{"id":"https://openalex.org/W4410447735","doi":"https://doi.org/10.3233/shti250479","title":"Applying AI to Support Categorization of Heterogeneous Epidemiological Datasets","display_name":"Applying AI to Support Categorization of Heterogeneous Epidemiological Datasets","publication_year":2025,"publication_date":"2025-05-15","ids":{"openalex":"https://openalex.org/W4410447735","doi":"https://doi.org/10.3233/shti250479","pmid":"https://pubmed.ncbi.nlm.nih.gov/40380587"},"language":"en","primary_location":{"id":"doi:10.3233/shti250479","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250479","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250479","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250479","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056549628","display_name":"Julia Sasse","orcid":"https://orcid.org/0000-0002-0660-7597"},"institutions":[{"id":"https://openalex.org/I4210112663","display_name":"ZB MED - Information Centre for Life Sciences","ror":"https://ror.org/0259fwx54","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210112663"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julia Sasse","raw_affiliation_strings":["ZB MED \u2013 Information Centre for Life Sciences, Cologne, Germany, https://ror.org/0259fwx54"],"raw_orcid":"https://orcid.org/0000-0002-0660-7597","affiliations":[{"raw_affiliation_string":"ZB MED \u2013 Information Centre for Life Sciences, Cologne, Germany, https://ror.org/0259fwx54","institution_ids":["https://openalex.org/I4210112663"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078446743","display_name":"Guillaume Fabre","orcid":"https://orcid.org/0000-0002-0124-9970"},"institutions":[{"id":"https://openalex.org/I2801766832","display_name":"McGill University Health Centre","ror":"https://ror.org/04cpxjv19","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2801766832"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Guillaume Fabre","raw_affiliation_strings":["Maelstrom Research, Research Institute of the McGill University Health Centre, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maelstrom Research, Research Institute of the McGill University Health Centre, Montreal, Canada","institution_ids":["https://openalex.org/I2801766832"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064120986","display_name":"Isabel Fortier","orcid":"https://orcid.org/0000-0001-8207-3059"},"institutions":[{"id":"https://openalex.org/I2801766832","display_name":"McGill University Health Centre","ror":"https://ror.org/04cpxjv19","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2801766832"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Isabel Fortier","raw_affiliation_strings":["Maelstrom Research, Research Institute of the McGill University Health Centre, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maelstrom Research, Research Institute of the McGill University Health Centre, Montreal, Canada","institution_ids":["https://openalex.org/I2801766832"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108953387","display_name":"Pierre Zimmermann","orcid":"https://orcid.org/0009-0001-1530-8820"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pierre Zimmermann","raw_affiliation_strings":["University of Bonn, Germany, https://ror.org/041nas322"],"raw_orcid":"https://orcid.org/0009-0001-1530-8820","affiliations":[{"raw_affiliation_string":"University of Bonn, Germany, https://ror.org/041nas322","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077378114","display_name":"Juliane Fluck","orcid":"https://orcid.org/0000-0003-1379-7023"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I4210112663","display_name":"ZB MED - Information Centre for Life Sciences","ror":"https://ror.org/0259fwx54","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210112663"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Juliane Fluck","raw_affiliation_strings":["University of Bonn, Germany, https://ror.org/041nas322","ZB MED \u2013 Information Centre for Life Sciences, Cologne, Germany, https://ror.org/0259fwx54"],"raw_orcid":"https://orcid.org/0000-0003-1379-7023","affiliations":[{"raw_affiliation_string":"University of Bonn, Germany, https://ror.org/041nas322","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"ZB MED \u2013 Information Centre for Life Sciences, Cologne, Germany, https://ror.org/0259fwx54","institution_ids":["https://openalex.org/I4210112663"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27312931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"327","issue":null,"first_page":"848","last_page":"852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9708999991416931,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9708999991416931,"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/T11937","display_name":"Research Data Management Practices","score":0.9695000052452087,"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"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9240000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7510937452316284},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7478418946266174},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6116141676902771},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.5818528532981873},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48487672209739685},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47268396615982056},{"id":"https://openalex.org/keywords/controlled-vocabulary","display_name":"Controlled vocabulary","score":0.4585575461387634},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.45664143562316895},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.44033458828926086},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42727839946746826},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3220404386520386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17347905039787292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510937452316284},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7478418946266174},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6116141676902771},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.5818528532981873},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48487672209739685},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47268396615982056},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.4585575461387634},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.45664143562316895},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.44033458828926086},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42727839946746826},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3220404386520386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17347905039787292},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073892","descriptor_name":"Health Information Interoperability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073892","descriptor_name":"Health Information Interoperability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005858","descriptor_name":"Germany","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005858","descriptor_name":"Germany","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti250479","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250479","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250479","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:40380587","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40380587","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":"Studies in health technology and informatics","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.3233/shti250479","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250479","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250479","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G7655486867","display_name":"NFDI4Health \u2013 Nationale Forschungsdateninfrastruktur f\u00fcr personenbezogene Gesundheitsdaten","funder_award_id":"442326535","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410447735.pdf","grobid_xml":"https://content.openalex.org/works/W4410447735.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2361861616","https://openalex.org/W2082577974","https://openalex.org/W1964419532","https://openalex.org/W1541278453","https://openalex.org/W2768577102","https://openalex.org/W2368748027","https://openalex.org/W2137937634","https://openalex.org/W4407801858"],"abstract_inverted_index":{"The":[0,22,68,141],"significance":[1],"of":[2,16,40,79,91,147,173,187],"Findable,":[3],"Accessible,":[4],"Interoperable,":[5],"and":[6,38,47,81,89,130,150,166,179,195],"Reusable":[7],"(FAIR)":[8],"data":[9,18,42,63,102,164,200],"is":[10],"increasing,":[11],"particularly":[12,155],"in":[13,20],"the":[14,35,54,87,110,171,184],"context":[15],"enhancing":[17,86,163],"reuse":[19],"research.":[21],"National":[23],"Research":[24],"Data":[25,30],"Infrastructure":[26],"for":[27,127,156],"Personal":[28],"Health":[29,57],"(NFDI4Health)":[31],"aims":[32],"to":[33,60,100],"enhance":[34],"findability,":[36],"reusability,":[37],"interoperability":[39],"health":[41,49,62],"derived":[43],"from":[44],"epidemiological,":[45],"clinical,":[46],"public":[48],"studies.":[50],"NFDI4Health":[51,108],"has":[52],"established":[53],"German":[55],"Central":[56],"Study":[58],"Hub":[59],"improve":[61],"findability":[64,88,165],"through":[65],"rich":[66],"metadata.":[67],"Maelstrom":[69,73],"Catalog,":[70],"provided":[71],"by":[72],"Research,":[74],"offers":[75],"a":[76,137,144,169],"comprehensive":[77],"dataset":[78],"labeled":[80],"harmonized":[82],"study":[83,174],"variables,":[84],"thereby":[85,162],"reusability":[90],"epidemiological":[92],"data.":[93],"Both":[94],"platforms":[95],"rely":[96],"on":[97],"standardized":[98,119],"categorization":[99,172],"optimize":[101],"reuse.":[103],"To":[104],"facilitate":[105],"this":[106,134],"process,":[107],"developed":[109],"Metadata":[111],"Annotation":[112],"Workbench,":[113],"which":[114],"supports":[115],"metadata":[116],"annotation":[117,131,153],"with":[118],"vocabulary.":[120],"This":[121],"paper":[122],"presents":[123],"an":[124],"AI":[125,189],"solution":[126],"automatic":[128],"classification":[129],"integrated":[132],"into":[133],"service,":[135],"using":[136],"BioBERT-based":[138],"text":[139],"classifier.":[140],"model":[142],"achieved":[143],"weighted":[145],"F1-score":[146],"over":[148],"92%":[149],"demonstrated":[151],"improved":[152],"performance,":[154],"non-experts.":[157],"It":[158],"accelerates":[159],"variable":[160],"categorization,":[161],"re-use.":[167],"As":[168],"result,":[170],"variables":[175],"can":[176],"be":[177],"accelerated":[178],"we":[180],"are":[181],"confident":[182],"that":[183],"further":[185],"development":[186],"such":[188],"approaches":[190],"will":[191],"reduce":[192],"curatorial":[193],"workload":[194],"promote":[196],"semantically":[197],"annotated":[198],"interoperable":[199],"catalogs.":[201]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
