A FAST INTELLIGENT DIAGNOSIS SYSTEM FOR THYROID DISEASES BASED ON EXTREME LEARNING MACHINE

Abstract

With iodine taken from outside, the thyroid gland is an organ that secretes hormones called thyroxin. All metabolic functions of human beings are controlled by these hormones. An overactive thyroid gland which is producing an excessive amount of these hormones causes hyperthyroidism, while an underactive thyroid gland that is not producing enough of these hormones causes hypothyroidism. The diagnosis of thyroid gland disorders by assessing the data of thyroid in clinical applications comes out as an important classification problem. In this study, Extreme Learning Machine (ELM) was applied to the thyroid data set taken from UCI machine learning repository. The ELM is single hidden layer feed-forward artificial neural network model which can be learnt fast. It was seen that the ELM, for the data set, has the upper hand in terms of both classification accuracy and speed when compared to other machine learning methods. The classification accuracy obtained through the ELM is 96.79% for 70-30% training-test partition.

 

Keywords

• Extreme Learning Machine, Thyroid Diseases, Machine Learning, Expert System

ANADOLU ÜNİVERSİTESİ

Abstract

Tiroit bezi dışarıdan alınan iyot minerali ile “tiroksin” denilen hormonları yapan bir organdır. İnsana ait tüm metabolizma faaliyetleri bu hormonları tarafından kontrol edilmektedir. Bu hormonların aşırı salınması hyperthyroidism, az salınması ise hypothyroidism bozuklarının ortaya çıkmasına neden olmaktadır. Klinik uygulamalarda tiroit verilerin yorumlanarak tiroit bezi bozukluğu tanısının konulması önemli bir sınıflandırma problemi olarak karşımıza çıkmakta. Bu çalışmada UCI makine öğrenmesi veri tabanından alınan tiroit veri setine aşırı öğrenme makinesi (AÖM) yöntemi uygulanmıştır. AÖM hızlı öğrenebilen tek gizli katmanlı ileri beslemeli bir yapay sinir ağ modelidir. Ele alınan veri seti için AÖM, diğer makine öğrenmesi yöntemlere göre hem sınıflandırma başarısı hem de hız bakımından önemli avantajlar sağladığı görülmüştür. AÖM ile elde edilen sınıflandırma başarısı 96.79 % olarak elde edilmiştir

Keywords

• Aşırı Öğrenme Makinesi, Tiroit Hastalıklar, Makine Öğrenmesi, Uzman Sistem

References

1. Chih-Lin C. , W. Nick Street, David A. Katz, “A Decision Support System for CostEffective Diagnosis”. Artificial Intelligence in Medicine, 50, 149-161, 2010.
2. Esin D., Akif D., Derya A., “An Expert System Based on Generalized Discriminant Analysis and Wavelet Support Vector Machine for Diagnosis of Thyroid Diseases”, Expert Systems with Applications, 38, 146-150, 2011.
3. Handoko, S. D., Keong, K. C., Ong, Y. S., Zhang G.L., Brusic V, “Extreme Learning Machine for Predicting HLAPeptide Binding”, Lecture Notes in Computer, 3973, 716–721, 2006.
4. Hai-Jun R.,Yew-Soon O., Ah-Hwee T., Zexuan Zhu, “A Fast Pruned-Extreme Learning Machine for Classification Problem”, Neurocomputing, 72, 359-366, 2008.
5. Halife K., Seral O., Arslan ,A., Gunes, S., “Medical Application of Information Gain Based Artificial Immune Recognition System (AIRS): Diagnosis of Thyroid Disease”, Expert Systems with Applications, 36, 3086-3092, 2009.
6. Hoshi, K., Kawakami, J., Kumagai, M., Kasahara, S., Nisimura, N., Nakamura, H., “An Analysis of Thyroid Function Diagnosis using Bayesian-type and SOMType Neural Networks”, Chemical and Pharmaceutical Bulletin, 53, 1570-1574, 2005.
7. Huang, G.B., Zhu, Q.Y., Siew, C.K. Extreme Learning Machine: Theory and Applications. Neurocomputing, 70 (1-3), 489-501, 2006.
8. Kaya, Y., “A New Intelligent Classifier for Breast Cancer Diagnosis Based on Rough Set and Extreme Learning Machine: RS+ELM”, Turkish Journal of Electrical Engineering and Computer Sciences, 21:2079-2091, 2013

9. Kaya, Y., Uyar, M., “A Hybrid Decision Support System Based on Rough Set and Extreme Learning Machine for Diagnosis of Hepatitis Disease”, Applied Soft Computing Journal, 13,3429- 3438, 2013.
10. Kaya, Y., Kayci, L., Tekin, R., Ertugrul, Ö.F., “Evaluation of Texture Features for Automatic Detecting Butterfly Species using Extreme Learning Machine”, Journal of Experimental & Theoretical Artificial Intelligence, DOI:10.1080/0952813X.2013.861875, 2014.
11. Keles, A., Keles, A. “ESTDD: Expert System for Thyroid Diseases Diagnosis”, Expert Systems with Applications, 34:1, 242-246, 2008.
12. Liang, N., Y., Saratchandran,P., Huang G., P., Sundararajan, N., “Classification of Mental Tasks From Eeg Signals using Extreme Learning Machine”, International. Journal of Neural Systems, 16 (1), 29-38, 2006.
13. Ozyılmaz, L. Yıldırım, T., “Diagnosis of Thyroid Disease using Artificial Neural Network Methods”, In Proceedings of The 9th International Conference on Neural Information Processing (ICONIP’02), 4, 2033-2036, 2002.
14. Paavo K., Pasi L., “Classification Method using Fuzzy Level Set Subgrouping”, Expert Systems with Applications, 34, 859-865, 2008.
15. Pasi, L., “Similarity Classifier Applied to Medical Data Sets”,10 Sivua, Fuzziness in Finland’04. In International Conference on Soft Computing, Helsinki, Finland & Gulf of Finland & Tallinn, Estonia, 2004.
16. Polat, K., Sahan, S., Gunes, S., “A Novel Hybrid Method Based on Artificial Immune Recognition System (AIRS) with Fuzzy Weighted Pre-processing for Thyroid Disease Diagnosis”, Expert Systems with Applications, 32, 1141- 1147, 2007.
17. Shu-Kay N., Geoffrey J. McLachlan. “Extension of Mixture-of-experts Networks for Binary Classification of Hierarchical Data”, Artificial Intelligence in Medicine. 41, 57-67, 2007.
18. Suresh S., Saraswathi S., Sundararajan N., “Performance Enhancement of Extreme Learning Machine for Multi-category sparse Data Classification Problems”, Engineering Applications of Artificial Intelligence, 23, 1149-1157, 2010.
19. Temurtas , T., “A Comparative Study on Thyroid Disease Diagnosis using Neural Networks”, Expert Systems with Applications, 36, 944-949, 2009.
20. UCI Repository of Machine Learning Databases, University of California at Irvine, Department of Computer Science. Last Accessed 31.12.2011.
21. Yuan Q., Weidong Z., Shufang L., Dongmei C. “Epileptic EEG Classification Based on Extreme Learning Machine and Nonlinear Features”, Epilepsy Research. 96, 29-36, 2011.
22. Zhang, G., Berardi, L. V., “An Investigation of Neural Networks in Thyroid Function Diagnosis”, Health Care Management Science, 29–37, 1998.
23. Zong, W. W.,Huang G. B., “Face Recognition Based on Extreme Learning Machine”, Neurocomputing, 74, 2541–2551, 2006.