Figure - available from: Archives of Gynecology and Obstetrics
This content is subject to copyright. Terms and conditions apply.
Exemplary machine-learning pipeline: The rudimentary process of creating ML model consists of three steps. Data gathering, which results in a working dataset, which in turn is used to train the ML model. The model is evaluated/used in a real-world setting to give prediction with new data as input
Source publication
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 improvem...
Citations
... The Fetal Medicine Foundation (FMF) has developed a competing risk model for PE, which is widespread as a decision support tool for first-trimester screening for PE [2,4]. The competing risk model combines maternal factors, mean arterial pressure (MAP), pulsatility index of the blood flow in the uterine arteries (UtA-PI), placental growth factor (PlGF), and pregnancy-associated plasma protein A (PAPP-A) [5]. ...
... A further development is to investigate the use of machine learning (ML), given its increasing utilization in healthcare, including obstetrics [7]. As highlighted in recent reviews conducted by Hackelöer et al. and Ranjbar et al., the use of ML has been investigated within the prediction of PE risk [4,7]. Multiple models have been tested along with different feature selections, where the features of maternal factors (ethnicity, age, obstetric history, hypertension, family history, diabetes, systemic lupus erythematosus, antiphospholipid syndrome, conception method, and body mass index (BMI) or weight and height), PAPP-A, PlGF, and UtA-PI are emerging as the standardized feature set, that researchers develop upon [8]. ...
Previous reviews have investigated machine learning (ML) models used to predict the risk of developing preeclampsia but have not described how the ML models are intended to be deployed throughout pregnancy or feature performance. The aim of this study is to provide an overview of the existing ML models and their intended deployment patterns and performance along with identified features of high importance. This review used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 guidelines. PubMed, Engineering Village, and the Association for Computing Machinery were searched between January and February 2024. A total of 86 studies were found of which 14 were included. Out of 12 studies, eight showed the intent to use the ML model as a single-use, two intended a dual-use, and two intended multiple-use. A total of seven studies listed the features of the highest importance. Systolic and diastolic blood pressure were listed along with mean arterial pressure to be of high importance. Out of four studies intending to use the ML model more than a single-use, three of them were conducted in the years 2023 and 2024, whereas the remaining study is from 2011. No ML model emerged as superior across the subgroups of PE. Utilizing body mass index and either mean arterial pressure or diastolic blood pressure and systolic blood pressure may benefit the performance. The deployment patterns are mainly single use being within the gestation weeks 11+0 to 14+1.
... [13] Therefore, the early identification of women who are at risk of preeclampsia is of great importance. [18] Multiple screening strategies have been developed over time to achieve the best results for the early diagnosis of preeclampsia. [19] AI is among the systems that have been developed in recent years. ...
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.
... Gene variants associated with cardiomyopathy are also associated with preeclampsia, and prolonged QT interval, altered p-wave duration, and LV strain are more common among females with preeclampsia compared to healthy pregnancies (10, 11). Infants with births complicated by preeclampsia are more likely to be premature, have intrauterine growth restriction and have an increased risk of death, resulting in up to 900,000 infant deaths per year (9,12,13). Identifying pregnant females at elevated risk for preeclampsia using lowcost tools may facilitate closer monitoring and timely interventions to reduce preeclampsia-related adverse events in both babies and mothers. ...
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.
... Rodríguez et al. (2020), Rodríguez et al. (2016), Gao et al. (2019), Wang et al. (2019) and Chill et al. (2021) proposed a model for early detection of severe maternal morbidity, particularly during and after delivery. Studies by Shazly et al. (2022), Pan et al. (2017), Schmidt et al. (2022), Wang et al. (2022) and Hackelöer et al. (2023) concluded that machine learning approaches were highly effective in identifying at-risk pregnancies and improving overall maternal and infant health outcomes. These studies often focus on identifying the most important risk factors for adverse parental outcomes and use these factors to develop predictive models that inform clinical decision-making and improve maternal health outcomes. ...
This research leverages the capabilities of explainable artificial intelligence (XAI) techniques, including Naive Bayes, support vector machine, decision tree, random forest, and multi-layer perceptron, to advance predictions of maternal outcomes during pregnancy. The specific focus is on critical determinants such as age, packed cell volume, weight, and maternal blood pressure. Ethical clearance was obtained for comprehensive data collection from 2,000 patients in the Niger Delta region of Nigeria spanning 2019 to 2022 across various healthcare facilities. While achieving commendable predictive accuracy and providing valuable insights into maternal risk factors and personalized care interventions, this study acknowledges its limitations, notably dataset specificity and variable selection. It emphasizes the need for further research with diverse datasets and contextual settings to ensure robust validation. Through the introduction of XAI, this investigation aims to empower healthcare providers with a powerful tool for more precise maternal health risk assessment, streamlined data analysis, and enhanced treatment planning. Ultimately, it seeks to save valuable time and resources, addressing a pivotal aspect of women's well-being during their childbearing years.
... Technologies like remote patient monitoring (Hackelöer et al., 2022;Marko et al., 2016) are making inroads into prenatal care, indicating a shift towards more proactive and patient-centered care models. ...
In the rapidly evolving healthcare landscape, integrative care delivery stands at the forefront of pioneering change, particularly in prenatal care. This comprehensive narrative review delves into the development of innovative models for integrative prenatal care, such as telemedicine-integrated home monitoring systems, mental health apps, virtual reality, artificial intelligence-powered predictive analytics and blockchain for secure health data management, proposing a paradigm shift from traditional methodologies to a more holistic, technology-empowered approach. We explore the interplay between cutting-edge technological advancements and interdisciplinary collaboration in crafting a care model that is patient-centric and adaptable to diverse healthcare settings. Moreover, key areas where integration can be significantly enhanced such as telemedicine, patient education, and continuous monitoring were identified, emphasizing the importance of synergy between medical expertise, patient engagement, and technology, aiming to improve outcomes for both mother and child and argue that the future of prenatal care lies in embracing innovation, flexibility, and inclusivity, setting a new standard in healthcare delivery. This work offers practical insights for healthcare professionals and policymakers aspiring to transform prenatal care into a more effective, accessible, and patient-friendly experience.
... Due to the complex nature of preeclampsia, machine learning algorithms, trained by large data sets to recognize and predict complex patterns, may be applied when exploring the predictive performance of multiple biomarkers [24,25]. Therefore, we explored the individual predictive value of 92 cardiovascular biomarkers in mid-pregnancy plasma to detect subsequent preeclampsia using proteomic profiling and machine learning. ...
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.
... Machine learning-based pipeline modeling is a new strategy employed in pre-eclampsia or hypertension in pregnant women [84]. A smart health system based on IoT for ambulatory maternal and fetal monitoring [56] is a gamechanging strategy for improving prenatal care. ...
Maternal mortality is a major public health concern worldwide. It is the number of preventable deaths that occur each year due to pregnancy and childbirth. The research investigates how machine learning may be used to minimize maternal mortality. Historical data on maternal health is used to develop predictive models, early detection systems, and resource allocation techniques. Machine learning helps to identify risk factors, monitor vital signs, and improve access to care. This allows for targeted interventions and better healthcare delivery. The challenges of data accessibility and model interpretation are addressed, highlighting the ethical and equitable applications of machine learning in maternal healthcare. This study emphasizes the potential of machine learning to reduce maternal mortality rates and the pressing need for its incorporation into healthcare systems worldwide.
... With the widespread availability of digital solutions, including decision support algorithms and remote monitoring devices, there is an opportunity for significant enhancements in healthcare. Two promising avenues of research and application emerge: firstly, on the patient side, home monitoring has the capacity to revolutionize the conventional healthcare journey [19] . ...
... Continuous monitoring: AI-powered monitoring systems can track vital signs and other indicators in real-time. These systems provide alerts to healthcare providers if abnormalities or signs of preeclampsia are detected, enabling rapid responses [19] . ...
Preeclampsia, a complex and potentially life-threatening condition during pregnancy, poses significant challenges to maternal and fetal health. This comprehensive narrative review explores the transformative role of Artificial Intelligence (AI) in the detection, prediction, and management of preeclampsia. Predictive models have been developed by leveraging diverse structured and unstructured data to ascertain effective techniques for preeclampsia prediction. The methodologies most prominently employed include the Random Forest, Support Vector Machine, and Artificial Neural Network (ANN). The additional algorithms include the following: Decision Tree, Naive Bayes, K-Nearest Neighbor and XG Boost. Furthermore, we explore the potential opportunities and obstacles within the realm of preeclampsia prediction, thereby promoting further advancements in
artificial intelligence systems research.
... 2. "Prediction of blood pressure response to treatment using machine learning algorithms in pregnancy with chronic hypertension" by (Hackelöer et al., 2022). The authors have used ML algorithms to identify blood pressure response to treatment in pregnant women with chronic hypertension. ...
Machine learning algorithms have the potential to revolutionize the way healthcare providers care for pregnant women. By using various input variables such as maternal characteristics, medical history, ultrasound measurements, and biomarkers, machine learning algorithms can develop personalized risk assessments to guide clinical decision-making and interventions. Additionally, these algorithms can monitor fetal well-being by analyzing electronic fetal monitoring data and detect signs of fetal distress. Image analysis algorithms can also identify fetal anomalies or complications more accurately and efficiently than manual interpretation of images. Finally, machine learning algorithms can develop personalized treatment recommendations based on clinical data, such as identifying optimal medication dosages and recommending the most appropriate delivery mode for women with prior cesarean deliveries. Overall, leveraging machine learning can improve the care of pregnant women and help ensure healthy outcomes for both mother and baby.
... Artificial Intelligence is becoming increasingly prevalent in healthcare, and obstetrics and gynecology is no exception. AI has the potential to improve patient outcomes and increase efficiency in the OBGYN field as pattern analysis, imaging interpretation of imaging tests, and even optimizing prediction models [9][10][11]. In the age of evidence-based medicine, it is crucial for physicians, particularly obstetricians and gynecologists, to possess the essential skill of critically reading, analyzing, and evaluating scientific literature. ...
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.
