Background: To establish and verify a nomogram model that can predict the risk of macrosomia in patients with gestational diabetes mellitus (GDM).
Methods: Data of patients with GDM who delivered their babies in Shanxi Bethune Hospital between November 2020 and February 2022 were analyzed. Multifactor logistic regression analysis was used to screen the independent risk factors for macrosomia. The model was constructed by R software. The area under the receiver operating characteristic curve (AUC) and goodness-of-fit analysis were used to evaluate its efficiency and accuracy. The clinical application value was evaluated using the decision curve analysis (DCA).
Results: A total of 991 patients with GDM were enrolled for modeling. Multigravida, pre-pregnancy body mass index, family history of hypertension, abdominal circumference, and biparietal diameter were independent risk factors for macrosomia, and the prediction model was established. The AUC in the training and test set were 0.93 (0.89-0.97) and 0.90 (0.84-0.96), respectively, and the difference was not statistically significant. The DCA suggested that the model has a high clinical application value.
Conclusion: The nomogram model for predicting macrosomia in patients with GDM was established. The model has certain accuracy and is expected to be a quantitative tool to guide clinical decision of delivery timing, individualized labor monitoring, and delivery mode.
Keywords: Gestational diabetes mellitus; macrosomia; nomogram; prediction model.