{"id":"https://openalex.org/W2894024364","doi":"https://doi.org/10.3233/978-1-61499-896-9-70","title":"Predicting Matching Quality of Record Linkage Algorithms on Growing Data Sets","display_name":"Predicting Matching Quality of Record Linkage Algorithms on Growing Data Sets","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2894024364","doi":"https://doi.org/10.3233/978-1-61499-896-9-70","mag":"2894024364","pmid":"https://pubmed.ncbi.nlm.nih.gov/30147043"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-896-9-70","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-896-9-70","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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011858015","display_name":"Mart\u00edn Schuster","orcid":"https://orcid.org/0000-0002-7674-0887"},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Kiel University","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Schuster Martin","raw_affiliation_strings":["Institute of Epidemiology, University of Kiel, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Epidemiology, University of Kiel, Germany","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040314937","display_name":"Lukas Tittmann","orcid":"https://orcid.org/0000-0002-8731-4592"},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Kiel University","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tittmann Lukas","raw_affiliation_strings":["Institute of Epidemiology, University of Kiel, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Epidemiology, University of Kiel, Germany","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111430795","display_name":"Andreas Wolf","orcid":null},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Kiel University","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolf Andreas","raw_affiliation_strings":["Institute of Medical Informatics and Statistics, University of Kiel, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Medical Informatics and Statistics, University of Kiel, Germany","institution_ids":["https://openalex.org/I32021983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011858015"],"corresponding_institution_ids":["https://openalex.org/I32021983"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14112421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"253","issue":null,"first_page":"70","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9837999939918518,"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/matching","display_name":"Matching (statistics)","score":0.7250030040740967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7037338018417358},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.7024648785591125},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.7020931839942932},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6583690047264099},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.6116520166397095},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5577389597892761},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.47054511308670044},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.44881314039230347},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44642025232315063},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3367822766304016},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3350715935230255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21888744831085205},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1728506088256836},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16589707136154175},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10894832015037537},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06406837701797485}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7250030040740967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7037338018417358},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.7024648785591125},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.7020931839942932},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6583690047264099},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.6116520166397095},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5577389597892761},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.47054511308670044},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.44881314039230347},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44642025232315063},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3367822766304016},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3350715935230255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21888744831085205},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1728506088256836},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16589707136154175},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10894832015037537},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06406837701797485},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":false},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","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":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-896-9-70","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-896-9-70","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:30147043","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30147043","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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W2176311362","https://openalex.org/W3012491082","https://openalex.org/W3211905090","https://openalex.org/W3114272811","https://openalex.org/W1936317645","https://openalex.org/W4310568775","https://openalex.org/W2178148352"],"abstract_inverted_index":{"A":[0],"record":[1,185],"linkage":[2],"algorithm":[3],"tries":[4],"to":[5,10,62,74,138,144,149,167],"identify":[6,139],"records":[7,50,125,164,175],"which":[8,59,142],"belong":[9],"the":[11,16,24,29,52,64,83,140,151,154,177,183],"same":[12],"individual.":[13],"We":[14,55,157],"analyze":[15],"matching":[17,26,129,155],"behavior":[18],"of":[19,34,40,77,89,105,112,130,153,163],"an":[20,131],"approach":[21],"used":[22],"in":[23,147,190],"E-PIX":[25],"tool":[27],"on":[28,66,93,116,170],"very":[30],"limited":[31,178],"attribute":[32,179],"set":[33,46,88,180],"first":[35],"name,":[36,38],"last":[37],"date":[39],"birth":[41],"and":[42,176],"sex.":[43],"Our":[44,120],"benchmark":[45],"contains":[47],"almost":[48],"37,000":[49],"from":[51],"Popgen":[53],"biobank.":[54],"develop":[56],"a":[57,75,86],"model":[58,95,121],"allows":[60],"us":[61],"predict":[63],"workload":[65],"clerical":[67,191],"review":[68],"for":[69,85,126],"data":[70,87,118,133,171],"sets":[71,100,172],"growing":[72,117],"up":[73],"factor":[76],"10":[78],"or":[79],"even":[80],"more,":[81],"without":[82],"need":[84,143],"this":[90,94],"size.":[91],"Based":[92],"we":[96],"show":[97,159],"two":[98],"parameter":[99],"with":[101,173],"comparable":[102],"detection":[103],"rate":[104],"true":[106],"duplicates,":[107],"but":[108],"where":[109],"only":[110],"one":[111],"them":[113],"scales":[114],"well":[115],"sets.":[119],"provides":[122],"realistic":[123],"example":[124],"each":[127],"predicted":[128],"upscaled":[132],"set.":[134],"Thus,":[135],"it":[136],"enables":[137],"parameters":[141],"be":[145],"adjusted":[146],"order":[148],"improve":[150],"quality":[152],"candidates.":[156],"also":[158],"that":[160],"unreviewed":[161],"merging":[162],"is":[165],"prone":[166],"homonym":[168],"errors":[169],"200,000":[174],"above,":[181],"while":[182],"merged":[184],"pairs":[186],"are":[187],"obviously":[188],"different":[189],"review.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
