Machine Learning Algorithm aims at providing computational method for accumulating, changing and updating knowledge in health care systems. In particular learning mechanism will assist us to procure knowledge from the data set. The classification of machine learning algorithm is used not only to detect diseases, but also measure better fidelity. This article emphasizes on codification of disease symptoms on thyroid disease among the public. Thyroid disease is rampant worldwide. There are feasibility of thyroid disease and disorder including thyroiditis and thyroid cancer. We used 7200 sample thyroid dataset from the University of California Irvine Machine Learning Repository, a large and highly imbalanced dataset that comprises both discrete and continuous attributes. In this work, we collate machine learning classifiers such as Logistic Regression, Linear Discriminant Analysis, Naive Bayes, k-Nearest Neighbours, Classification and Regression Tree, Support Vector Machine using python to classify the disease symptoms. This work is carried out using different classifiers to achieve more verisimilitude. The selected algorithms are evaluated using five performance metrics namely accuracy, sensitivity, specificity, F1-score and kappa, and also estimated from the confusion matrix produced by the selected classifier.

CART Decision Tree; KNN algorithm; Support Vector Machine; Thyroid Disease Diagnosis; Linear Regression; Linear Discriminant Analysis

[1] Li.LN.ouyang JH,Chen HL,Liu DY. A computer aided diagnosis system for thyroid disease using extreme learning machine. J Med Syst 2012;36:3327-37.
[2] Chen HL, Yang B, Wang G, Liu J Chen YD, Liu DY. A three stage expert system based on support vector machines for thyroid disease diagnosis. J Med Syst 2012;36;1953-63.
[3] Dogantekin E.Dogantekin A,Avci D. An expert system based on Generalized Discriminant analysis and Wavelet Support Vector Machine for diagnosis of thyroid disease. Expert Syst Appl 2011;38:146-50.
[4] Dogantekin E.Dogantekin A,Avci D. An Automatic diagnosis system based on thyroid gland; ADSTG. Expert Syst. Appl 2010;37;6368-72.
[5] Pasi L Similarity classifier applied to medical data sets. 2004. 10 sivua. Fuzziness in Finland ’04. International conference on soft computing, Helsinki. Estonia: Finland & Gulf of Finland & Tallinn; 2004.
[6] Feyzul lah Temurtas” A comparative study on thyroid disease diagnosis using neural networks”, Elsevier, Expert Systems with Applications 36 (2009) 944–949.
[7] Serpen G. Jiang H, Allred L. Performance analysis of probabilistic potential function neural network classifier. In Proceedings of artificial neural networks in engineering conference viol. 7 : 1997. p.471-6.
[8] Ozyilmaz, L., Yildirim,T.(2002). Diagnosis of thyroid disease using artificial neural network methods. In proceedings of ICONIP’02 9th international conference on neural information processing (pp.2033-2036). Singapore: Orchid Country Club.
[9] Liu DY. Chen HL Yang B.XE L, Li LN, Liu J. Design of an enhanced fuzzy k-nearest neighbour classifier based computer aided diagnostic system for thyroid disease. J Med Syst 2012;36:3243-4354.
[10] Ng SK. McLachlan GJ. Extension of mixture-of-experts networks for binary classification of hierarchical data. Artif Intell Med 2007;41:57-67.
[11] Chang WW.Yeh WC, Huang PC, A hybrid immune-estimation distribution of algorithm for mining thyroid gland data. Artif Intell Med 2007;41:57-67.
[12] Kodaz H. Ozsen S,Arslan A,Gunes S. Arslan A, Gunes S, Medical application of information gain based artificial immune recognition system(AIRS): Diagnosis of thyroid disease. Expert syst. Appl 2009;36:3086-92.
[13] Keles A.Keles A.ESTDD: expert system for thyroid disease diagnosis.Expert Syst Appl. 2008;34:242-6.
[14] Duch W.Adamezak R. Grabezewski K. A new methodology of extraction,optimization and application of crisp and fuzzy logic rules. IEEE Trams Neural Netw 2001;12:277-306.
[15] Bologna G. A model for single and multiple knowledge based networks. Artif Intell Med 2003;28:141-63.
[16] Abe S.Thawonmas R. A fuzzy classifier with ellipsoidal regions. IEEE Trans Fuzzy Syst 1997;5:358-63.
[17] Abe S. Thawonmas R, Kayama M, A fuzzy classifier with ellipsoidal regions for diagnosis problems. IEEE Trans Syst Man Cybern C Appl Rev 1999;29:140-9.
[18] Sharaf-EI-Deen DA, Moawad IF,Khalifa ME. A new hybrid case-based reasoning approach for medical diagnosis systems. J Med Syst 2014;38;9-19.
[19] Falco ID. Differential evolution for automatic rule extraction from medical databases. Appl soft Comput 2013;13;1265-83.
[20] Zhu P.Hu Q. Rule extraction from support vector machine based on consistent region covering reduction. Knowl Based Syst 2013;42;1-8.
[21] Napierala K. Stefanowski J. BRACID: a comprehensive approach to learning rules from imbalanced data. J Intell Inf Syst 2012;39;335-73.s
[22] Yongchuan Tang, Wuming Pan, Haiming Li and Yang Xu. Fuzzy Naïve Bayes Classifier based on fuzzy clustering. IEEE International Conference on System, Man and Cybernetics, Vol.5, 2002.
[23] Yaguang Ji, Songnian Yu and Yafeng Zang. A Novel Naïve Bayes Model: Packaged Hidden Naïve Bayes. Sixth IEEE Joint International Conference on Information Technology and Artificial Intelligence. pp.484-487, 2011.
[24] Park, Hyeoun-Ae, An Introduction to Logistic Regression: From Basic Concepts to Interpretation with Particular Attention to Nursing Domain, J Korean Acad Nurs Vol.43 No.2 April 2013
[25] Le,Cessie S, Van Houwelingen JC.Ridge estimators in logistic regression. Applied statistics.1992;p.191-201.doi:10.2307/2347628
[26] Jiawei Han , Micheline Kamber, Data Mining Concepts and Techniques. Published by Elsevier 2006.
[27]University of California, Irvine Learning Repository. (http: //archive.ics.uci.edu/ ml/machine-learning-databases/ thyroid-disease/)
[28] Anupam Shukla, Prabhdeep Kaur, Ritu Tiwari and R.R. Janghel, Diagnosis of Thyroid disease using Artificial Neural Network. In Proceedings of IEEE IACC 2009.
[29] Umar Sidiq, “Comparative Study of Existing Techniques for Diagnosing Various Thyroid Ailments”, Global Journal of Computer Science and Technology: E Network, Web & Security Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals Inc. (USA) Online ISSN: 0975-4172 & Print ISSN: 0975-4350
[30] Azar AT,Hassanien AE, Kim T(2012) Expert system based on neural fuzzy rules for thyroid disease diagnosis springer berlin.
[31] Liu B, Fang L, Liu F, Wang X, Chen J, Chou KC. Identification of real microRNA precursors with a pseudo structure status composition approach. PloS one. 2015;10(3):e0121501 doi: 10.1371/journal.pone.0121501 [PMC free article] [PubMed [32]
[32] Liu B, Fang L, Liu F, Wang X, Chou KC. iMiRNA-PseDPC: microRNA precursor identification with a pseudo distance-pair composition approach. Journal of Biomolecular Structure and Dynamics. 2016;34(1):223–235. doi: 10.1080/07391102.2015.1014422 [PubMed]
[34] Shiliang Sun, Rongquing Huang. An adaptive k-nearest neighbor. IEEE Seventh International Conference on Fuzzy System and Knowledge Discovery. pp.91-94, 2010.

[35] Thyroid disease diagnosis via hybrid architecture composing rough data sets theory & machine learning algorithms, V. Prasad, T. Srinivasa Rao, M.Surendra Prasad Babu, Springer, soft comput(2016) 20:1179-1189, DOI 10.1007/s00500-014-1581-5
[36] L.Breiman, J.Friedman, R. Olshen,et al; Classification & Regrssion trees, chapman & Hall, London(1984)
[37] L.Rokach, O.Maimon, classification trees, Data Mining & Knowledge Discovery, Springer New York Dordrecht Heidelberg London,(2010) 149-174
[38] Derrac, J., Chiclana, F., Garcia, S., & Herrera, F.(2016). Evloutionary fuzzy k-nearest neighbours algorithm using interval-valued fuzzy sets. Information sciences, 329, 144-163.
[39] Tom Fawcett, An introduction to ROC analysis, Institute for the study of learning and expertise,2164 staunton court, palo alto, CA 94306, USA,Elsevier
[40] Pontius, Robert; Millones, Marco (2011). "Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment". International Journal of Remote Sensing. 32: 4407–4429.
[41] Galton, F. (1892). Finger Prints Macmillan, London.
[42] Smeeton, N.C. (1985). "Early History of the Kappa tatistic". Biometrics. 41: 795. JSTOR 2531300.
[43] Powers, David M. W. (2012). "The Problem with Kappa" (PDF). Conference of the European Chapter of the Association for Computational Linguistics (EACL2012) Joint ROBUS-UNSUP Workshop.
[44] Nitin Aji Bhaskar. Performance Analysis of Neural Network and Support Vector Machine in Detection of Myocardial Infarction. International Conference on Information and Communication Technologies, pp.20-30, 2015.
[45] Kotsiantis, S. B., D. Kanellopoulos, and P.E. Pintelas. “Data preprocessing for supervised learning” International Journal of Computer Science 1.2(2006):111-117.
[46] Guyon, I., Weston, J., Barnhill, S. and Vapnik, V. Gene selection for cancer classification using support vector machines, Machine Learning, Vol.46, Issue 1-3, Pp.389-422,2002