To explore the potential value of a third trimester screening based on estimated fetal weight centile (EFWc) versus a combined model composed by maternal characteristics, ultrasound and biochemical markers for the prediction of smallness for gestational age (SGA) and late-onset fetal growth restriction (FGR). Nested case–control study within a cohort of 1590 singleton gestations referred for third-trimester evaluation (32–36 weeks). Maternal characteristics, fetoplacental ultrasound and circulating biochemical markers [PlGF, lipocalin-2, estriol, and inhibin-A] were assessed in all women who subsequently delivered a SGA neonate (BW < 10th centile; n = 175) and in a control group (n = 875). SGA cases with a BW <3rd centile and/or abnormal uterine artery (UtA) Doppler and/or abnormal cerebroplacental ratio were classified as FGR. Logistic regression predictive models were developed for SGA and FGR, and their performance was compared to that obtain using EFWc alone. Using EFWc alone, 52% (AUC 0.82, 95% CI 0.77-0.85) and 64% (AUC 0.86 95% CI 0.81-0.91) of SGA and FGR cases were predicted at a 10% FPR, respectively. At a 10% FPR, a screening model combining maternal characteristics, EFWc, UtA Doppler, PlGF, and estriol, predicted 61% [AUC 0.86 (95% CI 0.83-0.89)] and 77% [AUC 0.92 (95% CI 0.88-0.95)] of SGA and FGR cases, respectively. The DR of a combined model for the prediction of SGA and FGR performs significantly better than that obtained using EFWc alone (p < 0.05). Supporting information can be found in the online version of this abstract Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.