Machine-learning-based prediction of pre-eclampsia using first-trimester maternal characteristics and biomarkers

Noninvasive early prediction of preeclampsia in pregnancy using retinal vascular features

Preeclampsia (PE), a severe hypertensive disorder during pregnancy, significantly contributes to maternal and neonatal mortality. Existing prediction biomarkers are often invasive and expensive, hindering their widespread application. This study introduces PROMPT (Preeclampsia Risk factor + Ophthalmic data + Mean arterial pressure Prediction Test), an AI-driven model leveraging retinal photography for PE prediction, registered at ChiCTR (ChiCTR2100049850) in August 2021. Analyzing 1812 pregnancies before 14 gestational weeks, we extracted retinal parameters using a deep learning system. The PROMPT achieved an AUC of 0.87 (0.83-0.90) for PE prediction and 0.91 (0.85-0.97) for preterm PE prediction using machine learning, significantly outperforming the baseline model (p < 0.001). It also improved detection of severe adverse pregnancy outcomes from 35% to 41%. Economically, PROMPT was estimated to avert 1809 PE cases and saved over $50 million per 100,000 screenings. These results position PROMPT as a non-invasive and cost-effective tool for prenatal care, especially valuable in low- and middle-income countries.

Artificial Intelligence and Machine Learning: An Updated Systematic Review of Their Role in Obstetrics and Midwifery

Artificial intelligence (AI) and machine learning (ML) are rapidly evolving technologies with significant implications in obstetrics and midwifery. This systematic review aims to evaluate the latest advancements in AI and ML applications in obstetrics and midwifery. A search was conducted in three electronic databases (PubMed, Scopus, and Web of Science) for studies published between January 1, 2022, and February 20, 2025, using keywords related to AI, ML, obstetrics, and midwifery. The review adhered to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for updated systematic reviews. Studies were selected based on their focus on AI/ML applications in obstetrics and midwifery, while non-English publications and review studies were excluded. The review included 64 studies, highlighting significant advancements in AI and ML applications across various domains in obstetrics and midwifery. Findings indicate that AI and ML models and systems achieved high accuracy in areas, such as assisted reproduction, diagnosis (e.g., 3D/4D ultrasound and MRI), pregnancy risk assessment (e.g., preeclampsia, gestational diabetes, preterm birth), fetal monitoring, mode of birth, and perinatal outcomes (e.g., mortality rates, postpartum hemorrhage, hypertensive disorders, neonatal respiratory distress). AI and ML have significant potential in transforming obstetric and midwifery care. The great number of studies reporting significant improvements suggests that the widespread adoption of AI and ML in these fields is imminent. Interdisciplinary collaboration between clinicians, data scientists, and policymakers will be crucial in shaping the future of maternal and neonatal healthcare.

Artificial Intelligence and Machine Learning in Preeclampsia

Preeclampsia is a multisystem hypertensive disorder that manifests itself after 20 weeks of pregnancy, along with proteinuria. The pathophysiology of preeclampsia is incompletely understood. Artificial intelligence, especially machine learning with its capability to identify patterns in complex data, has the potential to revolutionize preeclampsia research. These data-driven techniques can improve early diagnosis, personalize risk assessment, uncover the disease's molecular basis, optimize treatments, and enable remote monitoring. This brief review discusses the recent applications of artificial intelligence and machine learning in preeclampsia management and research, including the improvements these approaches have brought, along with their challenges and limitations.

A novel multiple marker microarray analyzer and methodology to predict major obstetric syndromes using surface markers of circulating extracellular vesicles from maternal plasma

INTRODUCTION

Placental-derived extracellular vesicles (EVs) are nano-organelles that facilitate intercellular communication between the feto-placental unit and the mother. We evaluated a novel Multiple Microarray analyzer for identifying surface markers on plasma EVs that predict preterm delivery and preeclampsia compared to term delivery controls.

MATERIAL AND METHODS

In this prospective exploratory cohort study pregnant women between 24 and 40 gestational weeks with preterm delivery (n = 16), preeclampsia (n = 19), and matched term delivery controls (n = 15) were recruited from Bnai Zion Medical Center, Haifa, Israel. Plasma samples were tested using a multiple microarray analyzer. Glass slides with 17 antibodies against EV surface receptors - were incubated with raw plasma samples, detected by biotinylated secondary antibodies specific to EVs or placental EVs (PEVs), and labeled with cyanine 5-streptavidin. PBS and whole human IgG served as controls. The fluorescent signal ratio to negative controls was log 2 transformed and analyzed for sensitivity and specificity using the area under the receiver operating characteristics curves (AUROC). Best pair ratios of general EVs/PEVs were used for univariate analysis, and top pairs were combined for multivariate analysis. Results were validated by comparison with EVs purified using standard procedures.

RESULTS

Heatmaps differentiated surface profiles of preeclampsia, preterm delivery, and term delivery receptors on total EVs and PEVs. Similar results were obtained with enriched EVs and EVs from raw plasma. Univariate analyses identified markers predicting preterm delivery and preeclampsia over term delivery controls with AUC >0.6 and sensitivity >50% at 80% specificity. Combining the best markers in a multivariate model, preeclampsia prediction over term delivery had an AUC of 0.89 (95% CI: 0.72-1.0) with 90% sensitivity and 90% specificity, marked by inflammation (TNF RII), relaxation (placenta protein 13 (PP13)), and immune-modulation (LFA1) receptors. Preterm delivery prediction over term delivery had an AUC of 0.97 (0.94-1.0), 84% sensitivity, and 90% specificity, marked by cell adhesion (ICAM), immune suppression, and general EV markers (CD81, CD82, and Alix). Preeclampsia prediction over preterm delivery had an AUC of 0.91 (0.79-0.99) with 80% sensitivity and 90% specificity with markers for complement activation (C1q) and autoimmunity markers.

CONCLUSIONS

The new, robust EV Multi-Array analyzer and methodology offer a simple, fast diagnostic tool that reveals novel surface markers for major obstetric syndromes.

Prediction of Preeclampsia Using Machine Learning: A Systematic Review

Preeclampsia is one of the leading causes of maternal and perinatal morbidity and mortality. Early prediction is the need of the hour so that interventions like aspirin prophylaxis can be started. Nowadays, machine learning (ML) is increasingly being used to predict the disease and its prognosis. This review explores the methodologies, predictors, and performance of ML models for preeclampsia prediction, emphasizing their comparative advantages, challenges, and clinical applicability. We conducted a systematic search of databases including PubMed, Cochrane, and Scopus for studies published in the last 10 years using terms such as "preeclampsia", "risk factors", "machine learning", "artificial intelligence", and "deep learning". Words and phrases were selected using MeSH, a controlled vocabulary. Appropriate articles were selected using Boolean operators "OR" and "AND". The database search yielded 325 records. After removing duplicates and non-English articles, and completing a title and abstract search 55 research articles were assessed for eligibility of which 11 were included in this review. The risk of bias was found to be high in three of the studies and low in the rest. Clinicodemographic characteristics, laboratory reports, Doppler ultrasound, and some innovative ones like genotypic data and fundal images were predictors used to train ML models. More than ten different ML models were used in the 11 studies from diverse countries like the United States, the United Kingdom, China, and Korea. The area under the curve varied from 0.76 to 0.97. ML algorithms such as extreme gradient boosting (XGBoost), random forest, and neural networks consistently demonstrated superior predictive accuracy Non-interpretable or black box ML models may not find clinical application on ethical grounds. The future of preeclampsia prediction using ML lies in balancing model performance with interpretability. Human oversight remains indispensable in implementing and interpreting these models to achieve better maternal outcomes. Further research and validation across diverse populations are critical to establishing the universal applicability of these promising ML-based approaches.

Preeclampsia and its prediction: traditional versus contemporary predictive methods

OBJECTIVE

Preeclampsia (PE) poses a significant threat to maternal and perinatal health, so its early prediction, prevention, and management are of paramount importance to mitigate adverse pregnancy outcomes. This article provides a brief review spanning epidemiology, etiology, pathophysiology, and risk factors associated with PE, mainly discussing the emerging role of Artificial Intelligence (AI) deep learning (DL) technology in predicting PE, to advance the understanding of PE and foster the clinical application of early prediction methods.

METHODS

Our narrative review comprehensively examines the PE epidemiology, etiology, pathophysiology, risk factors and predictive approaches, including traditional models and AI deep learning technology.

RESULTS

Preeclampsia involves a wide range of biological and biochemical risk factors, among which poor uterine artery remodeling, excessive immune response, endothelial dysfunction, and imbalanced angiogenesis play important roles. Traditional PE prediction models exhibit significant limitations in sensitivity and specificity, particularly in predicting late-onset PE, with detection rates ranging from only 30% to 50%. AI models have exhibited a notable level of predictive accuracy and value across various populations and datasets, achieving detection rates of approximately 70%. Particularly, they have shown superior predictive capabilities for late-onset PE, thereby presenting novel opportunities for early screening and management of the condition.

CONCLUSION

AI DL technology holds promise in revolutionizing the prediction and management of PE. AI-based approaches offer a pathway toward more effective risk assessment methods by addressing the shortcomings of traditional prediction models. Ongoing research efforts should focus on expanding databases and validating the performance of AI in diverse populations, leading to the development of more sophisticated prediction models with improved accuracy.

Prediction of pre-eclampsia with machine learning approaches: Leveraging important information from routinely collected data

BACKGROUND

Globally, pre-eclampsia (PE) is a leading cause of maternal and perinatal morbidity and mortality. PE prediction using routinely collected data has the advantage of being widely applicable, particularly in low-resource settings. Early intervention for high-risk women might reduce PE incidence and related complications. We aimed to replicate our machine learning (ML) published work predicting another maternal condition (gestational diabetes) to (1) predict PE using routine health data, (2) identify the optimal ML model, and (3) compare it with logistic regression approach.

METHODS

Data were from a large health service network with 48,250 singleton pregnancies between January 2016 and June 2021. Supervised ML models were employed. Maternal clinical and medical characteristics were the feature variables (predictors), and a 70/30 data split was used for training and testing the model. Predictive performance was assessed using area under the curve (AUC) and calibration plots. Shapley value analysis assessed the contribution of feature variables.

RESULTS

The random forest approach provided excellent discrimination with an AUC of 0.84 (95% CI: 0.82-0.86) and highest prediction accuracy (0.79); however, the calibration curve (slope of 1.21, 95% CI 1.13-1.30) was acceptable only for a threshold of 0.3 or less. The next best approach was extreme gradient boosting, which provided an AUC of 0.77 (95% CI: 0.76-0.79) and well-calibrated (slope of 0.93, 95% CI 0.85-1.01). Logistic regression provided good discrimination performance with an AUC of 0.75 (95% CI: 0.74-0.76) and perfect calibration. Nulliparous, pre-pregnancy body mass index, previous pregnancy with prior PE, maternal age, family history of hypertension, and pre-existing hypertension and diabetes were the top-ranked features in Shapley value analysis.

CONCLUSION

Two ML models created the highest-performing prediction using routinely collected data to identify women at high risk of PE, with acceptable discrimination. However, to confirm this result and also examine model generalisability, external validation studies are needed in other settings, utilising standardised prognostic factors.

The role of cell-free DNA biomarkers and patient data in the early prediction of preeclampsia: an artificial intelligence model

BACKGROUND

Accurate individualized assessment of preeclampsia risk enables the identification of patients most likely to benefit from initiation of low-dose aspirin at 12 to 16 weeks of gestation when there is evidence for its effectiveness, and enables the guidance of appropriate pregnancy care pathways and surveillance.

OBJECTIVE

The primary objective of this study was to evaluate the performance of artificial neural network models for the prediction of preterm preeclampsia (<37 weeks' gestation) using patient characteristics available at the first antenatal visit and data from prenatal cell-free DNA screening. Secondary outcomes were prediction of early-onset preeclampsia (<34 weeks' gestation) and term preeclampsia (≥37 weeks' gestation).

METHODS

This secondary analysis of a prospective, multicenter, observational prenatal cell-free DNA screening study (SMART) included singleton pregnancies with known pregnancy outcomes. Thirteen patient characteristics that are routinely collected at the first prenatal visit and 2 characteristics of cell-free DNA (total cell-free DNA and fetal fraction) were used to develop predictive models for early-onset (<34 weeks), preterm (<37 weeks), and term (≥37 weeks) preeclampsia. For the models, the "reference" classifier was a shallow logistic regression model. We also explored several feedforward (nonlinear) neural network architectures with ≥1 hidden layers, and compared their performance with the logistic regression model. We selected a simple neural network model built with 1 hidden layer and made up of 15 units.

RESULTS

Of the 17,520 participants included in the final analysis, 72 (0.4%) developed early-onset, 251 (1.4%) preterm, and 420 (2.4%) term preeclampsia. Median gestational age at cell-free DNA measurement was 12.6 weeks, and 2155 (12.3%) had their cell-free DNA measurement at ≥16 weeks' gestation. Preeclampsia was associated with higher total cell-free DNA (median, 362.3 vs 339.0 copies/mL cell-free DNA; P<.001) and lower fetal fraction (median, 7.5% vs 9.4%; P<.001). The expected, cross-validated area under the curve scores for early-onset, preterm, and term preeclampsia were 0.782, 0.801, and 0.712, respectively, for the logistic regression model, and 0.797, 0.800, and 0.713, respectively, for the neural network model. At a screen-positive rate of 15%, sensitivity for preterm preeclampsia was 58.4% (95% confidence interval, 0.569-0.599) for the logistic regression model and 59.3% (95% confidence interval, 0.578-0.608) for the neural network model. The contribution of both total cell-free DNA and fetal fraction to the prediction of term and preterm preeclampsia was negligible. For early-onset preeclampsia, removal of the total cell-free DNA and fetal fraction features from the neural network model was associated with a 6.9% decrease in sensitivity at a 15% screen-positive rate, from 54.9% (95% confidence interval, 52.9-56.9) to 48.0% (95% confidence interval, 45.0-51.0).

CONCLUSION

Routinely available patient characteristics and cell-free DNA markers can be used to predict preeclampsia with performance comparable to that of other patient characteristic models for the prediction of preterm preeclampsia. Logistic regression and neural network models showed similar performance.

Development and validation of preeclampsia predictive models using key genes from bioinformatics and machine learning approaches

Background

Preeclampsia (PE) poses significant diagnostic and therapeutic challenges. This study aims to identify novel genes for potential diagnostic and therapeutic targets, illuminating the immune mechanisms involved.

Methods

Three GEO datasets were analyzed, merging two for training set, and using the third for external validation. Intersection analysis of differentially expressed genes (DEGs) and WGCNA highlighted candidate genes. These were further refined through LASSO, SVM-RFE, and RF algorithms to identify diagnostic hub genes. Diagnostic efficacy was assessed using ROC curves. A predictive nomogram and fully Connected Neural Network (FCNN) were developed for PE prediction. ssGSEA and correlation analysis were employed to investigate the immune landscape. Further validation was provided by qRT-PCR on human placental samples.

Result

Five biomarkers were identified with validation AUCs: CGB5 (0.663, 95% CI: 0.577-0.750), LEP (0.850, 95% CI: 0.792-0.908), LRRC1 (0.797, 95% CI: 0.728-0.867), PAPPA2 (0.839, 95% CI: 0.775-0.902), and SLC20A1 (0.811, 95% CI: 0.742-0.880), all of which are involved in key biological processes. The nomogram showed strong predictive power (C-index 0.873), while FCNN achieved an optimal AUC of 0.911 (95% CI: 0.732-1.000) in five-fold cross-validation. Immune infiltration analysis revealed the importance of T cell subsets, neutrophils, and NK cells in PE, linking these genes to immune mechanisms underlying PE pathogenesis.

Conclusion

CGB5, LEP, LRRC1, PAPPA2, and SLC20A1 are validated as key diagnostic biomarkers for PE. Nomogram and FCNN could credibly predict PE. Their association with immune infiltration underscores the crucial role of immune responses in PE pathogenesis.

Validation of the first-trimester machine learning model for predicting pre-eclampsia in an Asian population

OBJECTIVES

To evaluate the performance of an artificial intelligence (AI) and machine learning (ML) model for first-trimester screening for pre-eclampsia in a large Asian population.

METHODS

This was a secondary analysis of a multicenter prospective cohort study in 10 935 participants with singleton pregnancies attending for routine pregnancy care at 11-13+6 weeks of gestation in seven regions in Asia between December 2016 and June 2018. We applied the AI+ML model for the first-trimester prediction of preterm pre-eclampsia (<37 weeks), term pre-eclampsia (≥37 weeks), and any pre-eclampsia, which was derived and tested in a cohort of pregnant participants in the UK (Model 1). This model comprises maternal factors with measurements of mean arterial pressure, uterine artery pulsatility index, and serum placental growth factor (PlGF). The model was further retrained with adjustments for analyzers used for biochemical testing (Model 2). Discrimination was assessed by area under the receiver operating characteristic curve (AUC). The Delong test was used to compare the AUC of Model 1, Model 2, and the Fetal Medicine Foundation (FMF) competing risk model.

RESULTS

The predictive performance of Model 1 was significantly lower than that of the FMF competing risk model in the prediction of preterm pre-eclampsia (0.82, 95% confidence interval [CI] 0.77-0.87 vs. 0.86, 95% CI 0.811-0.91, P = 0.019), term pre-eclampsia (0.75, 95% CI 0.71-0.80 vs. 0.79, 95% CI 0.75-0.83, P = 0.006), and any pre-eclampsia (0.78, 95% CI 0.74-0.81 vs. 0.82, 95% CI 0.79-0.84, P < 0.001). Following the retraining of the data with adjustments for the PlGF analyzers, the performance of Model 2 for predicting preterm pre-eclampsia, term pre-eclampsia, and any pre-eclampsia was improved with the AUC values increased to 0.84 (95% CI 0.80-0.89), 0.77 (95% CI 0.73-0.81), and 0.80 (95% CI 0.76-0.83), respectively. There were no differences in AUCs between Model 2 and the FMF competing risk model in the prediction of preterm pre-eclampsia (P = 0.135) and term pre-eclampsia (P = 0.084). However, Model 2 was inferior to the FMF competing risk model in predicting any pre-eclampsia (P = 0.024).

CONCLUSION

This study has demonstrated that following adjustment for the biochemical marker analyzers, the predictive performance of the AI+ML prediction model for pre-eclampsia in the first trimester was comparable to that of the FMF competing risk model in an Asian population.

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.

The Holy Grail of obstetric ultrasound: can artificial intelligence detect hard-to-identify fetal cardiac anomalies?

Linked article: This Editorial comments on articles by Day et al. and Taksøe‐Vester et al.

Lipidomic signatures in patients with early-onset and late-onset Preeclampsia

BACKGROUND

Preeclampsia is a pregnancy-specific clinical syndrome and can be subdivided into early-onset preeclampsia (EOPE) and late-onset preeclampsia (LOPE) according to the gestational age of delivery. Patients with preeclampsia have aberrant lipid metabolism. This study aims to compare serum lipid profiles of normal pregnant women with EOPE or LOPE and screening potential biomarkers to diagnose EOPE or LOPE.

METHODS

Twenty normal pregnant controls (NC), 19 EOPE, and 19 LOPE were recruited in this study. Untargeted lipidomics based on ultra-performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS) was used to compare their serum lipid profiles.

RESULTS

The lipid metabolism profiles significantly differ among the NC, EOPE, and LOPE. Compared to the NC, there were 256 and 275 distinct lipids in the EOPE and LOPE, respectively. Furthermore, there were 42 different lipids between the LOPE and EOPE, of which eight were significantly associated with fetal birth weight and maternal urine protein. The five lipids that both differed in the EOPE and LOPE were DGTS (16:3/16:3), LPC (20:3), LPC (22:6), LPE (22:6), PC (18:5e/4:0), and a combination of them were a potential biomarker for predicting EOPE or LOPE. The receiver operating characteristic analysis revealed that the diagnostic power of the combination for distinguishing the EOPE from the NC and for distinguishing the LOPE from the NC can reach 1.000 and 0.992, respectively. The association between the lipid modules and clinical characteristics of EOPE and LOPE was investigated by the weighted gene co-expression network analysis (WGCNA). The results demonstrated that the main different metabolism pathway between the EOPE and LOPE was enriched in glycerophospholipid metabolism.

CONCLUSIONS

Lipid metabolism disorders may be a potential mechanism of the pathogenesis of preeclampsia. Lipid metabolites have the potential to serve as biomarkers in patients with EOPE or LOPE. Furthermore, lipid metabolites correlate with clinical severity indicators for patients with EOPE and LOPE, including fetal birth weight and maternal urine protein levels.

Prediction model of preeclampsia using machine learning based methods: a population based cohort study in China

Introduction

Preeclampsia is a disease with an unknown pathogenesis and is one of the leading causes of maternal and perinatal morbidity. At present, early identification of high-risk groups for preeclampsia and timely intervention with aspirin is an effective preventive method against preeclampsia. This study aims to develop a robust and effective preeclampsia prediction model with good performance by machine learning algorithms based on maternal characteristics, biophysical and biochemical markers at 11-13 + 6 weeks' gestation, providing an effective tool for early screening and prediction of preeclampsia.

Methods

This study included 5116 singleton pregnant women who underwent PE screening and fetal aneuploidy from a prospective cohort longitudinal study in China. Maternal characteristics (such as maternal age, height, pre-pregnancy weight), past medical history, mean arterial pressure, uterine artery pulsatility index, pregnancy-associated plasma protein A, and placental growth factor were collected as the covariates for the preeclampsia prediction model. Five classification algorithms including Logistic Regression, Extra Trees Classifier, Voting Classifier, Gaussian Process Classifier and Stacking Classifier were applied for the prediction model development. Five-fold cross-validation with an 8:2 train-test split was applied for model validation.

Results

We ultimately included 49 cases of preterm preeclampsia and 161 cases of term preeclampsia from the 4644 pregnant women data in the final analysis. Compared with other prediction algorithms, the AUC and detection rate at 10% FPR of the Voting Classifier algorithm showed better performance in the prediction of preterm preeclampsia (AUC=0.884, DR at 10%FPR=0.625) under all covariates included. However, its performance was similar to that of other model algorithms in all PE and term PE prediction. In the prediction of all preeclampsia, the contribution of PLGF was higher than PAPP-A (11.9% VS 8.7%), while the situation was opposite in the prediction of preterm preeclampsia (7.2% VS 16.5%). The performance for preeclampsia or preterm preeclampsia using machine learning algorithms was similar to that achieved by the fetal medicine foundation competing risk model under the same predictive factors (AUCs of 0.797 and 0.856 for PE and preterm PE, respectively).

Conclusions

Our models provide an accessible tool for large-scale population screening and prediction of preeclampsia, which helps reduce the disease burden and improve maternal and fetal outcomes.

First-trimester preterm preeclampsia prediction model for prevention with low-dose aspirin

INTRODUCTION

Preeclampsia (PE) is a major maternal and fetal threat. Previous risk-scoring methods in guidelines lacked precision. The Fetal Medicine Foundation (FMF) proposed a first-trimester PE screening model using Bayes' theorem.

PE PREDICTION MODEL

FMF prediction model combines maternal characteristics and medical/obstetrical history to determine prior risk and further incorporate maternal blood pressure, maternal serum biomarkers, and uterine Doppler pulsatility index expressed as multiples of the median (MoM) to estimate posterior risk.

LOW-DOSE ASPIRIN PREVENTION

Low-dose aspirin is one of the potential PE prevention strategies. Initiating it before 16 weeks is crucial. Aspirin's antiplatelet and anti-inflammatory properties align with PE's pathophysiology. Dosing and resistance warrant further study, but a standard regimen of 150 mg nightly, starting before 16 weeks, is widely supported.

PE PREVENTION IN PRACTICE

Clinical trials, including ASPRE, affirm aspirin's role in PE prevention. Starting aspirin based on FMF screening significantly reduces preterm PE and associated complications.

ADVANCEMENTS AND PROSPECTS

Emerging research explores predictors like maternal ophthalmic arterial waveform. Regional variations, especially in Asian populations, are considered. Machine learning and AI show promise, but examiner expertise remains essential for accurate prediction. In conclusion, integrating FMF's first-trimester PE screening with low-dose aspirin offers a promising strategy. Further advancements may enhance precision and broaden prevention efforts.

Performance of machine-learning approach for prediction of pre-eclampsia in a middle-income country

OBJECTIVE

Pre-eclampsia (PE) is a serious complication of pregnancy associated with maternal and fetal morbidity and mortality. As current prediction models have limitations and may not be applicable in resource-limited settings, we aimed to develop a machine-learning (ML) algorithm that offers a potential solution for developing accurate and efficient first-trimester prediction of PE.

METHODS

We conducted a prospective cohort study in Mexico City, Mexico to develop a first-trimester prediction model for preterm PE (pPE) using ML. Maternal characteristics and locally derived multiples of the median (MoM) values for mean arterial pressure, uterine artery pulsatility index and serum placental growth factor were used for variable selection. The dataset was split into training, validation and test sets. An elastic-net method was employed for predictor selection, and model performance was evaluated using area under the receiver-operating-characteristics curve (AUC) and detection rates (DR) at 10% false-positive rates (FPR).

RESULTS

The final analysis included 3050 pregnant women, of whom 124 (4.07%) developed PE. The ML model showed good performance, with AUCs of 0.897, 0.963 and 0.778 for pPE, early-onset PE (ePE) and any type of PE (all-PE), respectively. The DRs at 10% FPR were 76.5%, 88.2% and 50.1% for pPE, ePE and all-PE, respectively.

CONCLUSIONS

Our ML model demonstrated high accuracy in predicting pPE and ePE using first-trimester maternal characteristics and locally derived MoM. The model may provide an efficient and accessible tool for early prediction of PE, facilitating timely intervention and improved maternal and fetal outcome. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

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.

Preterm preeclampsia screening using biomarkers: combining phenotypic classifiers into robust prediction models

BACKGROUND

Preeclampsia screening is a critical component of antenatal care worldwide. Currently, the most developed screening test for preeclampsia at 11 to 13 weeks' gestation integrates maternal demographic characteristics and medical history with 3 biomarkers-serum placental growth factor, mean arterial pressure, and uterine artery pulsatility index-to identify approximately 75% of women who develop preterm preeclampsia with delivery before 37 weeks of gestation. It is generally accepted that further improvements to preeclampsia screening require the use of additional biomarkers. We recently reported that the levels of specific metabolites and metabolite ratios are associated with preterm preeclampsia. Notably, for several of these markers, preterm preeclampsia prediction varied according to maternal body mass index class. These findings motivated us to study whether patient classification allowed for combining metabolites with the current biomarkers more effectively to improve prediction of preterm preeclampsia.

OBJECTIVE

This study aimed to investigate whether metabolite biomarkers can improve biomarker-based preterm preeclampsia prediction in 3 screening resource scenarios according to the availability of: (1) placental growth factor, (2) placental growth factor+mean arterial pressure, and (3) placental growth factor+mean arterial pressure+uterine artery pulsatility index.

STUDY DESIGN

This was an observational case-control study, drawn from a large prospective screening study at 11 to 13 weeks' gestation on the prediction of pregnancy complications, conducted at King's College Hospital, London, United Kingdom. Maternal blood samples were also collected for subsequent research studies. We used liquid chromatography-mass spectrometry to quantify levels of 50 metabolites previously associated with pregnancy complications in plasma samples from singleton pregnancies. Biomarker data, normalized using multiples of medians, on 1635 control and 106 preterm preeclampsia pregnancies were available for model development. Modeling was performed using a methodology that generated a prediction model for preterm preeclampsia in 4 consecutive steps: (1) z-normalization of predictors, (2) combinatorial modeling of so-called (weak) classifiers in the unstratified patient set and in discrete patient strata based on body mass index and/or race, (3) selection of classifiers, and (4) aggregation of the selected classifiers (ie, bagging) into the final prediction model. The prediction performance of models was evaluated using the area under the receiver operating characteristic curve, and detection rate at 10% false-positive rate.

RESULTS

First, the predictor development methodology itself was evaluated. The patient set was split into a training set (2/3) and a test set (1/3) for predictor model development and internal validation. A prediction model was developed for each of the 3 different predictor panels, that is, placental growth factor+metabolites, placental growth factor+mean arterial pressure+metabolites, and placental growth factor+mean arterial pressure+uterine artery pulsatility index+metabolites. For all 3 models, the area under the receiver operating characteristic curve in the test set did not differ significantly from that of the training set. Next, a prediction model was developed using the complete data set for the 3 predictor panels. Among the 50 metabolites available for modeling, 26 were selected across the 3 prediction models; 21 contributed to at least 2 out of the 3 prediction models developed. Each time, area under the receiver operating characteristic curve and detection rate were significantly higher with the new prediction model than with the reference model. Markedly, the estimated detection rate with the placental growth factor+mean arterial pressure+metabolites prediction model in all patients was 0.58 (95% confidence interval, 0.49-0.70), a 15% increase (P<.001) over the detection rate of 0.43 (95% confidence interval, 0.33-0.55) estimated for the reference placental growth factor+mean arterial pressure. The same prediction model significantly improved detection in Black (14%) and White (19%) patients, and in the normal-weight group (18.5≤body mass index<25) and the obese group (body mass index≥30), with respectively 19% and 20% more cases detected, but not in the overweight group, when compared with the reference model. Similar improvement patterns in detection rates were found in the other 2 scenarios, but with smaller improvement amplitudes.

CONCLUSION

Metabolite biomarkers can be combined with the established biomarkers of placental growth factor, mean arterial pressure, and uterine artery pulsatility index to improve the biomarker component of early-pregnancy preterm preeclampsia prediction tests. Classification of the pregnant women according to the maternal characteristics of body mass index and/or race proved instrumental in achieving improved prediction. This suggests that maternal phenotyping can have a role in improving the prediction of obstetrical syndromes such as preeclampsia.

An Interpretable Longitudinal Preeclampsia Risk Prediction Using Machine Learning

Background

Preeclampsia is a pregnancy-specific disease characterized by new onset hypertension after 20 weeks of gestation that affects 2-8% of all pregnancies and contributes to up to 26% of maternal deaths. Despite extensive clinical research, current predictive tools fail to identify up to 66% of patients who will develop preeclampsia. We sought to develop a tool to longitudinally predict preeclampsia risk.

Methods

In this retrospective model development and validation study, we examined a large cohort of patients who delivered at six community and two tertiary care hospitals in the New England region between 02/2015 and 06/2023. We used sociodemographic, clinical diagnoses, family history, laboratory, and vital signs data. We developed eight datasets at 14, 20, 24, 28, 32, 36, 39 weeks gestation and at the hospital admission for delivery. We created linear regression, random forest, xgboost, and deep neural networks to develop multiple models and compared their performance. We used Shapley values to investigate the global and local explainability of the models and the relationships between the predictive variables.

Findings

Our study population (N=120,752) had an incidence of preeclampsia of 5.7% (N=6,920). The performance of the models as measured using the area under the curve, AUC, was in the range 0.73-0.91, which was externally validated. The relationships between some of the variables were complex and non-linear; in addition, the relative significance of the predictors varied over the pregnancy. Compared to the current standard of care for preeclampsia risk stratification in the first trimester, our model would allow 48.6% more at-risk patients to be identified.

Interpretation

Our novel preeclampsia prediction tool would allow clinicians to identify patients at risk early and provide personalized predictions, as well as longitudinal predictions throughout pregnancy.

Funding

National Institutes of Health, Anesthesia Patient Safety Foundation.

RESEARCH IN CONTEXT

Evidence before this study: Current tools for the prediction of preeclampsia are lacking as they fail to identify up to 66% of the patients who develop preeclampsia. We searched PubMed, MEDLINE, and the Web of Science from database inception to May 1, 2023, using the keywords "deep learning", "machine learning", "preeclampsia", "artificial intelligence", "pregnancy complications", and "predictive models". We identified 13 studies that employed machine learning to develop prediction models for preeclampsia risk based on clinical variables. Among these studies, six included biomarkers such as serum placental growth factor, pregnancy-associated plasma protein A, and uterine artery pulsatility index, which are not routinely available in our clinical practice; two studies were in diverse cohorts of more than 100 000 patients, and two studies developed longitudinal predictions using medical records data. However, most studies have limited depth, concerns about data leakage, overfitting, or lack of generalizability.Added value of this study: We developed a comprehensive longitudinal predictive tool based on routine clinical data that can be used throughout pregnancy to predict the risk of preeclampsia. We tested multiple types of predictive models, including machine learning and deep learning models, and demonstrated high predictive power. We investigated the changes over different time points of individual and group variables and found previously known and novel relationships between variables such as red blood cell count and preeclampsia risk.Implications of all the available evidence: Longitudinal prediction of preeclampsia using machine learning can be achieved with high performance. Implementation of an accurate predictive tool within the electronic health records can aid clinical care and identify patients at heightened risk who would benefit from aspirin prophylaxis, increased surveillance, early diagnosis, and escalation in care. These results highlight the potential of using artificial intelligence in clinical decision support, with the ultimate goal of reducing iatrogenic preterm birth and improving perinatal care.

Potential biomarkers for late-onset and term preeclampsia: A scoping review

Preeclampsia is a progressive, multisystem pregnancy disorder. According to the time of onset or delivery, preeclampsia has been subclassified into early-onset (<34 weeks) and late-onset (≥34 weeks), or preterm (<37 weeks) and term (≥37 weeks). Preterm preeclampsia can be effectively predicted at 11-13 weeks well before onset, and its incidence can be reduced by preventively using low-dose aspirin. However, late-onset and term preeclampsia are more prevalent than early forms and still lack effective predictive and preventive measures. This scoping review aims to systematically identify the evidence of predictive biomarkers reported in late-onset and term preeclampsia. This study was conducted based on the guidance of the Joanna Briggs Institute (JBI) methodology for scoping reviews. The Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for scoping reviews (PRISMA-ScR) was used to guide the study. The following databases were searched for related studies: PubMed, Web of Science, Scopus, and ProQuest. Search terms contain "preeclampsia," "late-onset," "term," "biomarker," or "marker," and other synonyms combined as appropriate using the Boolean operators "AND" and "OR." The search was restricted to articles published in English from 2012 to August 2022. Publications were selected if study participants were pregnant women and biomarkers were detected in maternal blood or urine samples before late-onset or term preeclampsia diagnosis. The search retrieved 4,257 records, of which 125 studies were included in the final assessment. The results demonstrate that no single molecular biomarker presents sufficient clinical sensitivity and specificity for screening late-onset and term preeclampsia. Multivariable models combining maternal risk factors with biochemical and/or biophysical markers generate higher detection rates, but they need more effective biomarkers and validation data for clinical utility. This review proposes that further research into novel biomarkers for late-onset and term preeclampsia is warranted and important to find strategies to predict this complication. Other critical factors to help identify candidate markers should be considered, such as a consensus on defining preeclampsia subtypes, optimal testing time, and sample types.