데이터 이산화와 러프 근사화 기술에 기반한 중요 임상검사항목의 추출방법: 담낭 및 담석증 질환의 감별진단에의 응용
Extraction Method of Significant Clinical Tests Based on Data Discretization and Rough Set Approximation Techniques: Application to Differential Diagnosis of Cholecystitis and Cholelithiasis Diseases
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The selection of meaningful clinical tests and its reference values from a high-dimensional clinical data with imbalanced class distribution, one class is represented by a large number of examples while the other is represented by only a few, is an important issue for differential diagnosis between similar diseases, but difficult. For this purpose, this study introduces methods based on the concepts of both discernibility matrix and function in rough set theory (RST) with two discretization approaches, equal width and frequency discretization. Here these discretization approaches are used to define the reference values for clinical tests, and the discernibility matrix and function are used to extract a subset of significant clinical tests from the translated nominal attribute values. To show its applicability in the differential diagnosis problem, we have applied it to extract the significant clinical tests and its reference values between normal (N = 351) and abnormal group (N = 101) with either cholecystitis or cholelithiasis disease. In addition, we investigated not only the selected significant clinical tests and the variations of its reference values,but also the average predictive accuracies on four evaluation criteria, i.e., accuracy, sensitivity, specificity, and geometric mean, during 10-fold cross validation. From the experimental results, we confirmed that two discretization approaches based rough set approximation methods with relative frequency give better results than those with absolute frequency, in the evaluation criteria (i.e., average geometric mean). Thus it shows that the prediction model using relative frequency can be used effectively in classification and prediction problems of the clinical data with imbalanced class distribution.
Abstract
The selection of meaningful clinical tests and its reference values from a high-dimensional clinical data with imbalanced class distribution, one class is represented by a large number of examples while the other is represented by only a few, is an important issue for differential diagnosis between similar diseases, but difficult. For this purpose, this study introduces methods based on the concepts of both discernibility matrix and function in rough set theory (RST) with two discretization approaches, equal width and frequency discretization. Here these discretization approaches are used to define the reference values for clinical tests, and the discernibility matrix and function are used to extract a subset of significant clinical tests from the translated nominal attribute values. To show its applicability in the differential diagnosis problem, we have applied it to extract the significant clinical tests and its reference values between normal (N = 351) and abnormal group (N = 101) with either cholecystitis or cholelithiasis disease. In addition, we investigated not only the selected significant clinical tests and the variations of its reference values,but also the average predictive accuracies on four evaluation criteria, i.e., accuracy, sensitivity, specificity, and geometric mean, during 10-fold cross validation. From the experimental results, we confirmed that two discretization approaches based rough set approximation methods with relative frequency give better results than those with absolute frequency, in the evaluation criteria (i.e., average geometric mean). Thus it shows that the prediction model using relative frequency can be used effectively in classification and prediction problems of the clinical data with imbalanced class distribution.
참고문헌 (17)
- K.N. Lee, "Standardization of reference values among laboratories of Korean association of health promotion", J. Lab. Med. & Quality Assuarance, 24(2), pp.185~195 (2002)
- E.J. Cha, "Automated clinical test results analysis system application to liver function test", J. Biomed. Eng. Res, 14(4), pp.341~348 (1993)
- 손창식, "데이터의 공간적인 분포를 이용한 가변 임계값 기반 특징선택", Healthcare Informatics Research, 15(4), pp.475~481 (2009), 대한의료정보학회
- 손창식, "호흡곤란환자의 입-퇴원 분석을 위한 규칙가중치 기반 퍼지 분류모델", 의공학회지, 31(1), pp.40~49 (2010), 대한의용생체공학회
- "ICD10 version 2007" (2007)[URL]
- D. Chiu, "Information discovery through hierarchical maximum entropy discretization and synthesis" (1991), MIT Press
- Z.Pawlak, "Rough sets", Int. J. Comput. Inf. Sci, 11(5), pp.341~356 (1982)
- R. Slowinski, "Rough classification in incomplete information systems", Math.Comput.Modeling, 12(10), pp.1347~1357 (1989)
- Z. Pawlak, "Rough sets: theoretical aspects of reasoning about data" (1991), Kluwer Academic Publisher
- R. Jensen, "Computational intelligence and feature selection: rough and fuzzy approaches" (2008), Wiley-IEEE Press
- Y.M. Sun, "Costsensitive boosting for classification of imbalanced data", Patt.Recog, 40(12), pp.3358~3378 (2007)
- 손창식, "데이터의 공간적 분포를 고려한 퍼지 이산화와 특징선택에의 응용", 한국지능시스템학회 논문지, 20(2), pp.165~172 (2010), 한국지능시스템학회
- 유교상, "담석증의 진단", 대한내과학회지, 75(6), pp.616~623 (2008), 대한내과학회
- R. Kerber, "ChiMerge: discretization of numeric attributes", Proceedings of AAAI-92, Ninth Intpppppl Conf., Artificial Intelligence, pp.123~128 (1992), AAAI-Press
- H. Liu, "Feature selection via discretization of numeric attributes", IEEE Trans. Knowl.Data Eng, 9(4), pp.642~645 (1997)
- U.M. Fayyad, "Multi-interval discretization of continuous attributes as preprocessing for classification learning", Proceedings of 13th International Joint Conference on Artificial Intelligence, pp.1022~1027 (1993)
- L. Kaufman, "Finding group in data: an introduction to cluster analysis" (1990), John Wiley & Sons