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

Maternal Health Risk Detection: Advancing Midwifery with Artificial Intelligence

Background/Objectives: Maternal health risks remain one of the critical challenges in the world, contributing much to maternal and infant morbidity and mortality, especially in the most vulnerable populations. In the modern era, with the recent progress in the area of artificial intelligence and machine learning, much promise has emerged with regard to achieving the goal of early risk detection and its management. This research is set out to relate high-risk, low-risk, and mid-risk maternal health using machine learning algorithms based on physiological data. Materials and Methods: The applied dataset contains 1014 instances (i.e., cases) with seven attributes (i.e., variables), namely, Age, SystolicBP, DiastolicBP, BS, BodyTemp, HeartRate, and RiskLevel. The preprocessed dataset used was then trained and tested with six classifiers using 10-fold cross-validation. Finally, the performance metrics of the models erre compared using metrics like Accuracy, Precision, and the True Positive Rate. Results: The best performance was found for the Random Forest, also reaching the highest values for Accuracy (88.03%), TP Rate (88%), and Precision (88.10%), showing its robustness in handling maternal health risk classification. The mid-risk category was the most challenging across all the models, characterized by lowered Recall and Precision scores, hence underlining class imbalance as one of the bottlenecks in performance. Conclusions: Machine learning algorithms hold strong potential for improving maternal health risk prediction. The findings underline the place of machine learning in advancing maternal healthcare by driving more data-driven and personalized approaches.

The Artificial Intelligence-Enhanced Echocardiographic Detection of Congenital Heart Defects in the Fetus: A Mini-Review

Artificial intelligence (AI) is rapidly gaining attention in radiology and cardiology for accurately diagnosing structural heart disease. In this review paper, we first outline the technical background of AI and echocardiography and then present an array of clinical applications, including image quality control, cardiac function measurements, defect detection, and classifications. Collectively, we answer how integrating AI technologies and echocardiography can help improve the detection of congenital heart defects. Particularly, the superior sensitivity of AI-based congenital heart defect (CHD) detection in the fetus (>90%) allows it to be potentially translated into the clinical workflow as an effective screening tool in an obstetric setting. However, the current AI technologies still have many limitations, and more technological developments are required to enable these AI technologies to reach their full potential. Also, integrating diagnostic AI technologies into the clinical workflow should resolve ethical concerns. Otherwise, deploying diagnostic AI may not address low-resource populations' healthcare access disadvantages. Instead, it will further exacerbate the access disparities. We envision that, through the combination of tele-echocardiography and AI, low-resource medical facilities may gain access to the effective detection of CHD at the prenatal stage.

Interactive Conversational Agents for Perinatal Health: A Mixed Methods Systematic Review

Background: Interactive conversational agents (chatbots) simulate human conversation using natural language processing and artificial intelligence. They enable dynamic interactions and are used in various fields, including education and healthcare. Objective: This systematic review aims to identify and synthesize studies on chatbots for women and expectant parents in the preconception, pregnancy, and postnatal period through 12 months postpartum. Methods: We searched in six electronic bibliographic databases (MEDLINE (Ovid), CINAHL (EBSCO), Embase, Web of Science, Inspec, and IEEE Xplore) using a pre-defined search strategy. We included sources if they focused on women in the preconception period, pregnant women and their partners, mothers, and fathers/coparents of babies up to 12 months old. Two reviewers independently screened studies and all disagreements were resolved by a third reviewer. Two reviewers independently extracted and validated data from the included studies into a standardized form and conducted quality appraisal. Results: Twelve studies met the inclusion criteria. Seven were from the USA, with others from Brazil, South Korea, Singapore, and Japan. The studies reported high user satisfaction, improved health intentions and behaviors, increased knowledge, and better prevention of preconception risks. Chatbots also facilitated access to health information and interactions with health professionals. Conclusion: We provide an overview of interactive conversational agents used in the perinatal period and their applications. Digital interventions using interactive conversational agents have a positive impact on knowledge, behaviors, attitudes, and the use of health services. Interventions using interactive conversational agents may be more effective than those using methods such as individual or group face-to-face delivery.

Artificial Intelligence in Fetal Growth Restriction Management: A Narrative Review

This narrative review examines the integration of Artificial Intelligence (AI) in prenatal care, particularly in managing pregnancies complicated by Fetal Growth Restriction (FGR). AI provides a transformative approach to diagnosing and monitoring FGR by leveraging advanced machine-learning algorithms and extensive data analysis. Automated fetal biometry using AI has demonstrated significant precision in identifying fetal structures, while predictive models analyzing Doppler indices and maternal characteristics improve the reliability of adverse outcome predictions. AI has enabled early detection and stratification of FGR risk, facilitating targeted monitoring strategies and individualized delivery plans, potentially improving neonatal outcomes. For instance, studies have shown enhancements in detecting placental insufficiency-related abnormalities when AI tools are integrated with traditional ultrasound techniques. This review also explores challenges such as algorithm bias, ethical considerations, and data standardization, underscoring the importance of global accessibility and regulatory frameworks to ensure equitable implementation. The potential of AI to revolutionize prenatal care highlights the urgent need for further clinical validation and interdisciplinary collaboration.

Innovations in Diabetes Management for Pregnant Women: Artificial Intelligence and the Internet of Medical Things

Pregnancies impacted by diabetes face the compounded challenge of strict glycemic control with mounting insulin resistance as the pregnancy progresses. New technological advances, including artificial intelligence (AI) and the Internet of Medical Things (IoMT), are revolutionizing health care delivery by providing innovative solutions for diabetes care during pregnancy. Together, AI and the IoMT are a multibillion-dollar industry that integrates advanced medical devices and sensors into a connected network that enables continuous monitoring of glucose levels. AI-driven clinical decision support systems (CDSSs) can predict glucose trends and provide tailored evidence-based treatments with real-time adjustments as insulin resistance changes with placental growth. Additionally, mobile health (mHealth) applications facilitate patient education and self-management through real-time tracking of diet, physical activity, and glucose levels. Remote monitoring capabilities are particularly beneficial for pregnant persons with diabetes as they extend quality care to underserved populations and reduce the need for frequent in-person visits. This high-resolution monitoring allows physicians and patients access to an unprecedented wealth of data to make more informed decisions based on real-time data, reducing complications for both the mother and fetus. These technologies can potentially improve maternal and fetal outcomes by enabling timely, individualized interventions based on personalized health data. While AI and IoMT offer significant promise in enhancing diabetes care for improved maternal and fetal outcomes, their implementation must address challenges such as data security, cost-effectiveness, and preserving the essential patient-provider relationship. KEY POINTS: · The IoMT expands how patients interact with their health care.. · AI has widespread application in the care of pregnancies complicated by diabetes.. · A need for validation and black-box methodologies challenges the application of AI-based tools.. · As research in AI grows, considerations for data privacy and ethical dilemmas will be required..

Predicting maternal risk level using machine learning models

BACKGROUND

Maternal morbidity and mortality remain critical health concerns globally. As a result, reducing the maternal mortality ratio (MMR) is part of goal 3 in the global sustainable development goals (SDGs), and previously, it was an important indicator in the Millennium Development Goals (MDGs). Therefore, identifying high-risk groups during pregnancy is crucial for decision-makers and medical practitioners to mitigate mortality and morbidity. However, the availability of accurate predictive models for maternal mortality and maternal health risks is challenging. Compared with traditional predictive models, machine learning algorithms have emerged as promising predictive modelling methods providing accurate predictive models.

METHODS

This work aims to explore the potential of machine learning (ML) algorithms in maternal risk level prediction using a nationwide maternal mortality dataset from Oman for the first time. A total of 402 maternal deaths from 1991 to 2023 in Oman were included in this study. We utilised principal component analysis (PCA) in the ML algorithms and compared them to the results of model performance without PCA. We employed and compared ten ML algorithms, including decision tree (DT), random forest (RF), K-Nearest Neighbors (KNN), Naïve Bayes (NB), Extreme Gradient Boosting (xgboost), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), Support Vector Machine (SVM) and Artificial Neural Network (ANN). Different metrics, including, accuracy, sensitivity, precision, and the F1- score, were utilised to assess Model performance.

RESULTS

The results indicated that the RF model outperformed the other methods in predicting the risk level (low or high) with an accuracy of 75.2%, precision of 85.7% and F1- score of 73% after PCA was applied.

CONCLUSIONS

We applied several machine learning models to predict maternal risk levels for the first time using real data from Oman. RF outperformed the other algorithms in this classification problem. A reliable estimate of maternal risk level would facilitate intervention plans for medical practitioners to reduce maternal death.

Impact of prenatal genomics on clinical genetics practice

Genetic testing for prenatal diagnosis in the pre-genomic era primarily focused on detecting common fetal aneuploidies, using methods that combine maternal factors and imaging findings. The genomic era, ushered in by the emergence of new technologies like chromosomal microarray analysis and next-generation sequencing, has transformed prenatal diagnosis. These new tools enable screening and testing for a broad spectrum of genetic conditions, from chromosomal to monogenic disorders, and significantly enhance diagnostic precision and efficacy. This chapter reviews the transition from traditional karyotyping to comprehensive sequencing-based genomic analyses. We discuss both the clinical utility and the challenges of integrating prenatal exome and genome sequencing into prenatal care and underscore the need for ethical frameworks, improved prenatal phenotypic characterization, and global collaboration to further advance the field.

Surface Rendering of Cross-Sectional Imaging and Medical Illustration for Perinatal Planning in Conjoined Twins

INTRODUCTION

Surface rendering of diagnostic imaging data can reveal hidden conditions with an almost life-like realism. However, early gestation images alone are often insufficient to accurately predict postnatal anatomy. Yet, time-sensitive decisions may have to be made before detailed imaging becomes possible. In this case series, we evaluate how combining medical illustration with cross-sectional diagnostic imaging can enhance the accuracy and clinical value of early visualization of conjoined twins.

METHODS

Early gestation magnetic resonance imaging scans underwent semiautomated computerized post hoc manipulation to allow the medical illustrator to create the most effective images of the twins.

RESULTS

Four sets of conjoined twins were diagnosed before 17 weeks. Surface modeling allowed spatial manipulation of the twins to highlight their anatomic connections. Further volumetric enhancement and critical interpretation of the models assisted the illustrator in creating life-like, accurate images of the twins. These illustrations allowed parents to visualize the likely presentation at birth and helped the multidisciplinary team to plan postnatal management.

CONCLUSION

Surface rendering and surface modeling can be combined with medical illustration to create realistic, informative images of developing fetuses, using a level of detail that is tailored to the intended audience. This may be particularly useful in visualizing complex anomalies like conjoined twins.

Neonatal Encephalopathy is a Complex Phenotype Representing Reproductive and Pregnancy Exposome Effects on the Maternal-Placental-Fetal Triad

Reproductive, pregnancy, and placental exposomes influence the fetal neural exposome through toxic stressor interplay, impairing the maternal-placental-fetal (MPF) triad. Neonatal encephalopathy represents different clinical presentations based on complex time-dependent etiopathogenetic mechanisms including hypoxia-ischemia that challenge diagnosis and prognosis. Reproductive, pregnancy, and placental exposomes impair the fetal neural exposome through toxic stressor interplay within the MPF triad. Long intervals often separate disease onset from phenotype. Interdisciplinary fetal-neonatal neurology training, practice, and research closes this knowledge gap. Maintaining reproductive health preserves MPF triad health with life-course benefits.

Artificial Intelligence in Predicting the Mode of Delivery: A Systematic Review

The integration of artificial intelligence (AI) into obstetric care offers significant potential to enhance clinical decision-making and optimize maternal and neonatal outcomes. Traditional prediction methods for mode of delivery often rely on subjective clinical judgment and limited statistical models, which may not fully capture complex patient data. This systematic review aims to evaluate the current state of research on AI applications in predicting the mode of delivery, comparing the performance of AI models with traditional methods, and identifying gaps for future research. A comprehensive literature search was conducted across PubMed, Google Scholar, Web of Science, and Scopus databases, covering publications from January 2010 to July 2024. Inclusion criteria were studies employing AI techniques to predict the mode of delivery, published in peer-reviewed journals, and involving human subjects. Studies were assessed for quality using the Prediction Model Risk of Bias Assessment Tool (PROBAST), and data were synthesized narratively due to heterogeneity. In total, 18 studies met the inclusion criteria, employing various AI models such as logistic regression, random forest, gradient boosting, and neural networks. Sample sizes ranged from 40 to 94,480 participants across diverse geographic settings. AI models demonstrated high accuracy rates, often exceeding 90%, and strong predictive metrics (area under the curve (AUC) values from 0.745 to 0.932). Key predictors included maternal age, gravidity, parity, gestational age, labor induction type, and fetal weight. Notable models like the Adana System and Categorical Boosting (CatBoost, Yandex LLC, Moscow, Russia) highlighted the effectiveness of AI in enhancing prediction accuracy and supporting clinical decisions. AI models significantly outperform traditional statistical methods in predicting the mode of delivery, providing a robust tool for obstetric care. Future research should focus on standardizing data collection, improving model interpretability, addressing ethical concerns, and ensuring fairness in AI predictions to enhance clinical trust and application.

Machine learning techniques for prediction in pregnancy complicated by autoimmune rheumatic diseases: Applications and challenges

Autoimmune rheumatic diseases are chronic conditions affecting multiple systems and often occurring in young women of childbearing age. The diseases and the physiological characteristics of pregnancy significantly impact maternal-fetal health and pregnancy outcomes. Currently, the integration of big data with healthcare has led to the increasing popularity of using machine learning (ML) to mine clinical data for studying pregnancy complications. In this review, we introduce the basics of ML and the recent advances and trends of ML in different prediction applications for common pregnancy complications by autoimmune rheumatic diseases. Finally, the challenges and future for enhancing the accuracy, reliability, and clinical applicability of ML in prediction have been discussed. This review will provide insights into the utilization of ML in identifying and assisting clinical decision-making for pregnancy complications, while also establishing a foundation for exploring comprehensive management strategies for pregnancy and enhancing maternal and child health.

A Theoretical Exploration of Artificial Intelligence's Impact on Feto-Maternal Health from Conception to Delivery

The implementation of Artificial Intelligence (AI) in healthcare is enhancing diagnostic accuracy in clinical setups. The use of AI in healthcare is steadily increasing with advancing technology, extending beyond disease diagnosis to encompass roles in feto-maternal health. AI harnesses Machine Learning (ML), Natural Language Processing (NLP), Artificial Neural Networks (ANN), and computer vision to analyze data and draw conclusions. Considering maternal health, ML analyzes vast datasets to predict maternal and fetal health outcomes, while NLP interprets medical texts and patient records to assist in diagnosis and treatment decisions. ANN models identify patterns in complex feto-maternal medical data, aiding in risk assessment and intervention planning whereas, computer vision enables the analysis of medical images for early detection of feto-maternal complications. AI facilitates early pregnancy detection, genetic screening, and continuous monitoring of maternal health parameters, providing real-time alerts for deviations, while also playing a crucial role in the early detection of fetal abnormalities through enhanced ultrasound imaging, contributing to informed decision-making. This review investigates into the application of AI, particularly through predictive models, in addressing the monitoring of feto-maternal health. Additionally, it examines potential future directions and challenges associated with these applications.

Epigenetic biomarkers for disease susceptibility and preventative medicine

The development of molecular biomarkers for disease makes it possible for preventative medicine approaches to be considered. Therefore, therapeutics, treatments, or clinical management can be used to delay or prevent disease development. The problem with genetic mutations as biomarkers is the low frequency with genome-wide association studies (GWASs), generally at best a 1% association of the patients with the disease. In contrast, epigenetic alterations have a high-frequency association of greater than 90%-95% of individuals with pathology in epigenome-wide association studies (EWASs). A wide variety of human diseases have been shown to have epigenetic biomarkers that are disease specific and that detect pathology susceptibility. This review is focused on the epigenetic biomarkers for disease susceptibility, and it distinct from the large literature on epigenetics of disease etiology or progression. The development of efficient epigenetic biomarkers for disease susceptibility will facilitate a paradigm shift from reactionary medicine to preventative medicine.

Enhancing Fetal Anomaly Detection in Ultrasonography Images: A Review of Machine Learning-Based Approaches

Fetal development is a critical phase in prenatal care, demanding the timely identification of anomalies in ultrasound images to safeguard the well-being of both the unborn child and the mother. Medical imaging has played a pivotal role in detecting fetal abnormalities and malformations. However, despite significant advances in ultrasound technology, the accurate identification of irregularities in prenatal images continues to pose considerable challenges, often necessitating substantial time and expertise from medical professionals. In this review, we go through recent developments in machine learning (ML) methods applied to fetal ultrasound images. Specifically, we focus on a range of ML algorithms employed in the context of fetal ultrasound, encompassing tasks such as image classification, object recognition, and segmentation. We highlight how these innovative approaches can enhance ultrasound-based fetal anomaly detection and provide insights for future research and clinical implementations. Furthermore, we emphasize the need for further research in this domain where future investigations can contribute to more effective ultrasound-based fetal anomaly detection.