Paper Infomation
Diagnosing Diabetes Type II Using a Soft Intelligent Binary Classification Model
Full Text(PDF, 623KB)
Author: Mehdi Khashei, Saeede Eftekhari, Jamshid Parvizian
Abstract: Diabetes, named also silent killer, is a metabolic disease characterized by high blood glucose levels, which result from body does not produce enough insulin or the body is resistant to the effects of insulin. Classification models are one of the most widely used groups of data mining tools that greatly help physicians to improve their prognosis, diagnosis or treatment planning procedures. Classification accuracy is one of the most important features in order to choose the appropriate classification model; hence, the researches directed at improving upon the effectiveness of these models have never stopped. Nowadays, despite the numerous classification models proposed in several past decades, it is widely recognized that diabetes are extremely difficult to classify. In this paper, a hybrid binary classification model is proposed for diabetes type II classification, based on the basic concepts of soft computing and artificial intelligence techniques. Empirical results of Pima Indian diabetes data classification indicate that hybrid model is generally better than other linear/nonlinear, soft/hard, and classic/intelligent classification models presented for diabetes classification. Therefore, our proposed model may be a suitable alternative model for medical classification to achieve greater accuracy, and to improve medical diagnosis.
Keywords: Artificial Intelligence; Soft Computing; Classification; Medical Diagnosis; Diabetes
References:
[1] Antal, P., Fannes, G., Timmerman, D., Moreau, Y., and Moor, B.D., “Bayesian applications of belief networks and multilayer perceptrons for ovarian tumor classification with rejection”, Artificial Intelligence in Medicine Vol. 29, pp. 39– 60, 2003.
[2] Benardos, P.G. and Vosniakos, G.C., “Optimizing feed-forward artificial neural network architecture”, Engineering Applications of Artificial Intelligence, Vol. 20, pp. 365– 382, 2007.
[3] Bennett, K. P. and Blue, J. A., “A support vector machine approach to decision trees”, IEEE World Congress on Computational Intelligence, pp. 2396– 2401, 1998.
[4] Berardi, V. and Zhang, G. P., “The effect of misclassification costs on neural network classifiers”, Decision Sciences, Vol. 30, pp. 659– 68, 1999.
[5] Berrueta, L., Alonso-Salces, R., Heberger, K., “Supervised pattern recognition in food analysis”, Journal of Chromatography A, 1158, pp. 196– 214, 2007.
[6] Billings, S. and Lee, K., “Nonlinear Fisher discriminant analysis using a minimum squared error cost function and the orthogonal least squares algorithm”, Neural Networks, Vol. 15, pp. 262– 270, 2002.
[7] Breault, J. L., Goodall, C. R., and Fos, P. J., “Data mining a diabetic data warehouse”, Artificial Intelligence in Medicine, Vol. 26, pp. 37– 54, 2002.
[8] Brown, M., Grundy, W., Lin, D., Cristianini, N., Sugnet, C., Furey, T., Ares, M., and Haussler, D., “Knowledge-based analysis of microarray gene expression data by using support vector machines” Proceedings of the National Academy of Sciences of the United States of America, Vol. 97, pp. 262– 267, 2000.
[9] Calisir D. and Dogantekin, E., “An automatic diabetes diagnosis system based on LDA-Wavelet Support Vector Machine Classifier”, Expert Systems with Applications, Vol. 38, pp. 8311– 8315, 2011.
[10] Chaovalitwongse, W., “On the time series k-nearest neighbor classification of abnormal brain activity”, IEEE Transactions on Systems, Man, and Cybernetics – Part A: Systems and Humans, Vol. 37, 2007.
[11] Charya, S., Odedra, D., Samanta, S., and Vidyarthi, S., “Computational Intelligence in Early Diabetes Diagnosis: A Review”, The Review of Diabetes Studies, Vol. 7, pp. 252– 262, 2010.
[12] Christianini, N.and Shawe-Taylor, J., “An introduction to support vector machines”, Cambridge University Press, 2000.
[13] Duda, R., Hart, P., and Stork, D., “Pattern classification”, New York: John Wiley & Sons, Inc.2001.
[14] Enas, G. and Choi, S., “Choice of the smoothing parameter and efficiency of k-nearest neighbor”, Computers and Mathematics with Applications, Vol. 12, pp. 235– 244, 1986.
[15] Fisher, R. A., “The use of multiple measurements in taxonomic problems”, Annals of Eugenics, Vol. 7, pp. 465– 475, 1936.
[16] Fix, E. and Hodges, J., “Discriminatory analysis – Nonparametric discrimination: Consistency properties”, Project No. 21-49-004, Report No. 4, Contract No. AF 41(128)-31, USAF School of Aviation, Randolph Field, Texas, 1951.
[17] Fix, E. and Hodges, J., “Discriminatory analysis– Nonparametric discrimination: Small sample performance. Project No. 21-49-004, Report No. 11, Contract No. AF 41(129)-31, USAF School of Aviation, Randolph Field, Texas, 1952.
[18] Friedman, N., Geiger, D., and Goldszmit, M., “Bayesian networks classifiers”, Machine Learning, Vol. 29, pp. 131– 163, 1997.
[19] Ganji M. F. and Abadeh, M. S., “A fuzzy classification system based on Ant Colony Optimization for diabetes disease diagnosis”, Expert Systems with Applications, Vol. 38, pp. 14650– 14659, 2011.
[20] Ghiassi, M. and Burnley, C., “Measuring effectiveness of a dynamic artificial neural network algorithm for classification problems”, Expert Systems with Applications, Vol. 37, pp. 3118– 3128, 2010.
[21] Golub, T.R., Slonim, D.K., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J.P., Coller, H., Loh, M.L., Downing, J.R., Caligiuri, M.A., Bloomfield, C.D., and Lander, E.S., “Molecular classification of cancer: class discovery and class prediction by gene expression monitoring”, Science, Vol. 286, pp. 531– 537, 1999.
[22] Hosseini, H., Luo, D., and Reynolds, K.J., “The comparison of different feed forward neural network architectures for ECG signal diagnosis”, Medical Engineering & Physics, Vol. 28, pp. 372– 378, 2006.
[23] Huang, Y., McCullagh, P., Black, N., and Harper, R., “Feature selection and classification model construction on type 2 diabetic patients' data”, Artificial Intelligence in Medicine, Vol. 41, pp. 251– 262, 2007.
[24] Ishibuchi, H. and Tanaka, H., “Interval regression analysis based on mixed 0-1 integer programming problem”, J. Japan Soc. Ind. Eng., Vol. 40, pp. 312– 319, 1988.
[25] Jen, C. H., Wang, C. C., Jiang, B. C., Chu, Y. H., and Chen, M. S., “Application of classification techniques on development an early-warning system for chronic illnesses” Expert Systems with Applications, Vol. 39, pp. 8852– 8858, 2012.
[26] Kahramanli H. and Allahverdi, N., “Design of a hybrid system for the diabetes and heart diseases”, Expert Systems with Applications, Vol. 35, pp. 82– 89, 2008.
[27] Kayaer, K. and Yildirim, T., “Medical diagnosis on pima Indian diabetes using general regression neural networks”, artificial neural networks and neural information processing (ICANN/ICONIP), Istanbul, Turkey, pp. 181– 184, 2003.
[28] Khashei, M. and Bijari, M., “A novel hybridization of artificial neural networks and ARIMA models for time series forecasting”, Applied Soft Computing, Vol. 11, pp. 2664– 2675, 2011.
[29] Khashei, M. and Bijari, M., “An artificial neural network (p, d, q) model for time series forecasting”, Expert Systems with Applications, Vol. 37, pp. 479– 489, 2010.
[30] Khashei, M., Bijari, M., and Hejazi, S. R., “Combining seasonal ARIMA models with computational intelligence techniques for time series forecasting”, Soft Computing, Vol. 16, pp. 1091– 1105, 2012.
[31] Khashei, M., Bijari, M., and Raissi, GH A., “Improvement of Auto-Regressive Integrated Moving Average models using fuzzy logic and artificial neural networks (ANNs)”, Neurocomputing, Vol. 72, pp. 956– 967, 2009.
[32] Khashei, M., Hamadani, A. Z., and Bijari, M., “A fuzzy intelligent approach to the classification problem in gene expression data analysis”, Knowledge-Based Systems, Vol.27, pp. 465– 474, 2012.
[33] Khashei, M., Hejazi, S. R., Bijari, M., “A new hybrid artificial neural networks and fuzzy regression model for time series forecasting”, Fuzzy Sets and Systems, Vol. 159, pp. 769– 786, 2008.
[34] Khashei, M., Zeinal Hamadani, A., Bijari, M., “A novel hybrid classification model of artificial neural networks and multiple linear regression models”, Expert Systems with Applications, Vol. 39, pp. 2606– 2620, 2012.
[35] Malhotra, M., Sharma, S. and Nair, S., ”Decision making using multiple models”, European Journal of Operational Research, Vol. 114, pp. 1– 14, 1999.
[36] Marks, S. and Dunn, O., “Discriminant functions when covariance matrices are unequal”, Journal of the American Statistical Association, Vol. 69, pp. 555– 559, 1974.
[37] Muezzinoglu, M. and Zurada, J., “RBF-based neurodynamic nearest neighbor classification in real pattern space”, Pattern Recognition, Vol. 39, pp. 747– 760, 2006.
[38] Patil, B. M., Joshi, R. C., and Toshniwal, D., “Hybrid prediction model for Type-2 diabetic patients”, Expert Systems with Applications, Vol. 37, pp. 8102– 8108, 2010.
[39] Polat, K., Gunes, S., and Arslan, A., “A cascade learning system for classification of diabetes disease: Generalized discriminate analysis and least square support vector machine”, Expert Systems with Applications, Vol. 34, pp. 482– 487, 2008.
[40] Rumelhart, D. and McClelland, J., "Parallel distributed processing", Cambridge, MA: MIT Press, 1986.
[41] Shi, Y., Eberhart, R., and Chen, Y., “Implementation of evolutionary fuzzy systems”, IEEE Transactions on Fuzzy Systems, Vol. 7, pp. 109– 119, 1999.
[42] Silva, L. Marques, J., and Alexandre, L. A., “Data classification with multilayer perceptrons using a generalized error function”, Neural Networks, Vol. 21, pp. 1302– 1310, 2008.
[43] Smith, C. A. “Some examples of discrimination”, Annals of Eugenics, Vol. 13, pp. 272– 282. 1947.
[44] Song, J. and Tang, H., “Support vector machines for classification of homo-oligomeric proteins by incorporating subsequence distributions”, Journal of Molecular Structure: THEOCHEM 722, pp. 97– 101, 2005.
[45] Su, C. T., Yang, C. H., Hsu, K. H., and Chiu, W. K., “Data mining for the diagnosis of type II diabetes from three-dimensional body surface anthropometrical scanning data”, Computers & Mathematics with Applications, Vol. 51, pp. 1075– 1092, 2006.
[46] Temurtas, H., Yumusak, N., and Temurtas, F., “A comparative study on diabetes disease diagnosis using neural networks”, Expert Systems with Applications, Vol. 36, pp. 8610– 8615, 2009.
[47] Vapnik, V., “Statistical learning theory”, Wiley, New York, 1998.
[48] Viaene, S., Derrig, R., Baesens, B., and Dadene, G., “A comparison of state-of-the art classification techniques for expert automobile insurance claim fraud detection”, The Journal of Risk and Insurance, Vol. 69, pp. 373– 421, 2002.
[49] Yildiz, T., Yildirim, S., Altilar, D., “Spam filtering with parallelized KNN algorithm”, Akademik Bilisim, 2008.
[50] Zadeh, L.A., “The concept of a linguistic variable and its application to approximate reasoning I”, Information Sciences, Vol. 8, pp. 199– 249, 1975.
[51] Zadeh, L.A., “The concept of a linguistic variable and its application to approximate reasoning II”, Information Sciences, Vol. 8, pp. 301– 357, 1975.
[52] Zhang, G. P., “An investigation of neural networks for linear time-series forecasting”, Computers and Operations Research, Vol. 28, pp. 1112– 1183, 2001.
[53] Zhang, G., Patuwo, B. E., and Hu, M. Y., “Forecasting with artificial neural networks: The state of the art”, International Journal of Forecasting, Vol. 14, pp. 35– 62, 1998.
[54] Zhao, H., “A multi-objective genetic programming approach to developing Pareto optimal decision trees”, Decision Support Systems, Vol. 43, pp. 809– 826, 2007.