{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T06:40:25Z","timestamp":1759992025129,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319642826"},{"type":"electronic","value":"9783319642833"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-64283-3_16","type":"book-chapter","created":{"date-parts":[[2017,8,2]],"date-time":"2017-08-02T01:02:54Z","timestamp":1501635774000},"page":"214-227","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A Machine Learning Trainable Model to Assess the Accuracy of Probabilistic Record Linkage"],"prefix":"10.1007","author":[{"given":"Robespierre","family":"Pita","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Everton","family":"Mendon\u00e7a","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandra","family":"Reis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos","family":"Barreto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Spiros","family":"Denaxas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,3]]},"reference":[{"issue":"6943","key":"16_CR1","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.1136\/bmj.308.6943.1552","volume":"308","author":"DG Altman","year":"1994","unstructured":"Altman, D.G., Bland, J.M.: Diagnostic tests 1: Sensitivity and specificity. BMJ Br. Med. J. 308(6943), 1552 (1994)","journal-title":"BMJ Br. Med. J."},{"issue":"6948","key":"16_CR2","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1136\/bmj.309.6948.188","volume":"309","author":"DG Altman","year":"1994","unstructured":"Altman, D.G., Bland, J.M.: Diagnostic tests 3: receiver operating characteristic plots. BMJ Br. Med. J. 309(6948), 188 (1994)","journal-title":"BMJ Br. Med. J."},{"issue":"6947","key":"16_CR3","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1136\/bmj.309.6947.102","volume":"309","author":"DG Altman","year":"1994","unstructured":"Altman, D.G., Bland, J.M.: Statistics notes: diagnostic tests 2: predictive values. BMJ 309(6947), 102 (1994)","journal-title":"BMJ"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Antonie, M.L., Zaiane, O.R., Holte, R.C.: Learning to use a learned model: a two-stage approach to classification. In: Sixth International Conference on Data Mining, ICDM 2006, pp. 33\u201342. IEEE (2006)","DOI":"10.1109\/ICDM.2006.97"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Barreto, M.E., Alves, A., Sena, S., Fiaccone, R.L., Amorim, L., Ichihara, M., Barreto, M.: Assessing the accuracy of probabilistic record linkage of huge brazilian healthcare databases, vol. 1, p. 12. Oxford (2016)","DOI":"10.23889\/ijpds.v1i1.276"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Kamath, B., Mooney, R.J.: Adaptive blocking: Learning to scale up record linkage. In: Sixth International Conference on Data Mining, ICDM 2006, pp. 87\u201396. IEEE (2006)","DOI":"10.1109\/ICDM.2006.13"},{"issue":"1","key":"16_CR7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"issue":"2","key":"16_CR8","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1023\/A:1009715923555","volume":"2","author":"CJ Burges","year":"1998","unstructured":"Burges, C.J.: A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2(2), 121\u2013167 (1998)","journal-title":"Data Min. Knowl. Discov."},{"key":"16_CR9","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/978-3-540-44918-8_6","volume-title":"Quality Measures in Data Mining","author":"P Christen","year":"2007","unstructured":"Christen, P., Goiser, K.: Quality and complexity measures for data linkage and deduplication. In: Guillet, F.J., Hamilton, H.J. (eds.) Quality Measures in Data Mining, pp. 127\u2013151. Springer, Heidelberg (2007)"},{"key":"16_CR10","unstructured":"Christen, P., et al.: Parallel techniques for high-performance record linkage (data matching). Data Mining Group, Australian National University, Epidemiology and Surveillance Branch, pp. 1-27 (2002). Project web page: http:\/\/datamining.anu.edu.au\/linkage.html"},{"issue":"3","key":"16_CR11","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"LR Dice","year":"1945","unstructured":"Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297\u2013302 (1945)","journal-title":"Ecology"},{"key":"16_CR12","unstructured":"Elfeky, M.G., Verykios, V.S., Elmagarmid, A.K.: Tailor: a record linkage toolbox. In: 18th International Conference on Data Engineering, 2002, Proceedings, pp. 17\u201328. IEEE (2002)"},{"issue":"328","key":"16_CR13","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"IP Fellegi","year":"1969","unstructured":"Fellegi, I.P., Sunter, A.B.: A theory for record linkage. J. Am. Stat. Assoc. 64(328), 1183\u20131210 (1969)","journal-title":"J. Am. Stat. Assoc."},{"issue":"4","key":"16_CR14","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/S0167-9473(01)00065-2","volume":"38","author":"JH Friedman","year":"2002","unstructured":"Friedman, J.H.: Stochastic gradient boosting. Comput. Stat. Data Anal. 38(4), 367\u2013378 (2002)","journal-title":"Comput. Stat. Data Anal."},{"key":"16_CR15","unstructured":"Kohavi, R., et al.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: IJCAI, vol. 14, pp. 1137\u20131145, Stanford, CA (1995)"},{"key":"16_CR16","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. Sov. Phys. Dokl. 10, 707\u2013710 (1966)","journal-title":"Sov. Phys. Dokl."},{"key":"16_CR17","unstructured":"McDonald, C.J.: Analysis of a probabilistic record linkage technique without human review (2003)"},{"issue":"34","key":"16_CR18","first-page":"1","volume":"17","author":"X Meng","year":"2016","unstructured":"Meng, X., Bradley, J., Yavuz, B., Sparks, E., Venkataraman, S., Liu, D., Freeman, J., Tsai, D., Amde, M., Owen, S., et al.: Mllib: machine learning in apache spark. J. Mach. Learn. Res. 17(34), 1\u20137 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR19","volume-title":"Machine Learning: An Artificial Intelligence Approach","author":"RS Michalski","year":"2013","unstructured":"Michalski, R.S., Carbonell, J.G., Mitchell, T.M.: Machine Learning: An Artificial Intelligence Approach. Springer Science & Business Media, Heidelberg (2013)"},{"key":"16_CR20","unstructured":"Michelson, M., Knoblock, C.A.: Learning blocking schemes for record linkage. In: AAAI, pp. 440\u2013445 (2006)"},{"issue":"3381","key":"16_CR21","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1126\/science.130.3381.954","volume":"130","author":"HB Newcombe","year":"1959","unstructured":"Newcombe, H.B., Kennedy, J.M., Axford, S., James, A.P.: Automatic linkage of vital records. Science 130(3381), 954\u2013959 (1959)","journal-title":"Science"},{"key":"16_CR22","unstructured":"Pinto, C., Pita, R., Melo, P., Sena, S., Barreto, M.: Correla\u00e7\u00e3o probabil\u00edstica de bancos de dados governamentais, pp. 77\u201388 (2015)"},{"key":"16_CR23","unstructured":"Pita, R., Pinto, C., Melo, P., Silva, M., Barreto, M., Rasella, D.: A spark-based workflow for probabilistic record linkage of healthcare data. In: EDBT\/ICDT Workshops, pp. 17\u201326 (2015)"},{"issue":"364","key":"16_CR24","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1080\/01621459.1978.10480080","volume":"73","author":"SJ Press","year":"1978","unstructured":"Press, S.J., Wilson, S.: Choosing between logistic regression and discriminant analysis. J. Am. Stat. Assoc. 73(364), 699\u2013705 (1978)","journal-title":"J. Am. Stat. Assoc."},{"issue":"1","key":"16_CR25","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1023\/B:AMAI.0000018580.96245.c6","volume":"41","author":"LE Raileanu","year":"2004","unstructured":"Raileanu, L.E., Stoffel, K.: Theoretical comparison between the gini index and information gain criteria. Ann. Math. Artif. Intell. 41(1), 77\u201393 (2004)","journal-title":"Ann. Math. Artif. Intell."},{"issue":"10","key":"16_CR26","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1109\/TMM.2016.2598482","volume":"18","author":"Y Siegert","year":"2016","unstructured":"Siegert, Y., Jiang, X., Krieg, V., Bartholomus, S.: Classification-based record linkage with pseudonymized data for epidemiological cancer registries. IEEE Trans. Multimed. 18(10), 1929\u20131941 (2016)","journal-title":"IEEE Trans. Multimed."},{"issue":"5","key":"16_CR27","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1590\/S0034-89102009005000060","volume":"43","author":"DP da Silveira","year":"2009","unstructured":"da Silveira, D.P., Artmann, E.: Accuracy of probabilistic record linkage applied to health databases: systematic review. Rev. Sa\u00fade P\u00fablica 43(5), 875\u2013882 (2009)","journal-title":"Rev. Sa\u00fade P\u00fablica"},{"issue":"4","key":"16_CR28","doi-asserted-by":"crossref","first-page":"356","DOI":"10.3414\/ME0489","volume":"47","author":"M Tromp","year":"2008","unstructured":"Tromp, M., Ravelli, A., Meray, N., Reitsma, J., Bonsel, G., et al.: An efficient validation method of probabilistic record linkage including readmissions and twins. Methods Inf. Med. 47(4), 356\u2013363 (2008)","journal-title":"Methods Inf. Med."},{"issue":"11","key":"16_CR29","doi-asserted-by":"publisher","first-page":"916","DOI":"10.7326\/0003-4819-110-11-916","volume":"110","author":"DF Williamson","year":"1989","unstructured":"Williamson, D.F., Parker, R.A., Kendrick, J.S.: The box plot: a simple visual method to interpret data. Ann. Intern. Med. 110(11), 916\u2013921 (1989)","journal-title":"Ann. Intern. Med."},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Wilson, D.R.: Beyond probabilistic record linkage: using neural networks and complex features to improve genealogical record linkage. In: The 2011 International Joint Conference on Neural Networks, pp. 9\u201314, July 2011","DOI":"10.1109\/IJCNN.2011.6033192"},{"key":"16_CR31","unstructured":"Winkler, W.E.: The state of record linkage and current research problems. In: Statistical Research Division, US Census Bureau. Citeseer (1999)"},{"key":"16_CR32","unstructured":"Winkler, W.E.: Methods for record linkage and bayesian networks. Technical report, Statistical Research Division, US Census Bureau, Washington, DC (2002)"},{"key":"16_CR33","unstructured":"Winkler, W.E., et al.: Machine learning, information retrieval and record linkage. In: Proceedings of Section on Survey Research Methods, American Statistical Association, pp. 20\u201329 (2000)"}],"container-title":["Lecture Notes in Computer Science","Big Data Analytics and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-64283-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:10:55Z","timestamp":1710267055000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-64283-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319642826","9783319642833"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-64283-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"3 August 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DaWaK","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data Analytics and Knowledge Discovery","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dawak2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.dexa.org\/dawak2017","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}