{"id":"https://openalex.org/W4366219700","doi":"https://doi.org/10.3389/fdata.2023.1173038","title":"Biomedical heterogeneous data categorization and schema mapping toward data integration","display_name":"Biomedical heterogeneous data categorization and schema mapping toward data integration","publication_year":2023,"publication_date":"2023-04-17","ids":{"openalex":"https://openalex.org/W4366219700","doi":"https://doi.org/10.3389/fdata.2023.1173038","pmid":"https://pubmed.ncbi.nlm.nih.gov/37139170"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2023.1173038","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2023.1173038","pdf_url":"https://www.frontiersin.org/articles/10.3389/fdata.2023.1173038/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fdata.2023.1173038/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070920055","display_name":"Priya Deshpande","orcid":null},"institutions":[{"id":"https://openalex.org/I102461120","display_name":"Marquette University","ror":"https://ror.org/04gr4te78","country_code":"US","type":"education","lineage":["https://openalex.org/I102461120"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Priya Deshpande","raw_affiliation_strings":["Marquette University, Milwaukee, WI, United States","Marquette University, United States"],"affiliations":[{"raw_affiliation_string":"Marquette University, Milwaukee, WI, United States","institution_ids":["https://openalex.org/I102461120"]},{"raw_affiliation_string":"Marquette University, United States","institution_ids":["https://openalex.org/I102461120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007690835","display_name":"Alexander Rasin","orcid":"https://orcid.org/0000-0001-7282-5763"},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Rasin","raw_affiliation_strings":["DePaul University, Chicago, IL, United States","DePaul University, United States"],"affiliations":[{"raw_affiliation_string":"DePaul University, Chicago, IL, United States","institution_ids":["https://openalex.org/I118353179"]},{"raw_affiliation_string":"DePaul University, United States","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080703148","display_name":"Roselyne Tchoua","orcid":"https://orcid.org/0000-0002-7195-4456"},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roselyne Tchoua","raw_affiliation_strings":["DePaul University, Chicago, IL, United States","DePaul University, United States"],"affiliations":[{"raw_affiliation_string":"DePaul University, Chicago, IL, United States","institution_ids":["https://openalex.org/I118353179"]},{"raw_affiliation_string":"DePaul University, United States","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001027068","display_name":"Jacob Furst","orcid":null},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Furst","raw_affiliation_strings":["DePaul University, Chicago, IL, United States","DePaul University, United States"],"affiliations":[{"raw_affiliation_string":"DePaul University, Chicago, IL, United States","institution_ids":["https://openalex.org/I118353179"]},{"raw_affiliation_string":"DePaul University, United States","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005267835","display_name":"Daniela Raicu","orcid":"https://orcid.org/0000-0002-2165-7234"},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniela Raicu","raw_affiliation_strings":["DePaul University, Chicago, IL, United States","DePaul University, United States"],"affiliations":[{"raw_affiliation_string":"DePaul University, Chicago, IL, United States","institution_ids":["https://openalex.org/I118353179"]},{"raw_affiliation_string":"DePaul University, United States","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086749835","display_name":"Michiel Schinkel","orcid":"https://orcid.org/0000-0002-9357-9917"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Michiel Schinkel","raw_affiliation_strings":["Center for Experimental and Molecular Medicine (CEMM), University of Amsterdam, Amsterdam, Netherlands","Center for Experimental and Molecular Medicine (CEMM), University of Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Center for Experimental and Molecular Medicine (CEMM), University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Center for Experimental and Molecular Medicine (CEMM), University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050086721","display_name":"Hari Trivedi","orcid":"https://orcid.org/0000-0001-6648-8334"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Trivedi","raw_affiliation_strings":["Emory University, Atlanta, GA, United States","Emory University, United States"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, United States","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Emory University, United States","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073995883","display_name":"Sameer Antani","orcid":"https://orcid.org/0000-0002-0040-1387"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sameer Antani","raw_affiliation_strings":["National Library of Medicine, National Institutes of Health, Bethesda, MD, United States","National Library of Medicine, National Institutes of Health, United States"],"affiliations":[{"raw_affiliation_string":"National Library of Medicine, National Institutes of Health, Bethesda, MD, United States","institution_ids":["https://openalex.org/I2800548410","https://openalex.org/I1299303238"]},{"raw_affiliation_string":"National Library of Medicine, National Institutes of Health, United States","institution_ids":["https://openalex.org/I2800548410","https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5070920055"],"corresponding_institution_ids":["https://openalex.org/I102461120"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":0.9136,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74591518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"6","issue":null,"first_page":"1173038","last_page":"1173038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9952999949455261,"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":0.8028523921966553},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.6844469308853149},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5980463027954102},{"id":"https://openalex.org/keywords/semantic-integration","display_name":"Semantic integration","score":0.5352763533592224},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.5338851809501648},{"id":"https://openalex.org/keywords/data-virtualization","display_name":"Data virtualization","score":0.5334584712982178},{"id":"https://openalex.org/keywords/data-mapping","display_name":"Data mapping","score":0.49746444821357727},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.4902947247028351},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.48513826727867126},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.47626587748527527},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.47269535064697266},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4597298204898834},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.44665074348449707},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.424255907535553},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42052125930786133},{"id":"https://openalex.org/keywords/semantic-heterogeneity","display_name":"Semantic heterogeneity","score":0.41554978489875793},{"id":"https://openalex.org/keywords/ontology-based-data-integration","display_name":"Ontology-based data integration","score":0.357869029045105},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2138725221157074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2012043297290802},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1671852171421051},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.11126625537872314},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.10652247071266174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028523921966553},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.6844469308853149},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5980463027954102},{"id":"https://openalex.org/C110903229","wikidata":"https://www.wikidata.org/wiki/Q7449064","display_name":"Semantic integration","level":4,"score":0.5352763533592224},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.5338851809501648},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.5334584712982178},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.49746444821357727},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.4902947247028351},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.48513826727867126},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.47626587748527527},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.47269535064697266},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4597298204898834},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.44665074348449707},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.424255907535553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42052125930786133},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.41554978489875793},{"id":"https://openalex.org/C22550185","wikidata":"https://www.wikidata.org/wiki/Q7095047","display_name":"Ontology-based data integration","level":3,"score":0.357869029045105},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2138725221157074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2012043297290802},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1671852171421051},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.11126625537872314},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.10652247071266174},{"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/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.0},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3389/fdata.2023.1173038","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2023.1173038","pdf_url":"https://www.frontiersin.org/articles/10.3389/fdata.2023.1173038/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmid:37139170","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37139170","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":"Frontiers in big data","raw_type":null},{"id":"pmh:oai:pure.amsterdamumc.nl:openaire_cris_publications/1a19fc5a-c3b9-4212-9ab5-c168b0100b67","is_oa":true,"landing_page_url":"https://pure.amsterdamumc.nl/en/publications/1a19fc5a-c3b9-4212-9ab5-c168b0100b67","pdf_url":"https://pure.amsterdamumc.nl/files/142725454/Biomedical-heterogeneous-data-categorization-and-schema-mapping-toward-data-integration.pdf","source":{"id":"https://openalex.org/S7407055222","display_name":"Pure Amsterdam UMC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Deshpande, P, Rasin, A, Tchoua, R, Furst, J, Raicu, D, Schinkel, M, Trivedi, H & Antani, S 2023, 'Biomedical heterogeneous data categorization and schema mapping toward data integration', Frontiers in Big Data, vol. 6, 1173038. https://doi.org/10.3389/fdata.2023.1173038","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pubmedcentral.nih.gov:10149933","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10149933","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10149933/pdf/fdata-06-1173038.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Big Data","raw_type":"Text"},{"id":"pmh:amcpub:oai:pure.amc.nl:publications/145a54a7-c309-4bf8-bd7f-bfe11e8b01ec","is_oa":true,"landing_page_url":"https://pure.amc.nl/en/publications/biomedical-heterogeneous-data-categorization-and-schema-mapping-toward-data-integration(145a54a7-c309-4bf8-bd7f-bfe11e8b01ec).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, 6:1173038. Frontiers Media S.A.","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:b7505530cc804846bec06c67ee9fcb16","is_oa":true,"landing_page_url":"https://doaj.org/article/b7505530cc804846bec06c67ee9fcb16","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":"Frontiers in Big Data, Vol 6 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdata.2023.1173038","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2023.1173038","pdf_url":"https://www.frontiersin.org/articles/10.3389/fdata.2023.1173038/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G3497591915","display_name":null,"funder_award_id":"(NIH)","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366219700.pdf","grobid_xml":"https://content.openalex.org/works/W4366219700.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2023458977","https://openalex.org/W2049017883","https://openalex.org/W2101174895","https://openalex.org/W2163412015","https://openalex.org/W2612374874","https://openalex.org/W2778083552","https://openalex.org/W2893303656","https://openalex.org/W2902250343","https://openalex.org/W2904302655","https://openalex.org/W2941163790","https://openalex.org/W2977292884","https://openalex.org/W3000144657","https://openalex.org/W3006194121","https://openalex.org/W3014954493","https://openalex.org/W3019820525","https://openalex.org/W3037224895","https://openalex.org/W3042621345","https://openalex.org/W4240849091","https://openalex.org/W4242302459","https://openalex.org/W6680551516","https://openalex.org/W6746782238","https://openalex.org/W6754576228","https://openalex.org/W6756654439","https://openalex.org/W6782470020"],"related_works":["https://openalex.org/W2779831736","https://openalex.org/W2343630457","https://openalex.org/W2368731870","https://openalex.org/W3013289937","https://openalex.org/W2036469985","https://openalex.org/W2352204529","https://openalex.org/W2378243565","https://openalex.org/W2112203342","https://openalex.org/W2381355883","https://openalex.org/W153770410"],"abstract_inverted_index":{"Data":[0],"integration":[1,60,95],"is":[2,66,118],"a":[3,61,155],"well-motivated":[4],"problem":[5],"in":[6,77,89,127],"the":[7,24,28,32,43,45,83,125,128,134,140,165,169,176],"clinical":[8,17,64,161,192],"data":[9,48,57,91,94,112,136,162,180,193],"science":[10],"domain.":[11],"Availability":[12],"of":[13,42,47,133,191],"patient":[14,53],"data,":[15,44],"reference":[16,173],"cases,":[18],"and":[19,39,50,52,59,73,80,104,120,131,145,159,171],"datasets":[20],"for":[21],"research":[22],"have":[23],"potential":[25],"to":[26,110,157,178,188],"advance":[27],"healthcare":[29],"industry.":[30],"However,":[31,114],"unstructured":[33],"(text,":[34],"audio,":[35],"or":[36],"video":[37],"data)":[38],"heterogeneous":[40],"nature":[41],"variety":[46],"standards":[49],"formats,":[51],"privacy":[54],"constraint":[55],"make":[56],"interoperability":[58],"challenge.":[62],"The":[63],"text":[65,141],"further":[67],"categorized":[68],"into":[69,142],"different":[70,78,90,135,196],"semantic":[71],"groups":[72],"may":[74,86],"be":[75],"stored":[76],"files":[79],"formats.":[81],"Even":[82],"same":[84],"organization":[85],"store":[87],"cases":[88,170,177],"structures,":[92],"making":[93],"more":[96],"challenging.":[97],"With":[98],"such":[99],"inherent":[100],"complexity,":[101],"domain":[102,105],"experts":[103],"knowledge":[106],"are":[107],"often":[108],"necessary":[109],"perform":[111,179],"integration.":[113,181],"expert":[115],"human":[116],"labor":[117],"time":[119],"cost":[121],"prohibitive.":[122],"To":[123],"overcome":[124],"variability":[126],"structure,":[129],"format,":[130],"content":[132],"sources,":[137],"we":[138,153,185],"map":[139],"common":[143],"categories":[144],"compute":[146],"similarity":[147],"within":[148],"those.":[149],"In":[150],"this":[151],"paper,":[152],"present":[154],"method":[156],"categorize":[158],"merge":[160,189],"by":[163],"considering":[164],"underlying":[166],"semantics":[167],"behind":[168],"use":[172],"information":[174],"about":[175],"Evaluation":[182],"shows":[183],"that":[184],"were":[186],"able":[187],"88%":[190],"from":[194],"five":[195],"sources.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
