A novel pattern extraction techniques used for classification of type-2 diabetic patients with back-propagation
Diabetes mellitus is the most common endocrine metabolic disorder and its diagnosis is increasing at an alarming rate . No perfect cure exists for this disorder, which is the third leading cause of death and morbidity in the Developing countries. The comparative risk for individuals with diabetes acquiring end-stage renal disease is 25 times that of individuals without diabetes. The relative risk of an individual with diabetes becoming blind is 20 times greater than for other individuals . Diabetes is classified into two types – Insulin dependent diabetes mellitus (type-1 diabetes) and Non-insulin dependent diabetes mellitus (type-2 diabetes). Type-1 is dependent on exogenous insulin to prevent ketoacidosis. A large amount of people are usually affected from Type-2 diabetes which develops after the age of 30 and is associated with obesity. The goal of predictive data mining in clinical medicine is to develop models that can use patient specific information to predict the significant result and thereby support clinical decision-making. In this study we develop prediction model to predict whether or not a newly diagnosed patient (pregnant women) would likely develop diabetes within five years from the time of first diagnosis. The datasets are taken from UCI machine learning database repository . The only motive for using this dataset is that it is very commonly used by various classification algorithms; hence it is easier to compare the results with our study.
KeywordsSupport Vector Machine Class Label Back Propagation Adaptive Neuro Fuzzy Inference System Little Square Support Vector Machine
Unable to display preview. Download preview PDF.
- 1.Diabetes Public Health Resource. Centers for disease Control.(http://www.cdc.gov/diabetes/statistics/prev/ national/fig1.htm).Accessed July5, 2009
- 2.Little, J. W., Falace, D. A. and Miller, C. S.N.L.1997 Rhodus, Dental Management of the Medically compromised PatientGoogle Scholar
- 3.Hettich, D. J., Blake, C. L. and Merz, C.J. 1998.UCI Repository of machine learning databases, Irvine, CA: University of California, Department of Information and Computer Science. (last assessed: 15/6/2009)Google Scholar
- 4.Michie, D., Spiegelhalter, D. J. and Taylor, C.C. 1994.Machine learning, neural and statistical Classification, Ellis HorwoodGoogle Scholar
- 5.Bioch, J. C., Meer, O., Potharst, R.1996.Classification using Bayesian neural nets.In Proc. IEEE Int. Conf. on neural networks, pp. 1488–1493Google Scholar
- 6.Carpenter, G. and Markuzon, A. N. 1998.ARTMAP-IC and medical diagnosis: Instance counting and inconsistent cases. Neural Networks no.11 pp. 323–336Google Scholar
- 8.Polat K., Gunes,S. 2007.An expert systemapproach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease, Digital Signal Processing vo.17.no.4.pp. 702–710Google Scholar
- 10.Han, J. and Kamber, M. 2006. Data mining: Concepts and techniques, Morgan KaufmannGoogle Scholar
- 12.Wei, J. T., Zhang, Z. S. Barnhill, D., Madyastha, K. R., Zhang, H., Oesterling, J.E. Understanding artificial neural networks and exploring their potential applications for the practicing urologist, Urology. 52. no. 2. pp. 161–172Google Scholar
- 13.Lisboa, P. J. 2002. A review of evidence of health benefit from artificial neural networks in medical intervention, Neural Network. vo. 15 no.1.pp. 11–39Google Scholar
- 14.Shin, C., Yun, U. T., Kim, H.K. and Park, S. C. 2000. A hybrid approach of neural network and memory-based learning to data mining. IEEE Transactions on Neural Networks, vo.11.no.3. pp. 637–646Google Scholar
- 15.Rumelhart, D. E., Hinton, G. and Williams, R. J. 1986. Learning internal representations by error propagation. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vo. 1, MIT Press, Cambridge, MA, pp. 318–362Google Scholar