A Machine Learning-Based Prediction Model for Preterm Birth in Rural India

Improved Birthweight Prediction With Feature-Wise Linear Modulation, GRU, and Attention Mechanism in Ultrasound Data

OBJECTIVES

Birthweight prediction in fetal development presents a challenge in direct measurement and often depends on empirical formulas based on the clinician's experience. Existing methods suffer from low accuracy and high execution times, limiting their clinical effectiveness. This study aims to introduce a novel approach integrating feature-wise linear modulation (FiLM), gated recurrent unit (GRU), and Attention network to improve birthweight prediction using ultrasound data.

METHODS

The proposed method utilizes FiLM for adaptive modulation, dynamically adjusting layer activations based on input specifics for enhanced information extraction. GRU is employed to capture sequential dependencies, recognizing the evolving maternal and fetal parameters during pregnancy. The Attention network selectively focuses on crucial parameters, dynamically adjusting feature weights for accurate predictions. The study evaluates classification accuracies for three groups: appropriate-for-gestational-age, large-for-gestational-age, and small-for-gestational-age (SGA). Prediction errors are minimized by optimizing parameters and using mean squared error as the loss function. Experimental evaluations are performed using multiple metrics.

RESULTS

The proposed strategy attains a high prediction accuracy of 98.8%, outperforming existing methods such as ensemble transfer learning model (83.5%), BabyNet++ (91.7%), bi-directional LSTM with CNN and a hybrid whale with oppositional fruit fly optimization (89.2%), linear regression-random forest-artificial neural network (79.5%), and Attention MFP-Unet (93.6%). The integrated network provides advanced insights into birthweight dynamics, enhancing both interpretability and accuracy.

CONCLUSIONS

The findings of this study are vital for birthweight prediction, clinical delivery guideline development, and implementation of decision-making. The proposed approach supports clinicians in making informed decisions during obstetric examinations and assists pregnant women in weight management, showcasing significant advancements in maternal healthcare.

Prediction of adverse pregnancy outcomes using machine learning techniques: evidence from analysis of electronic medical records data in Rwanda

BACKGROUND

Despite substantial progress in maternal and neonatal health, Rwanda's mortality rates remain high, necessitating innovative approaches to meet health related Sustainable Development Goals (SDGs). By leveraging data collected from Electronic Medical Records, this study explores the application of machine learning models to predict adverse pregnancy outcomes, thereby improving risk assessment and enhancing care delivery.

METHODS

This study utilized retrospective cohort data from the electronic medical record (EMR) system of 25 hospitals in Rwanda from 2020 to 2023. The independent variables included socioeconomic status, health status, reproductive health, and pregnancy-related factors. The outcome variable was a binary composite feature that combined adverse pregnancy outcomes in both the mother and the newborn. Extensive data cleaning was performed, with missing values addressed through various strategies, including the exclusion of variables and instances, imputation techniques using K-Nearest Neighbors and Multiple Imputation by Chained Equations. Data imbalance was managed using a synthetic minority oversampling technique. Six machine learning models-Logistic Regression, Decision Trees, Support Vector Machine, Gradient Boosting, Random Forest, and Multilayer Perceptron-were trained using 10-fold cross-validation and evaluated on an unseen dataset with-70 - 30 training and evaluation splits.

RESULTS

Data from 117,069 women across 25 hospitals in Rwanda were analyzed, leading to a final dataset of 32,783 women after removing entries with significant missing values. Among these women, 5,424 (16.5%) experienced adverse pregnancy outcomes. Random Forest and Gradient Boosting Classifiers demonstrated high accuracy and precision. After hyperparameter tuning, the Random Forest model achieved an accuracy of 90.6% and an ROC-AUC score of 0.85, underscoring its effectiveness in predicting adverse outcomes. However, a recall rate of 46.5% suggests challenges in detecting all the adverse cases. Key predictors of adverse outcomes identified in this study included gestational age, number of pregnancies, antenatal care visits, maternal age, vital signs, and delivery methods.

CONCLUSIONS

This study recommends enhancing EMR data quality, integrating machine learning into routine practice, and conducting further research to refine predictive models and address evolving pregnancy outcomes. In addition, this study recommends the design of AI-based interventions for high-risk pregnancies.

CLINICAL TRIAL NUMBER

Not applicable.

Novel Technologies in Preterm Birth Prediction: Current Advances and Ethical Challenges

Preterm birth (PTB) remains a significant challenge in modern obstetric practice, posing considerable risks to maternal and neonatal health. Despite advancements in medical technology, the incidence of PTB remains high, and its prediction continues to be complex. Traditional methods for predicting PTB, including medical history evaluation, cervical length measurement, and biochemical markers, have shown limited precision in preventing this serious complication. However, recent technological advancements-such as machine learning algorithms, biomarker profiling, and genetic analyses-offer new possibilities for improving prediction accuracy. This review critically examines current and emerging approaches for PTB prediction, highlighting their potential to transform early risk detection. It also addresses the ethical and societal implications of these technologies. This narrative review aims to comprehensively analyse contemporary methods for predicting preterm birth, evaluating established and emerging approaches. It will assess the efficacy of current predictive tools, examine the limitations they face, and explore the potential for integrating advanced technologies to improve outcomes. By highlighting recent developments in the field and addressing critical knowledge gaps, this review seeks to contribute to the ongoing effort to enhance PTB prediction, aiming to improve maternal and neonatal health outcomes. The study's novelty lies in its comprehensive analysis of cutting-edge innovations in PTB prediction and its focus on identifying critical gaps in current practices.

An AI-based approach to predict delivery outcome based on measurable factors of pregnant mothers

The desire for safer delivery mode that preserves the lives of both mother and child with minimal or no complications before, during and after childbirth is the wish for every expectant mother and their families. However, the choice for any particular delivery mode is supposedly influenced by a number of factors that leads to the ultimate decision of choice. Some of the factors identified include maternal birth history, maternal and child health conditions prevailing before and during labor onset. Predictive modeling has been used extensively to determine important contributory factors or artifacts influencing delivery choice in related research studies. However, missing among a myriad of features used in various research studies for this determination is maternal history of spontaneous, threatened and inevitable abortion(s). How its inclusion impacts delivery outcome has not been covered in extensive research work. This research work therefore takes measurable maternal features that include real time information on administered partographs to predict delivery outcome. This is achieved by adopting effective feature selection technique to estimate variable relationships with the target variable. Three supervised learning techniques are used and evaluated for performance. Prediction accuracy score of area under the curve obtained show Gradient Boosting classifier achieved 91% accuracy, Logistic Regression 93% and Random Forest 91%. Balanced accuracy score obtained for these techniques were; Gradient Boosting 82.73%, Logistic Regression 84.62% and Random Forest 83.02%. Correlation statistic for variable independence among input variables showed that delivery outcome type as an output is associated with fetal gestational age and the progress of maternal cervix dilatation during labor onset.

Prediction of risk for early or very early preterm births using high-resolution urinary metabolomic profiling

BACKGROUND

Preterm birth (PTB) is a serious health problem. PTB complications is the main cause of death in infants under five years of age worldwide. The ability to accurately predict risk for PTB during early pregnancy would allow early monitoring and interventions to provide personalized care, and hence improve outcomes for the mother and infant.

OBJECTIVE

This study aims to predict the risks of early preterm (< 35 weeks of gestation) or very early preterm (≤ 26 weeks of gestation) deliveries by using high-resolution maternal urinary metabolomic profiling in early pregnancy.

DESIGN

A retrospective cohort study was conducted by two independent preterm and term cohorts using high-density weekly urine sampling. Maternal urine was collected serially at gestational weeks 8 to 24. Global metabolomics approaches were used to profile urine samples with high-resolution mass spectrometry. The significant features associated with preterm outcomes were selected by Gini Importance. Metabolite biomarker identification was performed by liquid chromatography tandem mass spectrometry (LCMS-MS). XGBoost models were developed to predict early or very early preterm delivery risk.

SETTING AND PARTICIPANTS

The urine samples included 329 samples from 30 subjects at Stanford University, CA for model development, and 156 samples from 24 subjects at the University of Alabama, Birmingham, AL for validation.

RESULTS

12 metabolites associated with PTB were selected and identified for modelling among 7,913 metabolic features in serial-collected urine samples of pregnant women. The model to predict early PTB was developed using a set of 12 metabolites that resulted in the area under the receiver operating characteristic (AUROCs) of 0.995 (95% CI: [0.992, 0.995]) and 0.964 (95% CI: [0.937, 0.964]), and sensitivities of 100% and 97.4% during development and validation testing, respectively. Using the same metabolites, the very early PTB prediction model achieved AUROCs of 0.950 (95% CI: [0.878, 0.950]) and 0.830 (95% CI: [0.687, 0.826]), and sensitivities of 95.0% and 60.0% during development and validation, respectively.

CONCLUSION

Models for predicting risk of early or very early preterm deliveries were developed and tested using metabolic profiling during the 1st and 2nd trimesters of pregnancy. With patient validation studies, risk prediction models may be used to identify at-risk pregnancies prompting alterations in clinical care, and to gain biological insights of preterm birth.

Preterm birth risk stratification through longitudinal heart rate and HRV monitoring in daily life

Preterm birth (PTB) remains a global health concern, impacting neonatal mortality and lifelong health consequences. Traditional methods for estimating PTB rely on electronic health records or biomedical signals, limited to short-term assessments in clinical settings. Recent studies have leveraged wearable technologies for in-home maternal health monitoring, offering continuous assessment of maternal autonomic nervous system (ANS) activity and facilitating the exploration of PTB risk. In this paper, we conduct a longitudinal study to assess the risk of PTB by examining maternal ANS activity through heart rate (HR) and heart rate variability (HRV). To achieve this, we collect long-term raw photoplethysmogram (PPG) signals from 58 pregnant women (including seven preterm cases) from gestational weeks 12-15 to three months post-delivery using smartwatches in daily life settings. We employ a PPG processing pipeline to accurately extract HR and HRV, and an autoencoder machine learning model with SHAP analysis to generate explainable abnormality scores indicative of PTB risk. Our results reveal distinctive patterns in PTB abnormality scores during the second pregnancy trimester, indicating the potential for early PTB risk estimation. Moreover, we find that HR, average of interbeat intervals (AVNN), SD1SD2 ratio, and standard deviation of interbeat intervals (SDNN) emerge as significant PTB indicators.

Predicting risk of preterm birth in singleton pregnancies using machine learning algorithms

We aimed to develop, train, and validate machine learning models for predicting preterm birth (<37 weeks' gestation) in singleton pregnancies at different gestational intervals. Models were developed based on complete data from 22,603 singleton pregnancies from a prospective population-based cohort study that was conducted in 51 midwifery clinics and hospitals in Wenzhou City of China between 2014 and 2016. We applied Catboost, Random Forest, Stacked Model, Deep Neural Networks (DNN), and Support Vector Machine (SVM) algorithms, as well as logistic regression, to conduct feature selection and predictive modeling. Feature selection was implemented based on permutation-based feature importance lists derived from the machine learning models including all features, using a balanced training data set. To develop prediction models, the top 10%, 25%, and 50% most important predictive features were selected. Prediction models were developed with the training data set with 5-fold cross-validation for internal validation. Model performance was assessed using area under the receiver operating curve (AUC) values. The CatBoost-based prediction model after 26 weeks' gestation performed best with an AUC value of 0.70 (0.67, 0.73), accuracy of 0.81, sensitivity of 0.47, and specificity of 0.83. Number of antenatal care visits before 24 weeks' gestation, aspartate aminotransferase level at registration, symphysis fundal height, maternal weight, abdominal circumference, and blood pressure emerged as strong predictors after 26 completed weeks. The application of machine learning on pregnancy surveillance data is a promising approach to predict preterm birth and we identified several modifiable antenatal predictors.

Recent Advances and Challenges in the Early Diagnosis and Treatment of Preterm Labor

Preterm birth (PTB) is the primary cause of neonatal mortality and long-term disabilities. The unknown mechanism behind PTB makes diagnosis difficult, yet early detection is necessary for controlling and averting related consequences. The primary focus of this work is to provide an overview of the known risk factors associated with preterm labor and the conventional and advanced procedures for early detection of PTB, including multi-omics and artificial intelligence/machine learning (AI/ML)- based approaches. It also discusses the principles of detecting various proteomic biomarkers based on lateral flow immunoassay and microfluidic chips, along with the commercially available point-of-care testing (POCT) devices and associated challenges. After briefing the therapeutic and preventive measures of PTB, this review summarizes with an outlook.

Predicting preterm birth using explainable machine learning in a prospective cohort of nulliparous and multiparous pregnant women

Preterm birth (PTB) presents a complex challenge in pregnancy, often leading to significant perinatal and long-term morbidities. "While machine learning (ML) algorithms have shown promise in PTB prediction, the lack of interpretability in existing models hinders their clinical utility. This study aimed to predict PTB in a pregnant population using ML models, identify the key risk factors associated with PTB through the SHapley Additive exPlanations (SHAP) algorithm, and provide comprehensive explanations for these predictions to assist clinicians in providing appropriate care. This study analyzed a dataset of 3509 pregnant women in the United Arab Emirates and selected 35 risk factors associated with PTB based on the existing medical and artificial intelligence literature. Six ML algorithms were tested, wherein the XGBoost model exhibited the best performance, with an area under the operator receiving curves of 0.735 and 0.723 for parous and nulliparous women, respectively. The SHAP feature attribution framework was employed to identify the most significant risk factors linked to PTB. Additionally, individual patient analysis was performed using the SHAP and the local interpretable model-agnostic explanation algorithms (LIME). The overall incidence of PTB was 11.23% (11 and 12.1% in parous and nulliparous women, respectively). The main risk factors associated with PTB in parous women are previous PTB, previous cesarean section, preeclampsia during pregnancy, and maternal age. In nulliparous women, body mass index at delivery, maternal age, and the presence of amniotic infection were the most relevant risk factors. The trained ML prediction model developed in this study holds promise as a valuable screening tool for predicting PTB within this specific population. Furthermore, SHAP and LIME analyses can assist clinicians in understanding the individualized impact of each risk factor on their patients and provide appropriate care to reduce morbidity and mortality related to PTB.

Node embedding-based graph autoencoder outlier detection for adverse pregnancy outcomes

Adverse pregnancy outcomes, such as low birth weight (LBW) and preterm birth (PTB), can have serious consequences for both the mother and infant. Early prediction of such outcomes is important for their prevention. Previous studies using traditional machine learning (ML) models for predicting PTB and LBW have encountered two important limitations: extreme class imbalance in medical datasets and the inability to account for complex relational structures between entities. To address these limitations, we propose a node embedding-based graph outlier detection algorithm to predict adverse pregnancy outcomes. We developed a knowledge graph using a well-curated representative dataset of the Emirati population and two node embedding algorithms. The graph autoencoder (GAE) was trained by applying a combination of original risk factors and node embedding features. Samples that were difficult to reconstruct at the output of GAE were identified as outliers considered representing PTB and LBW samples. Our experiments using LBW, PTB, and very PTB datasets demonstrated that incorporating node embedding considerably improved performance, achieving a 12% higher AUC-ROC compared to traditional GAE. Our study demonstrates the effectiveness of node embedding and graph outlier detection in improving the prediction performance of adverse pregnancy outcomes in well-curated population datasets.

Adoption of a National Prophylactic Anticoagulation Guideline for Hospitalized Pregnant Women With COVID-19: Retrospective Cohort Study

BACKGROUND

Both COVID-19 and pregnancy are associated with hypercoagulability. Due to the increased risk for thrombosis, the United States National Institute of Health's recommendation for prophylactic anticoagulant use for pregnant patients has expanded from patients hospitalized for severe COVID-19 manifestation to all patients hospitalized for the manifestation of COVID-19 (no guideline: before December 26, 2020; first update: December 27, 2022; second update: February 24, 2022-present). However, no study has evaluated this recommendation.

OBJECTIVE

The objective of this study was to characterize prophylactic anticoagulant use among hospitalized pregnant people with COVID-19 from March 20, 2020, to October 19, 2022.

METHODS

This was a retrospective cohort study in large US health care systems across 7 states. The cohort of interest was pregnant patients who were hospitalized with COVID-19, without previous coagulopathy or contraindication to anticoagulants (n=2767). The treatment group consisted of patients prescribed prophylactic dose anticoagulation between 2 days before and 14 days after COVID-19 treatment onset (n=191). The control group was patients with no anticoagulant exposure between 14 days before and 60 days after COVID-19 treatment onset (n=2534). We ascertained the use of prophylactic anticoagulants with attention to the updates in guidelines and emerging SARS-CoV-2 variants. We propensity score matched the treatment and control group 1:1 on the most important features contributing to the prophylactic anticoagulant administration status classification. Outcome measures included coagulopathy, bleeding, COVID-19-related complications, and maternal-fetal health outcomes. Additionally, the inpatient anticoagulant administration rate was validated in a nationwide population from Truveta, a collective of 700 hospitals across the United States.

RESULTS

The overall administration rate of prophylactic anticoagulants was 7% (191/2725). It was lowest after the second guideline update (no guideline: 27/262, 10%; first update: 145/1663, 8.72%; second update: 19/811, 2.3%; P<.001) and during the omicron-dominant period (Wild type: 45/549, 8.2%; Alpha: 18/129, 14%; Delta: 81/507, 16%; and Omicron: 47/1551, 3%; P<.001). Models developed on retrospective data showed that the variable most associated with the administration of inpatient prophylactic anticoagulant was comorbidities prior to SARS-CoV-2 infection. The patients who were administered prophylactic anticoagulant were also more likely to receive supplementary oxygen (57/191, 30% vs 9/188, 5%; P<.001). There was no statistical difference in a new diagnosis of coagulopathy, bleeding, or maternal-fetal health outcomes between those who received treatment and the matched control group.

CONCLUSIONS

Most hospitalized pregnant patients with COVID-19 did not receive prophylactic anticoagulants across health care systems as recommended by guidelines. Guideline-recommended treatment was administered more frequently to patients with greater COVID-19 illness severity. Given the low rate of administration and differences between treated and untreated cohorts, efficacy could not be assessed.

On AI Approaches for Promoting Maternal and Neonatal Health in Low Resource Settings: A Review

A significant challenge for hospitals and medical practitioners in low- and middle-income nations is the lack of sufficient health care facilities for timely medical diagnosis of chronic and deadly diseases. Particularly, maternal and neonatal morbidity due to various non-communicable and nutrition related diseases is a serious public health issue that leads to several deaths every year. These diseases affecting either mother or child can be hospital-acquired, contracted during pregnancy or delivery, postpartum and even during child growth and development. Many of these conditions are challenging to detect at their early stages, which puts the patient at risk of developing severe conditions over time. Therefore, there is a need for early screening, detection and diagnosis, which could reduce maternal and neonatal mortality. With the advent of Artificial Intelligence (AI), digital technologies have emerged as practical assistive tools in different healthcare sectors but are still in their nascent stages when applied to maternal and neonatal health. This review article presents an in-depth examination of digital solutions proposed for maternal and neonatal healthcare in low resource settings and discusses the open problems as well as future research directions.

Prediction and prevention of preterm birth in pregnant women living with HIV on antiretroviral therapy

INTRODUCTION

The rate of spontaneous preterm-birth among pregnant women living with HIV on antiretroviral therapy (ART) is 3- to 4-fold higher when compared to HIV-negative women. The pathophysiology of preterm-birth related to HIV or ART remains unknown, especially as women living with HIV are often excluded from preterm birth studies.

AREAS COVERED

This review discusses the currently available evidence on the prediction and prevention of preterm-birth in pregnant women living with HIV. A review of the literature was conducted of primary articles between 2005 and 2021 measuring the association or lack thereof between combination ART and preterm birth, as well as of other predisposing factors to preterm birth in women living with HIV, including cervical length, vaginal microbiome, and cervico-vaginal biomarkers.

EXPERT OPINION

Further research into the effect of ART exposure on preterm-birth risk is critical, and development of preterm-birth predictive tools in this population should be a priority. Vaginal progesterone supplementation deserves further investigation as a therapeutic option to prevent recurrent preterm birth in pregnant women living with HIV. The ProSPAR study, a multicenter randomized controlled trial studying progesterone supplementation in pregnant women on protease inhibitor-based regimens, has been designed but is not yet recruiting patients.

Machine Learning-Based Prediction Model of Preterm Birth Using Electronic Health Record

Objective

Preterm birth (PTB) was one of the leading causes of neonatal death. Predicting PTB in the first trimester and second trimester will help improve pregnancy outcomes. The aim of this study is to propose a prediction model based on machine learning algorithms for PTB.

Method

Data for this study were reviewed from 2008 to 2018, and all the participants included were selected from a hospital in China. Six algorisms, including Naive Bayesian (NBM), support vector machine (SVM), random forest tree (RF), artificial neural networks (ANN), K-means, and logistic regression, were used to predict PTB. The receiver operating characteristic curve (ROC), accuracy, sensitivity, and specificity were used to assess the performance of the model.

Results

A total of 9550 pregnant women were included in the study, of which 4775 women had PTB. A total of 4775 people were randomly selected as controls. Based on 27 weeks of gestation, the area under the curve (AUC) and the accuracy of the RF model were the highest compared with other algorithms (accuracy: 0.816; AUC = 0.885, 95% confidence interval (CI): 0.873–0.897). Meanwhile, there was positive association between the accuracy and AUC of the RF model and gestational age. Age, magnesium, fundal height, serum inorganic phosphorus, mean platelet volume, waist size, total cholesterol, triglycerides, globulins, and total bilirubin were the main influence factors of PTB.

Conclusion

The results indicated that the prediction model based on the RF algorithm had a potential value to predict preterm birth in the early stage of pregnancy. The important analysis of the RF model suggested that intervention for main factors of PTB in the early stages of pregnancy would reduce the risk of PTB.

Introduction to Machine Learning in Obstetrics and Gynecology

In the digital age of the 21st century, we have witnessed an explosion in data matched by remarkable progress in the field of computer science and engineering, with the development of powerful and portable artificial intelligence-powered technologies. At the same time, global connectivity powered by mobile technology has led to an increasing number of connected users and connected devices. In just the past 5 years, the convergence of these technologies in obstetrics and gynecology has resulted in the development of innovative artificial intelligence-powered digital health devices that allow easy and accurate patient risk stratification for an array of conditions spanning early pregnancy, labor and delivery, and care of the newborn. Yet, breakthroughs in artificial intelligence and other new and emerging technologies currently have a slow adoption rate in medicine, despite the availability of large data sets that include individual electronic health records spanning years of care, genomics, and the microbiome. As a result, patient interactions with health care remain burdened by antiquated processes that are inefficient and inconvenient. A few health care institutions have recognized these gaps and, with an influx of venture capital investments, are now making in-roads in medical practice with digital products driven by artificial intelligence algorithms. In this article, we trace the history, applications, and ethical challenges of the artificial intelligence that will be at the forefront of digitally transforming obstetrics and gynecology and medical practice in general.