N-terminal pro-brain natriuretic peptide (NT-proBNP) and uric acid are elevated in pregnancies with preeclampsia (PE). Short-term prediction of PE using angiogenic factors has many false-positive results. Our objective was to validate a machine-learning model (MLM) to predict PE in patients with clinical suspicion, and evaluate if the model performed better than the sFlt-1/PlGF ratio alone. A multicentric cohort study of pregnancies with suspected PE between 24⁺⁰ and 36⁺⁶ weeks was used. The MLM included six predictors: gestational age, chronic hypertension, sFlt-1, PlGF, NT-proBNP, and uric acid. A total of 936 serum samples from 597 women were included. The PPV of the MLM for PE following 6 weeks was 83.1% (95% CI 78.5–88.2) compared to 72.8% (95% CI 67.4–78.4) for the sFlt-1/PlGF ratio. The specificity of the model was better; 94.9% vs. 91%, respectively. The AUC was significantly improved compared to the ratio alone [0.941 (95% CI 0.926–0.956) vs. 0.901 (95% CI 0.880–0.921), p < 0.05]. For prediction of preterm PE within 1 week, the AUC of the MLM was 0.954 (95% CI 0.937–0.968); significantly greater than the ratio alone [0.914 (95% CI 0.890–0.934), p < 0.01]. To conclude, an MLM combining the sFlt-1/PlGF ratio, NT-proBNP, and uric acid performs better to predict preterm PE compared to the sFlt-1/PlGF ratio alone, potentially increasing clinical precision.

Algorithms for first-trimester prediction of pre-eclampsia usually include maternal risk factors, blood pressure, placental growth factor (PlGF), and uterine artery Doppler pulsatility index. However, these models lack sensitivity for the prediction of late-onset pre-eclampsia and other placental complications of pregnancy, such as small for gestational age infants or preterm birth. The aim of this study was to assess the screening performance of PlGF, soluble fms-like tyrosine kinase-1 (sFlt-1), N-terminal pro-brain natriuretic peptide (NT-proBNP), uric acid, and high-sensitivity cardiac troponin T (hs-TnT) in the prediction of adverse obstetric outcomes related to placental insufficiency. This retrospective case–control study was based on a cohort of 1390 pregnant women, among which 210 presented pre-eclampsia, small for gestational age infants, or preterm birth. Two hundred and eight women with healthy pregnancies were selected as controls. Serum samples were collected between weeks 9 and 13 of gestation, and maternal serum concentrations of PlGF, sFlt-1, NT-proBNP, uric acid, and hs-TnT were measured. Multivariate regression analysis was used to generate predictive models combining maternal factors with the above-mentioned biomarkers. Women with placental dysfunction had lower median concentrations of PlGF (25.77 vs. 32.00 pg/mL; p < 0.001), sFlt-1 (1212.0 vs. 1363.5 pg/mL; p = 0.001), and NT-proBNP (51.22 vs. 68.71 ng/L; p < 0.001) and higher levels of uric acid (193.66 µmol/L vs. 177.40 µmol/L; p = 0.001). There was no significant difference between groups regarding the sFlt-1/PlGF ratio. Hs-TnT was not detected in 70% of the maternal serums analyzed. Altered biomarker concentrations increased the risk of the analyzed complications both in univariate and multivariate analyses. The addition of PlGF, sFlt-1, and NT-proBNP to maternal variables improved the prediction of pre-eclampsia, small for gestational age infants, and preterm birth (area under the curve: 0.710, 0.697, 0.727, and 0.697 vs. 0.668, respectively). Reclassification improvement was greater in maternal factors plus the PlGF model and maternal factors plus the NT-p roBNP model (net reclassification index, NRI: 42.2% and 53.5%, respectively). PlGF, sFlt-1, NT-proBNP, and uric acid measurements in the first trimester of pregnancy, combined with maternal factors, can improve the prediction of adverse perinatal outcomes related to placental dysfunction. In addition to PlGF, uric acid and NT-proBNP are two promising predictive biomarkers for placental dysfunction in the first trimester of pregnancy.