Interpretation of Clinical Data Based on C4.5 Algorithm for the Diagnosis of Coronary Heart Disease
2
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Objectives: The interpretation of clinical data for the diagnosis of coronary heart disease can be done using algorithms in data mining. Most clinical data interpretation systems for diagnosis developed using data mining algorithms with a blackbox approach cannot recognize examination attribute relationships with the incidence of coronary heart disease. Methods: This study proposes a system to interpretation clinical examination results for the diagnosis of coronary heart disease based the decision tree algorithm. This system comprises several stages. First, oversampling is carried out by a combination of the synthetic minority oversampling technique (SMOTE), feature selection, and the C4.5 classification algorithm. System testing is done using k-fold cross-validation. The performance parameters are sensitivity, specificity, positive prediction value (PPV), negative prediction value (NPV) and the area under the curve (AUC). Results: The results showed that the performance of the system has a sensitivity of 74.7%, a specificity of 93.7%, a PPV of 74.2%, an NPV of 93.7%, and an AUC of 84.2%. Conclusions: This study demonstrated that, by using C4.5 algorithms, data can be interpreted in the form of a decision tree, to aid the understanding of the clinician. In addition, the proposed system can provide better performance by category.
Abstract
Objectives: The interpretation of clinical data for the diagnosis of coronary heart disease can be done using algorithms in data mining. Most clinical data interpretation systems for diagnosis developed using data mining algorithms with a blackbox approach cannot recognize examination attribute relationships with the incidence of coronary heart disease. Methods: This study proposes a system to interpretation clinical examination results for the diagnosis of coronary heart disease based the decision tree algorithm. This system comprises several stages. First, oversampling is carried out by a combination of the synthetic minority oversampling technique (SMOTE), feature selection, and the C4.5 classification algorithm. System testing is done using k-fold cross-validation. The performance parameters are sensitivity, specificity, positive prediction value (PPV), negative prediction value (NPV) and the area under the curve (AUC). Results: The results showed that the performance of the system has a sensitivity of 74.7%, a specificity of 93.7%, a PPV of 74.2%, an NPV of 93.7%, and an AUC of 84.2%. Conclusions: This study demonstrated that, by using C4.5 algorithms, data can be interpreted in the form of a decision tree, to aid the understanding of the clinician. In addition, the proposed system can provide better performance by category.
참고문헌 (20)
- Garg AX, "Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: a systematic review", JAMA, 293(10), pp.1223~1238 (2005)
- Salari N, "A novel hybrid classification model of genetic algorithms, modified k-Nearest Neighbor and developed backpropagation neural network", PLoS One, 9(11), pp.e112987~ (2014)
- Wiharto W, "Performance analysis of multiclass support vector machine classification for diagnosis of coronary heart diseases", Int J Comput Sci Appl, 5(5), pp.27~37 (2015)
- Wiharto Wiharto, "Intelligence System for Diagnosis Level of Coronary Heart Disease with K-Star Algorithm", Healthcare Informatics Research, 22(1), pp.30~38 (2016), 대한의료정보학회[DOI]
- Santhanam T, "Heart disease prediction using hybrid genetic fuzzy model", Indian J Sci Technol, 8(9), pp.797~803 (2015)
- 김재권, "Data-Mining-Based Coronary Heart Disease Risk Prediction Model Using Fuzzy Logic and Decision Tree", Healthcare Informatics Research, 21(3), pp.167~174 (2015), 대한의료정보학회[DOI]
- Kim JK, "Adaptive mining prediction model for content recommendation to coronary heart disease patients", Cluster Comput, 17(3), pp.881~891 (2014)
- Nahar J, "Computational intelligence for heart disease diagnosis: a medical knowledge driven approach", Expert Syst Appl, 40(1), pp.96~104 (2013)
- Prabowo DW, "A study of data randomization on a computer based feature selection for diagnosing coronary artery disease", Adv Intell Syst, 53, pp.237~248 (2014)
- Dominic V, "An effective performance analysis of machine learning techniques for cardiovascular disease", Appl Med Inform, 36(1), pp.23~32 (2015)
- Setiawan NA, "Benchmarking of feature selection techniques for coronary artery disease diagnosis", Proceedings of 2014 6th International Conference on Information Technology and Electrical Engineering, pp.1~5 (2014)
- "Heart disease data set: Cleveland" (1988)[URL]
- Ramyachitra D, "Imbalanced dataset clas-sification and solutions: a review", Int J Comput Bus Res, 5(4), pp.1~29 (2014)
- Chawla NV, "SMOTE: synthetic minority over-sampling technique", J Artif Intell Res, 16, pp.321~357 (2002)
- Marateb HR, "A noninvasive method for coronary artery diseases diagnosis using a clinicallyinterpretable fuzzy rule-based system", J Res Med Sci, 20(3), pp.214~223 (2015)
- Jensen R, "Combining rough and fuzzy sets for feature selection", pp.2005
- Jain M, "An improved techniques based on naive Bayesian for attack detection", Int J Emerg Technol Adv Eng, 2(1), pp.324~331 (2012)
- Hssina B, "A comparative study of decision tree ID3 and C4.5", Int J Adv Comput Sci Appl, 4(2), pp.13~19 (2014)
- Choi JM, "A selective sampling method for imbalanced data learning on support vector machines", pp.2010
- Gorunescu F, "Data mining: concepts, models and techniques" (2011), Springer