Using Classification Tree for prediction of Diabetic Retinopathy on type II diabetes

Document Type : Original Article(s)

Authors

1 Assistant Professor, Department of Biostatistics and Epidemiology, School of Health, Isfahan University of Medical Sciences

2 Professor, Endocrine and Metabolism Research Center, Isfahan University of Medical Sciences, Isfahan

3 Associate Professor, Department of Community Medicine, School of Medicine, Isfahan University of Medical Sciences, Isfahan

4 MSc in Biostatistics, Department of Biostatistics and Epidemiology, School of Health, Isfahan University of Medical Sciences, Isfahan

Abstract

Background: Diabetes disease is a common disease in the world and diabetic retinopathy that is an eye disease, involve these patients so hardly that leads patients to blindness in elderly. Because of high incidence of type II diabetes in the society and the danger of retinopathy in this group of patients, in this study we attempted to introduce a classification and predictive model according to Classification and Regression Tree (CART) model for this disease. Methods: This study was performed according to the information of about 3734 patients with type II diabetes, consulted to Isfahan Metabolic and Endocrine Research Center from 1991 to 2006. According to the CART model, a classification pattern was introduced for predicting of retinopathy in these patients. Findings: In this study, classification tree model (CART) obtained with accuracy of 67 percents according to duration of disease, age, sex, systolic blood pressure, triglyceride, cholosterol and fasting blood sugar. This classification model had the sensitivity of 71% and specifity of 62%. Conclusion: By this study founds that the duration of diabetes is one of the most important element of retinopathy, in such a manner that the danger of retinopathy in type II diabetes patients with more than 7.5 years is more than other patients. Key words: Diabetic retinopathy, Type II diabetes, Classification tree.
Journal of Isfahan Medical School
Volume 28, Issue 104 - Serial Number 104
January and February 2010
Pages 17-27

Files

History

  • Receive Date: 07 November 2010
  • Revise Date:
  • Accept Date: 06 April 2022

Share

How to cite

Statistics