A stillbirth calculator: Development and internal validation of a clinical prediction model to quantify stillbirth risk

Artificial intelligence-driven predictive framework for early detection of still birth

Predictive modeling is becoming increasingly popular in the context of early disease detection. The use of machine learning approaches for predictive modeling can help early detection of diseases thereby enabling medical experts to appropriate medical treatments. Stillbirth prediction is a similar domain where artificial intelligence-based predictive modeling can alleviate this significant global health challenge. Despite advancements in prenatal care, the prevention of stillbirths remains a complex issue requiring further research and interventions. The cardiotocography (CTG) dataset is used in this research work from the UCI machine learning (ML) repository to investigate the efficiency of the proposed approach regarding stillbirth prediction. This research work adopts the Tabular Prior Data Fitted Network (TabPFN) model which was originally designed to solve small tabular classification. TabPFN is used to predict the still or live birth during pregnancy with 97.91% accuracy. To address this life-saving problem with more accurate results and in-depth analysis of ML models, this research work makes use of 13 renowned ML models for performance comparison with the proposed model. The proposed model is evaluated using precision, recall, F-score, Mathews Correlation Coefficient (MCC), and the area under the curve evaluation parameters and the results are 97.87%, 98.26%, 98.05%, 96.42%, and 98.88%, respectively. The results of the proposed model are further evaluated using k-fold cross-validation and its performance comparison with other state-of-the-art studies indicating the superior performance of TabPFN model.

A prediction model for stillbirth based on first trimester pre-eclampsia combined screening

OBJECTIVE

To evaluate the accuracy of combined models of maternal biophysical factors, ultrasound, and biochemical markers for predicting stillbirths.

METHODS

A retrospective cohort study of pregnant women undergoing first-trimester pre-eclampsia screening at 11-13 gestational weeks was conducted. Maternal characteristics and history, mean arterial pressure (MAP) measurement, uterine artery pulsatility index (UtA-PI) ultrasound, maternal ophthalmic peak ratio Doppler, and placental growth factor (PlGF) serum were collected during the visit. Stillbirth was classified as placental dysfunction-related when it occurred with pre-eclampsia or birth weight <10th percentile. Combined prediction models were developed from significant variables in stillbirths, placental dysfunction-related, and controls. We used the area under the receiver-operating-characteristics curve (AUC), sensitivity, and specificity based on a specific cutoff to evaluate the model's predictive performance by measuring the capacity to distinguish between stillbirths and live births.

RESULTS

There were 13 (0.79%) cases of stillbirth in 1643 women included in the analysis. The combination of maternal factors, MAP, UtA-PI, and PlGF, significantly contributed to the prediction of stillbirth. This model was a good predictor for all (including controls) types of stillbirth (AUC 0.879, 95% CI: 0.799-0.959, sensitivity of 99.3%, specificity of 38.5%), and an excellent predictor for placental dysfunction-related stillbirth (AUC 0.984, 95% CI: 0.960-1.000, sensitivity of 98.5, specificity of 85.7).

CONCLUSION

Screening at 11-13 weeks' gestation by combining maternal factors, MAP, UtA-PI, and PlGF, can predict a high proportion of stillbirths. Our model has good accuracy for predicting stillbirths, predominantly placental dysfunction-related stillbirths.

Interpretable machine learning to predict adverse perinatal outcomes: examining marginal predictive value of risk factors during pregnancy

BACKGROUND

The timely identification of nulliparas at high risk of adverse fetal and neonatal outcomes during pregnancy is crucial for initiating clinical interventions to prevent perinatal complications. Although machine learning methods have been applied to predict preterm birth and other pregnancy complications, many models do not provide explanations of their predictions, limiting the clinical use of the model.

OBJECTIVE

This study aimed to develop interpretable prediction models for a composite adverse perinatal outcome (stillbirth, neonatal death, estimated Combined Apgar score of <10, or preterm birth) at different points in time during the pregnancy and to evaluate the marginal predictive value of individual predictors in the context of a machine learning model.

STUDY DESIGN

This was a secondary analysis of the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-be data, a prospective cohort study in which 10,038 nulliparous pregnant individuals with singleton pregnancies were enrolled. Here, interpretable prediction models were developed using L1-regularized logistic regression for adverse perinatal outcomes using data available at 3 study visits during the pregnancy (visit 1: 6 0/7 to 13 6/7 weeks of gestation; visit 2: 16 0/7 to 21 6/7 weeks of gestation; visit 3: 22 0/7 to 29 6/7 weeks of gestation). We identified the important predictors for each model using SHapley Additive exPlanations, a model-agnostic method of computing explanations of model predictions, and evaluated the marginal predictive value of each predictor using the DeLong test.

RESULTS

Our interpretable machine learning model had an area under the receiver operating characteristic curves of 0.617 (95% confidence interval, 0.595-0.639; all predictor variables at visit 1), 0.652 (95% confidence interval, 0.631-0.673; all predictor variables at visit 2), and 0.673 (95% confidence interval, 0.651-0.694; all predictor variables at visit 3). For all visits, the placental biomarker inhibin A was a valuable predictor, as including inhibin A resulted in better performance in predicting adverse perinatal outcomes (P<.001, all visits). At visit 1, endoglin was also a valuable predictor (P<.001). At visit 2, free beta human chorionic gonadotropin (P=.001) and uterine artery pulsatility index (P=.023) were also valuable predictors. At visit 3, cervical length was also a valuable predictor (P<.001).

CONCLUSION

Despite various advances in predictive modeling in obstetrics, the accurate prediction of adverse perinatal outcomes remains difficult. Interpretable machine learning can help clinicians understand how predictions are made, but barriers exist to the widespread clinical adoption of machine learning models for adverse perinatal outcomes. A better understanding of the evolution of risk factors for adverse perinatal outcomes throughout pregnancy is necessary for the development of effective interventions.

Identifying risk of stillbirth using machine learning

BACKGROUND

Previous predictive models using logistic regression for stillbirth do not leverage the advanced and nuanced techniques involved in sophisticated machine learning methods, such as modeling nonlinear relationships between outcomes.

OBJECTIVE

This study aimed to create and refine machine learning models for predicting stillbirth using data available before viability (22-24 weeks) and throughout pregnancy, as well as demographic, medical, and prenatal visit data, including ultrasound and fetal genetics.

STUDY DESIGN

This is a secondary analysis of the Stillbirth Collaborative Research Network, which included data from pregnancies resulting in stillborn and live-born infants delivered at 59 hospitals in 5 diverse regions across the United States from 2006 to 2009. The primary aim was the creation of a model for predicting stillbirth using data available before viability. Secondary aims included refining models with variables available throughout pregnancy and determining variable importance.

RESULTS

Among 3000 live births and 982 stillbirths, 101 variables of interest were identified. Of the models incorporating data available before viability, the random forests model had 85.1% accuracy (area under the curve) and high sensitivity (88.6%), specificity (85.3%), positive predictive value (85.3%), and negative predictive value (84.8%). A random forests model using data collected throughout pregnancy resulted in accuracy of 85.0%; this model had 92.2% sensitivity, 77.9% specificity, 84.7% positive predictive value, and 88.3% negative predictive value. Important variables in the previability model included previous stillbirth, minority race, gestational age at the earliest prenatal visit and ultrasound, and second-trimester serum screening.

CONCLUSION

Applying advanced machine learning techniques to a comprehensive database of stillbirths and live births with unique and clinically relevant variables resulted in an algorithm that could accurately identify 85% of pregnancies that would result in stillbirth, before they reached viability. Once validated in representative databases reflective of the US birthing population and then prospectively, these models may provide effective risk stratification and clinical decision-making support to better identify and monitor those at risk of stillbirth.

On usage of artificial intelligence for predicting mortality during and post-pregnancy: a systematic review of literature

BACKGROUND

Care during pregnancy, childbirth and puerperium are fundamental to avoid pathologies for the mother and her baby. However, health issues can occur during this period, causing misfortunes, such as the death of the fetus or neonate. Predictive models of fetal and infant deaths are important technological tools that can help to reduce mortality indexes. The main goal of this work is to present a systematic review of literature focused on computational models to predict mortality, covering stillbirth, perinatal, neonatal, and infant deaths, highlighting their methodology and the description of the proposed computational models.

METHODS

We conducted a systematic review of literature, limiting the search to the last 10 years of publications considering the five main scientific databases as source.

RESULTS

From 671 works, 18 of them were selected as primary studies for further analysis. We found that most of works are focused on prediction of neonatal deaths, using machine learning models (more specifically Random Forest). The top five most common features used to train models are birth weight, gestational age, sex of the child, Apgar score and mother's age. Having predictive models for preventing mortality during and post-pregnancy not only improve the mother's quality of life, as well as it can be a powerful and low-cost tool to decrease mortality ratios.

CONCLUSION

Based on the results of this SRL, we can state that scientific efforts have been done in this area, but there are many open research opportunities to be developed by the community.

Prediction of stillbirth low resource setting in Northern Uganda

BACKGROUND

Women of Afro-Caribbean and Asian origin are more at risk of stillbirths. However, there are limited tools built for risk-prediction models for stillbirth within sub-Saharan Africa. Therefore, we examined the predictors for stillbirth in low resource setting in Northern Uganda.

METHODS

Prospective cohort study at St. Mary's hospital Lacor in Northern Uganda. Using Yamane's 1967 formula for calculating sample size for cohort studies using finite population size, the required sample size was 379 mothers. We doubled the number (to > 758) to cater for loss to follow up, miscarriages, and clients opting out of the study during the follow-up period. Recruited 1,285 pregnant mothers at 16-24 weeks, excluded those with lethal congenital anomalies diagnosed on ultrasound. Their history, physical findings, blood tests and uterine artery Doppler indices were taken, and the mothers were encouraged to continue with routine prenatal care until the time for delivery. While in the delivery ward, they were followed up in labour until delivery by the research team. The primary outcome was stillbirth 24 + weeks with no signs of life. Built models in RStudio. Since the data was imbalanced with low stillbirth rate, used ROSE package to over-sample stillbirths and under-sample live-births to balance the data. We cross-validated the models with the ROSE-derived data using K (10)-fold cross-validation and obtained the area under curve (AUC) with accuracy, sensitivity and specificity.

RESULTS

The incidence of stillbirth was 2.5%. Predictors of stillbirth were history of abortion (aOR = 3.07, 95% CI 1.11-8.05, p = 0.0243), bilateral end-diastolic notch (aOR = 3.51, 95% CI 1.13-9.92, p = 0.0209), personal history of preeclampsia (aOR = 5.18, 95% CI 0.60-30.66, p = 0.0916), and haemoglobin 9.5 - 12.1 g/dL (aOR = 0.33, 95% CI 0.11-0.93, p = 0.0375). The models' AUC was 75.0% with 68.1% accuracy, 69.1% sensitivity and 67.1% specificity.

CONCLUSION

Risk factors for stillbirth include history of abortion and bilateral end-diastolic notch, while haemoglobin of 9.5-12.1 g/dL is protective.

External validation of prognostic models to predict stillbirth using International Prediction of Pregnancy Complications (IPPIC) Network database: individual participant data meta-analysis

OBJECTIVE

Stillbirth is a potentially preventable complication of pregnancy. Identifying women at high risk of stillbirth can guide decisions on the need for closer surveillance and timing of delivery in order to prevent fetal death. Prognostic models have been developed to predict the risk of stillbirth, but none has yet been validated externally. In this study, we externally validated published prediction models for stillbirth using individual participant data (IPD) meta-analysis to assess their predictive performance.

METHODS

MEDLINE, EMBASE, DH-DATA and AMED databases were searched from inception to December 2020 to identify studies reporting stillbirth prediction models. Studies that developed or updated prediction models for stillbirth for use at any time during pregnancy were included. IPD from cohorts within the International Prediction of Pregnancy Complications (IPPIC) Network were used to validate externally the identified prediction models whose individual variables were available in the IPD. The risk of bias of the models and cohorts was assessed using the Prediction study Risk Of Bias ASsessment Tool (PROBAST). The discriminative performance of the models was evaluated using the C-statistic, and calibration was assessed using calibration plots, calibration slope and calibration-in-the-large. Performance measures were estimated separately in each cohort, as well as summarized across cohorts using random-effects meta-analysis. Clinical utility was assessed using net benefit.

RESULTS

Seventeen studies reporting the development of 40 prognostic models for stillbirth were identified. None of the models had been previously validated externally, and the full model equation was reported for only one-fifth (20%, 8/40) of the models. External validation was possible for three of these models, using IPD from 19 cohorts (491 201 pregnant women) within the IPPIC Network database. Based on evaluation of the model development studies, all three models had an overall high risk of bias, according to PROBAST. In the IPD meta-analysis, the models had summary C-statistics ranging from 0.53 to 0.65 and summary calibration slopes ranging from 0.40 to 0.88, with risk predictions that were generally too extreme compared with the observed risks. The models had little to no clinical utility, as assessed by net benefit. However, there remained uncertainty in the performance of some models due to small available sample sizes.

CONCLUSIONS

The three validated stillbirth prediction models showed generally poor and uncertain predictive performance in new data, with limited evidence to support their clinical application. The findings suggest methodological shortcomings in their development, including overfitting. Further research is needed to further validate these and other models, identify stronger prognostic factors and develop more robust prediction models. © 2021 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Synthetic minority oversampling of vital statistics data with generative adversarial networks

Objective

Minority oversampling is a standard approach used for adjusting the ratio between the classes on imbalanced data. However, established methods often provide modest improvements in classification performance when applied to data with extremely imbalanced class distribution and to mixed-type data. This is usual for vital statistics data, in which the outcome incidence dictates the amount of positive observations. In this article, we developed a novel neural network-based oversampling method called actGAN (activation-specific generative adversarial network) that can derive useful synthetic observations in terms of increasing prediction performance in this context.

Materials and Methods

From vital statistics data, the outcome of early stillbirth was chosen to be predicted based on demographics, pregnancy history, and infections. The data contained 363 560 live births and 139 early stillbirths, resulting in class imbalance of 99.96% and 0.04%. The hyperparameters of actGAN and a baseline method SMOTE-NC (Synthetic Minority Over-sampling Technique-Nominal Continuous) were tuned with Bayesian optimization, and both were compared against a cost-sensitive learning-only approach.

Results

While SMOTE-NC provided mixed results, actGAN was able to improve true positive rate at a clinically significant false positive rate and area under the curve from the receiver-operating characteristic curve consistently.

Discussion

Including an activation-specific output layer to a generator network of actGAN enables the addition of information about the underlying data structure, which overperforms the nominal mechanism of SMOTE-NC.

Conclusions

actGAN provides an improvement to the prediction performance for our learning task. Our developed method could be applied to other mixed-type data prediction tasks that are known to be afflicted by class imbalance and limited data availability.

Proposing a machine-learning based method to predict stillbirth before and during delivery and ranking the features: nationwide retrospective cross-sectional study

Background

Stillbirth is defined as fetal loss in pregnancy beyond 28 weeks by WHO. In this study, a machine-learning based method is proposed to predict stillbirth from livebirth and discriminate stillbirth before and during delivery and rank the features.

Method

A two-step stack ensemble classifier is proposed for classifying the instances into stillbirth and livebirth at the first step and then, classifying stillbirth before delivery from stillbirth during the labor at the second step. The proposed SE has two consecutive layers including the same classifiers. The base classifiers in each layer are decision tree, Gradient boosting classifier, logistics regression, random forest and support vector machines which are trained independently and aggregated based on Vote boosting method. Moreover, a new feature ranking method is proposed in this study based on mean decrease accuracy, Gini Index and model coefficients to find high-ranked features.

Results

IMAN registry dataset is used in this study considering all births at or beyond 28th gestational week from 2016/04/01 to 2017/01/01 including 1,415,623 live birth and 5502 stillbirth cases. A combination of maternal demographic features, clinical history, fetal properties, delivery descriptors, environmental features, healthcare service provider descriptors and socio-demographic features are considered. The experimental results show that our proposed SE outperforms the compared classifiers with the average accuracy of 90%, sensitivity of 91%, specificity of 88%. The discrimination of the proposed SE is assessed and the average AUC of ±95%, CI of 90.51% ±1.08 and 90% ±1.12 is obtained on training dataset for model development and test dataset for external validation, respectively. The proposed SE is calibrated using isotopic nonparametric calibration method with the score of 0.07. The process is repeated 10,000 times and AUC of SE classifiers using random different training datasets as null distribution. The obtained p-value to assess the specificity of the proposed SE is 0.0126 which shows the significance of the proposed SE.

Conclusions

Gestational age and fetal height are two most important features for discriminating livebirth from stillbirth. Moreover, hospital, province, delivery main cause, perinatal abnormality, miscarriage number and maternal age are the most important features for classifying stillbirth before and during delivery.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12884-021-03658-z.

Ethnic disparities in stillbirth risk in Yunnan, China: a prospective cohort study, 2010-2018

Background

Racial and ethnic disparities in stillbirth risk had been documented in most western countries, but it remains unknown in China. This study was to determine whether exist ethnic disparities in stillbirth risk in mainland China.

Methods

Pregnancy outcomes and ethnicity data were obtained from the National Free Preconception Health Examination Project (NEPHEP), a nationwide prospective population-based cohort study conducted in Yunnan China from 2010-2018. The Han majority and other four main minorities including Yi, Dai, Miao, Hani were investigated in the analysis. The stillbirth hazards were estimated by life-table analysis. The excess stillbirth risk (ESR) was computed for Chinese minorities using multivariable logistic regression.

Results

Compared with other four minorities, women in Han majority were more likely to more educated, less multiparous, and less occupied in agriculture. The pattern of stillbirth hazard of Dai women across different gestation intervals were found to be different from other ethnic groups, especially in 20-23 weeks with 3.2 times higher than Han women. The ESR of the Dai, Hani, Miao, and Yi were 45.05, 18.70, -4.17 and 12.28%, respectively. Adjusted for maternal age, education, birth order and other general risk factors, the ethnic disparity still persisted between Dai women and Han women. Adjusted for preterm birth further (gestation age <37 weeks) can reduce 16.91% ESR of Dai women and made the disparity insignificant. Maternal diseases and congenital anomalies explained little for ethnic disparities.

Conclusions

We identified the ethnic disparity in stillbirth risk between Dai women and Han women. General risk factors including sociodemographic factors and maternal diseases explained little. Considerable ethnic disparities can be attributed to preterm birth.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12889-020-10102-y.

Protocol for the development and validation of a risk prediction model for stillbirths from 35 weeks gestation in Australia

BACKGROUND

Despite advances in the care of women and their babies in the past century, an estimated 1.7 million babies are born still each year throughout the world. A robust method to estimate a pregnant woman's individualized risk of late-pregnancy stillbirth is needed to inform decision-making around the timing of birth to reduce the risk of stillbirth from 35 weeks of gestation in Australia, a high-resource setting.

METHODS

This is a protocol for a cross-sectional study of all late-pregnancy births in Australia (2005-2015) from 35 weeks of gestation including 5188 stillbirths among 3.1 million births at an estimated rate of 1.7 stillbirths per 1000 births. A multivariable logistic regression model will be developed in line with current Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) guidelines to estimate the gestation-specific probability of stillbirth with prediction intervals. Candidate predictors were identified from systematic reviews and clinical consultation and will be described through univariable regression analysis. To generate a final model, elimination by backward stepwise multivariable logistic regression will be performed. The model will be internally validated using bootstrapping with 1000 repetitions and externally validated using a temporally unique dataset. Overall model performance will be assessed with R², calibration, and discrimination. Calibration will be reported using a calibration plot with 95% confidence intervals (α = 0.05). Discrimination will be measured by the C-statistic and area underneath the receiver-operator curves. Clinical usefulness will be reported as positive and negative predictive values, and a decision curve analysis will be considered.

DISCUSSION

A robust method to predict a pregnant woman's individualized risk of late-pregnancy stillbirth is needed to inform timely, appropriate care to reduce stillbirth. Among existing prediction models designed for obstetric use, few have been subject to internal and external validation and many fail to meet recommended reporting standards. In developing a risk prediction model for late-gestation stillbirth with both providers and pregnant women in mind, we endeavor to develop a validated model for clinical use in Australia that meets current reporting standards.

Predicting risk of stillbirth and preterm pregnancies with machine learning

Modelling the risk of abnormal pregnancy-related outcomes such as stillbirth and preterm birth have been proposed in the past. Commonly they utilize maternal demographic and medical history information as predictors, and they are based on conventional statistical modelling techniques. In this study, we utilize state-of-the-art machine learning methods in the task of predicting early stillbirth, late stillbirth and preterm birth pregnancies. The aim of this experimentation is to discover novel risk models that could be utilized in a clinical setting. A CDC data set of almost sixteen million observations was used conduct feature selection, parameter optimization and verification of proposed models. An additional NYC data set was used for external validation. Algorithms such as logistic regression, artificial neural network and gradient boosting decision tree were used to construct individual classifiers. Ensemble learning strategies of these classifiers were also experimented with. The best performing machine learning models achieved 0.76 AUC for early stillbirth, 0.63 for late stillbirth and 0.64 for preterm birth while using a external NYC test data. The repeatable performance of our models demonstrates robustness that is required in this context. Our proposed novel models provide a solid foundation for risk prediction and could be further improved with the addition of biochemical and/or biophysical markers.

Prediction of stillbirth: an umbrella review of evaluation of prognostic variables

BACKGROUND

Stillbirth accounts for over 2 million deaths a year worldwide and rates remains stubbornly high. Multivariable prediction models may be key to individualised monitoring, intervention or early birth in pregnancy to prevent stillbirth.

OBJECTIVES

To collate and evaluate systematic reviews of factors associated with stillbirth in order to identify variables relevant to prediction model development.

SEARCH STRATEGY

MEDLINE, Embase, DARE and Cochrane Library databases and reference lists were searched up to November 2019.

SELECTION CRITERIA

We included systematic reviews of association of individual variables with stillbirth without language restriction.

DATA COLLECTION AND ANALYSIS

Abstract screening and data extraction were conducted in duplicate. Methodological quality was assessed using AMSTAR and QUIPS criteria. The evidence supporting association with each variable was graded.

RESULTS

The search identified 1198 citations. Sixty-nine systematic reviews reporting 64 variables were included. The most frequently reported were maternal age (n = 5), body mass index (n = 6) and maternal diabetes (n = 5). Uterine artery Doppler appeared to have the best performance of any single test for stillbirth. The strongest evidence of association was for nulliparity and pre-existing hypertension.

CONCLUSION

We have identified variables relevant to the development of prediction models for stillbirth. Age, parity and prior adverse pregnancy outcomes had a more convincing association than the best performing tests, which were PAPP-A, PlGF and UtAD. The evidence was limited by high heterogeneity and lack of data on intervention bias.

TWEETABLE ABSTRACT

Review shows key predictors for use in developing models predicting stillbirth include age, prior pregnancy outcome and PAPP-A, PLGF and Uterine artery Doppler.

Can risk prediction models help us individualise stillbirth prevention? A systematic review and critical appraisal of published risk models

BACKGROUND

Stillbirth prevention is an international priority - risk prediction models could individualise care and reduce unnecessary intervention, but their use requires evaluation.

OBJECTIVES

To identify risk prediction models for stillbirth, and assess their potential accuracy and clinical benefit in practice.

SEARCH STRATEGY

MEDLINE, Embase, DH-DATA and AMED databases were searched from inception to June 2019 using terms relevant to stillbirth, perinatal mortality and prediction models. The search was compliant with Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines.

SELECTION CRITERIA

Studies developing and/or validating prediction models for risk of stillbirth developed for application during pregnancy.

DATA COLLECTION AND ANALYSIS

Study screening and data extraction were conducted in duplicate, using the CHARMS checklist. Risk of bias was appraised using the PROBAST tool.

RESULTS

The search identified 2751 citations. Fourteen studies reporting development of 69 models were included. Variables consistently included were: ethnicity, body mass index, uterine artery Doppler, pregnancy-associated plasma protein and placental growth factor. For almost all models there were significant concerns about risk of bias. Apparent model performance (i.e. in the development dataset) was highest in models developed for use later in pregnancy and including maternal characteristics, and ultrasound and biochemical variables, but few were internally validated and none were externally validated.

CONCLUSIONS

Almost all models identified were at high risk of bias. There are first-trimester models of possible clinical benefit in early risk stratification; these require validation and clinical evaluation. There were few later pregnancy models but, if validated, these could be most relevant to individualised discussions around timing of birth.

TWEETABLE ABSTRACT

Prediction models using maternal factors, blood tests and ultrasound could individualise stillbirth prevention, but existing models are at high risk of bias.

Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980-2015

Quantification of stillbirth risk has potential to support clinical decision-making. Studies that have attempted to quantify stillbirth risk have been hampered by small event rates, a limited range of predictors that typically exclude obstetric history, lack of validation, and restriction to a single classifier (logistic regression). Consequently, predictive performance remains low, and risk quantification has not been adopted into antenatal practice. The study population consisted of all births to women in Western Australia from 1980 to 2015, excluding terminations. After all exclusions there were 947,025 livebirths and 5,788 stillbirths. Predictive models for stillbirth were developed using multiple machine learning classifiers: regularised logistic regression, decision trees based on classification and regression trees, random forest, extreme gradient boosting (XGBoost), and a multilayer perceptron neural network. We applied 10-fold cross-validation using independent data not used to develop the models. Predictors included maternal socio-demographic characteristics, chronic medical conditions, obstetric complications and family history in both the current and previous pregnancy. In this cohort, 66% of stillbirths were observed for multiparous women. The best performing classifier (XGBoost) predicted 45% (95% CI: 43%, 46%) of stillbirths for all women and 45% (95% CI: 43%, 47%) of stillbirths after the inclusion of previous pregnancy history. Almost half of stillbirths could be potentially identified antenatally based on a combination of current pregnancy complications, congenital anomalies, maternal characteristics, and medical history. Greatest sensitivity is achieved with addition of current pregnancy complications. Ensemble classifiers offered marginal improvement for prediction compared to logistic regression.

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.

Maternal and foetal medical conditions during pregnancy as determinants of intrapartum stillbirth in public health facilities of Addis Ababa: a case-control study

Introduction

globally, intrapartum stillbirth accounts for 1 million deaths of babies annually, representing approximately one-third of global stillbirth toll. Intrapartum stillbirth occurs due to causes ranging from maternal medical and obstetric conditions; access to quality obstetric care services during pregnancy; and types, timing and quality of intrapartum care. Different medical conditions including hypertensive & metabolic disorders, infections and nutritional deficiencies during pregnancy are among risk factors of stillbirth. Ethiopia remains one of the 10 high-burden stillbirth countries with estimated rate of more than 25 per 1000 births.

Methods

a case-control study using primary data from chart review of medical records of women who experienced intrapartum stillbirth in 23 public health facilities of Addis Ababa during the period July 1, 2010 - June 30, 2015 was conducted. Data was collected from charts of all cases of intrapartum stillbirth meeting the inclusion criteria and randomly selected charts of controls in two to one (2:1) control to case ratio.

Results

chronic medical conditions including diabetes, cardiac and renal diseases were less prevalent (1%) among the study population whereas only 6% of women experienced hypertensive disorder during the pregnancy in review. Moreover, 6.5% of the study population had HIV infection where being HIV negative was protective against intrapartum stillbirth (aOR 0.37, 95% CI 0.18-0.78). Women with non-cephalic foetal presentation during last ANC visit were three times more at risk of experiencing intrapartum stillbirth whereas singleton pregnancy had strong protective association against intrapartum stillbirth (p<0.05).

Conclusion

untreated chronic medical conditions, infection, poor monitoring of foetal conditions and multiple pregnancy are among important risk factors for intrapartum stillbirth.

Development and validation of a clinical model for preconception and early pregnancy risk prediction of gestational diabetes mellitus in nulliparous women

Implementation of dietary and lifestyle interventions prior to and early in pregnancy in high risk women has been shown to reduce the risk of gestational diabetes mellitus (GDM) development later in pregnancy. Although numerous risk factors for GDM have been identified, the ability to accurately identify women before or early in pregnancy who could benefit most from these interventions remains limited. As nulliparous women are an under-screened population with risk profiles that differ from their multiparous counterparts, development of a prediction model tailored to nulliparous women may facilitate timely preventive intervention and improve maternal and infant outcomes. We aimed to develop and validate a model for preconception and early pregnancy prediction of gestational diabetes mellitus based on clinical risk factors for nulliparous women. A risk prediction model was built within a large California birth cohort including singleton live birth records from 2007-2012. Model accuracy was assessed both internally and externally, within a cohort of women who delivered at University of Iowa Hospitals and Clinics between 2009-2017, using discrimination and calibration. Differences in predictive accuracy of the model were assessed within specific racial/ethnic groups. The prediction model included five risk factors: race/ethnicity, age at delivery, pre-pregnancy body mass index, family history of diabetes, and pre-existing hypertension. The area under the curve (AUC) for the California internal validation cohort was 0.732 (95% confidence interval (CI) 0.728, 0.735), and 0.710 (95% CI 0.672, 0.749) for the Iowa external validation cohort. The model performed particularly well in Hispanic (AUC 0.739) and Black women (AUC 0.719). Our findings suggest that estimation of a woman's risk for GDM through model-based incorporation of risk factors accurately identifies those at high risk (i.e., predicted risk >6%) who could benefit from preventive intervention encouraging prompt incorporation of this tool into preconception and prenatal care.

Prediction of fetal loss in Chinese pregnant patients with systemic lupus erythematosus: a retrospective cohort study

OBJECTIVE

To develop a predictive model for fetal loss in women with systemic lupus erythematosus (SLE).

DESIGN

A retrospective cohort study.

SETTING

Data were collected in a tertiary medical centre, located in Shanghai, China, from September 2011 to May 2017.

PARTICIPANTS

338 pregnancies with SLE were analysed retrospectively. Cases of multiple pregnancy and those in which artificial abortion was performed for personal reasons were excluded.

PRIMARY OUTCOME MEASURES

Fetal loss was the primary outcome. A stepwise regression to identify the predictors related to the fetal loss and coefficient B of each variable was used to develop a predictive model and make a corresponding risk classification. The Hosmer-Lemeshow test, Omnibus test and area under the receiver-operating characteristic curve (AUC) were used to assess the goodness-of-fit and discrimination of the predictive model. A 10-fold cross validation was used to assess the model for overfitting.

RESULTS

Unplanned pregnancies (OR 2.84, 95% CI 1.12 to 7.22), C₃ hypocomplementemia (OR 5.46, 95% CI 2.30 to 12.97) and 24 hour-urinary protein level (0.3≤protein<1.0 g/24 hours: OR 2.10, 95% CI 0.63 to 6.95; protein≥1.0 g/24 hours: OR 5.89, 95% CI 2.30 to 15.06) were selected by the stepwise regression. The Hosmer-Lemeshow test resulted in p=0.325; the Omnibus test resulted in p<0.001 and the AUC was 0.829 (95% CI 0.744 to 0.91) in the regression model. The corresponding risk score classification was divided into low risk (0-3) and high risk groups (>3), with a sensitivity of 60.5%, a specificity of 93.3%, positive likelihood ratio of 9.03 and negative likelihood ratio of 0.42.

CONCLUSIONS

A predictive model for fetal loss in women with SLE was developed using the timing of conception, C₃ complement and 24 hour-urinary protein level. This model may help clinicians in identifying women with high risk pregnancies, thereby carrying out monitoring or/and interventions for improving fetal outcomes.

Optimal Obstetric Management for Women with Diabetes: the Benefits and Costs of Fetal Surveillance

PURPOSE OF REVIEW

To elaborate on the risks and benefits associated with antenatal fetal surveillance for stillbirth prevention in women with diabetes.

RECENT FINDINGS

Women with pregestational diabetes have a 3- to 5-fold increased odds of stillbirth compared to women without diabetes. The stillbirth risk in women with gestational diabetes (GDM) is more controversial; while recent data suggest the odds for stillbirth are approximately 50% higher in women with GDM at term (37 weeks and beyond) than in those without GDM, it is unclear if this risk is seen in women with optimal glycemic control. Current professional society guidelines are broad with respect to fetal testing strategies and delivery timing in women with diabetes. The data supporting strategies to reduce the risk of stillbirth in women with diabetes are limited. Antepartum fetal surveillance should be performed to reduce stillbirth rates; however, the optimal test, frequency of testing, and delivery timing are not yet clear. Future studies of obstetric management for women with diabetes should consider not just individual but also system level costs and benefits associated with antenatal surveillance.