Radial Basis Function Neural Network and Logistic Regression Analysis For Prognostic Classifi cation of Coronary Artery Disease Koroner Arter Hastalığının Sınıfl anmasında Radial Basis Fonsiyonu Sinir

Abstract

Keywords

• -

Koroner Arter Hastalığının Sınıflanmasında Radial Basis Fonsiyonu Sinir Ağı ve Lojistik Regresyon Analizi

Abstract

Amaç: Önceki çalışmalarda geriye yayılım algoritması ile eğitilen yapay sinir ağları yaygın olarak incelenmiştir. Bu çalışmada, koroner arter hastalığının (KAH) sınıflanmasında radial basis fonksiyonu sinir ağı ve lojistik regresyon analizi tanıtılmaktadır. Yöntem: Kardiyoloji bölümüne müracaat eden ardışık 237 bireyin kayıtları analizde kullanılmıştır. Koroner arter hastalığının sınıflanmasında radial basis fonksiyonu sinir ağı ve lojistik regresyon analizi kullanılmıştır. Bulgular: Çalışmanın bulguları, radial basis fonksiyonu sinir ağı ve lojistik regresyon analizinin sınıflamada oldukça başarılı olduğunu ve incelenen klinik değişkenlere dayalı olarak koroner arter gibi hastalıkların sınıflanmasında invaziv olmayan bir biçimde kullanılabileceğini göstermiştir. Sonuç: İncelenen KAH’a ait verilerde, lojistik regresyon analizi, radial basis fonksiyonu sinir ağından daha iyi sonuçlar vermiştir. Ancak, daha büyük örnek çapları söz konusu olduğunda radial basis fonksiyonu sinir ağı daha iyi sınıflama sonuçları verebilir. Daha kesin karşılaştırma sonuçları elde edebilmek için, simülasyon çalışmaları değişik yöntemler kullanılarak yapılmalıdır.

Keywords

• Lojistik regresyon analizi, koroner arter hastalığı, radial basis fonksiyonu sinir ağı, sınıflama

References

1. Allison JS, Heo J, Iskandrian AE. Artificial neural network modeling of stress single- photon emission computed tomographic imaging for detecting extensive coronary artery disease. Am J Cardiol 2005; 95:178- 81.
2. Bigi R, Gregori D, Cortigiani L, et al. Artifi- cial neural networks and robust Bayesian classifiers for risk stratification following uncomplicated myocardial infarction. Int J Cardiol 2005; 101: 481-487.
3. Dubey AK. Using rough sets, neural networks, and logistic regression to pre- dict compliance with cholesterol guideli- nes goals in patients with coronary artery disease. AMIA Annu Symp Proc 2003; 834.
4. Linlon MF, Fazio S. A practical approach
5. Eapen BR. ‘Neural network’ algorithm to predict severity in epidermolysis bullosa simplex. Indian J Dermatol Venereol Lep- rol 2005; 71: 106-108.
6. Itchhaporia D, Snow PB, Almassy RJ, et al. Artificial Neural Networks: Current Status in Cardiovascular Medicine. JACC 1996; 28: 515-21.
7. Scott JA, Aziz K, Yasuda T, et al. Integrati- on of clinical and imaging data to predict the presence of coronary artery disease with the use of neural networks. Coron Artery Dis 2004; 15(7):427-34.
8. Tham CK, Heng CK, Chin WC. Predicting risk of coronary artery disease from DNA microarray-based genotyping using neu- ral networks and other statistical analysis tool. J Bioinform Comput Biol 2003; 1: 521-39.

9. Haykin S. “Neural Networks: A Compre- hensive Foundation”. New York, USA, 18. Kim HK, Chang SA, Choi EK, et al. Asso- Macmillan College Publishing Company, ISBN 0-0235-2761-7, 1994.
10. Hosmer DW, Lemeshow S. Applied Logis- tic Regression, John Wiley & Sons, 1989.
11. Kleinbaum, DG. Logistic Regression: A self-Learning Text, New York, 1992.
12. Gupta R, Sarna M, Thanvi J, et al. High Prevalence of Multiple Coronary Risk Fac- tors in Punjabi Bhatia Community: Jaipur Heart Watch-3, Indian Heart J 2004; 56: 646–652. to risk assesment to prevent coronary ar- tery disease and its complications. Am J Cardiol 2003; 92: 191-261.
13. Onat A. Risk Factors and cardiovascular disease in Turkey, Atherosclerosis 2001; 156: 1-10.
14. Shaw LJ, Peterson ED, Shaw LK, et al. Use of a Prognostic Treadmill Score in Iden- tifying Diagnostic Coronary Disease Subg- roups. Circulation 1998; 98: 1622-1630.
15. Yologlu S, Sezgin AT, Ozdemir R, et al. Identifying Risk Factors in a Patient Popu- lation Mostly Overweight with Coronery Artery Disease. Angiology 2003; 54: 181- 6.
16. Mobley BA, Schechter E, Moore WE, et al. Predictions of coronary artery stenosis by artificial neural network. Artificial Intelli- gence in Medicine 2000; 18: 187–203.
17. Gamberger D, Lavrac N, Krstacic G. Active subgroup mining: a case study in coro- nary heart disease risk group detection. Artificial Intelligence in Medicine 2003; 28: 27–57. ciation between plasma lipids, and apoli- poproteins and coronary artery disease: a cross-sectional study in a low-risk Korean population, Int J Cardiol 2005; 101: 435- 440.
18. Maas R, Böger RH. Old and new cardio- vascular risk factors from unresolved is- sues to new oppurtinies. Atherosclerosis Supplement 2003; 4: 5-17.
19. Chobanian AV, Bakris GL, Black HR, et al. National heart, lung, and blood institute joint national committee on prevention, detection, evaluation, and treatment of high blood pressure; national high blood pressure education program coordinating committee. JAMA 2003; 289: 2560–72.
20. Alberti KG, Zimmet PZ. New diagnostic criteria and classification of diabetes-aga- in? Diabet Med 1998; 15: 535–536.
21. Report of the expert committee on the di- agnosis and classification of diabetes mel- litus. Diabetes Care 1997; 20: 1183–97.
22. Clinical guidelines on the identification, evaluation, and treatment of overweight and obesity in adults: the evidence re- port. National Institutes of Health. Obes Res 1998; 6: 51S-209S.
23. Peng CYJ, Lee KL, Ingersoll GM. An intro- duction to logistic regression analysis and reporting. The Journal of Educational Re- search 2002; 96: 3-14.
24. Maren A, Harston C, Pap R. Handbook of Neural Computing Applications, London, Academic Press, ISBN 0-12-471260-6, 1990.
25. Chen S, Cowan, CFN, Grant PM. Ortho- gonal least squares learning algorithm for radial basis function networks. IEEE Transactions on Neural Networks. 1991; 302-309.
26. Moody J, Darken C. Fast-learning in networks of locally-tuned processing units. Neural Computation. 1989; 1: 281- 294.
27. Minai AA, Williams RD. Acceleration of backpropagation through learning rate and momentum adaptation. Int. Joint Conf. on Neural Networks 1990; 1; 676- 679.
28. Jacobs RA. Increased rate of convergence through learning rate adaptation. Neural Networks 1988; 1: 295-307.
29. Principe J, Euliano NR, Lefebvre WC. Neu- ral and adaptive systems: fundamentals through simulations. New York: John Wi- ley & Sons Inc; 1999.
30. Kotel’nikova EV, Gridnev VI, Dobgalevs- kii PIa, et al. Prognostication of coronary atherosclerosis for selection of tactics of management of patients with ischemic heart disease. Kardiologiia 2004; 44: 15- 9.
31. Adler Y, Fisman EZ, Shemesh J, et al. Use- fulness of helical computed tomography in detection of mitral annular calcificati- on as a marker of coronary artery disease. Int J Cardiol 2005; 101: 371-376.
32. Afiune Neto A, Mansur Ade P, Avakian SD, et al. Monocytosis is an independent risk marker for coronary artery disease. Arq Bras Cardiol 2006; 86: 240-4.
33. Costacou T, Lopes-Virella MF, Zgibor JC, et al. Markers of endothelial dysfunction in the prediction of coronary artery di- sease in Type 1 diabetes. The Pittsburgh Epidemiology of Diabetes Complications Study. J Diabetes Complications 2005; 19: 183-93.
34. Hou FF, Ma ZG, Mei CL, et al. Epidemio- logy of cardiovascular risk in Chinese ch- ronic kidney disease patients. Zhonghua Yi Xue Za Zhi 2005; 85: 753-9.
35. Senior PA, Welsh RC, McDonald CG, et al. Coronary artery disease is common in nonuremic, asymptomatic type 1 diabetic islet transplant candidates. Diabetes Care 2005; 28: 866-72.
36. Colak C, Colak MC, Orman MN. The comparison of logistic regression model selection methods for the prediction of coronary artery disease. Anadolu Kardiyol Derg. 2007; 7: 6-11.