TY - GEN
T1 - Result comparison between categorical and numerical predictor variables on CART method in predicting factors related to diabetic retinopathy in patients with type 2 diabetes mellitus
AU - Hariany, S. F.
AU - Siswantining, T.
AU - Bustamam, A.
AU - Budiman, B.
N1 - Publisher Copyright:
© 2018 Author(s).
PY - 2018/10/22
Y1 - 2018/10/22
N2 - CART (Classification and Regression Tree) is a classification nonparametric method that employs learning sample to construct decision tree. Type 2 Diabetes mellitus is classified under diabetes mellitus group that could result in complication, both macrovascular and microvascular. Diabetic Retinopathy is a part of microvascular complication of diabetes mellitus that is considered as the most frequent cause of blindness in adult. Predicting factors related to diabetic retinopathy is important to be done to decrease the prevalence of diabetic retinopathy. The aim of this research is to determine the factor related to diabetic retinopathy in patients with type 2 diabetes mellitus using CART method. CART method is applied in two types of independent variable data (numeric and category). The research uses 174 patients with type 2 diabetes mellitus in Cipto Mangunkusumo Hospital Jakarta as its sample. From the result of analyzing numeric data, the factor related with diabetic retinopathy is microalbuminuria, blood creatinine, gylocohemoglobin, and triglyceride. Meanwhile, from categorical data, factors that has correlation with diabetic retinopathy is microalbuminuria, 2 hour post prandial glucose, the history of diabetes mellitus in the family, and fasting blood glucose. From these two types of data that are analyzed using CART method, it is concluded that microalbuminuria is considered as the major factor that is related to diabetic retinopathy in patients with type 2 diabetes mellitus.
AB - CART (Classification and Regression Tree) is a classification nonparametric method that employs learning sample to construct decision tree. Type 2 Diabetes mellitus is classified under diabetes mellitus group that could result in complication, both macrovascular and microvascular. Diabetic Retinopathy is a part of microvascular complication of diabetes mellitus that is considered as the most frequent cause of blindness in adult. Predicting factors related to diabetic retinopathy is important to be done to decrease the prevalence of diabetic retinopathy. The aim of this research is to determine the factor related to diabetic retinopathy in patients with type 2 diabetes mellitus using CART method. CART method is applied in two types of independent variable data (numeric and category). The research uses 174 patients with type 2 diabetes mellitus in Cipto Mangunkusumo Hospital Jakarta as its sample. From the result of analyzing numeric data, the factor related with diabetic retinopathy is microalbuminuria, blood creatinine, gylocohemoglobin, and triglyceride. Meanwhile, from categorical data, factors that has correlation with diabetic retinopathy is microalbuminuria, 2 hour post prandial glucose, the history of diabetes mellitus in the family, and fasting blood glucose. From these two types of data that are analyzed using CART method, it is concluded that microalbuminuria is considered as the major factor that is related to diabetic retinopathy in patients with type 2 diabetes mellitus.
KW - Classification and Regression Tree
KW - diabetes mellitus type 2
KW - microalbuminuria
UR - http://www.scopus.com/inward/record.url?scp=85056139774&partnerID=8YFLogxK
U2 - 10.1063/1.5064223
DO - 10.1063/1.5064223
M3 - Conference contribution
AN - SCOPUS:85056139774
T3 - AIP Conference Proceedings
BT - Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017
A2 - Yuniati, Ratna
A2 - Mart, Terry
A2 - Anggraningrum, Ivandini T.
A2 - Triyono, Djoko
A2 - Sugeng, Kiki A.
PB - American Institute of Physics Inc.
T2 - 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017
Y2 - 26 July 2017 through 27 July 2017
ER -