KOMPARASI ALGORITMA KLASIFIKASI DECISION TREE, NAIVE BAYES DAN NEURAL NETWORK UNTUK PREDIKSI PENYAKIT GINJAL KRONIS

Raja Syahmudin Harahap

Abstract


Chronic kidney disease is a worldwide health crisis. In 2005, there were about 58 million deaths worldwide, with 35 million people associated  will chronic kidney disease. (World Health Organization). Data mining plays a vital role in health care domain, nowadays. There is an increased need for an efficient analytical methodology to detect unknown and valuable information in health data. It produces huge amount of data about patients, diseases, diagnosis and medicines so on. In the health care industry, the data mining is mainly used for predicting the diseases from the datasets. In order to obtain high accuracy algorithm will do a comparison few algorithms that have different characteristics, they are Decision Tree, Naïve Bayes and Neural Network. From the test results to measure the performance of the three algorithms using the test method Cross Validation, Confusion Matrix and ROC curves, it is known that the algorithm  Naïve Bayes has the highest accuracy value of 99,50%, followed by Decision Tree algorithm with the accuracy value of 97,25%, and  Neural Network algorithm with the accuracy value of 97,25% . AUC values for Naïve Bayes algorithm also showed the highest value, namely 1,000, followed by  Decision Tree algorithm with AUC values of 0,998 and the lowest is the Neural Network algorithm with AUC values of 0,991. All methods are include excellent classification because the AUC value between 0,90-1,00.

Full Text:

PDF

References


Alpaydin, Ethem. (2010). Introduction to Machine Learning. London: The MIT Press

Astuti, E. D. (2009). Pengantar Jaringan Saraf Tiruan. Wonosobo: Star Publishing.

Budi Santoso. (2007). Data Mining Teknik Pemanfaatan Data Untuk Keperluan Bisnis, 1st ed. Yogyakarta, Indonesia: Graha Ilmu.

Dr. S. Vijayarani; Mr.S.Dhayanand. (2015). ‘Kidney Disease Prediction Using Svm and Ann’, 6.2.

Florin Gorunescu. (2011). Data Mining: Concepts, Model and Techniques, Prof. Janusz Kacprzyk and Prof. Lakhmi C. Jain, Eds. Berlin, Jerman: Springer, vol. 12.

Gary S. Collins and others. (2013). ‘A Systematic Review Finds Prediction Models for Chronic Kidney Disease Were Poorly Reported and Often Developed Using Inappropriate Methods’, Journal of Clinical Epidemiology, 66.3, 268–77.

Han, J., & Kamber, M. (2006). Data Mining Concept and Tehniques. San Fransisco: Morgan Kauffman.

Ian H. Witten, frank Eibe, and Mark A. Hall. ( 2011). Data Mining: Practical Machine Learning Tools and Techniques, 3rd ed., Asma Stephan and Burlington, Eds. United States of America: Morgan Kaufmann.

Jiawei Han. (2007). Data Mining Concept And Technique, 2nd ed., Asma Stephan, Ed. Champaign, United States of America: Multiscience Press.

Kusrini, & Luthfi, E. T. (2009). Algoritma Data mining. Yogyakarta: Andi.

Larose, D. T. (2005). Discovering Knowledge in Data. Canada: Wiley Interscience.

Marc Breit and Klaus M. Weinberger. (2016). ‘Metabolic Biomarkers for Chronic Kidney Disease’, Archives of Biochemistry and Biophysics.

Mohammed Abdul Khaleel, Sateesh Kumar and Pradham G N Dash. (2013). ‘A Survey of Data Mining Techniques on Medical Data for Finding Locally Frequent Diseases’, International Journal of Advanced Research in Computer Science and Software Engineering, 3.8, 2277–128.

Parul sinha; Poonam Sinha. (2015). ‘Comparative Study of Chronic Kidney Disease Prediction Using KNN and SVM’, 4.12, 608–12.

Shukla, A., Tiwari, R., & Kala, R. (2010). Real Life Application of Soft Computing. CRC Press.

S.Ramya; Dr. N.Radha. (2016). ‘Diagnosis of Chronic Kidney Disease Using Machine Learning Algorithms’, Technology, 812–20.

Wu, Xindong& Kumar, Vipin. (2009). The Top Ten Algorithms in Data Mining. Boca Raton: CRC Press

Xindong Wu and Vipin Kumar. (2009). The top ten Algorithms in Data Mining: Taylor & Francis Group, LLC.


Refbacks

  • There are currently no refbacks.