Noor Akhmad Setiawan
Electrical Engineering and Information Technology Department
Universitas Gadjah Mada
Indonesia

Coronary artery disease (CAD) is considered as the first killer disease in the world. [1][2]. Diagnosis of coronary artery disease is difficult, especially when there is no symptom. Much information from patients are needed in order to draw the correct diagnosis. It will be beneficial to use an advanced computer method such as artificial intelligence to build a decision support system for the diagnosis of coronary artery disease. CAD is caused by the accumulation of plaques within the walls of the coronary arteries that supply blood to the myocardium. CAD may lead to continued temporary oxygen deprivation that will result in the damage of myocardium. The presence of CAD is considered to exist when the narrowing of at least one of the coronary arteries is more than 50%. Coronary angiogram or cardiac catheterization is considered as “gold standard” method to diagnose the presence of CAD. This method has high accuracy but it is invasive, expensive and not possible as a diagnosis for large population. Many research works have been conducted to diagnose the CAD using less expensive and non-invasive methods such as electrocardiogram (ECG) based analysis, heart sound analysis, medical image analysis, etc [2-5]. Development of computer methods for the diagnosis of heart disease attracts many researchers. At the earlier time, the use of computer is to build knowledge based decision support system which uses knowledge from medical experts and transfers this knowledge into computer algorithms manually. This process is time consuming and really depends on medical expert’s opinion which may be subjective. To handle this problem, machine learning techniques have been developed to gain knowledge automatically from examples or raw data. Detrano, et al, built a new discriminant function model for estimating probabilities of angiographic coronary disease [6]. This discrimination function operates based on logistic regression which is not interpretable easily. Modeling of heart disease using Bayesian network (also called belief network) is proposed by Jayanta and Marco [7][8]. Gamberger, et al, proposed Inductive Learning by Logic Minimization (ILLM). The aim of using machine learning technique is also to find the important and useful information extracted from medical data [9]. Another work is proposed by Yan, et al, by using multi-layer perceptron to build decision support system for the diagnosis of five major heart diseases [10]. Research work on Rough Set Theory (RST) to model prognostic power of cardiac tests has been proposed by Komorowski and Ohrn. The work explores and identifies the need of a scintigraphic scan of a group of patients using rough set approach [11]. A research work on automated diagnosis on CAD based on rule induction and fuzzy modeling is proposed by Tsipouras, et al. The rule induction method that used to extract rules indirectly is C4.5 algorithm [12][13]. One of emerging methods to successfully handle uncertainty is fuzzy type 2 system [14]. This research is about the development a fuzzy type 2 decision support system for the diagnosis of coronary artery disease. The coronary artery disease data sets taken from University California Irvine (UCI) are used [15]. The knowledge base of fuzzy type 2 decision support system is generated by using rules extraction method based on Rough Set Theory. The rules then will be selected and fuzzified based on information from discretization of numerical attributes. Fuzzy rules weight is proposed using the information from support of extracted rules. Finally the system will be validated using data sets from Cleveland, Hungarian, Long Beach, Switzerland [15].

References

[1] “Coronary heart disease statistics fact sheets 2008/2009,” British Heart Foundation, London 2008.
[2] B. L. Zaret, M. Moser, and L. S. Cohen, Yale university school of medicine heart book. New York: Hearst Books, 1992.
[3] B. Phibbs, The human heart: a basic guide to heart disease. Philadelphia: Lippincott Williams & Wilkins, 2007.
[4] A. Selzer, Understanding heart disease. Berkeley: University of California Press, 1992.
[5] O. S. Randall and D. S. Romaine, The encyclopedia of the heart and heart disease. New York, NY: Facts on File, 2005.
[6] R. Detrano, A. Janosi, W. Steinbrunn, M. Pfisterer, J.-J. Schmid, S. Sandhu, K. H. Guppy, S. Lee, and V. Froelicher, “International application of a new probability algorithm for the diagnosis of coronary artery disease,” The American Journal of Cardiology, vol.64, pp. 304-310, 1989.
[7] K. G. Jayanta and V. Marco, “Building a Bayesian network model of heart disease,” in Proceedings of the 38th annual on Southeast regional conference. Clemson, South Carolina: ACM, 2000.
[8] K. G. Jayanta and V. Marco, “Probabilistic model building of heart disease,” Department of Computer Science, University of South Carolina 1999.
[9] D. Gamberger, G. Krstačić, and T. Šmuc, “Medical Expert Evaluation of Machine Learning Results for a Coronary Heart Disease Database,” in Medical Data Analysis, 2000, pp. 119.
[10] H. Yan, Y. Jiang, J. Zheng, C. Peng, and Q. Li, “A multilayer perceptron-based medical decision support system for heart disease diagnosis,” Expert Systems with Applications, vol. 30, pp. 272, 2006.
[11] J. Komorowski and A. Ohrn, “Modelling prognostic power of cardiac tests using rough sets,” Artificial Intelligence in Medicine, vol. 15, pp. 167, 1999.
[12] M. G. Tsipouras, T. P. Exarchos, D. I. Fotiadis, A. Kotsia, A. Naka, and L. K. Michalis, “A decision support system for the diagnosis of coronary artery disease,” presented at 19th IEEE Symposium on Computer-Based Medical Systems, 2006.
[13] M. G. Tsipouras, T. P. Exarchos, D. I. Fotiadis, A. P. Kotsia, K. V. Vakalis, K. K. Naka, and L. K. Michalis, “Automated Diagnosis of Coronary Artery Disease Based on Data Mining and Fuzzy Modeling,” Information Technology in Biomedicine, IEEE Transactions on, vol. 12, pp. 447, 2008.
[14] P. Melin and O. Castillo, “A review on type-2 fuzzy logic applications in clustering , classification and pattern recognition,” Appl. Soft Comput. J., vol. 21, pp. 568–577, 2014.
[15] D. J. Newman, S. Hettich, C. L. Blake, and C. J. Merz, “UCI Repository of machine learning databases,” University California Irvine, Department of Information and Computer Science, 1998.