Clinical risk assessment in early pregnancy for preeclampsia in nulliparous women: A population based cohort study

Predicting intensive care need in women with preeclampsia using machine learning - a pilot study

BACKGROUND

Predicting severe preeclampsia with need for intensive care is challenging. To better predict high-risk pregnancies to prevent adverse outcomes such as eclampsia is still an unmet need worldwide. In this study we aimed to develop a prediction model for severe outcomes using routine biomarkers and clinical characteristics.

METHODS

We used machine learning models based on data from an intensive care cohort with severe preeclampsia (n=41) and a cohort of preeclampsia controls (n=40) with the objective to find patterns for severe disease not detectable with traditional logistic regression models.

RESULTS

The best model was generated by including the laboratory parameters aspartate aminotransferase (ASAT), uric acid and body mass index (BMI) with a cross-validation accuracy of 0.88 and an area under the curve (AUC) of 0.91. Our model was internally validated on a test-set where the accuracy was lower, 0.82, with an AUC of 0.85.

CONCLUSION

The clinical routine blood parameters ASAT and uric acid as well as BMI, were the parameters most indicative of severe disease. Aspartate aminotransferase reflects liver involvement, uric acid might be involved in several steps of the pathophysiologic process of preeclampsia, and obesity is a well-known risk factor for development of both severe and non-severe preeclampsia likely involving inflammatory pathways..[Figure: see text].

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.

Novel Associations Between Mid-Pregnancy Cardiovascular Biomarkers and Preeclampsia: An Explorative Nested Case-Control Study

Prediction of women at high risk of preeclampsia is important for prevention and increased surveillance of the disease. Current prediction models need improvement, particularly with regard to late-onset preeclampsia. Preeclampsia shares pathophysiological entities with cardiovascular disease; thus, cardiovascular biomarkers may contribute to improving prediction models. In this nested case-control study, we explored the predictive importance of mid-pregnancy cardiovascular biomarkers for subsequent preeclampsia. We included healthy women with singleton pregnancies who had donated blood in mid-pregnancy (~ 18 weeks' gestation). Cases were women with subsequent preeclampsia (n = 296, 10% of whom had early-onset preeclampsia [< 34 weeks]). Controls were women who had healthy pregnancies (n = 333). We collected data on maternal, pregnancy, and infant characteristics from medical records. We used the Olink cardiovascular II panel immunoassay to measure 92 biomarkers in the mid-pregnancy plasma samples. The Boruta algorithm was used to determine the predictive importance of the investigated biomarkers and first-trimester pregnancy characteristics for the development of preeclampsia. The following biomarkers had confirmed associations with early-onset preeclampsia (in descending order of importance): placental growth factor (PlGF), matrix metalloproteinase (MMP-12), lectin-like oxidized LDL receptor 1, carcinoembryonic antigen-related cell adhesion molecule 8, serine protease 27, pro-interleukin-16, and poly (ADP-ribose) polymerase 1. The biomarkers that were associated with late-onset preeclampsia were BNP, MMP-12, alpha-L-iduronidase (IDUA), PlGF, low-affinity immunoglobulin gamma Fc region receptor II-b, and T cell surface glycoprotein. Our results suggest that MMP-12 is a promising novel preeclampsia biomarker. Moreover, BNP and IDUA may be of value in enhancing prediction of late-onset preeclampsia.

Pre-pregnancy body mass index combined with peripheral blood PLGF, DCN, LDH, and UA in a risk prediction model for pre-eclampsia

Objective

This study analyzes the levels of peripheral blood placental growth factor (PLGF), body mass index (BMI), decorin (DCN), lactate dehydrogenase (LDH), uric acid (UA), and clinical indicators of patients with preeclampsia (PE), and establishes a predictive risk model of PE, which can provide a reference for early and effective prediction of PE.

Methods

81 cases of pregnant women with PE who had regular prenatal checkups and delivered in Jinshan Branch of Shanghai Sixth People's Hospital from June 2020 to December 2022 were analyzed, and 92 pregnant women with normal pregnancies who had their antenatal checkups and delivered at the hospital during the same period were selected as the control group. Clinical data and peripheral blood levels of PLGF, DCN, LDH, and UA were recorded, and the two groups were subjected to univariate screening and multifactorial logistic regression analysis. Based on the screening results, the diagnostic efficacy of PE was evaluated using the receiver operating characteristic (ROC) curve. Risk prediction nomogram model was constructed using R language. The Bootstrap method (self-sampling method) was used to validate and produce calibration plots; the decision curve analysis (DCA) was used to assess the clinical benefit rate of the model.

Results

There were statistically significant differences in age, pre-pregnancy BMI, gestational weight gain, history of PE or family history, family history of hypertension, gestational diabetes mellitus, and history of renal disease between the two groups (P < 0.05). The results of multifactorial binary logistic stepwise regression revealed that peripheral blood levels of PLGF, DCN, LDH, UA, and pre-pregnancy BMI were independent influences on the occurrence of PE (P < 0.05). The area under the curve of PLGF, DCN, LDH, UA levels and pre-pregnancy BMI in the detection of PE was 0.952, with a sensitivity of 0.901 and a specificity of 0.913, which is better than a single clinical diagnostic indicator. The results of multifactor analysis were constructed as a nomogram model, and the mean absolute error of the calibration curve of the modeling set was 0.023, suggesting that the predictive probability of the model was generally compatible with the actual value. DCA showed the predictive model had a high net benefit in the range of 5% to 85%, suggesting that the model has clinical utility value.

Conclusion

The occurrence of PE is related to the peripheral blood levels of PLGF, DCN, LDH, UA and pre-pregnancy BMI, and the combination of these indexes has a better clinical diagnostic value than a single index. The nomogram model constructed by using the above indicators can be used for the prediction of PE and has high predictive efficacy.

Predicting the onset of preeclampsia by longitudinal monitoring of metabolic changes throughout pregnancy with Raman spectroscopy

Preeclampsia is a life-threatening pregnancy disorder. Current clinical assays cannot predict the onset of preeclampsia until the late 2nd trimester, which often leads to poor maternal and neonatal outcomes. Here we show that Raman spectroscopy combined with machine learning in pregnant patient plasma enables rapid, highly sensitive maternal metabolome screening that predicts preeclampsia as early as the 1st trimester with >82% accuracy. We identified 12, 15 and 17 statistically significant metabolites in the 1st, 2nd and 3rd trimesters, respectively. Metabolic pathway analysis shows multiple pathways corresponding to amino acids, fatty acids, retinol, and sugars are enriched in the preeclamptic cohort relative to a healthy pregnancy. Leveraging Pearson's correlation analysis, we show for the first time with Raman Spectroscopy that metabolites are associated with several clinical factors, including patients' body mass index, gestational age at delivery, history of preeclampsia, and severity of preeclampsia. We also show that protein quantification alone of proinflammatory cytokines and clinically relevant angiogenic markers are inadequate in identifying at-risk patients. Our findings demonstrate that Raman spectroscopy is a powerful tool that may complement current clinical assays in early diagnosis and in the prognosis of the severity of preeclampsia to ultimately enable comprehensive prenatal care for all patients.

New advances in prediction and surveillance of preeclampsia: role of machine learning approaches and remote monitoring

Preeclampsia, a multisystem disorder in pregnancy, is still one of the main causes of maternal morbidity and mortality. Due to a lack of a causative therapy, an accurate prediction of women at risk for the disease and its associated adverse outcomes is of utmost importance to tailor care. In the past two decades, there have been successful improvements in screening as well as in the prediction of the disease in high-risk women. This is due to, among other things, the introduction of biomarkers such as the sFlt-1/PlGF ratio. Recently, the traditional definition of preeclampsia has been expanded based on new insights into the pathophysiology and conclusive evidence on the ability of angiogenic biomarkers to improve detection of preeclampsia-associated maternal and fetal adverse events.However, with the widespread availability of digital solutions, such as decision support algorithms and remote monitoring devices, a chance for a further improvement of care arises. Two lines of research and application are promising: First, on the patient side, home monitoring has the potential to transform the traditional care pathway. The importance of the ability to input and access data remotely is a key learning from the COVID-19 pandemic. Second, on the physician side, machine-learning-based decision support algorithms have been shown to improve precision in clinical decision-making. The integration of signals from patient-side remote monitoring devices into predictive algorithms that power physician-side decision support tools offers a chance to further improve care.The purpose of this review is to summarize the recent advances in prediction, diagnosis and monitoring of preeclampsia and its associated adverse outcomes. We will review the potential impact of the ability to access to clinical data via remote monitoring. In the combination of advanced, machine learning-based risk calculation and remote monitoring lies an unused potential that allows for a truly patient-centered care.

Machine learning applied in maternal and fetal health: a narrative review focused on pregnancy diseases and complications

Introduction

Machine learning (ML) corresponds to a wide variety of methods that use mathematics, statistics and computational science to learn from multiple variables simultaneously. By means of pattern recognition, ML methods are able to find hidden correlations and accomplish accurate predictions regarding different conditions. ML has been successfully used to solve varied problems in different areas of science, such as psychology, economics, biology and chemistry. Therefore, we wondered how far it has penetrated into the field of obstetrics and gynecology.

Aim

To describe the state of art regarding the use of ML in the context of pregnancy diseases and complications.

Methodology

Publications were searched in PubMed, Web of Science and Google Scholar. Seven subjects of interest were considered: gestational diabetes mellitus, preeclampsia, perinatal death, spontaneous abortion, preterm birth, cesarean section, and fetal malformations.

Current state

ML has been widely applied in all the included subjects. Its uses are varied, the most common being the prediction of perinatal disorders. Other ML applications include (but are not restricted to) biomarker discovery, risk estimation, correlation assessment, pharmacological treatment prediction, drug screening, data acquisition and data extraction. Most of the reviewed articles were published in the last five years. The most employed ML methods in the field are non-linear. Except for logistic regression, linear methods are rarely used.

Future challenges

To improve data recording, storage and update in medical and research settings from different realities. To develop more accurate and understandable ML models using data from cutting-edge instruments. To carry out validation and impact analysis studies of currently existing high-accuracy ML models.

Conclusion

The use of ML in pregnancy diseases and complications is quite recent, and has increased over the last few years. The applications are varied and point not only to the diagnosis, but also to the management, treatment, and pathophysiological understanding of perinatal alterations. Facing the challenges that come with working with different types of data, the handling of increasingly large amounts of information, the development of emerging technologies, and the need of translational studies, it is expected that the use of ML continue growing in the field of obstetrics and gynecology.

The Stockholm-Gotland perinatal cohort-A population-based cohort including longitudinal data throughout pregnancy and the postpartum period

BACKGROUND

Register-based reproductive and perinatal databases rarely contain detailed information from medical records or repeated measurements throughout pregnancy and delivery. This lack of enriched pregnancy and birth data led to the initiation of the Swedish Stockholm-Gotland Perinatal Cohort (SGPC).

OBJECTIVES

To describe the strengths of the SGPC, as well as the unique research questions that can be addressed using this cohort.

POPULATION

The SGPC is a prospectively collected, population-based cohort that includes all births (from 22 completed gestational weeks onwards) between 1 January 2008 and 15 June 2020 in the Stockholm and Gotland regions of Sweden (N 335,153 singleton and N 11,025 multiple pregnancies).

DESIGN

Descriptive study.

METHODS

The SGPC is based on the electronic medical records of women and their infants. The medical record system is used for all antenatal clinic visits and admissions, delivery and neonatal admissions, as well as postpartum clinical visits. SGPC has been further enriched with data linkages to 10 Swedish National Health Care and Quality Registers.

PRELIMINARY RESULTS

In contrast to other reproductive and perinatal databases available in Sweden, including the Medical Birth Register and the Pregnancy Register, SGPC contains highly detailed medical record data, including time-varying serial measurements for physiological parameters throughout pregnancy, delivery, and postpartum, for both mother and infant. These strengths have enabled studies that were previously inconceivable; the effects of serial measurements of pregnancy weight gain, changes in haemoglobin counts and blood pressure during pregnancy, fetal weight estimations by ultrasound, duration of stages and phases of labour, cervical dilatation and oxytocin use during delivery, and constructing reference curves for umbilical cord pH.

CONCLUSIONS

The SGPC-with its rich content, repeated measurements and linkages to numerous health care and quality registers-is a unique cohort that enables high-quality perinatal studies that would otherwise not be possible.

Comparison of machine learning and logistic regression as predictive models for adverse maternal and neonatal outcomes of preeclampsia: A retrospective study

Introduction

Preeclampsia, one of the leading causes of maternal and fetal morbidity and mortality, demands accurate predictive models for the lack of effective treatment. Predictive models based on machine learning algorithms demonstrate promising potential, while there is a controversial discussion about whether machine learning methods should be recommended preferably, compared to traditional statistical models.

Methods

We employed both logistic regression and six machine learning methods as binary predictive models for a dataset containing 733 women diagnosed with preeclampsia. Participants were grouped by four different pregnancy outcomes. After the imputation of missing values, statistical description and comparison were conducted preliminarily to explore the characteristics of documented 73 variables. Sequentially, correlation analysis and feature selection were performed as preprocessing steps to filter contributing variables for developing models. The models were evaluated by multiple criteria.

Results

We first figured out that the influential variables screened by preprocessing steps did not overlap with those determined by statistical differences. Secondly, the most accurate imputation method is K-Nearest Neighbor, and the imputation process did not affect the performance of the developed models much. Finally, the performance of models was investigated. The random forest classifier, multi-layer perceptron, and support vector machine demonstrated better discriminative power for prediction evaluated by the area under the receiver operating characteristic curve, while the decision tree classifier, random forest, and logistic regression yielded better calibration ability verified, as by the calibration curve.

Conclusion

Machine learning algorithms can accomplish prediction modeling and demonstrate superior discrimination, while Logistic Regression can be calibrated well. Statistical analysis and machine learning are two scientific domains sharing similar themes. The predictive abilities of such developed models vary according to the characteristics of datasets, which still need larger sample sizes and more influential predictors to accumulate evidence.

Reviewing Accuracy of First Trimester Screening for Preeclampsia Using Maternal Factors and Biomarkers

Preeclampsia is a common and important complication of pregnancy, one with potentially significant morbidity and even mortality to both mother and baby. Identifying those at high risk of developing the condition is helpful as there is evidence that the incidence of preeclampsia can be reduced with low dose aspirin taken in pregnancy. Accurately predicting the risk of preeclampsia allows for more targeted aspirin prophylaxis and a greater opportunity for early detection of maternal and/or fetal complications associated with impaired placentation through a schedule of enhanced antenatal surveillance. Traditional preeclampsia prediction models use maternal characteristics and risk factors and have been shown to be of low predictive value. Multiparametric screening tests combine patient characteristics with serum biomarkers and ultrasound Doppler indices and have been shown to be more effective at detecting those at high risk of preeclampsia – more specifically, early-onset preeclampsia (onset of preeclampsia <34 weeks’ gestation). Multiparametric screening has now been validated in different populations. The true cost effectiveness of a multiparametric screening model for preeclampsia screening is not yet fully known and will vary depending on the clinical setting. Despite the growing body of evidence for its improved detection rates, first trimester preeclampsia screening using multiparametric models is not widely implemented and is not part of the recommendations for antenatal screening from most international bodies. The International Federation of Gynecology and Obstetrics has advised universal preeclampsia screening using maternal risk factors and biomarkers and has strongly encouraged its promotion worldwide. Various barriers to implementation must be considered such as the immediate cost of equipment and training, the need for audit and quality control, and the expected benefit to the population. Low to middle income settings may require a pragmatic approach to the implementation of multiparametric screening given limited resources.

Development of early prediction model for pregnancy-associated hypertension with graph-based semi-supervised learning

Clinical guidelines recommend several risk factors to identify women in early pregnancy at high risk of developing pregnancy-associated hypertension. However, these variables result in low predictive accuracy. Here, we developed a prediction model for pregnancy-associated hypertension using graph-based semi-supervised learning. This is a secondary analysis of a prospective study of healthy pregnant women. To develop the prediction model, we compared the prediction performances across five machine learning methods (semi-supervised learning with both labeled and unlabeled data, semi-supervised learning with labeled data only, logistic regression, support vector machine, and random forest) using three different variable sets: [a] variables from clinical guidelines, [b] selected important variables from the feature selection, and [c] all routine variables. Additionally, the proposed prediction model was compared with placental growth factor, a predictive biomarker for pregnancy-associated hypertension. The study population consisted of 1404 women, including 1347 women with complete follow-up (labeled data) and 57 women with incomplete follow-up (unlabeled data). Among the 1347 with complete follow-up, 2.4% (33/1347) developed pregnancy-associated HTN. Graph-based semi-supervised learning using top 11 variables achieved the best average prediction performance (mean area under the curve (AUC) of 0.89 in training set and 0.81 in test set), with higher sensitivity (72.7% vs 45.5% in test set) and similar specificity (80.0% vs 80.5% in test set) compared to risk factors from clinical guidelines. In addition, our proposed model with graph-based SSL had a higher performance than that of placental growth factor for total study population (AUC, 0.71 vs. 0.80, p < 0.001). In conclusion, we could accurately predict the development pregnancy-associated hypertension in early pregnancy through the use of routine clinical variables with the help of graph-based SSL.

An imbalance-aware deep neural network for early prediction of preeclampsia

Preeclampsia (PE) is a hypertensive complication affecting 8-10% of US pregnancies annually. While there is no cure for PE, aspirin may reduce complications for those at high risk for PE. Furthermore, PE disproportionately affects racial minorities, with a higher burden of morbidity and mortality. Previous studies have shown early prediction of PE would allow for prevention. We approached the prediction of PE using a new method based on a cost-sensitive deep neural network (CSDNN) by considering the severe imbalance and sparse nature of the data, as well as racial disparities. We validated our model using large extant rich data sources that represent a diverse cohort of minority populations in the US. These include Texas Public Use Data Files (PUDF), Oklahoma PUDF, and the Magee Obstetric Medical and Infant (MOMI) databases. We identified the most influential clinical and demographic features (predictor variables) relevant to PE for both general populations and smaller racial groups. We also investigated the effectiveness of multiple network architectures using three hyperparameter optimization algorithms: Bayesian optimization, Hyperband, and random search. Our proposed models equipped with focal loss function yield superior and reliable prediction performance compared with the state-of-the-art techniques with an average area under the curve (AUC) of 66.3% and 63.5% for the Texas and Oklahoma PUDF respectively, while the CSDNN model with weighted cross-entropy loss function outperforms with an AUC of 76.5% for the MOMI data. Furthermore, our CSDNN model equipped with focal loss function leads to an AUC of 66.7% for Texas African American and 57.1% for Native American. The best results are obtained with 62.3% AUC with CSDNN with weighted cross-entropy loss function for Oklahoma African American, 58% AUC with DNN and balanced batch for Oklahoma Native American, and 72.4% AUC using either CSDNN with weighted cross-entropy loss function or CSDNN with focal loss with balanced batch method for MOMI African American dataset. Our results provide the first evidence of the predictive power of clinical databases for PE prediction among minority populations.

Waist Circumference Measurement for Prediction of Preeclampsia: A Population-Based Cohort Study

BACKGROUND

Identifying women at high risk for preeclampsia is essential for the decision to start treatment with prophylactic aspirin. Prediction models have been developed for this purpose, and these typically incorporate body mass index (BMI). As waist circumference (WC) is a better predictor for metabolic and cardiovascular outcomes than BMI in nonpregnant populations, we aimed to investigate if WC is a BMI-independent predictor for preeclampsia and if the addition of WC to a prediction model for preeclampsia improves its performance.

METHODS

We used a population-based cohort of 4,696 women with WC measurements taken in the first trimester. The influence of WC on the risk of developing preeclampsia was evaluated by multivariable logistic regression. We generated receiver operating characteristic curves and calculated the area under the curve (AUC) to evaluate the usefulness of WC measurements for prediction of preeclampsia.

RESULTS

Women who developed preeclampsia had greater early pregnancy WC than women who did not (85.8 ± 12.6 vs. 82.3 ± 11.3 cm, P < 0.001). The risk of preeclampsia increased with larger WC in a multivariate model, adjusted odds ratio 1.02 (95% confidence interval 1.01-1.03). However, when adding BMI into the model, WC was not independently associated with preeclampsia. The AUC value for preeclampsia prediction with BMI and the above variables was 0.738 and remained unchanged with the addition of WC to the model.

CONCLUSIONS

Large WC is associated with a higher risk of preeclampsia, but adding WC to a prediction model for preeclampsia that already includes BMI does not improve the model's performance.

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.

Determinants of Pregnancy-Induced Hypertension among Mothers Attending Public Hospitals in Wolaita Zone, South Ethiopia: Findings from Unmatched Case-Control Study

Background

It has been estimated that approximately 14% of maternal death has resulted due to pregnancy-induced hypertension. Evidence also suggests that pregnancy-induced hypertension may result in adverse maternal and child outcomes. The aim of this study was to assess the determinants of pregnancy-induced hypertension among mothers attending antenatal and delivery services at public health hospitals in Wolaita zone, southern Ethiopia.

Methods

An institutionally based unmatched case-control study was conducted at three public hospitals. A total of 283 study participants were recruited for this study. Cases were selected consecutively as they were being diagnosed for pregnancy-induced hypertension, and two controls were selected for each case. Data were collected via the face-to-face interview technique using a pretested questionnaire. Unconditional logistic regression analysis was used to identify the independent predictor variables and produced odds ratio (OR) as a measure of association.

Results

The mean ± (SD) ages of cases and controls were 26.1 ± 5.4 and 26.1 ± 4.5 years, respectively. Being rural residents (AOR: 2.25, 95% CI: 1.09-4.65), illiterate (AOR: 3.12, 95% CI: 1.20-8.08), having the history of pregnancy-induced hypertension (AOR: 6.62, 95% CI: 2.48-17.71), history of kidney disease (AOR: 3.14, 95% CI: 1.05-9.38), and family history of hypertension (AOR: 5.59, 95% CI: 2.73-11.45) were determinants that increased the odds of suffering from hypertensive disorders of pregnancy. More importantly, eating vegetables and fruit reduces the odds of suffering from pregnancy-induced hypertension by 77% (AOR: 0.23, 95% CI: 0.06-0.79).

Conclusion

Being rural residents, illiterate, having a history of pregnancy-induced hypertension, and history of kidney disease, as well as the family history of hypertension were identified determinates of hypertensive disorders of pregnancy in the study area. Furthermore, fruit and vegetable intakes were identified as protective factors for pregnancy-induced hypertension. Therefore, early diagnosis and intervention of this disorder are warranted to reduce adverse outcomes.

Novelelectronic health records applied for prediction of pre-eclampsia: Machine-learning algorithms

OBJECTIVE

To predict risk of pre-eclampsia (PE) in women using machine learning (ML) algorithms, based on electronic health records (EHR) collected at the early second trimester.

STUDY DESIGN

A total of 3759 cases of pregnancy who received antenatal care at Xinhua hospital Chongming branch Affiliated to Shanghai Jiaotong University were included in this retrospective EHR-based study. Thirty-eight candidate clinical parameters routinely available at the first visit in antenatal care were collected by manual chart review. Logistic regression (LR), random forest (RF), support vector machine (SVM) and extreme gradient boosting (XGBoost) were used to construct the prediction model. Features that contributed to the model predictions were identified using XGBoost.

OUTCOME MEASURES

The performance of ML models to predict women at risk of PE was quantified in terms of accuracy, precision, recall, false negative score, f1_score, brier score and the area under the receiver operating curve (auROC).

RESULTS

The XGboost model had the best prediction performance (accuracy = 0.920, precision = 0.447, recall = 0.789, f1_score = 0.571, auROC = 0.955). The most predictive feature of PE development was fasting plasma glucose, followed by mean blood pressure and body mass index. An easy-to-use model that a patient could answer independently still enabled accurate prediction, with auROC of 0.83.

CONCLUSION

risk of PE development can be predicted with excellent discriminative ability using ML algorithms based on EHR collected at the early second trimester. Future studies are needed to assess the real-world clinical utility of the model.

Routinely collected antenatal data for longitudinal prediction of preeclampsia in nulliparous women: a population-based study

The objective was to evaluate the sequentially updated predictive capacity for preeclampsia during pregnancy, using multivariable longitudinal models including data from antenatal care. This population-based cohort study in the Stockholm-Gotland Counties, Sweden, included 58,899 pregnancies of nulliparous women 2008-2013. Prospectively collected data from each antenatal care visit was used, including maternal characteristics, reproductive and medical history, and repeated measurements of blood pressure, weight, symphysis-fundal height, proteinuria, hemoglobin and blood glucose levels. We used a shared-effects joint longitudinal model including all available information up until a given gestational length (week 24, 28, 32, 34 and 36), to update preeclampsia prediction sequentially. Outcome measures were prediction of preeclampsia, preeclampsia with delivery < 37, and preeclampsia with delivery ≥ 37 weeks' gestation. The area under the curve (AUC) increased with gestational length. AUC for preeclampsia with delivery < 37 weeks' gestation was 0.73 (95% CI 0.68-0.79) at week 24, and increased to 0.87 (95% CI 0.84-0.90) in week 34. For preeclampsia with delivery ≥ 37 weeks' gestation, the AUC in week 24 was 0.65 (95% CI 0.63-0.68), but increased to 0.79 (95% CI 0.78-0.80) in week 36. The addition of routinely collected clinical measurements throughout pregnancy improve preeclampsia prediction and may be useful to individualize antenatal care.

A new risk score model to predict preeclampsia using maternal factors and mean arterial pressure in early pregnancy

The purpose of this study was to establish a multivariable risk-scoring model for preeclampsia (PE) prediction based on maternal characteristics and mean arterial pressure (MAP). Multivariate logistic regression analysis from 4600 pregnancies during a 10-year period was used to create the best fitting model. Significant risk factors and weighted scores consisted of age ≥30 years (3), BMI ≥25 kg/m² (2), multifetal pregnancy (9), history of PE (9), adverse perinatal outcomes (6), pregnancy interval >10 years (5), nulliparous (5), underlying renal disease (10), chronic hypertension (6), autoimmune disease (5), diabetes (2) and MAP ≥95 mmHg (5). The model achieved an ROC area 0.771 with detection rates of 34%, 44%, 53% and 58% at 5%, 10%, 15% and 20% fixed false-positive rates, respectively. The new risk score model could be a clinically useful screening tool for PE. Pregnant women who have total scores of 9-13 (high risk) and more than 14 (very high risk) should receive aspirin prophylaxis.Impact StatementWhat is already known on this subject? Preeclampsia (PE) is the major cause of maternal and perinatal mortality and morbidity; it can be prevented by antiplatelet agents.What the results of this study add? A new model for identifying maternal at risk for PE using clinical risk factors and MAP was created. Weighted scores were defined for each variable for easy use in clinical practice. According to their probability for PE, pregnant women were classified into three subgroups: low risk (score 0-8), high risk (score 9-13) and very high risk groups (score ≥ 14). Aspirin should be prescribed to high risk and very high risk groups. For safety concerns, very high risk pregnancies should have close antenatal surveillance in a tertiary care hospital to reduce adverse outcomes during pregnancy and childbirth.What the implications are of these findings for clinical practice and/or further research? This new model for identifying pregnant women at high risk for PE has the potential to reduce the morbidity and mortality associated with this disease.

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

Background

Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method.

Objective

This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians’ decision making.

Methods

Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians’ decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ² and I².

Results

Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I²=86%; τ²=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I²=75%; τ²=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I²=75%; τ²=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I²=83%; τ²=0.07).

Conclusions

Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines.

Trial Registration

PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106

Pre-Pregnancy Obesity vs. Other Risk Factors in Probability Models of Preeclampsia and Gestational Hypertension

In the face of the obesity epidemic around the world, attention should be focused on the role of maternal obesity in the development of pregnancy. The purpose of this analysis was to evaluate the prediction of preeclampsia (PE) and isolated gestational hypertension (GH) for a number of maternal factors, in order to investigate the importance of pre-pregnancy obesity (body mass index, BMI ≥ 30 kg/m²), compared to other risk factors (e.g., prior PE, pregnancy weight gain (GWG), infertility treatment, interpregnancy interval, family history, the lack of vitamin supplementation, urogenital infection, and socioeconomic factors). In total, 912 women without chronic diseases were examined in a Polish prospective cohort of women with a singleton pregnancy (recruited in 2015–2016). Separate analyses were performed for the women who developed GH (n = 113) vs. 775 women who remained normotensive, as well as for those who developed PE (n = 24) vs. 775 controls. The probability of each disease was assessed for the base prediction model (age + primiparity) and for the model extended by one (test) variable, using logistic regression. Three measures were used to assess the prediction: area under curve (AUC) of the base and extended model, integrated discrimination improvement (IDI) (the index shows the difference between the value of the mean change in the predicted probability between the group of sick and healthy women when a new factor is added to the model), and net reclassification improvement (NRI) (the index focuses on the reclassification table describing the number of women in whom an upward or downward shift in the disease probability value occurred after a new factor had been added, including results for healthy and sick women). In the GH prediction, AUC increased most strongly when we added BMI (kg/m²) as a continuous variable (AUC = 0.716, p < 0.001) to the base model. The highest IDI index was obtained for prior GH/PE (IDI = 0.068, p < 0.001). The addition of BMI as a continuous variable or BMI ≥ 25 kg/m² improved the classification for healthy and sick women the most (NRI = 0.571, p < 0.001). In the PE prediction, AUC increased most strongly when we added BMI categories (AUC = 0.726, p < 0.001) to the base model. The highest IDI index was obtained for prior GH/PE (IDI = 0.050, p = 0.080). The addition of BMI categories improved the classification for healthy and sick women the most (NRI = 0.688; p = 0.001). After summing up the results of three indexes, the probability of hypertension in pregnancy was most strongly improved by BMI, including BMI ≥ 25 kg/m² for the GH prediction, and BMI ≥ 30 kg/m² for the PE prediction. Main conclusions: Pre-pregnancy BMI was the most likely factor to increase the probability of developing hypertension in pregnancy, compared to other risk factors. Hierarchies of PE and GH risk factors may suggest different (or common) mechanisms of their development.