{"id":"https://openalex.org/W2188397702","doi":"https://doi.org/10.1136/amiajnl-2011-000461","title":"Missing values in deduplication of electronic patient data","display_name":"Missing values in deduplication of electronic patient data","publication_year":2011,"publication_date":"2011-10-16","ids":{"openalex":"https://openalex.org/W2188397702","doi":"https://doi.org/10.1136/amiajnl-2011-000461","mag":"2188397702","pmid":"https://pubmed.ncbi.nlm.nih.gov/22003173"},"language":"en","primary_location":{"id":"doi:10.1136/amiajnl-2011-000461","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2011-000461","pdf_url":"https://academic.oup.com/jamia/article-pdf/19/e1/e76/5878587/19-e1-e76.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/jamia/article-pdf/19/e1/e76/5878587/19-e1-e76.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021788298","display_name":"Murat Sariyar","orcid":"https://orcid.org/0000-0002-5595-689X"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]},{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"M. Sariyar","raw_affiliation_strings":["Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Centre of the Johannes Gutenberg University, Mainz, Germany. murat.sariyar@unimedizin-mainz.de","Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Centre of the Johannes Gutenberg University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Centre of the Johannes Gutenberg University, Mainz, Germany. murat.sariyar@unimedizin-mainz.de","institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"]},{"raw_affiliation_string":"Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Centre of the Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014815043","display_name":"Andreas Borg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Borg","raw_affiliation_strings":["Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Centre of the Johannes Gutenberg University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Centre of the Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113723350","display_name":"K. Pommerening","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"K. Pommerening","raw_affiliation_strings":["Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Centre of the Johannes Gutenberg University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Centre of the Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021788298"],"corresponding_institution_ids":["https://openalex.org/I197323543","https://openalex.org/I4210094062"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":3.8073,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93320546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"19","issue":"e1","first_page":"e76","last_page":"e82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9818999767303467,"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":0.9818999767303467,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.0019000000320374966,"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/T10350","display_name":"Electronic Health Records Systems","score":0.00139999995008111,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9425276517868042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5945960879325867},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5621736645698547},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3839629292488098},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3475741147994995},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.329328328371048},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27958428859710693},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15970566868782043}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9425276517868042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5945960879325867},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5621736645698547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3839629292488098},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3475741147994995},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.329328328371048},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27958428859710693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15970566868782043}],"mesh":[{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","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":"D012042","descriptor_name":"Registries","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":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1136/amiajnl-2011-000461","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2011-000461","pdf_url":"https://academic.oup.com/jamia/article-pdf/19/e1/e76/5878587/19-e1-e76.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:22003173","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22003173","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":"Journal of the American Medical Informatics Association : JAMIA","raw_type":null},{"id":"pmh:oai:europepmc.org:2665687","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3392851","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1136/amiajnl-2011-000461","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2011-000461","pdf_url":"https://academic.oup.com/jamia/article-pdf/19/e1/e76/5878587/19-e1-e76.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2188397702.pdf","grobid_xml":"https://content.openalex.org/works/W2188397702.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W36826027","https://openalex.org/W87072980","https://openalex.org/W1491002046","https://openalex.org/W1518784700","https://openalex.org/W1547556487","https://openalex.org/W1597164057","https://openalex.org/W1612155886","https://openalex.org/W1711349269","https://openalex.org/W1982806687","https://openalex.org/W2010954655","https://openalex.org/W2012466471","https://openalex.org/W2024018837","https://openalex.org/W2031250218","https://openalex.org/W2034143386","https://openalex.org/W2034190452","https://openalex.org/W2044758663","https://openalex.org/W2065199439","https://openalex.org/W2067566391","https://openalex.org/W2072510577","https://openalex.org/W2073471108","https://openalex.org/W2089367555","https://openalex.org/W2094423759","https://openalex.org/W2108991785","https://openalex.org/W2112076978","https://openalex.org/W2123170466","https://openalex.org/W2125055259","https://openalex.org/W2126275630","https://openalex.org/W2142023452","https://openalex.org/W2147845824","https://openalex.org/W2164788271","https://openalex.org/W2170902582","https://openalex.org/W2316704435","https://openalex.org/W2327666415","https://openalex.org/W2794286494","https://openalex.org/W2912934387","https://openalex.org/W3085162807","https://openalex.org/W3121539865","https://openalex.org/W3146259567"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4296125805","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W1982579475"],"abstract_inverted_index":{"INTRODUCTION:":[0],"Systematic":[1],"approaches":[2,113],"to":[3,117,139,148],"dealing":[4,96],"with":[5,26,61,97,102,144,150,161],"missing":[6,65,194],"values":[7,23,66,195],"in":[8,67],"record":[9],"linkage":[10],"are":[11,71,99,114,222],"still":[12],"lacking.":[13],"This":[14,203],"article":[15],"compares":[16],"the":[17,38,87,92,118,127,140,153,156,176,180,184,190,199,220],"ad-hoc":[18,191],"treatment":[19],"of":[20,37,64,120,183,201,211],"unknown":[21],"comparison":[22,90],"as":[24,43,45],"'unequal'":[25],"other":[27,231],"and":[28,58,81,109,126,174,213,234],"more":[29],"sophisticated":[30],"approaches.":[31],"An":[32],"empirical":[33,74,232],"evaluation":[34],"was":[35],"conducted":[36],"methods":[39],"on":[40,46,50,207,214],"real-world":[41],"data":[42,48,57,60,122,212],"well":[44],"simulated":[47],"based":[49,206],"them.":[51],"MATERIAL":[52],"AND":[53],"METHODS:":[54],"Cancer":[55],"registry":[56],"artificial":[59],"increased":[62],"numbers":[63],"a":[68,77,208,215],"relevant":[69],"variable":[70],"used":[72],"for":[73,95,124,193],"comparisons.":[75],"As":[76],"classification":[78,80,108],"method,":[79],"regression":[82],"trees":[83],"were":[84],"used.":[85],"On":[86],"resulting":[88],"binary":[89,181],"patterns,":[91],"following":[93],"strategies":[94],"missingness":[98],"considered:":[100],"imputation":[101,137,149],"unique":[103,135],"values,":[104],"sample-based":[105],"imputation,":[106],"reduced-model":[107],"complete-case":[110],"induction.":[111],"These":[112],"evaluated":[115],"according":[116],"number":[119],"training":[121,166],"needed":[123],"induction":[125],"F-scores":[128],"achieved.":[129],"RESULTS:":[130],"The":[131,187],"evaluations":[132],"reveal":[133],"that":[134,224],"value":[136,200],"leads":[138],"best":[141],"results.":[142],"Imputation":[143,160],"zero":[145,162],"is":[146,205],"preferred":[147],"0.5,":[151],"although":[152],"latter":[154],"shows":[155,169],"highest":[157],"median":[158],"F-scores.":[159],"needs":[163],"considerably":[164],"less":[165],"data,":[167],"it":[168],"only":[170],"slightly":[171],"worse":[172],"results":[173,188,226],"simplifies":[175],"computation":[177],"by":[178,198,230],"maintaining":[179],"structure":[182],"data.":[185],"CONCLUSIONS:":[186],"support":[189],"solution":[192],"'replace":[196],"NA":[197],"inequality'.":[202],"conclusion":[204],"limited":[209],"amount":[210],"specific":[216],"deduplication":[217],"method.":[218],"Nevertheless,":[219],"authors":[221],"confident":[223],"their":[225],"should":[227],"be":[228],"confirmed":[229],"analyses":[233],"applications.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}
