{"id":"https://openalex.org/W2058755145","doi":"https://doi.org/10.1145/1081870.1081923","title":"A hit-miss model for duplicate detection in the WHO drug safety database","display_name":"A hit-miss model for duplicate detection in the WHO drug safety database","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2058755145","doi":"https://doi.org/10.1145/1081870.1081923","mag":"2058755145"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5022900127","display_name":"G. Niklas Nor\u00e9n","orcid":"https://orcid.org/0000-0002-4595-230X"},"institutions":[{"id":"https://openalex.org/I111684115","display_name":"Uppsala Monitoring Centre","ror":"https://ror.org/057rhqk62","country_code":"SE","type":"other","lineage":["https://openalex.org/I111684115"]},{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"G. Niklas Nor\u00e9n","raw_affiliation_strings":["WHO Collaborating Centre for International Drug Monitoring, Uppsala, Sweden & Stockholm University, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"WHO Collaborating Centre for International Drug Monitoring, Uppsala, Sweden & Stockholm University, Stockholm, Sweden","institution_ids":["https://openalex.org/I111684115","https://openalex.org/I161593684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002855167","display_name":"Roland Orre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roland Orre","raw_affiliation_strings":["NeuroLogic Sweden AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"NeuroLogic Sweden AB, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002909029","display_name":"Andrew Bate","orcid":"https://orcid.org/0000-0003-3151-3653"},"institutions":[{"id":"https://openalex.org/I111684115","display_name":"Uppsala Monitoring Centre","ror":"https://ror.org/057rhqk62","country_code":"SE","type":"other","lineage":["https://openalex.org/I111684115"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Andrew Bate","raw_affiliation_strings":["WHO Collaborating Centre for International Drug Monitoring, Uppsala, Sweden","WHO Collaborating Centre for International Drug Monitoring, Uppsala, Sweden#TAB#"],"affiliations":[{"raw_affiliation_string":"WHO Collaborating Centre for International Drug Monitoring, Uppsala, Sweden","institution_ids":["https://openalex.org/I111684115"]},{"raw_affiliation_string":"WHO Collaborating Centre for International Drug Monitoring, Uppsala, Sweden#TAB#","institution_ids":["https://openalex.org/I111684115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022900127"],"corresponding_institution_ids":["https://openalex.org/I111684115","https://openalex.org/I161593684"],"apc_list":null,"apc_paid":null,"fwci":5.9092,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.96112028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"459","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13546","display_name":"Census and Population Estimation","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6846078038215637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6837272644042969},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.6206647157669067},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5136474967002869},{"id":"https://openalex.org/keywords/postmarketing-surveillance","display_name":"Postmarketing surveillance","score":0.4770968556404114},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45289531350135803},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4351430833339691},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3141723871231079},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.15660998225212097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14742818474769592},{"id":"https://openalex.org/keywords/adverse-effect","display_name":"Adverse effect","score":0.08463063836097717}],"concepts":[{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6846078038215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837272644042969},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.6206647157669067},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5136474967002869},{"id":"https://openalex.org/C197636746","wikidata":"https://www.wikidata.org/wiki/Q7234359","display_name":"Postmarketing surveillance","level":3,"score":0.4770968556404114},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45289531350135803},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4351430833339691},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3141723871231079},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.15660998225212097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14742818474769592},{"id":"https://openalex.org/C197934379","wikidata":"https://www.wikidata.org/wiki/Q2047938","display_name":"Adverse effect","level":2,"score":0.08463063836097717},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","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/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1081870.1081923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.835.2374","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.835.2374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.norc.org/PDFs/May%202011%20Personal%20Validation%20and%20Entity%20Resolution%20Conference/Hit-Miss%20Model%20for%20Duplicate%20Detection%20in%20WHO%20Drug%20Safety%20Database%20Paper_PVERConf_May2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1569123402","https://openalex.org/W1943251102","https://openalex.org/W1975723136","https://openalex.org/W1993637408","https://openalex.org/W2015487160","https://openalex.org/W2017008233","https://openalex.org/W2024770506","https://openalex.org/W2027708325","https://openalex.org/W2036021378","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2076457453","https://openalex.org/W2089696793","https://openalex.org/W2095644746","https://openalex.org/W2109974875","https://openalex.org/W2164456230","https://openalex.org/W2170320881"],"related_works":["https://openalex.org/W2079637050","https://openalex.org/W2479028015","https://openalex.org/W2063113598","https://openalex.org/W2462067835","https://openalex.org/W2082586020","https://openalex.org/W177034557","https://openalex.org/W2024018837","https://openalex.org/W2949074706","https://openalex.org/W2606460416","https://openalex.org/W2161989415"],"abstract_inverted_index":{"The":[0,195],"WHO":[1,61,166],"Collaborating":[2],"Centre":[3],"for":[4,91,106,115,138,161,177,199],"International":[5],"Drug":[6],"Monitoring":[7],"in":[8,36,59,94,140,164,204],"Uppsala,":[9],"Sweden,":[10],"maintains":[11],"and":[12,54,144,183,210],"analyses":[13],"the":[14,33,43,55,60,71,78,112,130,155,158,165,173,215],"world's":[15],"largest":[16],"database":[17,64,169],"of":[18,45,57,129,157],"reports":[19,72],"on":[20,32,89,111],"suspected":[21],"adverse":[22],"drug":[23,39,62,96,167,206],"reaction":[24],"incidents":[25],"that":[26],"occur":[27],"after":[28],"drugs":[29],"are":[30,73],"introduced":[31],"market.":[34],"As":[35],"other":[37,212],"post-marketing":[38,95,205],"safety":[40,63,97,168,207],"data":[41,51,202,208],"sets,":[42,209],"presence":[44],"duplicate":[46,92,108,162,176],"records":[47],"is":[48],"an":[49],"important":[50],"quality":[52],"problem":[53],"detection":[56,93,109,163],"duplicates":[58,186],"remains":[65],"a":[66,104,134,145,178],"formidable":[67],"challenge,":[68],"especially":[69],"since":[70],"anonymised":[74],"before":[75],"submitted":[76],"to":[77,81,148],"database.":[79],"However,":[80],"our":[82],"knowledge":[83],"no":[84],"work":[85],"has":[86],"been":[87],"published":[88],"methods":[90],"data.":[98],"In":[99],"this":[100],"paper,":[101],"we":[102],"propose":[103],"method":[105,147,197],"probabilistic":[107],"based":[110],"hit-miss":[113,132,135,159],"model":[114,137,160],"statistical":[116],"record":[117,142,151,180],"linkage":[118],"described":[119],"by":[120],"Copas":[121],"&":[122],"Hilton.":[123],"We":[124,153],"present":[125],"two":[126],"new":[127,146],"generalisations":[128],"standard":[131],"model:":[133],"mixture":[136],"errors":[139],"numerical":[141],"fields":[143],"handle":[149],"correlated":[150],"fields.":[152],"demonstrate":[154],"effectiveness":[156],"both":[170],"at":[171,184],"identifying":[172],"most":[174],"likely":[175],"given":[179],"(94.7%":[181],"accuracy)":[182],"discriminating":[185],"from":[187],"random":[188],"matches":[189],"(63%":[190],"recall":[191],"with":[192],"71%":[193],"precision).":[194],"proposed":[196],"allows":[198],"more":[200],"efficient":[201],"cleaning":[203],"perhaps":[211],"applications":[213],"throughout":[214],"KDD":[216],"community.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}