Decision Tree Application for Renal Calculi Diagnosis

Abstract

Data mining is used for the extraction of secret, valuable and usable data from the big data and to provide strategic decision support. It created a new perspective for the use of the data in healthcare in addition to finding the answers of unexplored questions. It has gained wider usage as a method. The aim of this study is to develop a decision tree and a list of rules by data mining for the early diagnosis of renal calculi. A data set including blind and retrospective data for 150 people can diagnose with 6 attributes. A decision support system analysis was developed for the diagnosis of the patients with suspected renal calculi. Based on the results obtained and the analysis developed, a decision tree and list of rules were created to determine the factors that affect renal calculi. Weka program and J48 algorithm were used to create the decision tree and the list of rules and it was found to be 74.63% successful.

Keywords

• Data Mining,Decision Tree,Renal Calculi Diagnosis

References

1. [1] E. Musoğlu, Sağlıkta Tıp Bilişiminin Önemi ve Dünyada Son Durum, Tıp Bilişimi Güz Okulu Dergisi. 2003, p. 4.
2. [2] Sincan M., Birinci Basamak Sağlık Hizmetleri İçin Bilişim Rehberi, Sürekli Tıp Eğitimi Dergisi. 2000.
3. [3] Yang W.S and Hwang S., A Process-Mining Framework for the Detection of Healthcare Fraud and Abuse, Expert Systems with Applications. 2006, vol.31, p.56-68.
4. [4] Can M.B., Çamur E., Koru M. and Rzayeva Z., Veri Kümelerinden Bilgi Keşki: Veri Madenciliği, Başkent Üniversitesi Tıp Fakültesi XIV. Öğrenci Sempozyumu. Ankara, 2008.
5. [5] Chandor A., The Penguin Dictionary of Computers, New York: Penguin Books. 1989, p.106.
6. [6] Albayrak M., “The detection of an epileptiform activity on EEG signals by using data mining process”, PhD Thesis, Graduate School of Natural and Applied Sciences, Sakarya University, Turkey, 2008.
7. [7] Azimli M., ”Tıpta Veri Madenciliği Uygulamaları”, MSc Thesis, Institute of Information, Gazi University, Turkey, 2011.
8. [8] Baykal A., Application Fields of Data Mining, Dicle University Journal of Ziya Gökalp Faculty of Education, 2006, p.95-107.

9. [9] Zhou Z. H., Three Perspectives of Data Mining, Artificial Intelligence. Elsevier, 2003, p.139-146.
10. [10] Makinacı M. and Güneşer C., Göğüs Kanseri Verilerinin Sınıflandırılması, Elektrik Elektronik-Bilgisayar Mühendisliği 12. Ulusal Kongresi, 2007.
11. [11] Yıldırım P., Uludağ M. and Görür A., Hastane Bilgi Sistemlerinde Veri Madenciliği, Akademik Bilişim Dergisi, 2008.
12. [12] Shah S.C. and Kursak A., Data Mining and Genetic Algorithms Based Gene / SNP Selection, SHAH, Artificial Intelligence in Medicine. 2004, vol. 31, p.183-196.
13. [13] Kamrani A., Rong W. and Gonzalez R., A Genetic Algorithm Methodology for Data Mining and Intelligent Knowledge Acquisition. Computers & Industrial Engineering, 2001, vol. 40, p.361-377.
14. [14] Feelders A., Daniels H. and Holsheimer M., Methodological and Practical Aspects of Data Mining. Information & Management, 2000, vol.37, p. 271-281.
15. [15] Subramanian A., Smith L.D., Nelson A.C., Campbell J.F. and Bird D.A., Strategic Planning for Data Warehousing. Information & Management, 1997, vol.33, p.99-113.
16. [16] Chien C.F. and Chen L.F., Data Mining to Improve Personnel Selection and Enhance Human Capital: A Case Study in High-Technology Industry. Expert Systems with Applications, 2008, vol.34, p. 280-290.
17. [17] Özekes S. and Çamurcu Y., Veri Madenci¬liğinde Sınıflama Ve Kestirim Uygulaması, Marmara Üniversitesi Fen Bilimleri Dergisi, 2002, vol.18, p.1-17.
18. [18] Quinlan J.R., C4.5: Programs for Machine Learning, Elsevier, 2014.
19. [19] Hall M., Frank E., Holmes G., Pfahringer B., Reutemann P. and Witten I.H., The WEKA Data Mining Software: An Update. ACM SIGKDD Explorations Newsletter, 2009, vol.11, p.10-18.
20. [20] Witten I.A., Frank E. and Hall M.A., Data Mining: Practical Machine Learning Tools and Techniques, Elsevier, USA, 2011.
21. [21] İlkuçar M., Diagnosis Chronic Kidney Disesa with Artificial Neural Network and Radial Basis Function Network, The Journal of Graduate School of Natural and Applied Sciences of Mehmet Akif Ersoy University. 2015, vol.6, p.82-88.
22. [22] Danacı M., Çelik M. and Akkaya A.E., Veri Madenciliği Yöntemleri Kullanılarak Meme Kanseri Hücrelerinin Tahmin ve Teşhisi, ASYU Conference, 2010.
23. [23] Yurtay Y., Salman Y. and Gençali F., Kansızlık Tanısına İlişkin Bir Veri Madenciliği Uygulaması, ISITES 2013, p.896-900.
24. [24] Özkan Ö., Yıldız M. and Köklükaya E., Improving Diagnostic Accuracy by Supporting The Laboratory Tests Which Used for Diagnosıs of Fibromyalgia Syndrome With The Sympathetic Skin Response Parameters, Sakarya University Journal of Science, 2011, vol.15, p.1-7.
25. [25] Kökver Y., Barışçı N., Çiftçi A. and Ekmekçi Y., Determining Affecting Factors of Hypertension with Data Mining Techniques, NWSA Academic Journal. 2014, vol.9, p.15-25.
26. [26] Kusiak A., Kernstine K.H., Kern J.A., McLaughlin K.A. and Tseng T.L., Medical and Engineering Case Studies, 2000.
27. [27] Topaloğlu M. and Sur H., Decision Tree Application to Reduce Incorrect Diagnosis in Symptoms of Jaundice, Nobel Medicus. 2015, vol.11, p.64-73.
28. [28] Çakır M., Firma Başarısızlığının Dinamiklerinin Belirlenmesinde Makine Öğrenmesi Teknikleri: Amprik Uygulamalar ve Karşılaştırılmalı Analiz. Uzmanlık Yeterlilik Tezi, Ankara, T.C. Merkez Bankası, 2005.