The Diagnosis and Estimate of Chronic Kidney Disease Using the Machine Learning Methods

Abstract

Chronic kidney disease is a prolonged disease that damages the kidneys and prevents the normal duties of the kidneys. This disease is diagnosed with an increase of urinary albumin excretion lasting more than three months or with significant reduction in a kidney functions. Chronic kidney disease can lead to complications such as high blood pressure, anemia, bone disease and cardiovascular disease. In this study we have been investigated to determine the factors that decisive for early detection of chronic kidney disease, launching early patients treatment processes, prevent complications resulting from the disease and predict of disease.  The study aimed diagnosis and prediction of disease using the data set that composed of data of 250 patients with chronic kidney disease and 150 healthy people. First, the chronic kidney disease data was classified with machine learning algorithms and then training and test results were analysed.  The estimation results of chronic kidney disease were compared with similar data and studies.

Keywords

• Chronic Kidney Disease,Machine Learning,Classification

References

1. [1] A.S. Albayrak and Ş.K. Yılmaz, "Veri Madenciliği Karar Ağacı Algoritmaları ve İMKB Verileri Üzerine Bir Uygulama", Süleyman Demirel Üniversitesi İİBF Dergisi, Volume 14, 2009.
2. [2] S. Bala and K. Kumar, "A Literature Review on Kidney Disease Prediction using Data Mining Classification Technique", International Journal of Computer Science and Mobile Computing, Volume 3, Issue 7, 2014.
3. [3] G. Süleymanlar, Akdeniz Üniversitesi Tıp Fakültesi İç Hastalıkları Nefroloji Bilim Dalı, Online Accessed: May, 2016, www.medikalakademi.com.tr/kronik-bobrek-yetmezligi-baslangic-belirtileri-tani-tedavisi/, 2013.
4. [4] G. Silahtaroğlu, "Veri Madenciliği Kavram ve Algoritmaları", Papatya Yayıncılık Eğitim, İstanbul, 2013.
5. [5] Soundarapandian, Online Accessed: May, 2016, https://archive.ics.uci.edu/ml/datasets/Chronic_Kidney_Disease, 2015.
6. [6] S. Vijayarani and S. Dhayanand, "Data mining classification algorithms for kidney disease prediction", International Journal on Cybernetics & Informatics (IJCI), Vol. 4, No. 4, 2015.
7. [7] S. R. Raghavan, V. Ladik and K. B. Meyer, "Developing decision support for dialysis treatment of chronic kidney failure", IEEE Transactıons on Information Technology in Biomedicine, vol. 9, no. 2, 2005.
8. [8] K. Krishna, A. Rayavarapu and V. Vadlapudi, “Statistical and Data Mining Aspects on Kidney Stones: A Systematic Review and Meta-analysis”, Open Access Scientific Reports, Volume 1, Issue 12, 2012.

9. [9] M. K. Zadeh, M. Rezapour and M. M. Sepehri, “Data Mining Performance in Identifying the Risk Factors of Early Arteriovenous Fistula Failure in Hemodialysis Patients”, International journal of hospital research, Volume 2, Issue 1, 2013.
10. [10] Y. Abeer and A. Hyari, “Chronic Kidney Disease Prediction System Using Classifying Data Mining Techniques”, Library of University of Jordan, 2012.
11. [11] X. Song, Z. Qiu and J. Mu, “Study on Data Mining Technology and its Application for Renal Failure Hemodialysis Medical Field”, International Journal of Advancements in Computing Technology (IJACT), Volume 4, Number 3, 2012.
12. [12] K. Kumar, "Artificial neural networks for diagnosis of kidney stones disease." International Journal of Information Technology and Computer Science (IJITCS) Volume 4, Issue 7, 2012.
13. [13] Ş.E. Şeker, “İş Zekası ve Veri Madenciliği”, Cinius Yayınları, İstabul, Türkiye, 2013.
14. [14] E. Celik and A. Kondiloglu, "Detection of fake banknotes with Artificial Neural Networks and Support Vector Machines", 23th Signal Processing and Communications Applications Conference (SIU), 2015.
15. [15] Y. Özkan, “Veri Madenciliği Yöntemleri”, Papatya Yayıncılık Eğitim, Türkiye, 2013.
16. [16] J.R. Quinlan, Online Accessed: May, 2016, http://www.cise.ufl.edu/~ddd/cap6635/Fall-97/Short-papers/2.htm, 2015