Development of a nomogram model for individualized prediction of fetal growth restriction in pregnant women with iron deficiency anemia.

PURPOSE: To develop a nomogram model for individualized prediction of fetal growth restriction (FGR) among pregnant women with iron deficiency anemia (IDA) and to evaluate its predictive performance and clinical utility.

METHODS

A retrospective study was conducted on 351 pregnant women diagnosed with IDA between December 2017 and October 2024. After excluding 95 participants based on predefined criteria, 256 women were included and divided into a training cohort (n = 179) and an internal test cohort (n = 77) at a ratio of 7:3 for model construction and internal validation, respectively. Least absolute shrinkage and selection operator (LASSO) regression was used to identify independent risk factors and construct the nomogram. The model's performance was evaluated based on discrimination (ROC curve and AUC), calibration (calibration curves), and clinical utility (Decision Curve Analysis).

RESULTS

Six independent predictors for FGR were identified: red blood cell count (RBC), hemoglobin (Hb), serum ferritin (SF), folic acid supplementation, gestational diabetes mellitus (GDM), and hypertensive disorders of pregnancy (HDP). The nomogram demonstrated excellent discriminative ability, with an AUC of 0.972 (95% CI: 0.946-0.998) in the training cohort and 0.950 (95% CI: 0.892-1.000) in the internal test cohort. Calibration curves showed high consistency between predicted and observed outcomes, and DCA confirmed the model's substantial net clinical benefit.

CONCLUSION

The individualized nomogram model based on clinical and hematological parameters provides an accurate and practical tool for predicting FGR in women with gestational anemia due to IDA, offering substantial potential for clinical risk stratification and early intervention.