ABSTRACT
BACKGROUND: Hemoglobin A1C (HbA1C) test is the best care evaluation measurement due to a strong correlation between the test results and diabetic complications. So, this cross-sectional study aimed to assess whether the level of HbA1C can predict Diabetic Retinopathy (DR) among Type 2 diabetes mellitus (T2DM) in the Iranian population. METHOD: One hundred sixty-eight diabetic patients were selected via the convenience sampling method. Data were collected by research made questionnaire scale and laboratory test had been done. To estimate the cut off point for some variables statistical tests, formal measures of classification performance, model evaluation criteria and a decision Tree were used. RESULTS: The prevalence of DR was 29.8%. The Receiver Operating Characteristic (ROC) curve and decision tree showed the optimal cut-off point for the HbA1C variable that separates the patient with and without DR is HbA1C = 8.15. CONCLUSION: Current study showed an appropriate cutoff point for detecting the development of DR among diabetic patients. So, this cutoff point can be used as guide evidence in several clinical judgments on the Iranian population.
