특징점 선택방법과 SVM 학습법을 이용한 당뇨병 데이터에서의 당뇨병성 신장합병증의 예측 = Prediction of Diabetic Nephropathy from Diabetes Dataset Using Feature Selection Methods and SVM Learning

다국어 초록 (Multilingual Abstract)

Diabetes mellitus can cause devastating complications, which often result in disability and death, and diabetic nephropathy is a leading cause of death in people with diabetes. In this study, we tried to predict the onset of diabetic nephropathy from an irregular and unbalanced diabetic dataset. We collected clinical data from 292 patients with type 2 diabetes and performed preprocessing to extract 184 features to resolve the irregularity of the dataset. We compared several feature selection methods, such as ReliefF and sensitivity analysis, to remove redundant features and improve the classification performance. We also compared learning methods with support vector machine, such as equal cost learning and cost-sensitive learning to tackle the unbalanced problem in the dataset. The best classifier with the 39 selected features gave 0.969 of the area under the curve by receiver operation characteristics analysis, which represents that our method can predict diabetic nephropathy with high generalization performance from an irregular and unbalanced dataset, and physicians can benefit from it for predicting diabetic nephropathy.

참고문헌 (Reference)

1 I. Kononenko, "analysis and extensions of relief"

2 K. J. Cios, "Uniqueness of medical data mining" 26 : 1-24, 2002.

3 T. Furuta, "The role of macrophages in diabetic glomeruloscelerosis American Journal of Kidney Diseases" 21 : 480-485, 1993.

4 C. Elkan, "The foundations of cost-sensitive learning" 2001.08

5 V. Vapnik, "The Nature of Statistical Learning Theory" New York: Springer 1995.

6 M. Stevensen, "Sensitivity of feedforward neural networks to weight errors" 1 : 71-80, 1990.

7 G. Sterner, "Raised platelet levels in diabetes mellitus complicated with nephropathy" 244 : 437-441, 1998.

8 H. S. Jo, "Quality control of diagnostic coding in the Korean Burden of Disease Project" 2004.10

9 J. C. Platt, "Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods" in Advances in Large Margin Classifiers: MIT Press 1999.

10 P. Rossing, "Predictors of mortality in insulin dependent diabetes 10 year observational follow up study" 313 : 779-784, 1996.

11 T. Onuma, "High incidence of diabetic nephropathy in non-insulin-dependent diabetic patients with heterozygous familial hypercholesterolemia" 55 : 532-536, 1994.

12 K. G. Alberti, "Definition, diagnosis and classification of diabetes mellitus and its complications. Part 1: diagnosis and classification of diabetes mellitus provisional report of a WHO consultation" 17 : 539-553, 1998.

13 K. Veropoulos, "Controlling the sensitivity of support vector machines" 1999.08

14 I. Guyon, "An introduction to variable and feature selection" 3 : 1157-1182, 2003.

15 C. J. C. Burges, "A tutorial on support vector machines for pattern recognition" 2 : 121-167, 1998.

16 H. S. Choi, "A study on the multi-view based computer aided diagnosis in digital mammography" 28 : 162-168, 2007.