A smart methodology for analyzing chronic kidney disease detection | [Journal of Natural & Applied Sciences Pakistan • 2019]

Author(s):

1. Rana M. Amir Latif: Department of Computer Science, Comsats University Islamabad, Sahiwal Campus, Pakistan

2. Muhammad Farhan: Department of Computer Science, Comsats University Islamabad, Sahiwal Campus, Pakistan

3. Farah Ijaz: Department of Computer Science, Comsats University Islamabad, Sahiwal Campus, Pakistan

4. Muhammad Umer: Department of Computer Science, Comsats University Islamabad, Sahiwal Campus, Pakistan

5. Syed Umair Aslam Shah: Department of Computer Science, Comsats University Islamabad, Sahiwal Campus, Pakistan

Abstract:

Chronic kidney disease is increasing day by day all over the world; this is also known as a chronic rental disease because this disease is life-threatening. To save people from this lifethreatening disease, we have given suitable techniques and results in this paper for its accurate and early detection. It will not ensure 100% safety from disease but provide a suitable time to get a cure from it with its early detection. We have used 24 symptoms of chronic kidney disease in this paper which help us to accurately detect this disease with the help of two machine learning classification algorithms, i.e., C4.5 and C5.0. We conclude the results by introducing the medical datasets to all two algorithms separately with the help of the decision tree and the statistical information about the dataset, also this medical dataset is feed into the machine learning algorithms which are built-in WEKA are used for comparison and to check the accuracy of the algorithm. Algorithms used in this comparison are J48, Naïve Bayes and Logistic Model Tree (LMT) are used and them accurately to predict the chronic kidney disease is calculated. This research proved the efficiency of the C5.0 algorithm since it predicted more accuracy, short duration and less error rate as compared to the C4.5 algorithm. Also, the J48 algorithm is the best algorithm to predict chronic kidney disease. The best algorithm among different algorithms can be selected prediction model can be used for determining chronic kidney disease.

Page(s): 206-216

DOI: DOI not available

Published: Journal: Journal of Natural & Applied Sciences Pakistan, Volume: 1, Issue: 2, Year: 2019

Keywords:

Chronic disease , Kidney diseases , Machine learning algorithms , medical dataset , WEKA

References:

[1] Webster A. C.,Nagler E. V.,Morton R. L. .2017 ."Chronic kidney disease,". The Lancet, 389(10075) : 1238-1252.

[2] Coresh J. .2007 ."Prevalence of chronic kidney disease in the United States,". Jama, 298(17) : 2038-2047.

[3] Ruggieri S. .2002 .5 [classification algorithm]," IEEE transactions on knowledge and data engineering. Efficient C4, 14(2) : 438-444.

[4] S .2009 .0 classification algorithm and application on individual credit evaluation of banks,". Systems Engineering-Theory & Practice, 29(12) : 94-104.

[5] Bhargava N.,Bhargava R.,Mathuria M. .2013 ."Decision tree analysis on a j48 algorithm for data mining,". Proceedings of International Journal of Advanced Research in Computer Science and Software Engineering, 3(6) : .

[6] Suresh K.,Dillibabu R. .2018 ."Designing a Machine Learning Based Software Risk Assessment Model Using Naïve Bayes Algorithm,". , : .

[7] Miyato T.,Ishii S.,Koyama M. .2018 ."Virtual adversarial training: a regularization method for supervised and semi-supervised learning,". IEEE transactions on pattern analysis and machine intelligence, : .

[8] L. J. R. R . .Chronic_Kidney_Disease Data Set. (2015-07-03), : .

[9] Kannan R.,Vasanthi V. .2019 ."Machine Learning Algorithms with ROC Curve for Predicting and Diagnosing the Heart Disease," in Soft Computing. , : 63-72.

[10] C. L. Manske Y.,Wang T.,Rector C.,White C. .1992 ."Coronary revascularisation in insulin-dependent diabetic patients with chronic renal failure,". The Lancet, 340(8826) : 998-1002.

[11] P. G. Norris .1990 ."Immune function, mutant frequency, and cancer risk in the DNA repair defective genodermatoses xeroderma pigmentosum, Cockayne's syndrome, and trichothiodystrophy,". Journal of Investigative Dermatology, 94(1) : 94-100.

[12] Coresh J.,Astor B. C.,Greene T.,G. T.,Levey A. S. .2003 ."Prevalence of chronic kidney disease and decreased kidney function in the adult US population: Third National Health and Nutrition Examination Survey," American journal of kidney diseases. , 41(1) : 1-12.

[13] Tangri N. .2011 ."A predictive model for progression of chronic kidney disease to kidney failure,". Jama, 305(15) : 1553-1559.

[14] Jena L.,Kamila N. K. .2015 ."Distributed data mining classification algorithms for prediction of chronic-kidney-disease,". International Journal of Emerging Research in Management &Technology, 4(11) : 110-118.

[15] Kusiak A.,Dixon B.,Shah S. .2005 ."Predicting survival time for kidney dialysis patients: a data mining approach," Computers in biology and medicine. , 35(4) : 311-327.

[16] T. B. Drüeke .2006 ."Normalization of hemoglobin level in patients with chronic kidney disease and anemia,". New England Journal of Medicine, 355(20) : 2071-2084.

Citations

Downloads

Views