{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T13:16:43Z","timestamp":1716383803339},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"2","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["J Am Med Inform Assoc"],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1136\/amiajnl-2013-002034","type":"journal-article","created":{"date-parts":[[2013,10,24]],"date-time":"2013-10-24T03:48:46Z","timestamp":1382586526000},"page":"252-262","update-policy":"http:\/\/dx.doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":16,"title":["Efficient sequential and parallel algorithms for record linkage"],"prefix":"10.1093","volume":"21","author":[{"given":"Abdullah-Al","family":"Mamun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Mi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Aseltine","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanguthevar","family":"Rajasekaran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2014,3,1]]},"reference":[{"key":"2015062905370861000_21.2.252.1","doi-asserted-by":"publisher","DOI":"10.1136\/ip.2003.004580"},{"key":"2015062905370861000_21.2.252.2","unstructured":"Fayyad U Piatetsky-Shapiro G Smyth P . From data mining to knowledge discovery in databases. AI Mag 1996;17:37\u201354."},{"key":"2015062905370861000_21.2.252.3","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2001.0080281"},{"key":"2015062905370861000_21.2.252.4","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M1696"},{"key":"2015062905370861000_21.2.252.5","doi-asserted-by":"crossref","unstructured":"Brin S Davis J Garcia-Molina H . Copy detection mechanisms for digital documents. In: Proceedings of the ACM SIGMOD Annual Conference: 22\u201325 May 1995; San Jose CA Carey MJ Schneider DA . eds. New York: ACM; 1995:398\u2013409.","DOI":"10.1145\/223784.223855"},{"key":"2015062905370861000_21.2.252.6","doi-asserted-by":"crossref","unstructured":"Shivakumar N Garcia-Molina H . Building a scalable and accurate copy detection mechanism. In: Proceedings of the 1st ACM International Conference on Digital Libraries: 20\u201323 March 1996; Bethesda, MD. Fox EA Marchionini G , eds. New York: ACM; 1996:160\u20138.","DOI":"10.1145\/226931.226961"},{"key":"2015062905370861000_21.2.252.7","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-12-59"},{"key":"2015062905370861000_21.2.252.8","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1147"},{"key":"2015062905370861000_21.2.252.9","unstructured":"Gu L Baxter R Vickers D . Record linkage: current practice and future directions. CSIRO Math Info Sci Tech Rep 2003;3:83."},{"key":"2015062905370861000_21.2.252.10","unstructured":"Winkler WE Thibaudeau Y . An application of the Fellegi-Sunter model of record linkage to the 1990 U.S. decennial census. Technical Report Statistical Research Report Series RR91\/09, U.S. Bureau of the Census, Washington, DC, 1991."},{"key":"2015062905370861000_21.2.252.11","doi-asserted-by":"crossref","unstructured":"Zhao Y Karypis G . Evaluation of hierarchical clustering algorithms for document datasets. In: Proceedings of the 11th international conference on Information and knowledge management: 4\u20139 November 2002; McLean, VA. New York: ACM; 2002:515\u201324.","DOI":"10.1145\/584792.584877"},{"key":"2015062905370861000_21.2.252.12","doi-asserted-by":"crossref","unstructured":"Vinh NX Epps J Bailey J . Information theoretic measures for clusterings comparison: is a correction for chance necessary? In: Proceedings of the 26th International Conference on Machine Learning: 14\u201318 June 2009; Montreal, Quebec, Canada. New York: ACM; 2009:1073\u201380.","DOI":"10.1145\/1553374.1553511"},{"key":"2015062905370861000_21.2.252.13","doi-asserted-by":"publisher","DOI":"10.1101\/gr.9.11.1106"},{"key":"2015062905370861000_21.2.252.14","unstructured":"Hawse JR Hejtmancik JF Huang Q . Identification and functional clustering of global gene expression differences between human age-related cataract and clear lenses. Mol Vis 2003;9:515\u201337."},{"key":"2015062905370861000_21.2.252.15","doi-asserted-by":"publisher","DOI":"10.1038\/nprot.2008.211"},{"key":"2015062905370861000_21.2.252.16","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2003-4-5-p3"},{"key":"2015062905370861000_21.2.252.17","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-007-0073-y"},{"key":"2015062905370861000_21.2.252.18","unstructured":"Ng RT Han J . Efficient and effective clustering methods for spatial data mining. In: Proceedings of the 20th International Conference on Very Large Data Bases: 12\u201315 September 1994; Santiago de Chile, Chile. Bocca JB . eds. San Francisco: Morgan Kaufmann Publishers; 1994:144\u201355."},{"key":"2015062905370861000_21.2.252.19","doi-asserted-by":"publisher","DOI":"10.1348\/135910705X25697"},{"key":"2015062905370861000_21.2.252.20","unstructured":"Sedgewick R . Algorithms in C++, third edition. Addison-Wesley Professional, 1998:424\u20137."},{"key":"2015062905370861000_21.2.252.21","doi-asserted-by":"crossref","unstructured":"Christen P . Data matching: concepts and techniques for record linkage, entity resolution, and duplicate detection. Springer, 2012.","DOI":"10.1007\/978-3-642-31164-2"},{"key":"2015062905370861000_21.2.252.22","doi-asserted-by":"crossref","unstructured":"Bhattacharya I Getoor L . Collective entity resolution in relational data. ACM TKDD 2007;1.","DOI":"10.1145\/1217299.1217304"},{"key":"2015062905370861000_21.2.252.23","unstructured":"Winkler WE . Overview of record linkage and current research directions. Technical Report Statistical Research Report Series RRS2006\/02, U.S. Bureau of the Census, Washington, DC, 2006."},{"key":"2015062905370861000_21.2.252.24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-44918-8_6"},{"key":"2015062905370861000_21.2.252.25","unstructured":"Winkler WE . The state of record linkage and current research problems. Technical Report Statistical Research Report Series RR99\/04, U.S. Bureau of the Census, Washington, DC, 1999."},{"key":"2015062905370861000_21.2.252.26","unstructured":"Winkler WE . Improved decision rules in the Fellegi-Sunter model of record linkage. Proceedings of on Survey Research Methods. American Statistical Association 1993;1:274\u20139."},{"key":"2015062905370861000_21.2.252.27","doi-asserted-by":"publisher","DOI":"10.2307\/2286061"},{"key":"2015062905370861000_21.2.252.28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.250581"},{"key":"2015062905370861000_21.2.252.29","doi-asserted-by":"crossref","unstructured":"Winkler WE . Matching and record linkage, business survey methods. New York: Wiley, 1995:355\u201384.","DOI":"10.1002\/9781118150504.ch20"},{"key":"2015062905370861000_21.2.252.30","unstructured":"Winkler WE . The state of record linkage and current research problems. Statistical Research Division, U.S. Census Bureau, 1999."},{"key":"2015062905370861000_21.2.252.31","unstructured":"Pasula H Marthi B Milch B . Identity uncertainty and citation matching. Advances in Neural Information Processing Systems 2003:1401\u20138."},{"key":"2015062905370861000_21.2.252.32","unstructured":"McCallum A Wellner B . Conditional models of identity uncertainty with application to noun coreference. Advances in Neural Information Processing Systems 2005:905\u201312."},{"key":"2015062905370861000_21.2.252.33","unstructured":"Lafferty J McCallum A Pereira F . Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proceedings of 18th International Conference on Machine Learning. 2001:282\u20139."},{"key":"2015062905370861000_21.2.252.34","doi-asserted-by":"crossref","unstructured":"Culotta A McCallum A . Joint deduplication of multiple record types in relational data. 14th ACM International Conference on Information and Knowledge Management 2005:257\u20138.","DOI":"10.1145\/1099554.1099615"},{"key":"2015062905370861000_21.2.252.35","unstructured":"Parag Domingos P . Multi-relational record linkage. Tenth International Conference on Knowledge Discovery and Data Mining. 2004:31\u201348."},{"key":"2015062905370861000_21.2.252.36","doi-asserted-by":"crossref","unstructured":"Christen P . A comparison of personal name matching: Techniques and practical issues. Second International Workshop on Mining Complex Data 2006:290\u20134.","DOI":"10.1109\/ICDMW.2006.2"},{"key":"2015062905370861000_21.2.252.37","unstructured":"Levenshtein VI . Binary codes capable of correcting deletions, insertions, and reversals. Soviet Phys, Doklady 1966; 10:707\u201310."},{"key":"2015062905370861000_21.2.252.38","doi-asserted-by":"publisher","DOI":"10.2307\/2289924"},{"key":"2015062905370861000_21.2.252.39","doi-asserted-by":"publisher","DOI":"10.1145\/146370.146380"},{"key":"2015062905370861000_21.2.252.40","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4809(92)90005-U"},{"key":"2015062905370861000_21.2.252.41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24775-3_75"},{"key":"2015062905370861000_21.2.252.42","unstructured":"Christen P . Febrl\u2014a freely available record linkage system with a graphical user interface. Second Australasian workshop on Health data and knowledge management 2008;80:17\u201325."},{"key":"2015062905370861000_21.2.252.43","doi-asserted-by":"crossref","unstructured":"Lee ML Ling TW Low WL . Intelliclean: A knowledge-based intelligent data cleanser. Sixth International Conference on Knowledge Discovery and Data Mining 2000:290\u20134.","DOI":"10.1145\/347090.347154"},{"key":"2015062905370861000_21.2.252.44","doi-asserted-by":"crossref","unstructured":"Hernandez MA Stolfo SJ . The merge\/purge problem for large databases. Proceedings of the 1995 ACM SIGMOD International Conference on Management of Data. 1995:127\u201338.","DOI":"10.1145\/223784.223807"},{"key":"2015062905370861000_21.2.252.45","doi-asserted-by":"crossref","unstructured":"McCallum A Nigam K Ungar LH . Efficient clustering of high-dimensional data sets with application to reference matching. Proceedings of the Sixth International Conference on Knowledge Discovery and Data Mining. 2000:169\u201378.","DOI":"10.1145\/347090.347123"},{"key":"2015062905370861000_21.2.252.46","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687771"},{"key":"2015062905370861000_21.2.252.47","doi-asserted-by":"publisher","DOI":"10.1109\/34.61708"},{"key":"2015062905370861000_21.2.252.48","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(95)00017-I"},{"key":"2015062905370861000_21.2.252.49","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2005.72"},{"key":"2015062905370861000_21.2.252.50","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.2000.1644"},{"key":"2015062905370861000_21.2.252.51","unstructured":"Kawai H Garcia-Molina H Benjelloun O . P-Swoosh: parallel algorithm for generic entity resolution. Technical Report, Department of Computer Science, Stanford University, 2006."},{"key":"2015062905370861000_21.2.252.52","doi-asserted-by":"crossref","unstructured":"Kim H Lee D . Parallel Linkage. ACM CIKM 2007:283\u201392.","DOI":"10.1145\/1321440.1321482"},{"key":"2015062905370861000_21.2.252.53","unstructured":"Kirsten T Kolb L Hartung M . Data partitioning for parallel entity matching. Proc VLDB Endowment 2010;3."},{"key":"2015062905370861000_21.2.252.54","doi-asserted-by":"crossref","unstructured":"Bianco GD Galante R Heuser CA . A fast approach for parallel deduplication on multicore processors. Proceedings of the 2011 ACM Symposium on Applied Computing 2011:1027\u201332.","DOI":"10.1145\/1982185.1982411"},{"key":"2015062905370861000_21.2.252.55","doi-asserted-by":"crossref","unstructured":"Mi T Aseltine R Rajasekaran S . Data integration on multiple data sets. Proceedings of the 2008 IEEE International Conference on Bioinformatics and Biomedicine 2008:443\u20136.","DOI":"10.1109\/BIBM.2008.48"},{"key":"2015062905370861000_21.2.252.56","doi-asserted-by":"crossref","unstructured":"Greiner J . A comparison of parallel algorithms for connected components. Symposium on Parallel Algorithms and Architectures 1994:16\u201325.","DOI":"10.1145\/181014.181021"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","deposited":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T22:03:24Z","timestamp":1716069804000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article-lookup\/doi\/10.1136\/amiajnl-2013-002034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3]]},"references-count":56,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2014,3,1]]},"published-print":{"date-parts":[[2014,3]]}},"alternative-id":["10.1136\/amiajnl-2013-002034"],"URL":"https:\/\/doi.org\/10.1136\/amiajnl-2013-002034","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,3]]}}}