Dental Data Mining: Potential Pitfalls and Practical Issues:
作者： S.A. Gansky
DOI: 10.1177/154407370301700125
关键词: Lift (data mining) 、 Decision tree 、 Regression 、 Covariate 、 Regression analysis 、 Logistic regression 、 Data mining 、 Sample size determination 、 Computer science 、 Knowledge extraction
摘要: Knowledge Discovery and Data Mining (KDD) have become popular buzzwords. But what exactly is data mining? What are its strengths limitations? Classic regression, artificial neural network (ANN), classification regression tree (CART) models common KDD tools. Some recent reports (e.g., Kattan et al., 1998) show that ANN CART can perform better than classic models: excel at covariate interactions, while nonlinear covariates. Model prediction performance examined with the use of validation procedures evaluating concordance, sensitivity, specificity, likelihood ratio. To aid interpretation, various plots predicted probabilities utilized, such as lift charts, receiver operating characteristic curves, cumulative captured-response plots. A dental caries study used an illustrative example. This paper compares logistic methods in analyzing from Rochester study. With careful analysis, sufficient sample size proper competitors, problems naive analyses (Schwarzer 2000) be carefully avoided.
sagepub.com
sci-hub.se 参考文章(19)
James Franklin, The elements of statistical learning : data mining, inference,and prediction The Mathematical Intelligencer. ,vol. 27, pp. 83- 85 ,(2005) , 10.1007/BF02985802
R D Goodey, M R Brickley, C M Hill, J P Shepherd, A controlled trial of three referral methods for patients with third molars. British Dental Journal. ,vol. 189, pp. 556- 560 ,(2000) , 10.1038/SJ.BDJ.4800828
Mark R. Brickley, Jonathan P. Shepherd, Performance of a Neural Network Trained to Make Third-molar Treatment-planning Decisions Medical Decision Making. ,vol. 16, pp. 153- 160 ,(1996) , 10.1177/0272989X9601600207
Hannu Hausen, Caries prediction – state of the art Community Dentistry and Oral Epidemiology. ,vol. 25, pp. 87- 96 ,(1997) , 10.1111/J.1600-0528.1997.TB00904.X
Tobias Nilsson, Ted Lundgren, Hans Odelius, Rudolf Sillén, Jörgen G. Norén, A computerized induction analysis of possible co-variations among different elements in human tooth enamel Artificial Intelligence in Medicine. ,vol. 8, pp. 515- 526 ,(1996) , 10.1016/S0933-3657(96)00350-8
D.H. Leverett, J.D.B. Featherstone, H.M. Proskin, S.M. Adair, A.D. Eisenberg, S.A. Mundorff-Shrestha, C.P. Shields, C.L. Shaffer, R.J. Billings, Caries Risk Assessment by a Cross-sectional Discrimination Model: Journal of Dental Research. ,vol. 72, pp. 529- 537 ,(1993) , 10.1177/00220345930720021001
Guido Schwarzer, Werner Vach, Martin Schumacher, On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology. Statistics in Medicine. ,vol. 19, pp. 541- 561 ,(2000) , 10.1002/(SICI)1097-0258(20000229)19:4<541::AID-SIM355>3.0.CO;2-V
ROY C. PAGE, ELIZABETH A. KRALL, JOHN MARTIN, LLOYD MANCL, RAUL I. GARCIA, Validity and accuracy of a risk calculator in predicting periodontal disease. Journal of the American Dental Association. ,vol. 133, pp. 569- 576 ,(2002) , 10.14219/JADA.ARCHIVE.2002.0232
P M Speight, A E Elliott, J A Jullien, M C Downer, J M Zakzrewska, The use of artificial intelligence to identify people at risk of oral cancer and precancer British Dental Journal. ,vol. 179, pp. 382- 387 ,(1995) , 10.1038/SJ.BDJ.4808932
Michael W Kattan, Kenneth R Hess, J Robert Beck, None, Experiments to determine whether recursive partitioning (CART) or an artificial neural network overcomes theoretical limitations of Cox proportional hazards regression Computers and Biomedical Research. ,vol. 31, pp. 363- 373 ,(1998) , 10.1006/CBMR.1998.1488