{"id":"https://openalex.org/W2140926830","doi":"https://doi.org/10.1136/amiajnl-2013-002034","title":"Efficient sequential and parallel algorithms for record linkage","display_name":"Efficient sequential and parallel algorithms for record linkage","publication_year":2013,"publication_date":"2013-10-24","ids":{"openalex":"https://openalex.org/W2140926830","doi":"https://doi.org/10.1136/amiajnl-2013-002034","mag":"2140926830","pmid":"https://pubmed.ncbi.nlm.nih.gov/24154837"},"language":"en","primary_location":{"id":"doi:10.1136/amiajnl-2013-002034","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2013-002034","pdf_url":"https://academic.oup.com/jamia/article-pdf/21/2/252/9517653/21-2-252.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":"hybrid","oa_url":"https://academic.oup.com/jamia/article-pdf/21/2/252/9517653/21-2-252.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100970396","display_name":"Abdullah-Al Mamun","orcid":null},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdullah-Al Mamun","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Connecticut, Storrs, Connecticut, USA","Department of Computer Science and Engineering, University of Connecticut Storrs, Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689981","display_name":"Tian Mi","orcid":"https://orcid.org/0000-0003-3230-0633"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Mi","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Connecticut, Storrs, Connecticut, USA","Department of Computer Science and Engineering, University of Connecticut Storrs, Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030001545","display_name":"Robert H. Aseltine","orcid":"https://orcid.org/0000-0003-3007-9867"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Aseltine","raw_affiliation_strings":["Institute for Public Health Research, University of Connecticut, East Hartford, Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Public Health Research, University of Connecticut, East Hartford, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034177039","display_name":"Sanguthevar Rajasekaran","orcid":null},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanguthevar Rajasekaran","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Connecticut, Storrs, Connecticut, USA","Department of Computer Science and Engineering, University of Connecticut Storrs, Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034177039"],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":{"value":3967,"currency":"USD","value_usd":3967},"fwci":2.1306,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88834101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"2","first_page":"252","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9884999990463257,"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":0.9884999990463257,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.0044999998062849045,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.0005000000237487257,"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/computer-science","display_name":"Computer science","score":0.8186548352241516},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6881183385848999},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5838916897773743},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.5220622420310974},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5042389631271362},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.490416020154953},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.445813924074173},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.43428274989128113},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.4318885803222656},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.20896682143211365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1555754542350769},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12302267551422119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186548352241516},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6881183385848999},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5838916897773743},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.5220622420310974},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5042389631271362},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.490416020154953},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.445813924074173},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.43428274989128113},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.4318885803222656},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.20896682143211365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1555754542350769},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12302267551422119}],"mesh":[{"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":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1136/amiajnl-2013-002034","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2013-002034","pdf_url":"https://academic.oup.com/jamia/article-pdf/21/2/252/9517653/21-2-252.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:24154837","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24154837","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:2913793","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3932463","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":"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":"Text"}],"best_oa_location":{"id":"doi:10.1136/amiajnl-2013-002034","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2013-002034","pdf_url":"https://academic.oup.com/jamia/article-pdf/21/2/252/9517653/21-2-252.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W36024057","https://openalex.org/W46452414","https://openalex.org/W107023076","https://openalex.org/W1522410437","https://openalex.org/W1547612978","https://openalex.org/W1575476631","https://openalex.org/W1582775886","https://openalex.org/W1587236234","https://openalex.org/W1597164057","https://openalex.org/W1647671624","https://openalex.org/W1751533507","https://openalex.org/W1971318281","https://openalex.org/W1976208596","https://openalex.org/W1979629649","https://openalex.org/W1997657677","https://openalex.org/W2001383125","https://openalex.org/W2004918398","https://openalex.org/W2007842132","https://openalex.org/W2010595692","https://openalex.org/W2024770506","https://openalex.org/W2034190452","https://openalex.org/W2036216970","https://openalex.org/W2039001182","https://openalex.org/W2049631158","https://openalex.org/W2050071106","https://openalex.org/W2066505785","https://openalex.org/W2073471108","https://openalex.org/W2094423759","https://openalex.org/W2097225630","https://openalex.org/W2097730395","https://openalex.org/W2098034668","https://openalex.org/W2108503327","https://openalex.org/W2108524699","https://openalex.org/W2108991785","https://openalex.org/W2113054345","https://openalex.org/W2122683221","https://openalex.org/W2129270691","https://openalex.org/W2132038418","https://openalex.org/W2132215016","https://openalex.org/W2133035795","https://openalex.org/W2133236963","https://openalex.org/W2133555107","https://openalex.org/W2147880316","https://openalex.org/W2148019918","https://openalex.org/W2148524305","https://openalex.org/W2158217645","https://openalex.org/W2159481891","https://openalex.org/W2163598528","https://openalex.org/W2163847742","https://openalex.org/W2223011434","https://openalex.org/W2295151155","https://openalex.org/W2913519381","https://openalex.org/W3025699485","https://openalex.org/W3146259567","https://openalex.org/W4230502578","https://openalex.org/W4242744113","https://openalex.org/W4255971601"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2146343568","https://openalex.org/W2031630671","https://openalex.org/W2950592963","https://openalex.org/W4300800892","https://openalex.org/W2059382600","https://openalex.org/W2607998022"],"abstract_inverted_index":{"BACKGROUND":[0],"AND":[1],"OBJECTIVE:":[2],"Integrating":[3],"data":[4],"from":[5,27,135],"multiple":[6],"sources":[7],"is":[8,82,99,236],"a":[9,102,123,183,192],"crucial":[10],"and":[11,50,62,108,116,129,203,225],"challenging":[12],"problem.":[13],"Even":[14],"though":[15],"there":[16],"exist":[17],"numerous":[18],"algorithms":[19,52,68,72,118],"for":[20,53,149],"record":[21,54],"linkage":[22,55],"or":[23,32],"deduplication,":[24],"they":[25,40],"suffer":[26],"either":[28],"large":[29],"time":[30],"needs":[31],"restrictions":[33],"on":[34,85,122],"the":[35,74,110,153,157,164,216,231,237],"number":[36,59],"of":[37,60,126,163,185,218,241],"datasets":[38,61,131],"that":[39,79,104,227,240],"can":[41],"integrate.":[42],"In":[43],"this":[44,242],"paper":[45],"we":[46,80,181],"report":[47],"efficient":[48],"sequential":[49,115,141,220],"parallel":[51,117,174],"which":[56],"handle":[57],"any":[58,93,150],"outperform":[63],"previous":[64,154,232,243],"algorithms.":[65],"METHODS:":[66],"Our":[67,114,140],"employ":[69],"hierarchical":[70],"clustering":[71],"as":[73,239],"basis.":[75],"A":[76],"key":[77],"idea":[78,98],"use":[81],"radix":[83],"sorting":[84],"certain":[86],"attributes":[87],"to":[88,100,137],"eliminate":[89],"identical":[90],"records":[91,107,128],"before":[92],"further":[94],"processing.":[95],"Another":[96],"novel":[97],"form":[101],"graph":[103],"links":[105],"similar":[106],"find":[109],"connected":[111],"components.":[112],"RESULTS:":[113],"have":[119,214],"been":[120],"tested":[121],"real":[124],"dataset":[125],"1,083,878":[127],"synthetic":[130],"ranging":[132],"in":[133,191,200,209],"size":[134],"50,000":[136],"9,000,000":[138],"records.":[139],"algorithm":[142,159,175,221,229],"runs":[143],"at":[144],"least":[145],"two":[146,201],"times":[147],"faster,":[148],"dataset,":[151],"than":[152],"best-known":[155,244],"algorithm,":[156],"two-phase":[158],"using":[160],"faster":[161],"computation":[162],"edit":[165],"distance":[166],"(TPA":[167],"(FCED)).":[168],"The":[169,234],"speedups":[170],"obtained":[171],"by":[172],"our":[173,219,228],"are":[176],"almost":[177],"linear.":[178],"For":[179],"example,":[180],"get":[182],"speedup":[184],"7.5":[186],"with":[187,196,205,222],"8":[188],"cores":[189,198,207],"(residing":[190,199,208],"single":[193],"node),":[194],"14.1":[195],"16":[197],"nodes),":[202],"26.4":[204],"32":[206],"four":[210],"nodes).":[211],"CONCLUSIONS:":[212],"We":[213],"compared":[215],"performance":[217],"TPA":[223],"(FCED)":[224],"found":[226],"outperforms":[230],"one.":[233],"accuracy":[235],"same":[238],"algorithm.":[245]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-05-19T21:40:30.786675","created_date":"2025-10-10T00:00:00"}