Delayed onset of lactogenesis can complicate early postpartum recovery in women with gestational diabetes mellitus (GDM), highlighting the need for early risk identification. A prospective study published in Frontiers in Clinical Diabetes and Healthcare developed and validated a clinical prediction model to estimate this risk.

The study enrolled 511 mothers with GDM from seven tertiary hospitals across five cities in Guangdong Province, China, between October 2023 and December 2024. Using univariate, least absolute shrinkage and selection operator (LASSO), and logistic regression analyses, the model identified independent predictors of delayed lactogenesis and generated a nomogram for clinical application.

Significant predictors included pre-delivery body mass index (BMI), Edinburgh Postnatal Depression Scale score, serum albumin levels, LATCH score, and glycemic control during pregnancy. The model demonstrated strong discrimination with an area under the receiver operating characteristic curve (AUC) of 0.828 (95% CI 0.779-0.877), with sensitivity of 70.9% and specificity of 83.7% at an optimal cutoff of 0.341.

Internal validation showed consistent performance with an AUC of 0.806 (95% CI 0.728-0.884). Calibration analysis demonstrated agreement between predicted and observed outcomes, supported by a non-significant Hosmer-Lemeshow test (χ² = 7.226; p = 0.546). Decision curve analysis indicated clinical utility across relevant thresholds.

These findings support the use of a validated prediction model to estimate delayed lactogenesis risk in women with GDM, enabling early identification and targeted postpartum support.