27-LB: A Prediction Model for Diabetic Retinopathy Based on Plasma Adipokines among Patients with Type 2 Diabetes

Abstract

Background: Accumulating evidence has suggested a link between adipokines and diabetic retinopathy (DR). This study aimed to investigate the risk factors for sight-threatening DR (STDR) and establish a prognostic model for predicting STDR among patients with type 2 diabetes mellitus (T2DM). Methods: In the case-control set, principal component analysis (PCA) was performed to select optimal predictive cytokines for STDR. Support vector machine (SVM) was used to examine the possible combination of baseline plasma adipokines to discriminate the mild participants who will later develop STDR. An individual prospective cohort with a follow-up period of 3 years was used for the external validation. Results: In both training and testing sets, comprised of 306 patients with DR, median levels of plasma adiponectin, leptin, and fatty acid-binding protein 4 (FABP4) were significantly higher in the STDR group than those in mild DR. Except for adipsin, the other three adipokines, FABP4, adiponectin, and leptin, were selected by PCA and integrated into SVM. The accuracy of the multivariate SVM classification model was acceptable in both the training set (AUC = 0.81, sensitivity = 71%, specificity = 91%) and the testing set (AUC = 0.77, sensitivity = 61%, specificity = 92%). 110 T2DM mild NPDR patients were enrolled for external validation. High- and low-risk groups were grouped by the median value of adiponectin, FABP4, and leptin. More STDR occurred in the high-risk group than in the low-risk group among the three predictors. SVM demonstrated acceptable performance, with the AUC, sensitivity, and specificity of 0.77, 64%, and 91%, respectively. Conclusions: Adiponectin, leptin, and FABP4 were demonstrated to be associated with the severity of DR and maybe good predictors for STDR, suggesting that adipokines may play an important role in the pathophysiology of DR development. Disclosure Y. An: None. J. Ke: None. D. Zhao: None.