/W2888297916","https://openalex.org/W2910283416","https://openalex.org/W2911964244","https://openalex.org/W2936984225","https://openalex.org/W2963693643","https://openalex.org/W3098131897","https://openalex.org/W3149026346","https://openalex.org/W4234726042","https://openalex.org/W4250690046","https://openalex.org/W4302423442","https://openalex.org/W6637568146","https://openalex.org/W6730456626","https://openalex.org/W7070524128"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"There":[0],"is":[1,79,232,241,249],"a":[2,73],"growing":[3],"demand":[4],"for":[5,54,120,141],"the":[6,80,92,95,128,165,176,234],"uptake":[7],"of":[8,17,39,75,82,91,94,130,178,190,217,236],"modern":[9],"artificial":[10],"intelligence":[11],"technologies":[12,19],"within":[13],"healthcare":[14],"systems.":[15],"Many":[16],"these":[18],"exploit":[20],"historical":[21],"patient":[22,47,112,151,179],"health":[23],"data":[24,60,85,97,123,145,203,214,239],"to":[25,34,51,57,61,246,251],"build":[26],"powerful":[27],"predictive":[28],"models":[29,119],"that":[30,49,70,87,105,205,240],"can":[31,200],"be":[32,52,62,252],"used":[33],"improve":[35],"diagnosis":[36],"and":[37,102,138,164,197,222],"understanding":[38],"disease.":[40],"However,":[41],"there":[42],"are":[43,206],"many":[44,90],"issues":[45,78],"concerning":[46],"privacy":[48,77],"need":[50],"accounted":[53],"in":[55,215],"order":[56],"enable":[58],"this":[59],"better":[63],"harnessed":[64],"by":[65],"all":[66],"sectors.":[67],"One":[68],"approach":[69,189],"could":[71],"offer":[72],"method":[74],"circumventing":[76],"creation":[81],"realistic":[83,143],"synthetic":[84,122,144,182,202,238],"sets":[86,204],"capture":[88],"as":[89],"complexities":[93],"original":[96,211],"set":[98],"(distributions,":[99],"non-linear":[100],"relationships,":[101],"noise)":[103],"but":[104],"does":[106],"not":[107,207],"actually":[108],"include":[109],"any":[110],"real":[111,247],"data.":[113,152],"While":[114],"previous":[115],"research":[116],"has":[117],"explored":[118],"generating":[121,237],"sets,":[124],"here":[125],"we":[126,155,199],"explore":[127],"integration":[129],"resampling,":[131,198],"probabilistic":[132],"graphical":[133,195],"modelling,":[134],"latent":[135],"variable":[136],"identification,":[137],"outlier":[139,192],"analysis":[140,168,193,224],"producing":[142],"based":[146],"on":[147,157],"UK":[148],"primary":[149],"care":[150],"In":[153],"particular,":[154],"focus":[156],"handling":[158],"missingness,":[159],"complex":[160],"interactions":[161],"between":[162],"variables,":[163],"resulting":[166],"sensitivity":[167,223],"statistics":[169,225],"from":[170,181,210],"machine":[171,228],"learning":[172,229],"classifiers,":[173],"while":[174],"quantifying":[175],"risks":[177],"re-identification":[180],"datapoints.":[183],"We":[184],"show":[185],"that,":[186],"through":[187],"our":[188],"integrating":[191],"with":[194],"modelling":[196],"achieve":[201],"significantly":[208],"different":[209],"ground":[212],"truth":[213],"terms":[216],"feature":[218,220],"distributions,":[219],"dependencies,":[221],"when":[226],"inferring":[227],"classifiers.":[230],"What":[231],"more,":[233],"risk":[235],"identical":[242],"or":[243],"very":[244],"similar":[245],"patients":[248],"shown":[250],"low.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":45},{"year":2024,"cited_by_count":53},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":41},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}