Mortazavi M, Atapour A, Mohammadi M, Sattari M. Predicting the cause of kidney stones in patients using random forest, support vector machine and neural network. Tehran Univ Med J 2021; 79 (9) :706-714
URL:
http://tumj.tums.ac.ir/article-1-11437-en.html
1- Isfahan Kidney Diseases Research Center, Isfahan University of Medical Sciences, Isfahan, Iran.
2- Department of Health Information Technology and Management, School of Medical Management and Information Sciences, Isfahan University of Medical Sciences, Isfahan, Iran.
3- Health Information Technology Research Center, Isfahan University of Medical Sciences, Isfahan, Iran. , msattarimng.mui@gmail.com
Abstract: (1299 Views)
Background: Today, with the advancement of technology in various fields, the importance of recording data in the field of health is increasing so much that for many diseases around the world, including kidney disease, registration systems have been set up. This is happening in our country and in the future, the number of these systems will increase. The medical data set contains valuable information that will be time-consuming and costly to obtain using laboratory methods, so there is a need for low-cost methods for extracting information. This study focuses on developing a predictive model for classifying the cause of kidney stones in Isfahan using three data mining techniques.
Methods: This cross-sectional research has been done from February 2021 to May 2021. The used medical data set includes information of 353 kidney stone patients in Isfahan. In this study, six target attributes of sodium, phosphate, oxalate, citrate, cysteine and uric acid were identified. The techniques for each of the 6 attributes are used separately. The techniques used in this study were three data mining techniques including random forest (RF), artificial neural network (ANN) and support vector machine (SVM).
Results: The best performance in terms of accuracy is related to support vector machine techniques in uric acid class, support vector machine in oxalate class and neural network in cysteine class. The worst performance is related to the random forest technique in the citrate class. The safest rules with a 66% confidence level are for the citrate and sodium classes, and the least reliable rule with a 50% confidence level is for the oxalate class.
|
Conclusion: Kidney stones can occur due to various reasons such as low citrate and high calcium oxalate. For example, for citrate, factors such as blood pH (potential of hydrogen), blood sugar and blood pressure are effective. To prevent any of the causes of kidney stones, factors should be controlled.
Type of Study:
Original Article |