sFlt-1/PlGF ratio for the prediction of delivery within 48 hours and adverse outcomes in expectantly managed early-onset preeclampsia

Does a sFlt-1/PlGF ratio result > 655 before 34 weeks' gestation necessitate preterm delivery within 2 days? A retrospective observational study

INTRODUCTION

Preeclampsia is associated with adverse perinatal outcomes, including fetal growth restriction (FGR) and preterm delivery. The maternal serum ratio of soluble fms-like tyrosine kinase receptor-1 (sFlt-1) to placental growth factor (PlGF) can be used to evaluate placental dysfunction in cases of preeclampsia and FGR. A need for delivery within 2 days has been recommended for sFlt-1/PlGF ratios > 655 (normal ratio < 38) measured before 34 weeks' gestation. However, few studies have assessed this recommendation in a real-world setting and there remains a need for further evidence-based guidance on the use of the ratio in delivery timing planning in this situation.

AIM

To assess the need for delivery within 2 days associated with sFlt-1/PlGF ratios > 655 before 34 weeks' gestation.

METHODS

A retrospective audit of all sFlt-1/PlGF ratio test results obtained at a single maternity hospital between September 2016 and November 2022. The primary outcome was time to delivery after recording a ratio > 655 in patients with a pregnancy between 20 + 0 and 33 + 6 weeks' gestation. Statistical analysis was performed using IBM SPSS Statistics v29.0.0.0.

RESULTS

During the study period a total of 33 patients with suspected or confirmed preeclampsia and/or FGR recorded sFlt-1/PlGF ratios > 655 before 34 + 0 weeks' gestation. Amongst cases with ratios > 655, median time to delivery was 4 days (IQR 1.0-9.0), with 14 (42.4%) delivering in ≤ 2 days, 8 (24.2%) delivering between 2 and 7 days and 11 (33.3%) delivering after 7 days. A significant inverse correlation was observed between time to delivery and gestational age at the time of ratio testing (rs = -0.484, p = 0.004).

DISCUSSION

This study provides updated recommendations on the use of the sFlt-1/PlGF ratio in predicting the risk of imminent delivery amongst those with high ratios > 655 measured before 34 weeks' gestation. Our results suggest that the risk of imminent delivery can be stratified based on ratio level and gestational age, which in combination with the results of other clinical assessments, can be used to plan delivery timing and allow for considerations of fetal lung maturing corticosteroid and neuroprotective magnesium sulfate therapies prior to delivery.

Prediction of adverse maternal and perinatal outcomes associated with pre-eclampsia and hypertensive disorders of pregnancy: a systematic review and meta-analysis

Background

Hypertensive disorders of pregnancy are a leading cause of maternal and perinatal morbidity and mortality. If women at high risk for developing complications could be identified early, level of care could be triaged, limited resources could be correctly allocated and targeted interventions to prevent complications could be implemented.

Methods

We updated a systematic review and meta-analysis and added single outcomes. Women with hypertensive disorders of pregnancy were included. Exposures were tests predicting adverse maternal and/or perinatal outcomes. We searched Medline, Embase, CINAHL, and Cochrane library from January 2016-February 2024. We included studies identified from the previous review. We calculated effect measures. For similar predictive tests and outcomes, area under the receiver-operating-characteristic curve (AUROC) were pooled. This study was registered by PROSPERO: CRD42022336368.

Findings

Of the 2898 studies identified, 80 were included. Thirty were added from the previous review resulting in 110 included studies with 506,178 women. Despite more than 1500 tests being performed, most outcomes could not be pooled due to heterogeneity in populations, tests, and outcome definitions. For maternal outcomes, only studies reporting on the Pre-eclampsia Integrated Estimate of RiSk (fullPIERS) model could be pooled. For the composite outcome within 48-h the AUROC was 0.78 (95% CI 0.71-0.86, N = 8). There was significant heterogeneity (I 2  = 95.7%). For perinatal outcomes, data were pooled for pulsatility index in the umbilical artery and soluble FMS-like tyrosine kinase-1 (sFlt-1)/placental growth factor (PlGF) ratio. Biomarkers like the sFlt-1/PlGF ratio showed promising predictive performance for some outcomes but were not externally validated.

Interpretation

Despite including over 100 studies with more than 1500 predictors, we were unable to pool any single maternal outcomes and only a few individual perinatal outcomes. The fullPIERS model was externally validated, showing moderate accuracy which varied across studies and should be validated in each new population. Angiogenic biomarkers showed promise but need validation. Future studies should use standardized outcome measures and validate promising tests.

Funding

VB is supported by the Swedish Research Council, Grant number 2020-01481. University of Gothenburg.

sFlt-1/PlGF ratio predicts serious outcomes in confirmed early-onset preeclampsia

OBJECTIVES

We aimed to determine whether a high ratio of soluble fms-like tyrosine kinase-1 (sFlt-1) to placental growth factor (PlGF) would be associated with serious negative consequences and shorter pregnancy duration in cases of early-onset preeclampsia (PE).

STUDY DESIGN

This retrospective cohort study included women (n = 65) diagnosed with PE at <34.0 weeks of gestation and recruited from a single primary and tertiary medical centre in Japan. The sFlt-1/PlGF ratio in the study participants was measured. To determine the optimal threshold for the sFlt-1/PlGF ratio, a receiver operating characteristic curve was employed, with the aim of predicting serious adverse outcomes within 1 week after serum angiogenic marker measurements. We performed Kaplan-Meier analysis and the log-rank test to assess delivery probability based on the sFlt-1/PlGF ratio.

RESULTS

Thirty-seven women (56.9 %) delivered within 1 week of serum angiogenic marker measurements due to the aggravation of early-onset preeclampsia. Women who developed serious adverse outcomes within 1 week had a significantly higher sFlt-1/PlGF ratio than that of women who did not develop serious complications (408.5 vs. 166.6, P < 0.001). A cut-off value of 224.6 for the sFlt-1/PlGF ratio predicted serious adverse outcomes, with a sensitivity of 81.1 % and a specificity of 71.4 % (area under the curve: 0.77). Moreover, 78.9 % of women with an sFlt-1/PlGF ratio ≥ 224.6 compared to 25.9 % of those with an sFlt-1/PlGF ratio < 224.6 delivered within 1 week of presentation (P < 0.001).

CONCLUSIONS

Women with confirmed early-onset preeclampsia and high sFlt-1/PlGF ratio are more likely to develop serious adverse outcomes within 1 week after serum angiogenic marker measurements.

Trends in antenatal corticosteroid administration: did our timing improve?

OBJECTIVES

We aimed to analyze trends in the rate of effective antenatal corticosteroid prophylaxis (ACS) administrations across a spectrum of typical diagnoses associated with preterm birth.

METHODS

In this retrospective study we utilized delivery data after ACS from 2014 to 2020 at Charité Berlin, Germany. We evaluated the rate of effective ACS administrations defined as ≤10 days between last dose of ACS and delivery as well as the rate of post-ACS births on/after 37 + 0 weeks. We explored conditions associated with high rates of ineffective ACS administrations (>10 days before delivery). We analyzed the trend of ACS-effectiveness during the study period in the overall cohort and in placental dysfunction and cervical insufficiency diagnoses.

RESULTS

The overall rate of effective ACS administrations was 42 % (709/1,672). The overall percentage of deliveries after/at 37 + 0 weeks following ACS administration was 19 % (343). Placenta previa, twin pregnancy and isthmocervical insufficiency were associated with ineffective ACS (19-34 % effective i.e. ≤10 days before delivery). The overall ratio of effective ACS applications rose over time (p=0.002). Over the course of this study ACS effectiveness increased in placental dysfunction and isthmocervical insufficiency diagnoses (p=0.028; p=0.001).

CONCLUSIONS

Compared to a previous publication we found a decrease of post-ACS deliveries after/at 37 + 0 weeks (19 vs. 27 %). Ineffective ACS administrations are still frequent in patients with placenta previa, twin pregnancy and isthmocervical insufficiency. It remains to be investigated in future trials if the introduction of new diagnostic tools such as soluble Fms-like tyrosinkinase-1/placental growth factor (sFlt-1/PlGF) testing and placental alpha-microglobulin-1 (PAMG-1) testing directly led to an increased ACS effectiveness.

Bowtie Nanoantenna LSPR Biosensor for Early Prediction of Preeclampsia

OBJECTIVE

The concentration of the placental circulating factor in early pregnancy is often extremely low, and the traditional prediction method cannot meet the clinical demand for early detection preeclampsia in high-risk gravida. It is of prime importance to seek an ultra-sensitive early prediction method.

METHODS

In this study, finite-different time-domain (FDTD) and Discrete Dipole Approximation (DDA) simulation, and electron beam lithography (EBL) methods were used to develop a bowtie nanoantenna (BNA) with the best field enhancement and maximum coupling efficiency. Bio-modification of the placental circulating factor (sFlt-1, PLGF) to the noble nanoparticles based on the amino coupling method were explored. A BNA LSPR biosensor which can specifically identify the placental circulating factor in preeclampsia was constructed.

RESULTS

The BNA LSPR biosensor can detect serum placental circulating factors without toxic labeling. Serum sFlt-1 extinction signal (Δλmax) in the preeclampsia group was higher than that in the normal pregnancy group (14.37 ± 2.56 nm vs. 4.21 ± 1.36 nm), p = 0.008, while the serum PLGF extinction signal in the preeclampsia group was lower than that in the normal pregnancy group (5.36 ± 3.15 nm vs. 11.47 ± 4.92 nm), p = 0.013. The LSPR biosensor detection results were linearly consistent with the ELISA kit.

CONCLUSIONS

LSPR biosensor based on BNA can identify the serum placental circulating factor of preeclampsia with high sensitivity, without toxic labeling and with simple operation, and it is expected to be an early detection method for preeclampsia.

Longitudinal assessment of angiogenic markers in prediction of adverse outcome in women with confirmed pre-eclampsia

OBJECTIVES

Angiogenic marker assessment, such as the ratio of soluble fms-like tyrosine kinase-1 (sFlt-1) to placental growth factor (PlGF), is known to be a useful tool in the prediction of pre-eclampsia (PE). However, evidence from surveillance strategies in pregnancies with a PE diagnosis is lacking. Therefore, we aimed to assess the predictive performance of longitudinal maternal serum angiogenic marker assessment for both maternal and perinatal adverse outcomes when compared to standard laboratory parameters in pregnancies with confirmed PE.

METHODS

This was a retrospective analysis of prospectively collected data from January 2013 to December 2020 at the Medical University of Vienna. The inclusion criteria were singleton pregnancy with confirmed PE and post-diagnosis maternal serum angiogenic marker assessment at a minimum of two timepoints. The primary outcome was the predictive performance of longitudinal sFlt-1 and PlGF assessment for adverse maternal and perinatal outcomes compared to conventional laboratory monitoring at the same time in pregnancies with confirmed PE. Composite adverse maternal outcome included intensive care unit admission, pulmonary edema, eclampsia and/or death. Composite adverse perinatal outcome included stillbirth, neonatal death, placental abruption, neonatal intensive care unit admission, intraventricular hemorrhage, necrotizing enterocolitis, respiratory distress syndrome and/or mechanical ventilator support.

RESULTS

In total, 885 post-diagnosis sFlt-1/PlGF ratio measurements were obtained from 323 pregnant women with confirmed PE. For composite adverse maternal outcome, the highest standalone predictive accuracy was obtained using maternal serum sFlt-1/PlGF ratio (area under the receiver-operating-characteristics curve (AUC), 0.72 (95% CI, 0.62-0.81)), creatinine (AUC, 0.71 (95% CI, 0.62-0.81)) and lactate dehydrogenase (LDH) levels (AUC, 0.73 (95% CI, 0.65-0.81)). Maternal platelet levels (AUC, 0.65 (95% CI, 0.55-0.74)), serum alanine aminotransferase (ALT) (AUC, 0.59 (95% CI, 0.49-0.69)) and aspartate aminotransferase (AST) (AUC, 0.61 (95% CI, 0.51-0.71) levels had poor standalone predictive accuracy. The best prediction model consisted of a combination of maternal serum LDH, creatinine levels and sFlt-1/PlGF ratio, which had an AUC of 0.77 (95% CI, 0.68-0.85), significantly higher than sFlt-1/PlGF ratio alone (P = 0.037). For composite adverse perinatal outcome, the highest standalone predictive accuracy was obtained using maternal serum sFlt-1/PlGF ratio (AUC, 0.82 (95% CI, 0.75-0.89)) and creatinine (AUC, 0.74 (95% CI, 0.67-0.80)) levels, sFlt-1/PlGF ratio being superior to creatinine alone (P < 0.001). Maternal serum LDH levels (AUC, 0.65 (95% CI, 0.53-0.74)), platelet count (AUC, 0.57 (95% CI, 0.44-0.67)), ALT (AUC, 0.58 (95% CI, 0.48-0.67)) and AST (AUC, 0.58 (95% CI, 0.48-0.67)) levels had poor standalone predictive accuracy. No combination of biomarkers was superior to maternal serum sFlt-1/PlGF ratio alone for prediction of composite adverse perinatal outcome (P > 0.05 for all).

CONCLUSIONS

In pregnancies with confirmed PE, longitudinal maternal serum angiogenic marker assessment is a good predictor of adverse maternal and perinatal outcomes and superior to some conventional laboratory parameters. Further studies should focus on optimal surveillance following diagnosis of PE. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Correlation of sFlt/PlGF ratio with severity of preeclampsia in an Indian population

Background

Preeclampsia affects 2% to 8% of pregnant women and significantly increases the risk for maternal and perinatal morbidity, especially in low- and middle-income countries. There is increasing evidence to support the use of biochemical markers such as placental growth factor and soluble fms-like tyrosine kinase-1 in predicting the severity of preeclampsia and to rule out severe disease in clinical conditions masquerading as severe preeclampsia.

OBJECTIVE

This study aimed to assess the role of the sFlt-1/PlGF ratio in predicting adverse perinatal and maternal outcomes in women with preeclampsia in a South Asian population with a higher rate of the disease and its associated complications.

STUDY DESIGN

This was a prospective cohort study of women diagnosed with preeclampsia or suspected to have preeclampsia who underwent biophysical and biochemical investigations to measure the severity, including determining maternal hemodynamic indices, mean arterial pressure, fetal biometric and Doppler parameters, and soluble fms-like tyrosine kinase-1 and placental growth factor levels. The performance of these markers, individually or in combination, in predicting adverse perinatal and maternal outcomes was then assessed using receiver operating characteristic curve analysis. An adverse maternal outcome was defined as 1 or more of severe hypertension; admission to the intensive care unit; eclampsia; placental abruption; hemolysis, elevated liver enzymes, low-platelet count syndrome; disseminated intravascular coagulation; platelets <100×10⁹/L; creatinine >1.1 mg/dL; and alanine aminotransferase >100 U/L. An adverse perinatal outcome was defined as 1 or more of preterm birth ≤34+0 weeks' gestation, neonatal intensive care unit admission for >48 hours, respiratory distress syndrome, intraventricular hemorrhage, hypoxic ischemic encephalopathy, necrotizing enterocolitis, retinopathy of prematurity, and confirmed fetal infection.

RESULTS

We recruited 91 women with preeclampsia with a mean gestational age of 30.63±2.86 weeks. Women who had adverse maternal events had higher median maternal concentrations of soluble fms-like tyrosine kinase (11,500.0 pg/mL vs 3051.0 pg/mL; P<.001), lower concentrations of placental growth factor (44.88 pg/mL vs 148.50 pg/mL; P<.001), and a higher sFlt-1/PlGF ratio (306.22 vs 30.63; P<.001) than women who did not. Pregnancies with an adverse perinatal outcome also had a higher soluble fms-like tyrosine kinase concentration (12,100.0 pg/mL vs 3051.0 pg/mL; P<.001), lower placental growth factor concentration (27.2 pg/mL vs 148.50 pg/mL; P<.001), and higher sFlt-1/PlGF ratio (378.45.4 vs 30.63; P<.001). The area under the receiver operating characteristic curve showed that soluble fms-like tyrosine kinase and placental growth factor were the best biomarkers when compared with other biochemical markers to predict adverse maternal (area under the curve, 0.81; 95% confidence interval, 0.72-0.90) and fetal (area under the curve, 0.88; 95% confidence interval, 0.80-0.96) outcomes in preeclampsia.

CONCLUSION

The sFlt-1/PlGF ratio correlates better with adverse maternal and perinatal outcomes than any other biochemical marker in an Indian population. The incorporation of the sFlt-1/PlGF ratio in women with preeclampsia can help in predicting the severity of the condition and the timings of the delivery.

Prediction of adverse neonatal outcome at admission for early-onset preeclampsia with severe features

BACKGROUND

Preeclampsia remains the leading cause of maternal morbidity and mortality. Consequently, research has focused on validating tools to predict maternal outcomes regarding clinical and biochemical features from the maternal compartment. However, preeclampsia also leads to neonatal complications due to placental insufficiency and prematurity, being the early-onset type associated with the poorest outcome. Hence, it is imperative to study whether these existing tools can predict adverse neonatal outcome.

OBJECTIVE

To assess the predictive value for adverse neonatal outcome of Doppler ultrasound, angiogenic factors and multi-parametric risk-score models in women with early-onset severe preeclampsia.

STUDY DESIGN

This is a prospective cohort study of consecutive singleton pregnancies complicated by early-onset (developed before 34 week's gestation) severe preeclampsia.

RESULTS

63 women with early-onset severe preeclampsia, 18 (28.6%) presented an adverse neonatal outcome. Placental growth factor (PlGF) showed the best discrimination between neonatal outcomes among angiogenic factors. PREP-L score is a multi-parametric risk-score for the prediction of complications in early-onset preeclampsia which includes maternal characteristics and clinical and analytical data obtained at admission. Good predictive values for the prediction of neonatal complications were found with the combination of PREP-L score with advanced Doppler (AUC ROC 0.9 95% CI 0.82-0.98]) and with PlGF levels (AUC ROC 0.91 [95% CI 0.84-0.98]).

CONCLUSIONS

The combination of maternal risk scoring (PREP-L score) with angiogenic factors or fetal Doppler ultrasound at the time of diagnosis of early-onset preeclampsia with severe features performs well in predicting adverse neonatal outcome.

Performance of sFlt-1/PIGF Ratio for the Prediction of Perinatal Outcome in Obese Pre-Eclamptic Women

Obese women are at high risk of developing pre-eclampsia (PE). As an altered angiogenic profile is characteristic for PE, measurement of soluble fms-like tyrosine kinase-1 (sFlt-1)/placental growth factor (PIGF) ratio in the maternal serum can be helpful for PE diagnosis, as well as for adverse perinatal outcome (APO) prediction. There is growing evidence that obesity might influence the level of sFlt-1/PIGF and, therefore, the aim of the study was the evaluation of sFlt-1/PIGF as an APO predictor in obese women with PE. Pre-eclamptic women who had an sFlt-1/PIGF measurement at the time of diagnosis were retrospectively included. Women were classified according to their pre-pregnancy body mass index (BMI) as normal weight (BMI < 25 kg/m2), overweight (BMI > 25−29.9 kg/m2) or obese (BMI ≥ 30 kg/m2). APO was defined as the occurrence of one of the following outcomes: Small for gestational age, defined as a birthweight < 3rd centile, neonatal mortality, neonatal seizures, admission to neonatal unit required (NICU) or respiratory support. A total of 141 women were included. Of them, 28 (20%) patients were obese. ROC (receiver operating characteristic) analysis revealed a high predictive value for sFlt-1/PIGF and APO across the whole study cohort (AUC = 0.880, 95% CI: 0.826−0.936; p < 0.001). However, the subgroup of obese women showed a significantly lower level of sFlt-1 and, therefore, the performance of sFlt-1/PIGF as APO predictor was poorer compared to normal or overweight PE women (AUC = 0.754, 95% CI: 0.552−0.956, p = 0.025). In contrast to normal or overweight women, a ratio of sFlt-1/PIGF < 38 could not rule out APO in women with obesity.

Role of placental, fetal and maternal cardiovascular markers in predicting adverse outcome in women with suspected or confirmed pre-eclampsia

OBJECTIVE

To assess the performance of placental, fetal and maternal cardiovascular markers in the prediction of adverse perinatal and maternal outcomes in women with suspected or confirmed pre-eclampsia.

METHODS

This was a prospective prognostic accuracy study of women with suspected or confirmed pre-eclampsia who underwent a series of investigations to measure maternal hemodynamic indices, mean arterial pressure, augmentation index, ophthalmic artery peak systolic velocity (PSV) ratio, uterine artery pulsatility index (UtA-PI), fetal biometric and Doppler parameters, soluble fms-like tyrosine kinase-1 (sFlt-1) and placental growth factor (PlGF). The performance of these markers, individually or in combination, in predicting adverse perinatal and maternal outcomes was then assessed using receiver-operating-characteristics (ROC)-curve analysis. Adverse maternal outcome was defined as one or more of severe hypertension, admission to the intensive care unit, eclampsia, placental abruption, HELLP syndrome, disseminated intravascular coagulation, platelets < 100 × 109 /L, creatinine > 90 μmol/L and alanine aminotransferase > 100 U/L. Adverse perinatal outcome was defined as one or more of preterm birth at or before 34 + 0 weeks, neonatal intensive care unit admission for > 48 h, respiratory distress syndrome, intraventricular hemorrhage, hypoxic ischemic encephalopathy, necrotizing enterocolitis, retinopathy of prematurity and confirmed fetal infection.

RESULTS

We recruited 126 women with suspected (n = 31) or confirmed (n = 95) pre-eclampsia at a median gestational age of 33.9 weeks (interquartile range, 30.9-36.3 weeks). Pregnancies with adverse perinatal outcome compared to those without had a higher median UtA-PI (1.3 vs 0.8; P < 0.001), ophthalmic artery PSV ratio (0.8 vs 0.7; P = 0.01) and umbilical artery PI percentile (82.0 vs 68.5; P < 0.01) and lower median estimated fetal weight percentile (4.0 vs 43.0; P < 0.001), abdominal circumference percentile (4.0 vs 63.0; P < 0.001), middle cerebral artery PI percentile (28.0 vs 58.5; P < 0.001) and cerebroplacental ratio percentile (18.0 vs 46.5; P < 0.001). Pregnancies with adverse perinatal outcome also had a higher median sFlt-1 (8208.0 pg/mL vs 4508.0 pg/mL; P < 0.001), lower PlGF (27.2 pg/mL vs 76.3 pg/mL; P < 0.001) and a higher sFlt-1/PlGF ratio (445.4 vs 74.4; P < 0.001). The best performing individual marker for predicting adverse perinatal outcome was the sFlt-1/PlGF ratio (area under the ROC curve (AUC), 0.87 (95% CI, 0.81-0.93)), followed by estimated fetal weight (AUC, 0.81 (95% CI, 0.73-0.89)). Women who experienced adverse maternal outcome had a higher median sFlt-1 level (7471.0 pg/mL vs 5131.0 pg/mL; P < 0.001) and sFlt-1/PlGF ratio (204.3 vs 93.3; P < 0.001) and a lower PlGF level (37.0 pg/mL vs 66.1 pg/mL; P = 0.01) and estimated fetal weight percentile (16.5 vs 37.0; P = 0.04). All markers performed poorly in predicting adverse maternal outcome, with sFlt-1 (AUC, 0.69 (95% CI, 0.60-0.79)) and sFlt-1/PlGF ratio (AUC, 0.69 (95% CI, 0.59-0.78)) demonstrating the best individual performance. The addition of cardiovascular, fetal or other placental indices to the sFlt-1/PlGF ratio did not improve the prediction of adverse maternal or perinatal outcomes.

CONCLUSIONS

The sFlt-1/PlGF ratio performs well in predicting adverse perinatal outcomes but is a poor predictor of adverse maternal outcomes in women with suspected or diagnosed pre-eclampsia. The addition of cardiovascular or fetal indices to the model is unlikely to improve the prognostic performance of the sFlt-1/PlGF ratio. © 2022 International Society of Ultrasound in Obstetrics and Gynecology.

A machine-learning-based algorithm improves prediction of preeclampsia-associated adverse outcomes

BACKGROUND

Preeclampsia presents a highly prevalent burden on pregnant women with an estimated incidence of 2% to 5%. Preeclampsia increases the maternal risk of death 20-fold and is one of the main causes of perinatal morbidity and mortality. Novel biomarkers, such as soluble fms-like tyrosine kinase-1 and placental growth factor in addition to a wide span of conventional clinical data (medical history, physical symptoms, laboratory parameters, etc.), present an excellent basis for the application of early-detection machine-learning models.

OBJECTIVE

This study aimed to develop, train, and test an automated machine-learning model for the prediction of adverse outcomes in patients with suspected preeclampsia.

STUDY DESIGN

Our real-world dataset of 1647 (2472 samples) women was retrospectively recruited from women who presented to the Department of Obstetrics at the Charité - Universitätsmedizin Berlin, Berlin, Germany, between July 2010 and March 2019. After standardization and data cleaning, we calculated additional features regarding the biomarkers soluble fms-like tyrosine kinase-1 and placental growth factor and sonography data (umbilical artery pulsatility index, middle cerebral artery pulsatility index, mean uterine artery pulsatility index), resulting in a total of 114 features. The target metric was the occurrence of adverse outcomes throughout the remaining pregnancy and 2 weeks after delivery. We trained 2 different models, a gradient-boosted tree and a random forest classifier. Hyperparameter training was performed using a grid search approach. All results were evaluated via a 10 × 10-fold cross-validation regimen.

RESULTS

We obtained metrics for the 2 naive machine-learning models. A gradient-boosted tree model was performed with a positive predictive value of 88%±6%, a negative predictive value of 89%±3%, a sensitivity of 66%±5%, a specificity of 97%±2%, an overall accuracy of 89%±3%, an area under the receiver operating characteristic curve of 0.82±0.03, an F1 score of 0.76±0.04, and a threat score of 0.61±0.05. The random forest classifier returned an equal positive predictive value (88%±6%) and specificity (97%±1%) while performing slightly inferior on the other available metrics. Applying differential cutoffs instead of a naive cutoff for positive prediction at ≥0.5 for the classifier's results yielded additional increases in performance.

CONCLUSION

Machine-learning techniques were a valid approach to improve the prediction of adverse outcomes in pregnant women at high risk of preeclampsia vs current clinical standard techniques. Furthermore, we presented an automated system that did not rely on manual tuning or adjustments.

Prediction of Adverse Pregnancy Outcome Related to Placental Dysfunction Using the sFlt-1/PlGF Ratio: A Narrative Review

The sFlt-1 (soluble fms-like tyrosine kinase-1)/PlGF (placental growth factor) ratio is a helpful tool for the prediction and diagnosis of preeclampsia (PE). Current data even show that the ratio has the potential to predict adverse pregnancy outcomes (APO) caused by placental pathologies. The aim of this article is to give a brief overview of recent findings on APO predictions based on the sFlt-1/PlGF ratio. The focus is on obstetric pathologies related to placental dysfunction (PD) such as PE and/or fetal growth restriction (FGR). New uses of the sFlt-1/PlGF ratio as a predictor of APO demonstrate its potential with regard to planning hospitalization and corticosteroid administration and the optimal timing of delivery. However, prospective interventional studies are warranted to define the exact role of the sFlt-1/PlGF ratio as a predictor of adverse pregnancy outcomes caused by placental pathologies.

Prediction of adverse perinatal outcome and the mean time until delivery in twin pregnancies with suspected pre-eclampsia using sFlt-1/PIGF ratio

PURPOSE

An elevated soluble fms-like tyrosine kinase-1 (sFlt-1) / placental growth factor (PlGF) ratio is associated with adverse perinatal outcome (APO) and the mean time until delivery (MTUD) in singleton pregnancies complicated by pre-eclampsia (PE). Data on APO and MTUD prediction in twin pregnancies using sFlt-1/PlGF ratio are scarce. We evaluated the predictive value of the sFlt-1/PIGF ratio regarding APO and MTUD in twin pregnancies with suspected PE and/or HELLP syndrome.

METHODS

This is a single center retrospective cohort study. All twin pregnancies with suspected PE/HELLP and determined sFlt-1/PIGF were included. Composite APO (CAPO) was defined as the presence of at least one of the following outcomes: respiratory distress syndrome (RDS), intubation, admission to neonatal intensive care unit (NICU) and arterial umbilical cord pH value < 7.10. Selective fetal growth restriction (s-FGR) was analyzed separately.

RESULTS

For final analysis, 49 twin pregnancies were included. Median sFlt-1/PIGF ratio was not significantly different in patients with CAPO compared to those without (89.45 vs. 62.00, p = 0.669). MTUD was significantly negative correlated with sFlt-1/PIGF ratio (r = -0.409, p < 0.001). For the whole study cohort, ROC analysis revealed no predictive value for sFlt-1/PIGF and CAPO (AUC = 0.618, 95% CI: 0.387-0.849, p = 0.254). However, sFlt-1/PIGF ratio showed a predictive value for s-FGR (AUC = 0.755, 95% CI: 0.545-0.965, p = 0.032).

CONCLUSION

In twin pregnancies with PE and/or HELLP, sFlt-1/PIGF ratio may be helpful for s-FGR prediction and decision-making regarding close monitoring of high-risk patients. However, further prospective studies are warranted to define the role of sFlt-1/PlGF ratio as outcome predictor in twin pregnancies.