{"id":"https://openalex.org/W3165241404","doi":"https://doi.org/10.3233/shti210183","title":"Automatic Detection of Metadata Errors in a Registry of Clinical Studies Using Shapes Constraint Language (SHACL) Graphs","display_name":"Automatic Detection of Metadata Errors in a Registry of Clinical Studies Using Shapes Constraint Language (SHACL) Graphs","publication_year":2021,"publication_date":"2021-05-27","ids":{"openalex":"https://openalex.org/W3165241404","doi":"https://doi.org/10.3233/shti210183","mag":"3165241404","pmid":"https://pubmed.ncbi.nlm.nih.gov/34042768"},"language":"en","primary_location":{"id":"doi:10.3233/shti210183","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti210183","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI210183","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/SHTI210183","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050065000","display_name":"Daniel Keuchel","orcid":null},"institutions":[{"id":"https://openalex.org/I159743108","display_name":"Dortmund University of Applied Sciences and Arts","ror":"https://ror.org/03dv91853","country_code":"DE","type":"education","lineage":["https://openalex.org/I159743108"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Keuchel","raw_affiliation_strings":["University of Applied Sciences and Arts Dortmund, Dept. of Computer Science, Dortmund, Germany"],"affiliations":[{"raw_affiliation_string":"University of Applied Sciences and Arts Dortmund, Dept. of Computer Science, Dortmund, Germany","institution_ids":["https://openalex.org/I159743108"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049149990","display_name":"Nicolai Spicher","orcid":"https://orcid.org/0000-0002-2879-9948"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]},{"id":"https://openalex.org/I34809795","display_name":"Medizinische Hochschule Hannover","ror":"https://ror.org/00f2yqf98","country_code":"DE","type":"education","lineage":["https://openalex.org/I34809795"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nicolai Spicher","raw_affiliation_strings":["Technical University of Braunschweig and Hannover Medical School, Peter L. Reichertz Institute for Medical Informatics, Braunschweig, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Braunschweig and Hannover Medical School, Peter L. Reichertz Institute for Medical Informatics, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681","https://openalex.org/I34809795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049149990"],"corresponding_institution_ids":["https://openalex.org/I34809795","https://openalex.org/I94509681"],"apc_list":null,"apc_paid":null,"fwci":2.0461,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85954858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"281","issue":null,"first_page":"372","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9975000023841858,"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":0.9975000023841858,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9923999905586243,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8975841999053955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7582277059555054},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.5896547436714172},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5516475439071655},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.49837779998779297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47906550765037537},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4482805132865906},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4418555200099945},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20476627349853516},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13481959700584412},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10135510563850403}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8975841999053955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582277059555054},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.5896547436714172},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5516475439071655},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.49837779998779297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47906550765037537},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4482805132865906},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4418555200099945},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20476627349853516},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13481959700584412},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10135510563850403},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012042","descriptor_name":"Registries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012042","descriptor_name":"Registries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012042","descriptor_name":"Registries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti210183","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti210183","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI210183","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:34042768","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34042768","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}],"best_oa_location":{"id":"doi:10.3233/shti210183","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti210183","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI210183","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3165241404.pdf","grobid_xml":"https://content.openalex.org/works/W3165241404.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2005871247","https://openalex.org/W2165428180","https://openalex.org/W2767029295","https://openalex.org/W2891527409","https://openalex.org/W2953359258","https://openalex.org/W2989726711"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2341492732","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W3187193180","https://openalex.org/W2501188010","https://openalex.org/W4299935056"],"abstract_inverted_index":{"Registries":[0],"of":[1,11,16,33,46,78,107,140,169,177,184,186],"clinical":[2,187],"studies":[3,142],"such":[4,113],"as":[5,114],"ClinicalTrials.gov":[6,86],"are":[7],"an":[8],"important":[9],"source":[10],"information.":[12],"However,":[13],"the":[14,30,34,49,53,75,84,149,167,170,175,182],"process":[15],"manually":[17],"entering":[18],"metadata":[19,50,99,111],"is":[20],"prone":[21],"to":[22,83,156],"errors":[23,47,108],"which":[24],"impedes":[25],"their":[26],"use":[27],"and":[28,66,159],"thereby":[29],"overall":[31],"usefulness":[32],"registry.":[35],"In":[36,148],"this":[37,134,154],"work,":[38],"we":[39,151],"propose":[40],"a":[41,70,104,123],"generic":[42],"approach":[43],"towards":[44],"detection":[45],"in":[48,94,109],"by":[51,164],"using":[52,133],"Shapes":[54],"Constraint":[55],"Language":[56],"for":[57,74],"defining":[58],"rule":[59,80],"templates":[60],"covering":[61],"constraints":[62],"regarding":[63],"value":[64,183],"type":[65],"cardinality.":[67],"We":[68],"developed":[69],"Python":[71],"3":[72],"algorithm":[73],"automatic":[76],"validation":[77],"15":[79],"instances":[81],"applied":[82],"whole":[85],"database":[87],"(355,862":[88],"studies;":[89],"27th":[90],"October":[91],"2020)":[92],"resulting":[93],"more":[95,146,161],"than":[96],"5":[97],"million":[98],"verifications.":[100],"Our":[101],"results":[102],"show":[103],"large":[105],"number":[106],"different":[110],"fields,":[112],"i)":[115],"missing":[116],"values,":[117],"ii)":[118],"values":[119],"not":[120],"coming":[121],"from":[122],"predefined":[124],"set":[125],"or":[126,145],"iii)":[127],"wrong":[128],"cardinalities,":[129],"can":[130],"be":[131],"detected":[132],"approach.":[135],"Since":[136],"2015":[137],"approximately":[138],"5%":[139],"all":[141],"contain":[143],"one":[144],"errors.":[147],"future,":[150],"will":[152],"apply":[153],"technique":[155],"other":[157],"registries":[158,185],"develop":[160],"complex":[162],"rules":[163],"focusing":[165],"on":[166],"semantics":[168],"metadata.":[171],"This":[172],"could":[173],"render":[174],"possibility":[176],"automatically":[178],"correcting":[179],"entries,":[180],"increasing":[181],"studies.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
