Second-trimester maternal serum markers in the prediction of preeclampsia

Machine Learning Algorithms Versus Classical Regression Models in Pre-Eclampsia Prediction: A Systematic Review

PURPOSE OF REVIEW

Machine learning (ML) approaches are an emerging alternative for healthcare risk prediction. We aimed to synthesise the literature on ML and classical regression studies exploring potential prognostic factors and to compare prediction performance for pre-eclampsia.

RECENT FINDINGS

From 9382 studies retrieved, 82 were included. Sixty-six publications exclusively reported eighty-four classical regression models to predict variable timing of onset of pre-eclampsia. Another six publications reported purely ML algorithms, whilst another 10 publications reported ML algorithms and classical regression models in the same sample with 8 of 10 findings that ML algorithms outperformed classical regression models. The most frequent prognostic factors were age, pre-pregnancy body mass index, chronic medical conditions, parity, prior history of pre-eclampsia, mean arterial pressure, uterine artery pulsatility index, placental growth factor, and pregnancy-associated plasma protein A. Top performing ML algorithms were random forest (area under the curve (AUC) = 0.94, 95% confidence interval (CI) 0.91-0.96) and extreme gradient boosting (AUC = 0.92, 95% CI 0.90-0.94). The competing risk model had similar performance (AUC = 0.92, 95% CI 0.91-0.92) compared with a neural network. Calibration performance was not reported in the majority of publications. ML algorithms had better performance compared to classical regression models in pre-eclampsia prediction. Random forest and boosting-type algorithms had the best prediction performance. Further research should focus on comparing ML algorithms to classical regression models using the same samples and evaluation metrics to gain insight into their performance. External validation of ML algorithms is warranted to gain insights into their generalisability.

Evaluation of maternal serum SERPINC1, E-selectin, P-selectin, RBP4 and PP13 levels in pregnancies complicated with preeclampsia

OBJECTIVE

The aim of this study is to investigate whether Serpin clade C (SERPINC1), E-selectin, P-selectin, Placental protein 13 (PP13), and Retinol-binding protein-4 (RBP4) levels in maternal serum were associated with the presence of preeclampsia and to compare them with uncomplicated pregnancies.

METHODS

This prospective study included 40 women with preeclampsia and 40 healthy pregnant women. An enzyme-linked immunosorbent assay kit was used to measure serum SERPINC1, E-selectin, P-selectin, PP13, and RBP4 levels.

RESULTS

The preeclampsia group had significantly higher E-selectin and P-selectin levels than the control group. PP13 and SERPINC1 levels were also significantly lower than the control group. There was no significant difference in RBP4 levels. The receiver operating characteristic curve revealed the best cutoff values for the following: E-selectin >19.2 ng/mL, with 87.5% sensitivity and 95% specificity; P-selectin >5.1 ng/mL, with 97.5% sensitivity and 100% specificity; PP13 ≤ 107.03 pg/mL, with 72.5% sensitivity and 77.5% specificity; and SERPINC1 ≤ 87.76 ng/mL, with 100% sensitivity and 97.5% specificity.

CONCLUSION

In this study, the endothelial dysfunction parameters SERPINC1, PP13, E-selectin, and P-selectin were found to be associated with preeclampsia. Endothelial dysfunction biomarkers in maternal non-serum body fluids may differ. More research is needed, especially to determine the relationship between SERPINC1 and preeclampsia.

A prediction model for cesarean delivery based on the glycemia in the second trimester: a nested case control study from two centers

OBJECTIVE

Maternal glycemia is associated with the risk of cesarean delivery (CD); therefore, our study aims to developed a prediction model based on glucose indicators in the second trimester to earlier identify the risk of CD.

METHODS

This was a nested case-control study, and data were collected from the 5th Central Hospital of Tianjin (training set) and Changzhou Second People's Hospital (testing set) from 2020 to 2021. Variables with significant difference in training set were incorporated to develop the random forest model. Model performance was assessed by calculating the area under the curve (AUC) and Komogorov-Smirnoff (KS), as well as accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULTS

A total of 504 eligible women were enrolled; of these, 169 underwent CD. Pre-pregnancy body mass index (BMI), first pregnancy, history of full-term birth, history of livebirth, 1 h plasma glucose (1hPG), glycosylated hemoglobin (HbA1c), fasting plasma glucose (FPG), and 2 h plasma glucose (2hPG) were used to develop the model. The model showed a good performance, with an AUC of 0.852 [95% confidence interval (CI): 0.809-0.895]. The pre-pregnancy BMI, 1hPG, 2hPG, HbA1c, and FPG were identifies as the more significant predictors. External validation confirmed the good performance of our model, with an AUC of 0.734 (95%CI: 0.664-0.804).

CONCLUSIONS

Our model based on glucose indicators in the second trimester performed well to predict the risk of CD, which may reach the earlier identification of CD risk and may be beneficial to make interventions in time to decrease the risk of CD.

Maternal Serum Activin A, Inhibin A and Follistatin-Related Proteins across Preeclampsia: Insights into Their Role in Pathogenesis and Prediction

BACKGROUND

Within the endocrine-paracrine signalling network at the maternal-foetal interface, the activin-inhibin-follistatin system modulates extravillous trophoblast invasion, suggesting a potential role in preeclampsia pathogenesis. This study aimed to compile the evidence published in the last decade regarding the variation in maternal serum activins, inhibin- and follistatin-related proteins in preeclamptic pregnancies compared to healthy pregnancies, and to discuss their role in predicting and understanding the pathophysiology of preeclampsia.

MATERIAL AND METHODS

A scoping review was conducted in MEDLINE, EMBASE and LILACS databases to identify studies published within the last ten years (2012-2022).

RESULTS

Thirty studies were included. None of the studies addressed maternal serum changes of isoforms different from activin A, inhibin A, follistatin, and follistatin-like 3. Sixteen studies evaluated the potential of these isoforms in predicting preeclampsia through the area under the curve from a receiver operating characteristic curve.

CONCLUSIONS

In preeclampsia, inhibin A is upregulated in all trimesters, whereas activin A increases exclusively in the late second and third trimesters. Serum follistatin levels are reduced in women with preeclampsia during the late second and third trimesters. However, changes in follistatin-like 3 remain inconclusive. Inhibin A and activin A can potentially serve as biomarkers of early-onset preeclampsia based on the outcomes of the receiver operating characteristic curve analysis. Further investigations are encouraged to explore the feasibility of quantifying maternal serum levels of activin A and inhibin A as a clinical tool in early preeclampsia prediction.

Snail mediates GDF-8-stimulated human extravillous trophoblast cell invasion by upregulating MMP2 expression

BACKGROUND

Extravillous trophoblast (EVT) cell invasion is a tightly regulated process that requires for a normal pregnancy. The epithelial-mesenchymal transition (EMT) has been implicated in EVT cell invasion. Growth differentiation factor-8 (GDF-8), a member of the transforming growth factor-beta (TGF-β) superfamily, is expressed in the human placenta and promotes EVT cell invasion by upregulating the expression of matrix metalloproteinase 2 (MMP2). However, the underlying molecular mechanism of GDF-8-induced MMP2 expression remains undetermined. Therefore, the present study aims to examine the role of Snail and Slug, the EMT-related transcriptional regulators, in GDF-8-stimulated MMP2 expression and cell invasion in HTR-8/SVneo human EVT cell line and primary cultures of human EVT cells.

METHODS

HTR-8/SVneo and primary cultures of human EVT cells were used to examine the effect of GDF-8 on MMP2 expression and explore the underlying mechanism. For gene silencing and overexpression, the HTR-8/SVneo cell line was used to make the experiments more technically feasible. The cell invasiveness was measured by Matrigel-coated transwell invasion assay.

RESULTS

GDF-8 stimulated MMP2 expression in both HTR-8/SVneo and primary EVT cells. The stimulatory effect of GDF-8 on MMP2 expression was blocked by the inhibitor of TGF-β type-I receptors, SB431542. Treatment with GDF-8 upregulated Snail and Slug expression in both HTR-8/SVneo and primary EVT cells. The stimulatory effects of GDF-8 on Snail and Slug expression were blocked by pretreatment of SB431542 and siRNA-mediated knockdown of SMAD4. Interestingly, using the siRNA knockdown approach, our results showed that Snail but not Slug was required for the GDF-8-induced MMP2 expression and cell invasion in HTR-8/SVneo cells. The reduction of MMP2 expression in the placentas with preeclampsia (PE) was also observed.

CONCLUSIONS

These findings discover the physiological function of GDF-8 in the human placenta and provide important insights into the regulation of MMP2 expression in human EVT cells. Video Abstract.

Myostatin increases human trophoblast cell invasion by upregulating N-cadherin via SMAD2/3-SMAD4 Signaling

Placental insufficiency disorders are major obstetric complications that share a common phenomenon of poor placental trophoblast cell invasion and remodeling of uterine tissues. Myostatin is a transforming growth factor (TGF)-β superfamily member well-known for its important role in muscle growth control. Myostatin is also produced in the placenta and has been shown to regulate some trophoblast functions. However, its roles in placental development are still poorly understood. In this study, we tested the hypothesis that myostatin increases trophoblast cell invasion by upregulating N-cadherin via SMAD2/3-SMAD4 signaling. Primary and immortalized (HTR8/SVneo) trophoblast cells were used as study models. Matrigel-coated transwell invasion assays were used to study the effects of recombinant human myostatin on trophoblast cell invasion. RT-qPCR and Western blot were used to measure myostatin effects on N-cadherin mRNA and protein levels, respectively. Small inhibitor molecules as well as siRNA-mediated knockdown were used to block myostatin receptor and downstream signaling, respectively. Data were analyzed either by unpaired Student T test or one-way ANOVA followed by Newman Keuls test for multiple group comparisons. Myostatin significantly increased primary and HTR8/SVneo trophoblast cell invasion. Moreover, myostatin upregulated N-cadherin mRNA and protein levels in a time dependent manner in both study models. These effects were blocked by inhibition of TGF-β type I receptors as well as siRNA-mediated knockdown of SMAD2/3 combined or common SMAD4. Importantly, myostatin-induced trophoblast cell invasion was abolished by knockdown of N-cadherin, SMAD2/3 or SMAD4. Myostatin may increase human trophoblast cell invasion by upregulating N-cadherin via SMAD2/3-SMAD4 signaling.

Association between pentraxin-3 and the risk of preeclampsia: A meta-analysis

An association between circulating pentraxin-3 (PTX3) and the risk of preeclampsia (PE) remains to be established. We performed a meta-analysis of observational studies to evaluate their relationship.The PubMed, Embase, Cochrane Library, China National Knowledge Infrastructure, and WanFang databases were searched for related observational studies evaluating PTX3 and PE risk. A random-effects or a fixed-effects model was used in the meta-analysis, depending on the heterogeneity among the included studies.Nine case-control studies were included, with 396 PE patients and 438 controls. The results showed that PTX3 was significantly higher in pregnant women with PE as compared to those without PE (standardized mean difference [SMD] = 2.48, P < .001), with significant heterogeneity (I2 = 98%), particularly for those over 30 years old (SMD = 3.75, P < .001). Subsequent analyses showed that patients with severe or early-onset PE had higher PTX3 levels compared to those with mild or late-onset PE (SMD = 0.93, P = .01), suggesting that PTX3 may be a marker of PE severity. The association between PTX3 and PE was not significantly affected by the statistical method used. Sensitivity analyses by omitting one study at a time did not significantly affect the results. However, the funnel plots were asymmetric, suggesting the potential existence of publication bias.PTX3 may be related to the risk and severity of PE in pregnant women. These results should be evaluated and confirmed in cohort studies.

Circulating pentraxin-3 and preeclampsia: a meta-analysis of 17 case-control studies

Introduction: Change of circulating pentraxin-3 (PTX-3), a novel marker of inflammation, has been observed in women with preeclampsia (PE). However, results of previous studies were inconsistent. We performed a meta-analysis to evaluate the difference of circulating PTX-3 between women with PE and normal pregnancies.Methods: Case-control studies comparing circulating PTX-3 level between women with PE and normal pregnancies were identified via search of PubMed and Embase databases according to a predefined search strategy and inclusion criteria by two independent authors. Meta-analysis was performed with a random-effect model to incorporate heterogeneity.Results: Seventeen studies including 814 women with PE and 949 women with normal pregnancy were included. Results showed that women with PE had significantly higher circulating PTX-3 at diagnosis as compared to women with normal pregnancy (standardized mean difference [SMD]: = 1.74, 95% CI: 1.20-2.29, p < .001; I² = 94%). The results were consistent regardless of study characteristics including study location, maternal age, sample size, early or late onset of PE, blood sample for PTX-3 measurement, or NOS quality scores. Moreover, higher circulating PTX-3 was also observed before the diagnosis of PE (SMD = 0.65, 95% CI: 0.02-1.29, p = .04; I² = 87%).Conclusion: Women with PE have higher circulating PTX-3 than women with normal pregnancy. The elevated PTX-3 could be observed before the clinical onset of PE. Future studies are needed to determine whether PTX-3 is an active molecular in the pathogenesis of PE.

The prediction of early preeclampsia: Results from a longitudinal proteomics study

OBJECTIVES

To identify maternal plasma protein markers for early preeclampsia (delivery <34 weeks of gestation) and to determine whether the prediction performance is affected by disease severity and presence of placental lesions consistent with maternal vascular malperfusion (MVM) among cases.

STUDY DESIGN

This longitudinal case-control study included 90 patients with a normal pregnancy and 33 patients with early preeclampsia. Two to six maternal plasma samples were collected throughout gestation from each woman. The abundance of 1,125 proteins was measured using high-affinity aptamer-based proteomic assays, and data were modeled using linear mixed-effects models. After data transformation into multiples of the mean values for gestational age, parsimonious linear discriminant analysis risk models were fit for each gestational-age interval (8-16, 16.1-22, 22.1-28, 28.1-32 weeks). Proteomic profiles of early preeclampsia cases were also compared to those of a combined set of controls and late preeclampsia cases (n = 76) reported previously. Prediction performance was estimated via bootstrap.

RESULTS

We found that 1) multi-protein models at 16.1-22 weeks of gestation predicted early preeclampsia with a sensitivity of 71% at a false-positive rate (FPR) of 10%. High abundance of matrix metalloproteinase-7 and glycoprotein IIbIIIa complex were the most reliable predictors at this gestational age; 2) at 22.1-28 weeks of gestation, lower abundance of placental growth factor (PlGF) and vascular endothelial growth factor A, isoform 121 (VEGF-121), as well as elevated sialic acid binding immunoglobulin-like lectin 6 (siglec-6) and activin-A, were the best predictors of the subsequent development of early preeclampsia (81% sensitivity, FPR = 10%); 3) at 28.1-32 weeks of gestation, the sensitivity of multi-protein models was 85% (FPR = 10%) with the best predictors being activated leukocyte cell adhesion molecule, siglec-6, and VEGF-121; 4) the increase in siglec-6, activin-A, and VEGF-121 at 22.1-28 weeks of gestation differentiated women who subsequently developed early preeclampsia from those who had a normal pregnancy or developed late preeclampsia (sensitivity 77%, FPR = 10%); 5) the sensitivity of risk models was higher for early preeclampsia with placental MVM lesions than for the entire early preeclampsia group (90% versus 71% at 16.1-22 weeks; 87% versus 81% at 22.1-28 weeks; and 90% versus 85% at 28.1-32 weeks, all FPR = 10%); and 6) the sensitivity of prediction models was higher for severe early preeclampsia than for the entire early preeclampsia group (84% versus 71% at 16.1-22 weeks).

CONCLUSION

We have presented herein a catalogue of proteome changes in maternal plasma proteome that precede the diagnosis of preeclampsia and can distinguish among early and late phenotypes. The sensitivity of maternal plasma protein models for early preeclampsia is higher in women with underlying vascular placental disease and in those with a severe phenotype.

ELABELA plasma concentrations are increased in women with late-onset preeclampsia

Objective: ELABELA is a newly discovered peptide hormone that appears to be implicated in the mechanisms leading to preeclampsia, independently of angiogenic factors. The aim of the current study was to investigate whether women with early- or late-onset preeclampsia have altered ELABELA plasma concentrations compared to gestational-age-matched normal pregnant women.Methods: This retrospective cross-sectional study focused on the maternal plasma samples collected from 232 women with a singleton pregnancy who were allocated into the following groups: (1) early-onset preeclampsia (<34 weeks of gestation, N = 56); (2) late-onset preeclampsia (≥34 weeks of gestation, N = 57); and (3) gestational-age-matched controls with a normal pregnancy [(<34 weeks of gestation, N = 59); (≥34 weeks of gestation, N = 60)]. ELABELA plasma concentrations were determined using a validated enzyme immunoassay.Results: (1) ELABELA plasma concentrations are higher in patients with late-onset preeclampsia compared with those from gestational-age-matched controls with a normal pregnancy [median: 7.99 ng/mL (IQR, 5.3-13.95 ng/mL) versus median: 4.17 ng/mL (IQR, 3-11.19 ng/mL), p =.001]; (2) ELABELA plasma concentrations in patients with early-onset preeclampsia do not differ from those of normal pregnant women [median: 6.09 ng/mL (IQR, 2.8-10.66 ng/mL) versus median: 4.02 ng/mL (IQR, 3.26-7.49), p = .32]; and (3) ELABELA plasma concentrations are higher in patients with late-onset preeclampsia compared to those with early-onset preeclampsia [median: 7.99 ng/mL (IQR, 5.3-13.95 ng/mL) versus median: 6.09 ng/mL (IQR, 2.8-10.66 ng/mL), p = .01].Conclusion: ELABELA plasma concentrations are higher in patients with late-onset preeclampsia than in those with a normal pregnancy. However, women with early-onset preeclampsia have similar ELABELA plasma concentrations to those with a normal pregnancy. These findings provide insight into the ELABELA axis during the human syndrome of preeclampsia. In addition, these data support the concept that different pathophysiologic mechanisms are implicated in early- and late-onset preeclampsia.