{"id":"https://openalex.org/W160070906","doi":null,"title":"Optimized dual threshold entity resolution for electronic health record databases--training set size and active learning.","display_name":"Optimized dual threshold entity resolution for electronic health record databases--training set size and active learning.","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W160070906","mag":"160070906","pmid":"https://pubmed.ncbi.nlm.nih.gov/24551372","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900213"},"language":"en","primary_location":{"id":"pmh:oai:europepmc.org:2909096","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900213","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},"volume":null,"type":"article","indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001663845","display_name":"Erel Joffe","orcid":"https://orcid.org/0000-0002-7883-289X","observed_orcids":["https://orcid.org/0000-0002-7883-289X"]},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erel Joffe","raw_affiliation_strings":["School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Michael J Byrne","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J Byrne","raw_affiliation_strings":["School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091909333","display_name":"Phillip Reeder","orcid":"https://orcid.org/0000-0002-8633-7872","observed_orcids":["https://orcid.org/0000-0002-8633-7872"]},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phillip Reeder","raw_affiliation_strings":["School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069247158","display_name":"Jorge R Herskovic","orcid":"https://orcid.org/0000-0002-0167-5646","observed_orcids":["https://orcid.org/0000-0002-0167-5646"]},"institutions":[{"id":"https://openalex.org/I1343551460","display_name":"The University of Texas MD Anderson Cancer Center","ror":"https://ror.org/04twxam07","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1343551460"]},{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jorge R Herskovic","raw_affiliation_strings":["School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX. ; Department of Bioinformatics and Computational Biology, MD Anderson Cancer Center, Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX. ; Department of Bioinformatics and Computational Biology, MD Anderson Cancer Center, Houston, TX","institution_ids":["https://openalex.org/I1343551460","https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026988600","display_name":"Craig W Johnson","orcid":"https://orcid.org/0000-0003-4361-9703","observed_orcids":["https://orcid.org/0000-0003-4361-9703","https://orcid.org/0000-0002-3161-3753"]},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig W Johnson","raw_affiliation_strings":["School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086954690","display_name":"Allison B. McCoy","orcid":"https://orcid.org/0000-0003-2292-9147","observed_orcids":["https://orcid.org/0000-0003-2292-9147"]},"institutions":[{"id":"https://openalex.org/I1306862143","display_name":"Memorial Hermann","ror":"https://ror.org/049d9a475","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1306862143"]},{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allison B McCoy","raw_affiliation_strings":["School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX. ; UT Houston - Memorial Hermann Center for Healthcare Quality & Safety, Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX. ; UT Houston - Memorial Hermann Center for Healthcare Quality & Safety, Houston, TX","institution_ids":["https://openalex.org/I1306862143","https://openalex.org/I919571938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075275684","display_name":"Elmer Victor Bernstam","orcid":"https://orcid.org/0000-0001-7643-791X","observed_orcids":["https://orcid.org/0000-0001-7643-791X"]},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elmer V Bernstam","raw_affiliation_strings":["School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX. ; Division of General Internal Medicine, Department of Internal Medicine, Medical School, The University of Texas Health Science Center at Houston, Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX. ; Division of General Internal Medicine, Department of Internal Medicine, Medical School, The University of Texas Health Science Center at Houston, Houston, TX","institution_ids":["https://openalex.org/I919571938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3652,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82897785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2013","issue":null,"first_page":"721","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T10350","display_name":"Electronic Health Records Systems","score":9.999999747378752e-05,"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/T14400","display_name":"Medical Coding and Health Information","score":9.999999747378752e-05,"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/entity-resolution","display_name":"entity resolution","score":0.9769999980926514},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.9710000157356262},{"id":"https://openalex.org/keywords/training-set-size","display_name":"training data size","score":0.8970000147819519},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.9990000128746033},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"particle swarm optimization","score":0.8080000281333923},{"id":"https://openalex.org/keywords/fuzzy-inference-engine","display_name":"fuzzy inference engine","score":0.7860000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056477665901184},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.631608247756958},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6044620871543884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5009298324584961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952830374240875},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.49323052167892456},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.48721688985824585},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4275780916213989},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4244527816772461},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4219200015068054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4118180274963379},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08285173773765564},{"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"pmh:oai:europepmc.org:2909096","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900213","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3900213","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900213","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"AMIA Annu Symp Proc","raw_type":"Text"},{"id":"pmid:24551372","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24551372","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,"listed_in":[],"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":"AMIA ... Annual Symposium proceedings. AMIA Symposium","raw_type":"Journal Article"},{"id":"mag:160070906","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24551372","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":{"id":"pmh:oai:europepmc.org:2909096","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900213","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[{"score":0.428600013256073,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W98226599","https://openalex.org/W143151647","https://openalex.org/W1566255553","https://openalex.org/W1570596343","https://openalex.org/W1597164057","https://openalex.org/W1871563011","https://openalex.org/W1964584862","https://openalex.org/W1965346830","https://openalex.org/W1981590391","https://openalex.org/W2034190452","https://openalex.org/W2053606499","https://openalex.org/W2067566391","https://openalex.org/W2072178063","https://openalex.org/W2089099908","https://openalex.org/W2101508813","https://openalex.org/W2106521941","https://openalex.org/W2109364787","https://openalex.org/W2111908265","https://openalex.org/W2152571127","https://openalex.org/W2161600801","https://openalex.org/W2164260925","https://openalex.org/W2188397702","https://openalex.org/W3123518987"],"related_works":["https://openalex.org/W2152571127","https://openalex.org/W2767681556","https://openalex.org/W2997438158","https://openalex.org/W4313328922","https://openalex.org/W1134508972","https://openalex.org/W2106675345","https://openalex.org/W2244198747","https://openalex.org/W2340101790","https://openalex.org/W7120783656","https://openalex.org/W3014074327"],"abstract_inverted_index":{"Clinical":[0],"databases":[1],"may":[2],"contain":[3],"several":[4],"records":[5,121],"for":[6,48,95],"a":[7,32],"single":[8],"patient.":[9],"Multiple":[10],"general":[11],"entity-resolution":[12],"algorithms":[13,56],"have":[14],"been":[15],"developed":[16],"to":[17,31,41],"identify":[18],"such":[19],"duplicate":[20],"records.":[21,140],"To":[22],"achieve":[23],"optimal":[24],"accuracy,":[25],"algorithm":[26,66],"parameters":[27,58],"must":[28],"be":[29],"tuned":[30],"particular":[33],"dataset.":[34],"The":[35],"purpose":[36],"of":[37,119],"this":[38],"study":[39],"was":[40],"determine":[42],"the":[43,61,120,150],"required":[44,126,151],"training":[45,127,152],"set":[46,153],"size":[47,82,102],"probabilistic,":[49],"deterministic":[50],"and":[51,74,111,145],"Fuzzy":[52],"Inference":[53],"Engine":[54],"(FIE)":[55],"with":[57,138],"optimized":[59],"using":[60],"particle":[62],"swarm":[63],"approach.":[64],"Each":[65],"classified":[67,117],"potential":[68],"duplicates":[69],"into:":[70],"definite":[71],"match,":[72],"non-match":[73],"indeterminate":[75],"(i.e.,":[76],"requires":[77],"manual":[78,100],"review).":[79],"Training":[80],"sets":[81],"ranged":[83],"from":[84],"2,000-10,000":[85],"randomly":[86],"selected":[87],"record-pairs.":[88,132],"We":[89],"also":[90],"evaluated":[91],"marginal":[92],"uncertainty":[93],"sampling":[94,147],"active":[96],"learning.":[97],"Optimization":[98],"reduced":[99],"review":[101],"(Deterministic":[103],"11.6%":[104],"vs.":[105,109,114],"2.5%;":[106],"FIE":[107,116],"49.6%":[108],"1.9%;":[110],"Probabilistic":[112],"10.5%":[113],"3.5%).":[115],"98.1%":[118],"correctly":[122],"(precision=1.0).":[123],"Best":[124],"performance":[125],"on":[128],"all":[129],"10,000":[130],"randomly-selected":[131],"Active":[133],"learning":[134],"achieved":[135],"comparable":[136],"results":[137],"3,000":[139],"Automated":[141],"optimization":[142],"is":[143],"effective":[144],"targeted":[146],"can":[148],"reduce":[149],"size.":[154]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}