Validation of machine-learning model for first-trimester prediction of pre-eclampsia using cohort from PREVAL study.

OBJECTIVE: Effective first-trimester screening for pre-eclampsia (PE) can be achieved using a competing-risks model that combines risk factors from the maternal history with multiples of the median (MoM) values of biomarkers. A new model using artificial intelligence through machine-learning methods has been shown to achieve similar screening performance without the need for conversion of raw data of biomarkers into MoM. This study aimed to investigate whether this model can be used across populations without specific adaptations. METHODS: Previously, a machine-learning model derived with the use of a fully connected neural network for first-trimester prediction of early (< 34 weeks), preterm (< 37 weeks) and all PE was developed and tested in a cohort of pregnant women in the UK. The model was based on maternal risk factors and mean arterial blood pressure (MAP), uterine artery pulsatility index (UtA-PI), placental growth factor (PlGF) and pregnancy-associated plasma protein-A (PAPP-A). In this study, the model was applied to a dataset of 10 110 singleton pregnancies examined in Spain who participated in the first-trimester PE validation (PREVAL) study, in which first-trimester screening for PE was carried out using the Fetal Medicine Foundation (FMF) competing-risks model. The performance of screening was assessed by examining the area under the receiver-operating-characteristics curve (AUC) and detection rate (DR) at a 10% screen-positive rate (SPR). These indices were compared with those derived from the application of the FMF competing-risks model. The performance of screening was poor if no adjustment was made for the analyzer used to measure PlGF, which was different in the UK and Spain. Therefore, adjustment for the analyzer used was performed using simple linear regression. RESULTS: The DRs at 10% SPR for early, preterm and all PE with the machine-learning model were 84.4% (95% CI, 67.2-94.7%), 77.8% (95% CI, 66.4-86.7%) and 55.7% (95% CI, 49.0-62.2%), respectively, with the corresponding AUCs of 0.920 (95% CI, 0.864-0.975), 0.913 (95% CI, 0.882-0.944) and 0.846 (95% CI, 0.820-0.872). This performance was achieved with the use of three of the biomarkers (MAP, UtA-PI and PlGF); inclusion of PAPP-A did not provide significant improvement in DR. The machine-learning model had similar performance to that achieved by the FMF competing-risks model (DR at 10% SPR, 82.7% (95% CI, 69.6-95.8%) for early PE, 72.7% (95% CI, 62.9-82.6%) for preterm PE and 55.1% (95% CI, 48.8-61.4%) for all PE) without requiring specific adaptations to the population. CONCLUSIONS: A machine-learning model for first-trimester prediction of PE based on a neural network provides effective screening for PE that can be applied in different populations. However, before doing so, it is essential to make adjustments for the analyzer used for biochemical testing. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

Comparison of different methods of first-trimester screening for preterm pre-eclampsia: cohort study.

OBJECTIVE: To compare the predictive performance of three different mathematical models for first-trimester screening of pre-eclampsia (PE), which combine maternal risk factors with mean arterial pressure (MAP), uterine artery pulsatility index (UtA-PI) and serum placental growth factor (PlGF), and two risk-scoring systems. METHODS: This was a prospective cohort study performed in eight fetal medicine units in five different regions of Spain between September 2017 and December 2019. All pregnant women with singleton pregnancy and a non-malformed live fetus attending their routine ultrasound examination at 11 + 0 to 13 + 6 weeks' gestation were invited to participate in the study. Maternal characteristics and medical history were recorded and measurements of MAP, UtA-PI, serum PlGF and pregnancy-associated plasma protein-A (PAPP-A) were converted into multiples of the median (MoM). Risks for term PE, preterm PE (< 37 weeks' gestation) and early PE (< 34 weeks' gestation) were calculated according to the FMF competing-risks model, the Crovetto et al. logistic regression model and the Serra et al. Gaussian model. PE classification was also performed based on the recommendations of the National Institute for Health and Care Excellence (NICE) and the American College of Obstetricians and Gynecologists (ACOG). We estimated detection rates (DR) with their 95% CIs at a fixed 10% screen-positive rate (SPR), as well as the area under the receiver-operating-characteristics curve (AUC) for preterm PE, early PE and all PE for the three mathematical models. For the scoring systems, we calculated DR and SPR. Risk calibration was also assessed. RESULTS: The study population comprised 10 110 singleton pregnancies, including 32 (0.3%) that developed early PE, 72 (0.7%) that developed preterm PE and 230 (2.3%) with any PE. At a fixed 10% SPR, the FMF, Crovetto et al. and Serra et al. models detected 82.7% (95% CI, 69.6-95.8%), 73.8% (95% CI, 58.7-88.9%) and 79.8% (95% CI, 66.1-93.5%) of early PE; 72.7% (95% CI, 62.9-82.6%), 69.2% (95% CI, 58.8-79.6%) and 74.1% (95% CI, 64.2-83.9%) of preterm PE; and 55.1% (95% CI, 48.8-61.4%), 47.1% (95% CI, 40.6-53.5%) and 53.9% (95% CI, 47.4-60.4%) of all PE, respectively. The best correlation between predicted and observed cases was achieved by the FMF model, with an AUC of 0.911 (95% CI, 0.879-0.943), a slope of 0.983 (95% CI, 0.846-1.120) and an intercept of 0.154 (95% CI, -0.091 to 0.397). The NICE criteria identified 46.7% (95% CI, 35.3-58.0%) of preterm PE at 11% SPR and ACOG criteria identified 65.9% (95% CI, 55.4-76.4%) of preterm PE at 33.8% SPR. CONCLUSIONS: The best performance of screening for preterm PE is achieved by mathematical models that combine maternal factors with MAP, UtA-PI and PlGF, as compared to risk-scoring systems such as those of NICE and ACOG. While all three algorithms show similar results in terms of overall prediction, the FMF model showed the best performance at an individual level. © 2024 International Society of Ultrasound in Obstetrics and Gynecology.

Performance of first-trimester combined screening for preterm pre-eclampsia: findings from cohort of 10 110 pregnancies in Spain.

OBJECTIVE: To evaluate the diagnostic accuracy of the Fetal Medicine Foundation (FMF) competing-risks model, incorporating maternal characteristics, mean arterial pressure (MAP), uterine artery pulsatility index (UtA-PI) and placental growth factor (PlGF) (the 'triple test'), for the prediction at 11-13 weeks' gestation of preterm pre-eclampsia (PE) in a Spanish population. METHODS: This was a prospective cohort study performed in eight fetal medicine units in five different regions of Spain between September 2017 and December 2019. All pregnant women with a singleton pregnancy and a non-malformed live fetus attending a routine ultrasound examination at 11 + 0 to 13 + 6 weeks' gestation were invited to participate. Maternal demographic characteristics and medical history were recorded and MAP, UtA-PI, serum PlGF and pregnancy-associated plasma protein-A (PAPP-A) were measured following standardized protocols. Treatment with aspirin during pregnancy was also recorded. Raw values of biomarkers were converted into multiples of the median (MoM), and audits were performed periodically to provide regular feedback to operators and laboratories. Patient-specific risks for term and preterm PE were calculated according to the FMF competing-risks model, blinded to pregnancy outcome. The performance of screening for PE, taking into account aspirin use, was assessed by calculating the area under the receiver-operating-characteristics curve (AUC) and detection rate (DR) at a 10% fixed screen-positive rate (SPR). Risk calibration of the model was assessed. RESULTS: The study population comprised 10 110 singleton pregnancies, including 72 (0.7%) that developed preterm PE. In the preterm PE group, compared to those without PE, median MAP MoM and UtA-PI MoM were significantly higher, and median serum PlGF MoM and PAPP-A MoM were significantly lower. In women with PE, the deviation from normal in all biomarkers was inversely related to gestational age at delivery. Screening for preterm PE by a combination of maternal characteristics and medical history with MAP, UtA-PI and PlGF had a DR, at 10% SPR, of 72.7% (95% CI, 62.9-82.6%). An alternative strategy of replacing PlGF with PAPP-A in the triple test was associated with poorer screening performance for preterm PE, giving a DR of 66.5% (95% CI, 55.8-77.2%). The calibration plot showed good agreement between predicted risk and observed incidence of preterm PE, with a slope of 0.983 (95% CI, 0.846-1.120) and an intercept of 0.154 (95% CI, -0.091 to 0.397). CONCLUSIONS: The FMF model is effective in predicting preterm PE in the Spanish population at 11-13 weeks' gestation. This method of screening is feasible to implement in routine clinical practice, but it should be accompanied by a robust audit and monitoring system, in order to maintain high-quality screening. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.