Prediction of Gestational Diabetes Mellitus (GDM) risk in early pregnancy based on clinical data and ultrasound information: a nomogram.

Background: Gestational diabetes mellitus (GDM) is one of the most common complications during pregnancy and has been on a continuous increase in recent years. This study aimed to establish a combined prediction model for the risk of GDM and to provide more reliable reference information for non-invasive assessment of GDM in clinical practice.

Methods: This study retrospectively collected clinical data and ultrasound information of 122 pregnant women who underwent fetal nuchal translucency screening, which divided into 36 cases of the GDM group and 86 cases of the non-gestational diabetes mellitus(NGDM) group. The collected clinical data and ultrasound information were analyzed using Student's t-test and Wilcoxon W test for univariate analysis. Independent risk factors for patients with GDM were screened through binary logistic regression analysis. A model was established based on the screened results, and the diagnostic performance of different models was evaluated by drawing the receiver operating characteristic curve(ROC). The optimal prediction model was selected, and the calibration curve and clinical decision curve were drawn to evaluate the goodness of fit and clinical application efficiency of the model.

Results: Univariate results showed that age, body mass index(BMI), number of abortions, gravidity, placental volume(PV), vascularization index(VI), flow index(FI), and vascularization flow index(VFI) all had statistically significant differences between the GDM and NGDM groups(p < 0.05). Binary logistic regression analysis showed that BMI, number of abortions, PV, VI, and FI were independent risk factors for the development of GDM in pregnant women (p < 0.05). Based on these results, five prediction models were established in this study. Their area under the ROC curve(AUC) were 0.67, 0.80, 0.80, 0.87, and 0.85, respectively. The model combining clinical data with 30° ultrasound data had the highest AUC, so we constructed a nomogram for this model. The results of its calibration curve showed that the model had a good fit, and the results of the clinical decision curve showed that the model had good clinical application efficiency.

Conclusion: The nomogram model combining clinical data with 30° ultrasound data has good accuracy and clinical application value for predicting the risk of GDM.