{"id":"https://openalex.org/W4413956518","doi":"https://doi.org/10.3233/shti251390","title":"Catnip for MedCAT: Optimizing the Input for Automated SNOMED CT Mapping of Clinical Variables","display_name":"Catnip for MedCAT: Optimizing the Input for Automated SNOMED CT Mapping of Clinical Variables","publication_year":2025,"publication_date":"2025-09-03","ids":{"openalex":"https://openalex.org/W4413956518","doi":"https://doi.org/10.3233/shti251390","pmid":"https://pubmed.ncbi.nlm.nih.gov/40899536"},"language":"en","primary_location":{"id":"doi:10.3233/shti251390","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251390","pdf_url":null,"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":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti251390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049862200","display_name":"Julia Gehrmann","orcid":"https://orcid.org/0000-0002-4101-5458"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]},{"id":"https://openalex.org/I4210153755","display_name":"University Hospital Cologne","ror":"https://ror.org/05mxhda18","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210153755"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Julia Gehrmann","raw_affiliation_strings":["Institute for Biomedical Informatics, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4101-5458","affiliations":[{"raw_affiliation_string":"Institute for Biomedical Informatics, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I4210153755","https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101402907","display_name":"Ahmet Do\u011fan","orcid":"https://orcid.org/0000-0001-5110-4027"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]},{"id":"https://openalex.org/I4210153755","display_name":"University Hospital Cologne","ror":"https://ror.org/05mxhda18","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210153755"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Asme Dogan","raw_affiliation_strings":["Department of Pediatrics, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I4210153755","https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119528502","display_name":"Lea Hagelschuer","orcid":null},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]},{"id":"https://openalex.org/I4210153755","display_name":"University Hospital Cologne","ror":"https://ror.org/05mxhda18","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210153755"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lea Hagelschuer","raw_affiliation_strings":["Center for Rare Diseases, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany","Department of Pediatrics, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Rare Diseases, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I4210153755","https://openalex.org/I180923762"]},{"raw_affiliation_string":"Department of Pediatrics, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I4210153755","https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042508571","display_name":"Lars Quakulinski","orcid":null},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]},{"id":"https://openalex.org/I4210153755","display_name":"University Hospital Cologne","ror":"https://ror.org/05mxhda18","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210153755"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lars Quakulinski","raw_affiliation_strings":["Institute for Biomedical Informatics, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Biomedical Informatics, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I4210153755","https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031869394","display_name":"Anne Koy","orcid":"https://orcid.org/0000-0002-7991-4432"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]},{"id":"https://openalex.org/I4210153755","display_name":"University Hospital Cologne","ror":"https://ror.org/05mxhda18","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210153755"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anne Koy","raw_affiliation_strings":["Center for Rare Diseases, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany","Department of Pediatrics, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Rare Diseases, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I4210153755","https://openalex.org/I180923762"]},{"raw_affiliation_string":"Department of Pediatrics, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I4210153755","https://openalex.org/I180923762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067635650","display_name":"Oya Beyan","orcid":"https://orcid.org/0000-0001-7611-3501"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]},{"id":"https://openalex.org/I4210110507","display_name":"Fraunhofer Institute for Applied Information Technology","ror":"https://ror.org/01ak24c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210110507","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4210153755","display_name":"University Hospital Cologne","ror":"https://ror.org/05mxhda18","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210153755"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oya Beyan","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, Fraunhofer FIT, Sankt Augustin, Germany","Institute for Biomedical Informatics, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Fraunhofer FIT, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210110507"]},{"raw_affiliation_string":"Institute for Biomedical Informatics, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I4210153755","https://openalex.org/I180923762"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049862200"],"corresponding_institution_ids":["https://openalex.org/I180923762","https://openalex.org/I4210153755"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41784567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"331","issue":null,"first_page":"142","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5914999842643738,"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":0.5914999842643738,"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/T10350","display_name":"Electronic Health Records Systems","score":0.17159999907016754,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.06560000032186508,"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/snomed-ct","display_name":"SNOMED CT","score":0.9676263332366943},{"id":"https://openalex.org/keywords/systematized-nomenclature-of-medicine","display_name":"Systematized Nomenclature of Medicine","score":0.806463360786438},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8059472441673279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6936095952987671},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5300288796424866},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4530493915081024},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.23502027988433838},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12669163942337036}],"concepts":[{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.9676263332366943},{"id":"https://openalex.org/C44681071","wikidata":"https://www.wikidata.org/wiki/Q4048820","display_name":"Systematized Nomenclature of Medicine","level":4,"score":0.806463360786438},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8059472441673279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6936095952987671},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5300288796424866},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4530493915081024},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.23502027988433838},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12669163942337036},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":[{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D039061","descriptor_name":"Systematized Nomenclature of Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D039061","descriptor_name":"Systematized Nomenclature of Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.3233/shti251390","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251390","pdf_url":null,"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:40899536","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40899536","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":null},{"id":"pmh:oai:publica.fraunhofer.de:publica/497128","is_oa":true,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/497128","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.3233/shti251390","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251390","pdf_url":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2581432157","https://openalex.org/W983237315","https://openalex.org/W4386159309","https://openalex.org/W4295077997","https://openalex.org/W4384914659","https://openalex.org/W2419080317","https://openalex.org/W328302119","https://openalex.org/W2042499546","https://openalex.org/W2202817416","https://openalex.org/W2026282251"],"abstract_inverted_index":{"INTRODUCTION:":[0],"Mapping":[1],"local":[2],"medical":[3,12,24],"data":[4,8,17],"assets":[5],"to":[6,121,143,205,232],"international":[7],"standards":[9],"such":[10,40],"as":[11,41],"ontology":[13],"SNOMED":[14,34,63,93,115,145,206],"CT":[15,35,64,94,116,146,207],"fosters":[16],"harmonization":[18],"and,":[19],"thereby,":[20],"global":[21],"progress":[22],"in":[23,80,187,197],"research.":[25],"Since":[26],"its":[27],"intense":[28],"resource":[29],"requirements":[30],"often":[31],"hinder":[32],"manual":[33,119,237],"mapping,":[36],"automated":[37],"mapping":[38,104,165,202,226,241],"tools":[39],"MedCAT":[42,199],"have":[43],"been":[44],"developed.":[45],"We":[46,70],"investigated":[47],"how":[48],"the":[49,57,62,75,109,133,170,184,240],"formulation":[50],"of":[51,61,113,135,239],"study":[52,193,203],"variable":[53],"names":[54],"(VNs)":[55],"influences":[56],"efficacy":[58],"and":[59,82,111,219,247],"accuracy":[60,124],"concepts":[65,147],"identified":[66,114,194],"by":[67,137],"MedCAT.":[68],"METHODS:":[69],"extracted":[71],"763":[72],"VNs":[73,85,136,173,215,250],"from":[74,183],"GEPESTIM":[76],"database":[77],"hosted":[78],"locally":[79],"REDCap":[81,88],"created":[83,101],"three":[84],"using":[86,118,198],"different":[87],"metadata":[89,140,158,185],"items":[90,141],"for":[91,200,224,244,248],"MedCAT-based":[92],"mapping.":[95],"A":[96],"fourth":[97],"VN":[98,177,222],"version":[99,178],"was":[100,105,167],"manually.":[102],"The":[103,162],"evaluated":[106],"based":[107],"on":[108,169],"number":[110],"quality":[112],"concepts,":[117],"scoring":[120],"assess":[122],"concept":[123],"while":[125,174],"ensuring":[126],"a":[127,175,235],"blind":[128],"evaluation":[129],"process.":[130],"RESULTS:":[131],"Increasing":[132],"expressiveness":[134],"adding":[138],"more":[139,144],"led":[142],"being":[148],"mapped,":[149],"but":[150],"also":[151],"introduced":[152],"mismatches,":[153],"particularly":[154],"when":[155],"additionally":[156],"included":[157],"contained":[159],"misleading":[160,217],"terms.":[161],"best":[163],"overall":[164],"performance":[166],"achieved":[168],"manually":[171],"specified":[172],"basic":[176],"with":[179],"minimal":[180],"extra":[181],"information":[182],"resulted":[186],"similarly":[188],"good":[189],"results.":[190],"CONCLUSION:":[191],"Our":[192],"key":[195],"challenges":[196],"automatically":[201],"variables":[204,246],"concepts.":[208],"To":[209],"improve":[210],"accuracy,":[211],"we":[212],"recommend":[213],"refining":[214],"reducing":[216],"terms":[218],"iteratively":[220],"improving":[221],"phrasing":[223],"optimal":[225],"outcome.":[227],"Furthermore,":[228],"it":[229],"appears":[230],"reasonable":[231],"always":[233],"conduct":[234],"final":[236],"review":[238],"outcome":[242],"especially":[243],"critical":[245],"those":[249],"containing":[251],"negations":[252],"or":[253],"abbreviations.":[254]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}
