CLASSIFICATION OF HYPOTHYROID DISEASE WITH EXTREME LEARNING MACHINE MODEL

Abstract

Aim: Bu In this study, it is aimed to classify hypothyroidism by applying the Extreme Learning Machine model, which is one of the artificial neural network models, on the open access Hypothyroid dataset. Materials and Methods: In this study, the data set named "Hypothyroid Disease Data Set" was obtained from https://www.kaggle.com/nguyenthilua/hypothyroidcsv. Extreme Learning Machine model, one of the artificial neural network models, was used to classify hypothyroidism. The classification performance of the model was evaluated with classification performance criteria such as accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value and F1-score. Results: The accuracy obtained from the model was calculated as 0.922, balanced accuracy 0.523, sensitivity 1, specificity 0.047, positive predictive value 0.922, negative predictive value 1 and F1-score 0.959. Conclusion: The findings obtained from this study showed that the extreme learning machine model used gave successful predictions in the classification of hypothyroidism.

Keywords

• Hypothyroidism
• classification
• artificial neural networks
• extreme learning machine

References

1. [1] L. E. Braverman and D. Cooper, Werner & Ingbar's the thyroid: a fundamental and clinical text: Lippincott Williams & Wilkins, 2012.
2. [2] A. S. Fauci, Harrison's principles of internal medicine vol. 2: McGraw-Hill, Medical Publishing Division New York, 2008.
3. [3] T. R. Kıran, "Hipertiroidili ve hipotiroidili hastalarda oksidatif stres parametreleri ve adenozin deaminaz aktivitesi," 2007.
4. [4] S. Koloğlu and G. Erdoğan, "Tiroid: Genel Görüş ve Bilgiler," Koloğlu Endokrinoloji, Temel ve Klinik, vol. 2, pp. 155-72.
5. [5] M. Özata, Tiroid hastalıkları: tanı ve tedavisi: GATA Basımevi, 2003.
6. [6] D. C. Bauer, B. Ettinger, and W. S. Browner, "Thyroid function and serum lipids in older women: a population-based study," The American journal of medicine, vol. 104, pp. 546-551, 1998.
7. [7] J. Norman, "Hypothyroidism: Too Little Thyroid Hormone," 2013.
8. [8] S. Haykin, "Neural Networks, a comprehensive foundation, Prentice-Hall Inc," Upper Saddle River, New Jersey, vol. 7458, pp. 161-175, 1999.

9. [9] H. H. Dodurgalı, "Karınca Kolonisi Optimizasyonu İle Eğitilmiş Çok Katmanlı Yapay Sinir Ağı İle Sınıflandırma," Fen Bilimleri Enstitüsü, 2010.
10. [10] C. KARAKUZU and A. BAKIRCI, "Dynamic System Identification Based on an Ensemble of ELMs."
11. [11] Ö. F. ALÇİN, "Aşırı öğrenme makinelerinin seyrek geri çatma algoritmaları ile optimizasyonu/Optimization of extreme learning machine with sparse recovery algorithms," 2015.
12. [12] Available: https://www.kaggle.com/nguyenthilua/hypothyroidcsv.
13. [13] G.-B. Huang, Q.-Y. Zhu, and C.-K. Siew, "Extreme learning machine: theory and applications," Neurocomputing, vol. 70, pp. 489-501, 2006.
14. [14] M. Özçalici, "Aşiri Öğrenme Makineleri İle Hisse Senedi Fiyat Tahmini," Hacettepe Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, vol. 35, pp. 67-88, 2017.
15. [15] O. KAYNAR, H. ARSLAN, Y. GÖRMEZ, and Y. E. IŞIK, "Makine Öğrenmesi ve Öznitelik Seçim Yöntemleriyle Saldırı Tespiti," Bilişim Teknolojileri Dergisi, vol. 11, pp. 175-185, 2018.
16. [16] C. Schmid, C. Zwimpfer, M. Brändle, P. A. Krayenbühl, J. Zapf, and P. Wiesli, "Effect of thyroxine replacement on serum IGF‐I, IGFBP‐3 and the acid‐labile subunit in patients with hypothyroidism and hypopituitarism," Clinical endocrinology, vol. 65, pp. 706-711, 2006.
17. [17] P.-Q. Yuan and H. Yang, "Hypothyroidism increases Fos immunoreactivity in cholinergic neurons of brain medullary dorsal vagal complex in rats," American Journal of Physiology-Endocrinology and Metabolism, vol. 289, pp. E892-E899, 2005.
18. [18] M. Akın and M. Ceylan, "İyi Huylu Karaciğer Lezyonlarının Sınıflandırılmasında Yapay Sinir Ağı ve Aşırı Öğrenme Makinesi’nin Karşılaştırılması Comparison of Artificial Neural Network and Extreme Learning Machine in Benign Liver Lesions Classification."
19. [19] K. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural networks, vol. 2, pp. 359-366, 1989.
20. [20] W. Sun, C. Wang, and C. Zhang, "Factor analysis and forecasting of CO2 emissions in Hebei, using extreme learning machine based on particle swarm optimization," Journal of cleaner production, vol. 162, pp. 1095-1101, 2017.
21. [21] N.-Y. Liang, G.-B. Huang, P. Saratchandran, and N. Sundararajan, "A fast and accurate online sequential learning algorithm for feedforward networks," IEEE Transactions on neural networks, vol. 17, pp. 1411-1423, 2006.