{"id":"https://openalex.org/W4387635986","doi":"https://doi.org/10.48550/arxiv.2310.08532","title":"Platform for generating medical datasets for machine learning in public health","display_name":"Platform for generating medical datasets for machine learning in public health","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387635986","doi":"https://doi.org/10.48550/arxiv.2310.08532"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.08532","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08532","pdf_url":"https://arxiv.org/pdf/2310.08532","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.08532","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089126344","display_name":"\u0410\u043d\u043d\u0430 \u0415\u0432\u0433\u0435\u043d\u044c\u0435\u0432\u043d\u0430 \u0410\u043d\u0434\u0440\u0435\u0439\u0447\u0435\u043d\u043a\u043e","orcid":"https://orcid.org/0000-0001-6359-0763","observed_orcids":["https://orcid.org/0000-0001-6359-0763"]},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andreychenko, Anna","raw_affiliation_strings":["Digital Public Health Technologies\u00bb Laboratory ITMO University Saint-Petersburg , Russian Federation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Public Health Technologies\u00bb Laboratory ITMO University Saint-Petersburg , Russian Federation","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018361447","display_name":"Viktoriia Mikhailovna Korzhuk","orcid":"https://orcid.org/0000-0002-0240-9067","observed_orcids":["https://orcid.org/0000-0002-0240-9067"]},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Korzhuk, Viktoriia","raw_affiliation_strings":["Digital Public Health Technologies\u00bb Laboratory ITMO University Saint-Petersburg , Russian Federation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Public Health Technologies\u00bb Laboratory ITMO University Saint-Petersburg , Russian Federation","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104182910","display_name":"Stanislav Kondratenko","orcid":"https://orcid.org/0009-0007-3769-5044","observed_orcids":["https://orcid.org/0009-0007-3769-5044"]},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Kondratenko, Stanislav","raw_affiliation_strings":["Digital Public Health Technologies\u00bb Laboratory ITMO University Saint-Petersburg , Russian Federation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Public Health Technologies\u00bb Laboratory ITMO University Saint-Petersburg , Russian Federation","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093063170","display_name":"Polina Cheraneva","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Cheraneva, Polina","raw_affiliation_strings":["Digital Public Health Technologies\u00bb Laboratory ITMO University Saint-Petersburg , Russian Federation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Public Health Technologies\u00bb Laboratory ITMO University Saint-Petersburg , Russian Federation","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173089394"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10350","display_name":"Electronic Health Records Systems","score":0.6211000084877014,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10350","display_name":"Electronic Health Records Systems","score":0.6211000084877014,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.09309999644756317,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.06840000301599503,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/health-data-interoperability","display_name":"health data interoperability","score":0.7020000219345093},{"id":"https://openalex.org/keywords/multimodal-medical-data","display_name":"multimodal medical data","score":0.7620000243186951},{"id":"https://openalex.org/keywords/data-harmonization","display_name":"data harmonization","score":0.8960000276565552},{"id":"https://openalex.org/keywords/data-anonymization","display_name":"data anonymization","score":0.9660000205039978},{"id":"https://openalex.org/keywords/data-annotation","display_name":"data annotation","score":0.7940000295639038},{"id":"https://openalex.org/keywords/microservices","display_name":"microservices","score":0.7730000019073486},{"id":"https://openalex.org/keywords/public-health-data","display_name":"public health data","score":0.6150000095367432}],"concepts":[{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6824951767921448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736409068107605},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.6629117727279663},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.6523257493972778},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5526533722877502},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.52394700050354},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5186806917190552},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5022292137145996},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4633399248123169},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4109935760498047},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.38907063007354736},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3590814173221588},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15565994381904602},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.08532","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08532","pdf_url":"https://arxiv.org/pdf/2310.08532","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.08532","doi":"https://doi.org/10.48550/arxiv.2310.08532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.08532","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.08532","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08532","pdf_url":"https://arxiv.org/pdf/2310.08532","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.6240000128746033}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327682","display_name":"Fondation Schlumberger pour l\u2019Education et la Recherche","ror":"https://ror.org/004pwee45"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387635986.pdf","grobid_xml":"https://content.openalex.org/works/W4387635986.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4214845829"],"related_works":["https://openalex.org/W7215069743","https://openalex.org/W4391946584","https://openalex.org/W4313145777","https://openalex.org/W4405760712","https://openalex.org/W4312596775","https://openalex.org/W4406231644","https://openalex.org/W3082502009","https://openalex.org/W3191406794","https://openalex.org/W7220427657","https://openalex.org/W4402005872"],"abstract_inverted_index":{"Currently,":[0],"there":[1],"are":[2],"many":[3],"difficulties":[4],"regarding":[5],"the":[6,20,23,36,52,69,91,94,96,99,102,117,129,135,145,190],"interoperability":[7],"of":[8,22,25,38,54,83,93,98,134,144,151,156,192],"medical":[9,42,56,158,193],"data":[10,14,27,57,137,162,194],"and":[11,32,101,132,153,176],"related":[12],"population":[13],"sources.":[15],"These":[16,122],"complications":[17],"get":[18],"in":[19,125],"way":[21],"generation":[24,150],"high-quality":[26],"sets":[28,155],"at":[29],"city,":[30],"region":[31],"national":[33],"levels.":[34],"Moreover,":[35],"collection":[37,53],"datasets":[39],"within":[40],"large":[41],"centers":[43],"is":[44,61,73,87],"feasible":[45],"due":[46],"to":[47,74,89,127,184,189],"own":[48],"IT":[49],"departments":[50],"whereas":[51],"raw":[55],"from":[58,116,163],"multiple":[59],"organizations":[60],"a":[62,111,142,148,170,186],"more":[63],"complicated":[64],"process.":[65],"In":[66],"these":[67],"circumstances,":[68],"most":[70],"appropriate":[71],"option":[72],"develop":[75],"digital":[76],"products":[77],"based":[78],"on":[79],"microservice":[80],"architecture.":[81],"Because":[82],"this":[84],"approach,":[85,105],"it":[86,168],"possible":[88],"ensure":[90,128],"multimodality":[92],"system,":[95],"flexibility":[97],"interface":[100],"internal":[103],"system":[104,182],"when":[106,119],"interconnected":[107],"elements":[108],"behave":[109],"as":[110],"whole,":[112],"demonstrating":[113],"behavior":[114,118],"different":[115,164],"working":[120],"independently.":[121],"conditions":[123],"allow,":[124],"turn,":[126],"maximum":[130],"number":[131],"representativeness":[133],"resulting":[136],"sets.":[138],"This":[139],"paper":[140],"demonstrates":[141],"concept":[143],"platform":[146],"for":[147,196],"sustainable":[149],"quality":[152,195],"reliable":[154],"multimodal":[157],"data.":[159,179],"It":[160],"collects":[161],"external":[165],"sources,":[166],"harmonizes":[167],"using":[169],"special":[171],"service,":[172],"anonymizes":[173],"harmonized":[174],"data,":[175],"labels":[177],"processed":[178],"The":[180],"proposed":[181],"aims":[183],"be":[185],"promising":[187],"solution":[188],"improvement":[191],"machine":[197],"learning.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2023-10-14T00:00:00"}