WBC

This study aimed to develop a risk prediction model for gestational diabetes mellitus (GDM) using maternal demographics and routine clinical variables in a Chinese population. Data from 3,263 pregnant women (17.2% with GDM) were analyzed. The predictive model incorporated variables such as maternal age, pre-pregnancy BMI, early pregnancy weight gain, history of GDM, family history of diabetes, sex hormone usage, fasting glucose, triglycerides, white blood cell count, and positive urinary glucose. The model showed good consistency between predicted and actual data (Hosmer-Lemeshow test, p = 0.586) and demonstrated fair discriminatory ability with an area under the ROC curve (AUC) of 0.720 (95% CI: 0.697–0.744). Internal validity was confirmed via fivefold cross-validation, and clinical utility was supported by decision curve analysis. A user-friendly nomogram was created to facilitate clinical implementation of the scoring system for GDM risk assessment.