PERFORMANCE EVALUATION OF THE ENSEMBLE LEARNING MODELS IN THE CLASSIFICATION OF CHRONIC KIDNEY FAILURE

Abstract

Aim: This study aims to classify the CKF by applying the community learning method, which is an important sub-field of machine learning, on the open access CKF data set. Materials and Methods: In this study, the community learning methods Bagging, Boosting and Stacking methods were applied to the open access data set named “Chronic Kidney Disease”. The performance of the models used was evaluated with accuracy, sensitivity, specitivity, positive predictive value, and negative predictive value. Results: Accuracy, , sensitivity, specificity, positive predictive value and negative predictive value obtained from the Bagging model were 96.5, 96.8, 96, 97.5 and 94.7 respectively. Accuracy, , sensitivity, specificity, positive predictive value and negative predictive value obtained from the Boosting model were 98.75, 98, 1, 1 and 96.7 respectively. Accuracy, , sensitivity, specificity, positive predictive value and negative predictive value obtained from the Stacking model were 99.25, 99.6, 98.9, 99.2 and 99.3 respectively. Conclusion: The findings obtained from this study showed that successful results were obtained in the study performed with the relational classification model heart failure data set. In addition, certain rules regarding the disease to be used in preventive medicine practices have been obtained with this model

Keywords

• Chronic kidney failure
• classification
• machine learning

References

1. [1] N. Erol, "Diyaliz tedavisine başlanmayan kronik böbrek yetmezliği hastaları ile hemodiyaliz tedavisi olan hastaların yaşam kalitelerinin karşılaştırılması," Sağlık Bilimleri Enstitüsü, 2010.
2. [2] E. Crowe, D. Halpin, and P. Stevens, "Early identification and management of chronic kidney disease: summary of NICE guidance," Bmj, vol. 337, p. a1530, 2008.
3. [3] M. ESKİCİOĞLU, Ü. Eda, and A. ÖZDEMİR, "Böbrek Hastalarının Klinikte Yattığı Sürede Öğrenim Gereksinimlerinin Tespiti," Uludağ Üniversitesi Tıp Fakültesi Dergisi, vol. 45, pp. 205-210.
4. [4] Ü. Yıldırım, "Hİpervolemİk kronİk böbrek yetmezlİğİ hastalarinda troponin düzeyleri ve medİkal dİürez tedavisinin troponin düzeyi üzerine etkileri," Uzmanlık, Van yyü üniversitesi, 2020.
5. [5] H. Akpınar, "Veri tabanlarında bilgi keşfi ve veri madenciliği," İÜ İşletme Fakültesi Dergisi, vol. 29, pp. 1-22, 2000.
6. [6] D. J. Hand, "Principles of data mining," Drug safety, vol. 30, pp. 621-622, 2007.
7. [7] R. Polikar, "Ensemble learning," in Ensemble machine learning, ed: Springer, 2012, pp. 1-34.
8. [8] L. Rokach and O. Maimon, "Clustering methods," in Data mining and knowledge discovery handbook, ed: Springer, 2005, pp. 321-352.

9. [9] T. G. Dietterich, "Ensemble methods in machine learning," in International workshop on multiple classifier systems, 2000, pp. 1-15.
10. [10] M. Atalay and E. Çelik, "Büyük Veri Analizinde Yapay Zekâ Ve Makine Öğrenmesi Uygulamalari-Artificial Intelligence and Machine Learning Applications in Big Data Analysis," Mehmet Akif Ersoy Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, vol. 9, pp. 155-172, 2017.
11. [11] S. Sun, "Ensemble learning methods for classifying EEG signals," in International Workshop on Multiple Classifier Systems, 2007, pp. 113-120.
12. [12] S.-L. Hsieh, S.-H. Hsieh, P.-H. Cheng, C.-H. Chen, K.-P. Hsu, I.-S. Lee, et al., "Design ensemble machine learning model for breast cancer diagnosis," Journal of medical systems, vol. 36, pp. 2841-2847, 2012.
13. [13] C. Zhang and Y. Ma, Ensemble machine learning: methods and applications: Springer, 2012.
14. [14] L. Rokach, Pattern classification using ensemble methods vol. 75: World Scientific, 2010.
15. [15] L. Breiman, "Bagging predictors," Machine learning, vol. 24, pp. 123-140, 1996.
16. [16] A. J. Ferreira and M. A. Figueiredo, "Boosting algorithms: A review of methods, theory, and applications," in Ensemble machine learning, ed: Springer, 2012, pp. 35-85.
17. [17] J. H. Friedman, "Greedy function approximation: a gradient boosting machine," Annals of statistics, pp. 1189-1232, 2001.
18. [18] J. Friedman, T. Hastie, and R. Tibshirani, "Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors)," The annals of statistics, vol. 28, pp. 337-407, 2000.
19. [19] Y. Freund and R. E. Schapire, "Experiments with a new boosting algorithm," in icml, 1996, pp. 148-156.
20. [20] F. Divina, A. Gilson, F. Goméz-Vela, M. García Torres, and J. F. Torres, "Stacking ensemble learning for short-term electricity consumption forecasting," Energies, vol. 11, p. 949, 2018.
21. [21] N. R. Hill, S. T. Fatoba, J. L. Oke, J. A. Hirst, C. A. O’Callaghan, D. S. Lasserson, et al., "Global prevalence of chronic kidney disease–a systematic review and meta-analysis," PloS one, vol. 11, p. e0158765, 2016.
22. [22] S. F. Yalin, E. Parmaksiz, M. Mese, Z. Dogu, N. D. Çeçen, and Z. B. Bahçebasi, "Evaluating the causes for rejection of potential live-renal donors: Single center experience/potansiyel canli bobrek vericilerinin reddedilme nedenlerinin degerlendirilmesi: Tek merkez deneyimi," Journal of Istanbul Faculty of Medicine, vol. 82, pp. 127-131, 2019.
23. [23] A. C. Webster, E. V. Nagler, R. L. Morton, and P. Masson, "Chronic kidney disease," The lancet, vol. 389, pp. 1238-1252, 2017.
24. [24] A. Doganer, "Topluluk öğrenme yöntemleri ile renal hücreli karsnom’un tahmin edilmesi," Doktora, İnönü Üniversitesi, 2020.
25. [25] Y. Qi, "Random forest for bioinformatics," in Ensemble machine learning, ed: Springer, 2012, pp. 307-323.
26. [26] H. Polat, H. D. Mehr, and A. Cetin, "Diagnosis of chronic kidney disease based on support vector machine by feature selection methods," Journal of medical systems, vol. 41, p. 55, 2017.