{"id":"https://openalex.org/W4387933386","doi":"https://doi.org/10.1101/2023.10.24.23297460","title":"Geometrically-aggregated training samples: Leveraging summary statistics to enable healthcare data democratization","display_name":"Geometrically-aggregated training samples: Leveraging summary statistics to enable healthcare data democratization","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4387933386","doi":"https://doi.org/10.1101/2023.10.24.23297460"},"language":"en","primary_location":{"id":"doi:10.1101/2023.10.24.23297460","doi":"https://doi.org/10.1101/2023.10.24.23297460","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.10.24.23297460","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2023/10/25/2023.10.24.23297460.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.medrxiv.org/content/medrxiv/early/2023/10/25/2023.10.24.23297460.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030438721","display_name":"Jenny Yang","orcid":"https://orcid.org/0000-0003-0352-8452","observed_orcids":["https://orcid.org/0000-0003-0352-8452"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jenny Yang","raw_affiliation_strings":["Institute of Biomedical Engineering, Dept. Engineering Science, University of Oxford"],"raw_orcid":"https://orcid.org/0000-0003-0352-8452","affiliations":[{"raw_affiliation_string":"Institute of Biomedical Engineering, Dept. Engineering Science, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035845115","display_name":"Anshul Thakur","orcid":"https://orcid.org/0000-0002-7006-1947","observed_orcids":["https://orcid.org/0000-0002-7006-1947"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anshul Thakur","raw_affiliation_strings":["Institute of Biomedical Engineering, Dept. Engineering Science, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biomedical Engineering, Dept. Engineering Science, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023184985","display_name":"Andrew A. S. Soltan","orcid":"https://orcid.org/0000-0003-2391-5361","observed_orcids":["https://orcid.org/0000-0003-2391-5361"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210147381","display_name":"Oxford University Hospitals NHS Trust","ror":"https://ror.org/03h2bh287","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210147381"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew A. S. Soltan","raw_affiliation_strings":["Institute of Biomedical Engineering, Dept. Engineering Science, University of Oxford","Nuffield Department of Population Health, University of Oxford","Oxford Cancer & Haematology Centre, Oxford University Hospitals NHS Foundation Trust"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biomedical Engineering, Dept. Engineering Science, University of Oxford","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Nuffield Department of Population Health, University of Oxford","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford Cancer & Haematology Centre, Oxford University Hospitals NHS Foundation Trust","institution_ids":["https://openalex.org/I4210147381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040302008","display_name":"David Andrew Clifton","orcid":"https://orcid.org/0000-0002-9848-8555","observed_orcids":["https://orcid.org/0000-0002-9848-8555"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David A. Clifton","raw_affiliation_strings":["Institute of Biomedical Engineering, Dept. Engineering Science, University of Oxford","Oxford-Suzhou Centre for Advanced Research (OSCAR), Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biomedical Engineering, Dept. Engineering Science, University of Oxford","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford-Suzhou Centre for Advanced Research (OSCAR), Suzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030438721"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9990000128746033,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9990000128746033,"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":0.00019999999494757503,"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":9.999999747378752e-05,"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/summary-statistics","display_name":"summary statistics","score":0.8320000171661377},{"id":"https://openalex.org/keywords/healthcare-data-privacy","display_name":"healthcare data privacy","score":0.7070000171661377},{"id":"https://openalex.org/keywords/data-democratization","display_name":"data democratization","score":0.8510000109672546},{"id":"https://openalex.org/keywords/data-accessibility","display_name":"data accessibility","score":0.4399999976158142},{"id":"https://openalex.org/keywords/tabular-data","display_name":"tabular data","score":0.7429999709129333},{"id":"https://openalex.org/keywords/time-series","display_name":"time series","score":0.9850000143051147},{"id":"https://openalex.org/keywords/eicu","display_name":"eICU","score":0.6620000004768372},{"id":"https://openalex.org/keywords/curial","display_name":"Curial","score":0.8740000128746033}],"concepts":[{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.6627265214920044},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6539794206619263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.617526113986969},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.5814300775527954},{"id":"https://openalex.org/C17058734","wikidata":"https://www.wikidata.org/wiki/Q1064441","display_name":"Democratization","level":4,"score":0.5752403736114502},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5752280354499817},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4837198555469513},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.43696409463882446},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34721559286117554},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.22602984309196472},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.20190849900245667},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.18257936835289001},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.119121253490448},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.10859403014183044},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.10391074419021606},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C555826173","wikidata":"https://www.wikidata.org/wiki/Q7174","display_name":"Democracy","level":3,"score":0.0},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2023.10.24.23297460","doi":"https://doi.org/10.1101/2023.10.24.23297460","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.10.24.23297460","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2023/10/25/2023.10.24.23297460.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/2023.10.24.23297460","doi":"https://doi.org/10.1101/2023.10.24.23297460","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.10.24.23297460","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2023/10/25/2023.10.24.23297460.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.6240000128746033,"display_name":"Good health and well-being"},{"id":"https://metadata.un.org/sdg/10","score":0.5676000118255615,"display_name":"Reduced inequalities"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2552211666","display_name":null,"funder_award_id":"ACF-2020-13-015","funder_id":"https://openalex.org/F4320319990","funder_display_name":"National Institute for Health and Care Research"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G467017269","display_name":null,"funder_award_id":"0009350","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"},{"id":"https://openalex.org/G837917936","display_name":"MOnItoRing of large scale complex technologicAl systems","funder_award_id":"955681","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"},{"id":"https://openalex.org/F4320319990","display_name":"National Institute for Health and Care Research","ror":"https://ror.org/0187kwz08"},{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320320290","display_name":"University of Oxford","ror":"https://ror.org/052gg0110"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323675","display_name":"Oxford University Hospitals NHS Foundation Trust","ror":"https://ror.org/03h2bh287"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387933386.pdf","grobid_xml":"https://content.openalex.org/works/W4387933386.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1686946872","https://openalex.org/W2095705004","https://openalex.org/W2105289139","https://openalex.org/W2162800060","https://openalex.org/W2170204206","https://openalex.org/W2516089573","https://openalex.org/W2617539464","https://openalex.org/W2792263949","https://openalex.org/W2801400022","https://openalex.org/W2906805076","https://openalex.org/W2908109788","https://openalex.org/W2954395498","https://openalex.org/W2970360512","https://openalex.org/W2973342229","https://openalex.org/W2985060393","https://openalex.org/W3007325053","https://openalex.org/W3009344235","https://openalex.org/W3023341615","https://openalex.org/W3035364336","https://openalex.org/W3037898045","https://openalex.org/W3038139858","https://openalex.org/W3098480654","https://openalex.org/W3107668265","https://openalex.org/W3110677219","https://openalex.org/W3211713204","https://openalex.org/W3211758366","https://openalex.org/W4220924972","https://openalex.org/W4224305896","https://openalex.org/W4281920142","https://openalex.org/W4283789713","https://openalex.org/W4285149890","https://openalex.org/W4312607194","https://openalex.org/W4323349058","https://openalex.org/W4361285150","https://openalex.org/W4389074726","https://openalex.org/W4391210555","https://openalex.org/W6600281463"],"related_works":["https://openalex.org/W7116286882","https://openalex.org/W7116529085","https://openalex.org/W4414214120","https://openalex.org/W7134932714","https://openalex.org/W4375869721","https://openalex.org/W7128428166","https://openalex.org/W2940517749","https://openalex.org/W7128740076","https://openalex.org/W7090839027","https://openalex.org/W7083813989"],"abstract_inverted_index":{"Abstract":[0],"Healthcare":[1],"data":[2,27,152],"is":[3,40,92],"highly":[4,109],"sensitive":[5],"and":[6,11,17,59,127,133,135,154],"confidential,":[7],"with":[8,45],"strict":[9],"regulations":[10,21],"laws":[12],"to":[13,28,47,52,104],"protect":[14],"patient":[15,112],"privacy":[16],"security.":[18],"However,":[19],"these":[20,117],"impede":[22],"the":[23,68,72,142],"access":[24,46],"of":[25,71,78,96,141],"healthcare":[26,38,79],"a":[29,35,62,93,139],"wider":[30],"AI":[31,37],"research":[32,39],"community.":[33],"As":[34],"result,":[36],"often":[41],"dominated":[42],"by":[43],"organisations":[44],"larger":[48],"datasets":[49,129],"or":[50],"limited":[51,63],"silo-based":[53],"development,":[54],"where":[55,88],"models":[56],"are":[57,108],"trained":[58],"evaluated":[60],"on":[61,124],"population.":[64],"Taking":[65],"inspiration":[66],"from":[67,102],"non-sensitive":[69],"nature":[70],"summary":[73,140],"statistics":[74],"(mean,":[75],"variance,":[76],"etc.)":[77],"data,":[80],"this":[81],"paper":[82],"proposes":[83],"geometrically-aggregated":[84],"training":[85,90,119,123,144],"samples":[86],"(GATS)":[87],"each":[89],"sample":[91,107],"convex":[94],"combination":[95],"multiple":[97],"patients\u2019":[98],"characteristics.":[99],"Thus,":[100],"mappings":[101],"patients":[103],"any":[105],"constructed":[106],"convoluted,":[110],"preserving":[111],"privacy.":[113],"We":[114],"demonstrate":[115],"that":[116],"\u201csummary":[118],"units\u201d":[120],"provide":[121],"effective":[122],"different":[125],"tabular":[126],"time-series":[128],"(CURIAL,":[130],"UCI":[131],"Adult,":[132],"eICU),":[134],"indeed":[136],"behave":[137],"as":[138],"original":[143],"datasets.":[145],"This":[146],"approach":[147],"takes":[148],"important":[149],"steps":[150],"towards":[151],"accessibility":[153],"democratization.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2023-10-26T00:00:00"}