Early identification of diabetic retinopathy (DR) remains important for preventing vision-related complications in individuals with type 2 diabetes mellitus (T2DM). A retrospective cohort study published in Diabetes, Metabolic Syndrome and Obesity evaluated a predictive nomogram designed to estimate DR risk in young and middle-aged patients with T2DM.

The study included 337 patients aged 15–59 years who were admitted to Luoyang Central Hospital between July 2022 and January 2024. The Fundus examination categorized participants into DR (n = 155) and non-DR (n = 182) groups. Demographic characteristics and clinical variables were collected, and significant predictors were identified using multivariable logistic regression. A nomogram for DR risk estimation was subsequently constructed and evaluated using calibration plots, receiver operating characteristic analysis, and decision curve analysis.

Multivariable analysis identified four predictors related to DR detection. These included diabetes duration (OR 1.125; 95% CI 1.07-1.182; P<0.001), brachial–ankle pulse wave velocity (OR 1.269; 95% CI 1.133-1.421; P<0.001), blood urea nitrogen (OR 1.223; 95% CI 1.052-1.423; P = 0.009), and age (OR 0.955; 95% CI 0.922–0.989; P = 0.01).

The predictive model demonstrated discrimination with an area under the curve of 0.75 (95% CI 0.696-0.800). The model showed improved discrimination compared with individual predictors, with increases in AUC ranging from 0.05 to 0.18. Calibration assessment showed a bootstrap C-index of 0.749. Decision curve analysis indicated clinical utility across threshold probabilities between 2% and 85%. These findings describe a nomogram integrating routine clinical parameters to estimate DR risk in younger adults with T2DM.