{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:21:36Z","timestamp":1780492896818,"version":"3.54.1"},"publisher-location":"Berlin, Heidelberg","reference-count":29,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540278313","type":"print"},{"value":"9783540318842","type":"electronic"}],"license":[{"start":{"date-parts":[[2005,1,1]],"date-time":"2005-01-01T00:00:00Z","timestamp":1104537600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2005,1,1]],"date-time":"2005-01-01T00:00:00Z","timestamp":1104537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11527770_59","type":"book-chapter","created":{"date-parts":[[2010,12,22]],"date-time":"2010-12-22T08:42:35Z","timestamp":1293007355000},"page":"434-443","source":"Crossref","is-referenced-by-count":15,"title":["A Data Pre-processing Method to Increase Efficiency and Accuracy in Data Mining"],"prefix":"10.1007","author":[{"given":"Amir R.","family":"Razavi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans","family":"Gill","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans","family":"\u00c5hlfeldt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nosrat","family":"Shahsavar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"59_CR1","first-page":"125","volume":"5","author":"F. Uckert","year":"2002","unstructured":"Uckert, F., Ataian, M., Gorz, M., Prokosch, H.U.: Functions of an electronic health record. Int J Comput Dent\u00a05, 125\u2013132 (2002)","journal-title":"Int J Comput Dent"},{"key":"59_CR2","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1002\/(SICI)1097-0142(20000315)88:6<1445::AID-CNCR24>3.0.CO;2-T","volume":"88","author":"G. Sandblom","year":"2000","unstructured":"Sandblom, G., Dufmats, M., Nordenskjold, K., Varenhorst, E.: Prostate carcinoma trends in three counties in Sweden 1987-1996: results from a population-based national cancer register. South-East Region Prostate Cancer Group. Cancer\u00a088, 1445\u20131453 (2000)","journal-title":"Cancer"},{"key":"59_CR3","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1177\/14034948020300020101","volume":"30","author":"M. Rosen","year":"2002","unstructured":"Rosen, M.: National Health Data Registers: a Nordic heritage to public health. Scand J Public Health\u00a030, 81\u201385 (2002)","journal-title":"Scand J Public Health"},{"key":"59_CR4","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/S1089-9472(04)00216-3","volume":"19","author":"P.E. Windle","year":"2004","unstructured":"Windle, P.E.: Data mining: an excellent research tool. J Perianesth Nurs\u00a019, 355\u2013356 (2004)","journal-title":"J Perianesth Nurs"},{"key":"59_CR5","volume-title":"C4.5: Programs for Machine Learning","author":"J.R. Quinlan","year":"1993","unstructured":"Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993)"},{"key":"59_CR6","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1023\/A:1016409317640","volume":"26","author":"V. Podgorelec","year":"2002","unstructured":"Podgorelec, V., Kokol, P., Stiglic, B., Rozman, I.: Decision trees: an overview and their use in medicine. J Med Syst\u00a026, 445\u2013463 (2002)","journal-title":"J Med Syst"},{"key":"59_CR7","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1155\/S1110724303210032","volume":"2003","author":"A. Vlahou","year":"2003","unstructured":"Vlahou, A., Schorge, J.O., Gregory, B.W., Coleman, R.L.: Diagnosis of Ovarian Cancer Using Decision Tree Classification of Mass Spectral Data. J Biomed Biotechnol\u00a02003, 308\u2013314 (2003)","journal-title":"J Biomed Biotechnol"},{"key":"59_CR8","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1164\/rccm.200202-124OC","volume":"166","author":"L.B. Gerald","year":"2002","unstructured":"Gerald, L.B., Tang, S., Bruce, F., Redden, D., Kimerling, M.E., Brook, N., Dunlap, N., Bailey, W.C.: A decision tree for tuberculosis contact investigation. Am J Respir Crit Care Med\u00a0166, 1122\u20131127 (2002)","journal-title":"Am J Respir Crit Care Med"},{"key":"59_CR9","volume-title":"Data Mining Concepts and Techniques","author":"J. Han","year":"2001","unstructured":"Han, J., Kamber, M.: Data Mining Concepts and Techniques. Morgan Kaufmann, San Francisco (2001)"},{"key":"59_CR10","first-page":"269","volume":"95","author":"A. Duhamel","year":"2003","unstructured":"Duhamel, A., Nuttens, M.C., Devos, P., Picavet, M., Beuscart, R.: A preprocessing method for improving data mining techniques. Application to a large medical diabetes database. Stud Health Technol Inform\u00a095, 269\u2013274 (2003)","journal-title":"Stud Health Technol Inform"},{"key":"59_CR11","volume-title":"The EM algorithm and extensions","author":"G.J. McLachlan","year":"1997","unstructured":"McLachlan, G.J., Krishnan, T.: The EM algorithm and extensions. John Wiley & Sons, Chichester (1997)"},{"key":"59_CR12","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1097\/00004356-200412000-00014","volume":"27","author":"E. Silva Cardoso","year":"2004","unstructured":"Silva Cardoso, E., Blalock, K., Allen, C.A., Chan, F., Rubin, S.E.: Life skills and subjective well-being of people with disabilities: a canonical correlation analysis. Int J Rehabil Res\u00a027, 331\u2013334 (2004)","journal-title":"Int J Rehabil Res"},{"key":"59_CR13","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1093\/bioinformatics\/btg062","volume":"19","author":"A. Antoniadis","year":"2003","unstructured":"Antoniadis, A., Lambert-Lacroix, S., Leblanc, F.: Effective dimension reduction methods for tumor classification using gene expression data. Bioinformatics\u00a019, 563\u2013570 (2003)","journal-title":"Bioinformatics"},{"key":"59_CR14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A.P. Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood from Incomplete Data via the EM Algorithm. J R Stat Soc Ser B\u00a039, 1\u201338 (1977)","journal-title":"J R Stat Soc Ser B"},{"key":"59_CR15","doi-asserted-by":"publisher","first-page":"183","DOI":"10.2190\/3B1X-EE5T-T7GR-KGUD","volume":"28","author":"R.L. Vogel","year":"1998","unstructured":"Vogel, R.L., Ackermann, R.J.: Is primary care physician supply correlated with health outcomes? Int J Health Serv\u00a028, 183\u2013196 (1998)","journal-title":"Int J Health Serv"},{"key":"59_CR16","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1080\/00221309809595345","volume":"125","author":"W. Dunlap","year":"1998","unstructured":"Dunlap, W., Landis, R.: Interpretations of multiple regression borrowed from factor analysis and canonical correlation. J Gen Psychol\u00a0125, 397\u2013407 (1998)","journal-title":"J Gen Psychol"},{"key":"59_CR17","doi-asserted-by":"crossref","DOI":"10.4135\/9781412983570","volume-title":"Canonical correlation analysis: Uses and interpretation","author":"B. Thompson","year":"1984","unstructured":"Thompson, B.: Canonical correlation analysis: Uses and interpretation. Sage, Thousand Oaks (1984)"},{"key":"59_CR18","unstructured":"SPSS Inc.: SPSS for Windows. SPSS Inc. (2001)"},{"key":"59_CR19","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/1475-925X-3-21","volume":"3","author":"S.A. Pavlopoulos","year":"2004","unstructured":"Pavlopoulos, S.A., Stasis, A.C., Loukis, E.N.: A decision tree\u2013based method for the differential diagnosis of Aortic Stenosis from Mitral Regurgitation using heart sounds. Biomed Eng Online\u00a03, 21 (2004)","journal-title":"Biomed Eng Online"},{"key":"59_CR20","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1111\/1541-0420.00046","volume":"59","author":"Y. Luo","year":"2003","unstructured":"Luo, Y., Lin, S.: Information gain for genetic parameter estimation with incorporation of marker data. Biometrics\u00a059, 393\u2013401 (2003)","journal-title":"Biometrics"},{"key":"59_CR21","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1023\/A:1016461301710","volume":"26","author":"M. Zorman","year":"2002","unstructured":"Zorman, M., Eich, H.P., Stiglic, B., Ohmann, C., Lenic, M.: Does size really matter\u2013using a decision tree approach for comparison of three different databases from the medical field of acute appendicitis. J Med Syst\u00a026, 465\u2013477 (2002)","journal-title":"J Med Syst"},{"key":"59_CR22","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1109\/34.589207","volume":"19","author":"F. Esposito","year":"1997","unstructured":"Esposito, F., Malerba, D., Semeraro, G., Kay, J.: A comparative analysis of methods for pruning decision trees. IEEE Trans Pattern Anal Mach Intell\u00a019, 476\u2013491 (1997)","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"59_CR23","volume-title":"Data Mining: Practical machine learning tools with Java implementations","author":"I.H. Witten","year":"2000","unstructured":"Witten, I.H., Frank, E.: Data Mining: Practical machine learning tools with Java implementations. Morgan Kaufmann, San Francisco (2000)"},{"key":"59_CR24","unstructured":"Kohavi, R.: A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. In: Proc. International Joint Conference on Artificial Intelligence, pp. 1137\u20131145 (1995)"},{"key":"59_CR25","doi-asserted-by":"crossref","unstructured":"Delen, D., Walker, G., Kadam, A.: Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med (2004) (in press)","DOI":"10.1016\/j.artmed.2004.07.002"},{"key":"59_CR26","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1055\/s-0038-1633845","volume":"43","author":"M. Pfaff","year":"2004","unstructured":"Pfaff, M., Weller, K., Woetzel, D., Guthke, R., Schroeder, K., Stein, G., Pohlmeier, R., Vienken, J.: Prediction of cardiovascular risk in hemodialysis patients by data mining. Methods Inf Med\u00a043, 106\u2013113 (2004)","journal-title":"Methods Inf Med"},{"key":"59_CR27","first-page":"409","volume":"68","author":"A. Babic","year":"1999","unstructured":"Babic, A.: Knowledge discovery for advanced clinical data management and analysis. Stud Health Technol Inform\u00a068, 409\u2013413 (1999)","journal-title":"Stud Health Technol Inform"},{"key":"59_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0933-3657(02)00049-0","volume":"26","author":"K.J. Cios","year":"2002","unstructured":"Cios, K.J., Moore, G.W.: Uniqueness of medical data mining. Artif Intell Med\u00a026, 1\u201324 (2002)","journal-title":"Artif Intell Med"},{"key":"59_CR29","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1109\/32.965340","volume":"27","author":"I. Myrtveit","year":"2001","unstructured":"Myrtveit, I., Stensrud, E., Olsson, U.H.: Analyzing data sets with missing data: an empirical evaluation of imputation methods and likelihood-based methods. IEEE Trans Softw Eng\u00a027, 999\u20131013 (2001)","journal-title":"IEEE Trans Softw Eng"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/11527770_59","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T08:20:45Z","timestamp":1750148445000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/11527770_59"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540278313","9783540318842"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/11527770_59","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005]]}}}