BUN

This study aimed to develop and evaluate a predictive nomogram for early assessment of gestational diabetes mellitus (GDM) risk factors during early pregnancy to assist with clinical management and intervention. A total of 824 pregnant women from Zhongnan Hospital of Wuhan University and the Maternal and Child Health Hospital of Hubei Province were enrolled in a retrospective observational study, forming the training dataset. Routine clinical and laboratory data were collected, and least absolute shrinkage and selection operator (LASSO) logistic regression and multivariate ROC risk analysis were used to identify significant predictors for the nomogram. Five key risk predictors were identified: age, blood urea nitrogen (BUN), fibrinogen-to-albumin ratio (FAR), blood urea nitrogen-to-creatinine ratio (BUN/Cr), and blood urea nitrogen-to-albumin ratio (BUN/ALB). The nomogram was evaluated using ROC curve, C-index, calibration curve, and decision curve analysis (DCA) with a validation dataset of 392 early pregnancy files. The results showed that the nomogram demonstrated optimal predictive power, and DCA indicated its clinical applicability. The study concluded that the established nomogram can help predict GDM and support early clinical management and intervention during pregnancy.