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

Cadmium Associated Preeclampsia: A Systematic Literature Review of Pregnancy and Birth Outcomes

Preeclampsia (PE), caused by multiple factors, is one of the most serious complications of pregnancy. Cadmium (Cd) is a heavy metal environmental pollutant, reproductive toxicant, and endocrine disruptor, which can increase the risk of PE. Cd toxicity due to occupational, diet, and environmental factors has worsened the risk. Studies showed elevated Cd concentration in maternal blood and placenta of PE women. However, the implicit association between Cd associated PE is still not highlighted. We systematically reviewed Cd-associated PE and its effect on pregnancy and birth outcomes. Based on "Preferred reporting items for systematic reviews and meta-analyses (PRISMA)" guidelines, eighty-six studies were identified by PubMed, Web of Science (WOS), and Scopus databases. Publications were included until October 2023 and articles screened based on our inclusion criteria. Our study identified that the exposure of controlled and uncontrolled Cd induces PE, which negatively affects pregnancy and birth outcomes. Given the serious nature of this finding, Cd is a potential adverse agent that impacts pregnancy and future neonatal health. Further comprehensive studies covering the whole trimesters of pregnancy and neonatal developments are warranted. Data on the molecular mechanisms behind Cd-induced PE is also essential for potential preventive, diagnostic, or therapeutic targets.

Balancing hormonal symphony: the dynamics of reproduction and pregnancy

The biology and endocrinology of reproduction form a broad and dynamic research field that garners significant attention due to its impact on everyday life. This field involves the study of hormones and neuroendocrine factors that are either produced by or act on reproductive tissues, including the hypothalamus, anterior pituitary gland, ovaries, endometrium, and placenta.

Integrating Remote Monitoring Into the Pregnancy Care: Perspectives of Pregnant Women and Healthcare Professionals

Remote monitoring has been proposed to provide new opportunities to monitor pregnancy in the home environment and reduce the number of follow-up visits to the maternity clinic. Still, the integration of remote monitoring into the pregnancy care process has not been achieved. This descriptive qualitative study aimed to explore pregnant women's and healthcare professionals' perceptions of integrating remote monitoring into pregnancy monitoring process. A convenience sample of 10 pregnant women and 11 healthcare professionals participated in the focus group interviews. The data were analyzed with reflexive thematic analysis. The results comprised a four-step pregnancy monitoring process organizing the issues to consider when integrating remote monitoring into these steps. According to pregnant women and healthcare professionals, remote pregnancy monitoring should allow a holistic assessment to ensure the well-being of the pregnant woman and the fetus. Clear criteria for monitoring should guide the adaptation of monitoring to the identified monitoring needs. Ideally, remote monitoring could enable more personalized maternity care, supporting the monitoring-related decision-making of both pregnant women and healthcare professionals and facilitating the early detection of pregnancy complications. However, integration of remote monitoring would require significant restructuring of current pregnancy care processes.

Leveraging Machine Learning to Predict and Assess Disparities in Severe Maternal Morbidity in Maryland

BACKGROUND

Severe maternal morbidity (SMM) is increasing in the United States. The main objective of this study is to test the use of machine learning (ML) techniques to develop models for predicting SMM during delivery hospitalizations in Maryland. Secondarily, we examine disparities in SMM by key sociodemographic characteristics.

METHODS

We used the linked State Inpatient Database (SID) and the American Hospital Association (AHA) Annual Survey data from Maryland for 2016-2019 (N = 261,226 delivery hospitalizations). We first estimated relative risks for SMM across key sociodemographic factors (e.g., race, income, insurance, and primary language). Then, we fitted LASSO and, for comparison, Logit models with 75 and 18 features. The selection of SMM features was based on clinical expert opinion, a literature review, statistical significance, and computational resource constraints. Various model performance metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, precision, and recall values were computed to compare predictive performance.

RESULTS

During 2016-2019, 76 per 10,000 deliveries (1976 of 261,226) were in patients who experienced an SMM event. The Logit model with a full list of 75 features achieved an AUC of 0.71 in the validation dataset, which marginally decreased to 0.69 in the reduced model with 18 features. The LASSO algorithm with the same 18 features demonstrated slightly superior predictive performance and an AUC of 0.80. We found significant disparities in SMM among patients living in low-income areas, with public insurance, and who were non-Hispanic Black or non-English speakers.

CONCLUSION

Our results demonstrate the feasibility of utilizing ML and administrative hospital discharge data for SMM prediction. The low recall score is a limitation across all models we compared, signifying that the algorithms struggle with identifying all SMM cases. This study identified substantial disparities in SMM across various sociodemographic factors. Addressing these disparities requires multifaceted interventions that include improving access to quality care, enhancing cultural competence among healthcare providers, and implementing policies that help mitigate social determinants of health.

The association between first trimester blood pressure, blood pressure trajectory, mid-pregnancy blood pressure drop and maternal and fetal outcomes: A systematic review and meta-analysis

BACKGROUND

Hypertensive disorders of pregnancy occur in 5-10 % of pregnancies and are associated with an increased risk of adverse perinatal outcomes.

OBJECTIVES

This review investigates the association between first trimester blood pressure (BP), mid-pregnancy BP drop, and BP-trajectories during pregnancy and adverse perinatal outcomes, exploring the fit of prediction and prevention.

SEARCH STRATEGY

Observational studies published before September 2023, reporting on desired determinants of BP and outcomes (preeclampsia (PE), severe hypertension, small for gestational age (SGA), fetal growth restriction (FGR)) were identified in MEDLINE, Embase and Cochrane.

DATA COLLECTION AND ANALYSIS

Data were collected in Excel. Results were analysed per BP-determinant. Meta analysis was performed for first trimester BP.

MAIN RESULTS

Ten studies met selection criteria. A great variety of cut-off values were used for BP categorization. Pooled analysis of 6 studies showed that women with borderline or hypertensive first trimester BP had a higher risk of PE compared to normotensive BP, OR 3.23 (95 % CI 1.99-5.26) and 7.86 (95 % CI 1.28-48.31), respectively. Additionally, first trimester hypertension correlated with a higher risk of SGA neonate (pooled OR of 1.87 (95 % CI 1.17-2.99)) compared to normotension or borderline hypertension. Throughout pregnancy, prehypertension, hypertension, elevated and high stable trajectories increased PE risk. High-stable trajectory increased SGA neonate risk.

CONCLUSIONS

The findings suggest that women with borderline and hypertensive BP in the first trimester are at increased risk for PE and SGA. However, standardization of cut-off values and BP measurement is necessary to estimate outcome risks more accurately.

Predictive and Diagnostic Value of the Angiogenic Proteins in Patients With Chronic Kidney Disease

BACKGROUND

Our objective was to investigate the predictive and diagnostic accuracy of the angiogenic proteins sFlt-1 (soluble fms-like tyrosine kinase-1) and PlGF (placental growth factor) for preterm preeclampsia and explore the relationship between renal function and these proteins.

METHODS

We completed a blinded, prospective, longitudinal, observational study of patients with chronic kidney disease followed at a tertiary center (2018-2023). Serum samples were obtained at 3 time points along gestation (planned sampling): 12-16, 18-22, and 28-32 weeks. In addition, samples were obtained whenever preeclampsia was suspected (indicated sampling). sFlt-1 and PlGF levels remained concealed until the study ended. The primary outcome was preterm preeclampsia. The planned and indicated samples were used to estimate the predictive and diagnostic accuracy of the angiogenic proteins, respectively.

RESULTS

Of the 97 participants, 21 (21.6%) experienced preterm preeclampsia. In asymptomatic patients with chronic kidney disease, the angiogenic proteins were predictive of preterm preeclampsia only when sampled in the third trimester, in which case the sFlt-1/PlGF ratio (false positive rate of 37% for a detection rate of 80%) was more predictive than either sFlt-1 or PlGF in isolation. In patients with suspected preeclampsia, the diagnostic accuracy of the sFlt-1/PlGF ratio (false positive rate of 26% for a detection rate of 80%) was higher than that of sFlt-1 and PlGF in isolation. Diminished renal function was associated with increased levels of PlGF.

CONCLUSIONS

sFlt-1 and PlGF can effectively predict and improve the diagnostic accuracy for preterm preeclampsia among patients with chronic kidney disease. The optimal sFlt-1/PlGF ratio cutoff to rule out preeclampsia may need to be lower in patients with impaired renal function.

Angiogenic factors for early prediction of preeclampsia

 .

Impact of Antiphospholipid Syndrome on Reproductive Outcomes: Current Insights and Management Approaches

Antiphospholipid syndrome (APS) is a disease characterized by the presence of antiphospholipid (aPL) antibodies, thrombosis, and obstetric complications. While patients with APS can have successful pregnancies, many important considerations exist. APS can also cooccur with other systemic autoimmune diseases which can affect pregnancy, particularly systemic lupus erythematosus. This article reviews specific considerations for pregnancy and reproductive health in patients with APS. Similar to other autoimmune diseases, stable or quiescent disease and planning with a rheumatologist and obstetrician prior to conception are vital components of a successful pregnancy. Pregnancy management for patients with aPL antibodies or diagnosis of APS with aspirin and/or anticoagulation depending on disease profile is discussed, as well as the effects of physiologic changes during pregnancy in maternal and fetal outcomes for this population. Given the reproductive span lasts beyond conception through delivery, we include discussions on safe contraception options, the use of assistive reproductive technology, pregnancy termination, menopause, and male fertility. While APS is a relatively rare condition, the effects this disease can have on maternal and fetal outcomes even with available therapies demonstrates the need for more high-quality, evidence-based research.

Machine learning, advanced data analysis, and a role in pregnancy care? How can we help improve preeclampsia outcomes?

The value of machine learning capacity in maternal health, and in particular prediction of preeclampsia will only be realised when there are high quality clinical data provided, representative populations included, different health systems and models of care compared, and a culture of rapid use and application of real-time data and outcomes. This review has been undertaken to provide an overview of the language, and early results of machine learning in a pregnancy and preeclampsia context. Clinicians of all backgrounds are encouraged to learn the language of Machine Learning (ML) and Artificial intelligence (AI) to better understand their potential and utility to improve outcomes for women and their families. This review will outline some definitions and features of ML that will benefit clinician's knowledge in the preeclampsia discipline, and also outline some of the future possibilities for preeclampsia-focussed clinicians via understanding AI. It will further explore the criticality of defining the risk, and outcome being determined.

Biomarkers for Early Prediction and Management of Preeclampsia: A Comprehensive Review

Preeclampsia is a common complication of pregnancy. It is a multi-organ disorder that remains one of the main causes of maternal morbidity and mortality. Additionally, preeclampsia leads to many complications that can occur in the fetus or newborn. Preeclampsia occurs in about 1 in 20 pregnant women. This review focuses on the prediction of preeclampsia in women, using various biomarkers, in particular, a factor combining the use of soluble FMS-like tyrosinokinase-1 (sFlt-1) and placental growth factor (PlGF). A low value of the sFlt-1/PlGF ratio rules out the occurrence of preeclampsia within 4 weeks of the test result, and its high value predicts the occurrence of preeclampsia within even 1 week. The review also highlights other factors, such as pregnancy-associated plasma protein A, placental protein 13, disintegrin and metalloprotease 12, ß-human chorionic gonadotropin, inhibin-A, soluble endoglin, nitric oxide, and growth differentiation factor 15. Biomarker testing offers reliable and cost-effective screening methods for early detection, prognosis, and monitoring of preeclampsia. Early diagnosis in groups of women at high risk for preeclampsia allows for quick intervention, preventing the undesirable effects of preeclampsia. However, further research is needed to validate and optimize the use of biomarkers for more accurate prediction and diagnosis. This article aims to review the role of biomarkers, including the sFlt1/PlGF ratio, in the prognosis and management of preeclampsia.

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.

Angiogenic Biomarkers in Preeclampsia

Preeclampsia contributes disproportionately to maternal and neonatal morbidity and mortality throughout the world. A critical driver of preeclampsia is angiogenic imbalance, which is often present weeks to months before overt disease. Two placenta-derived angiogenic biomarkers, soluble fms-like tyrosine kinase 1 (sFlt-1) and placental growth factor (PlGF), have proved useful as diagnostic and prognostic tests for preeclampsia. Recently, the U.S. Food and Drug Administration approved the sFlt-1/PlGF assay to aid in the prediction of preeclampsia with severe features among women with hypertensive disorders of pregnancy at 24-34 weeks of gestation. In this narrative review, we summarize the body of work leading to this approval and describe how the sFlt-1/PlGF ratio may be implemented in clinical practice as an adjunctive measure to help optimize care and to reduce adverse outcomes in preeclampsia.

AI-based preeclampsia detection and prediction with electrocardiogram data

Introduction

More than 76,000 women die yearly from preeclampsia and hypertensive disorders of pregnancy. Early diagnosis and management of preeclampsia can improve outcomes for both mother and baby. In this study, we developed artificial intelligence models to detect and predict preeclampsia from electrocardiograms (ECGs) in point-of-care settings.

Methods

Ten-second 12-lead ECG data was obtained from two large health care settings: University of Tennessee Health Science Center (UTHSC) and Atrium Health Wake Forest Baptist (AHWFB). UTHSC data was split into 80% training and 20% holdout data. The model used a modified ResNet convolutional neural network, taking one-dimensional raw ECG signals comprising 12 channels as an input, to predict risk of preeclampsia. Sub-analyses were performed to assess the predictive accuracy for preeclampsia prediction within 30, 60, or 90 days before diagnosis.

Results

The UTHSC cohort included 904 ECGs from 759 females (78.8% African American) with a mean ± sd age of 27.3 ± 5.0 years. The AHWFB cohort included 817 ECGs from 141 females (45.4 African American) with a mean ± sd age of 27.4 ± 5.9 years. The cross-validated ECG-AI model yielded an AUC (95% CI) of 0.85 (0.77-0.93) on UTHSC holdout data, and an AUC (95% CI) of 0.81 (0.77-0.84) on AHWFB data. The sub-analysis of different time windows before preeclampsia prediction resulted in AUCs (95% CI) of 0.92 (0.84-1.00), 0.89 (0.81-0.98) and 0.90 (0.81-0.98) when tested on ECGs 30 days, 60 days and 90 days, respectively, before diagnosis. When assessed on early onset preeclampsia (preeclampsia diagnosed at <34 weeks of pregnancy), the model's AUC (95% CI) was 0.98 (0.89-1.00).

Discussion

We conclude that preeclampsia can be identified with high accuracy via application of AI models to ECG data.

Artificial Intelligence in Early Diagnosis of Preeclampsia

BACKGROUND

Every day, 810 women die of preventable causes related to pregnancy and childbirth worldwide, and preeclampsia is among the top three causes of maternal deaths.

AIM

To develop a diagnostic system with artificial intelligence for the early diagnosis of preeclampsia.

METHODS

This retrospective study included pregnant women who were screened for the inclusion criteria on the hospital's database, and the sample consisted of the data of 1158 pregnant women diagnosed with preeclampsia and 9194 pregnant women who were not diagnosed with preeclampsia at Kahramanmaras Necip Fazıl City Hospital Gynecology and Pediatrics Additional Service Building, Kahramanmaras/Turkey. The statistical analysis was performed using the Statistical Package for social sciences (SPSS) version 22 for windows. Artificial intelligence models were created using Python, scikit-learn, and TensorFlow.

RESULTS

The model achieved 73.7% sensitivity (95% confidence interval (CI): 70.2%-77.1%) and 92.7% specificity (95% CI: 91.7%-93.6%) on the test set. Furthermore, the model had 90.6% accuracy (95% CI: 90.1% - 91.1%) and an area under the curve (AUC) value of 0.832 (95% CI: 0.818-0.846). The significant parameters in predicting preeclampsia in the model were hemoglobin (HGB), age, aspartate transaminase level (AST), alanine transferase level (ALT), and the blood group.

CONCLUSION

Artificial intelligence is effective in the prediction and diagnosis of preeclampsia.

Uterine arteries pulsatility index by Doppler ultrasound in the prediction of preeclampsia: an updated systematic review and meta-analysis

BACKGROUND

Preeclampsia is a common pregnancy complication with serious potential risks for maternal and neonatal health. Early prediction of preeclampsia is crucial for timely prevention, surveillance, and treatment to improve maternal and neonatal outcomes. This systematic review aimed to summarize the available evidence on the prediction of preeclampsia based on Doppler ultrasound of uterine arteries at different gestational ages.

METHODS

A systematic literature search and meta-analysis were conducted to evaluate the sensitivity and specificity of the pulsatility index of Doppler ultrasound of uterine arteries for predicting preeclampsia. The timing of ultrasound scans within and beyond 20 weeks of gestational age was compared to assess its effect on the sensitivity and specificity of the pulsatility index.

RESULTS

This meta-analysis included 27 studies and 81,673 subjects (3309 preeclampsia patients and 78,364 controls). The pulsatility index had moderate sensitivity (0.586) and high specificity for predicting preeclampsia (0.879) (summary point: sensitivity 0.59; 1-specificity 0.12). Subgroup analysis revealed that ultrasound scans performed within 20 weeks of gestational age did not significantly affect the sensitivity and specificity for predicting preeclampsia. The summary receiver operator characteristic curve showed the pulsatility index's optimal range of sensitivity and specificity.

CONCLUSIONS

The uterine arteries pulsatility index measured by Doppler ultrasound is useful and effective for predicting preeclampsia and should be implemented in the clinical practice. The timing of ultrasound scans at different gestational age ranges does not significantly affect the sensitivity and specificity.

Exploring the use of ChatGPT in OBGYN: a bibliometric analysis of the first ChatGPT-related publications

PURPOSE

Little is known about the scientific literature regarding the new revolutionary tool, ChatGPT. We aim to perform a bibliometric analysis to identify ChatGPT-related publications in obstetrics and gynecology (OBGYN).

STUDY DESIGN

A bibliometric study through PubMed database. We mined all ChatGPT-related publications using the search term "ChatGPT". Bibliometric data were obtained from the iCite database. We performed a descriptive analysis. We further compared IF among publications describing a study vs. other publications.

RESULTS

Overall, 42 ChatGPT-related publications were published across 26 different journals during 69 days. Most publications were editorials (52%) and news/briefing (22%), with only one (2%) research article identified. Five (12%) publications described a study performed. No ChatGPT-related publications in OBGYN were found. The leading journal by the number of publications was Nature (24%), followed by Lancet Digital Health and Radiology (7%, for both). The main subjects of publications were ChatGPT's scientific writing quality (26%) and a description of ChatGPT (26%) followed by tested performance of ChatGPT (14%), authorship and ethical issues (10% for both topics).In a comparison of publications describing a study performed (n = 5) vs. other publications (n = 37), mean IF was lower in the study-publications (mean 6.25 ± 0 vs. 25.4 ± 21.6, p < .001).

CONCLUSIONS

The study highlights main trends in ChatGPT-related publications. OBGYN is yet to be represented in this literature.