Prediction of the mode of delivery using artificial intelligence algorithms

Artificial intelligence models for predicting the mode of delivery in maternal care

BACKGROUND

Accurate prediction of the mode of delivery is critical in maternal care to improve prenatal counseling, optimize clinical decision-making, and reduce maternal and neonatal complications.

OBJECTIVES

This study aims to evaluate and compare the predictive accuracy of AI algorithms in predicting the mode of delivery (vaginal or cesarean) using routinely collected antepartum data from electronic health records (EHRs).

METHODS

A retrospective dataset of 16,651 pregnancies monitored at St. Mary's Hospital, London, over a four-year period was utilized. The dataset included 12,639 vaginal deliveries and 4012 unplanned cesarean deliveries, with 92 variables recorded for each patient. Five machine learning algorithms were evaluated: XGBoost, AdaBoost, random forest, decision tree, and multi-layer perceptron (MLP) classifier. A comprehensive feature importance analysis was conducted on the trained models to identify the key predictors influencing the mode of delivery classification.

RESULTS

All five models demonstrated excellent predictive performance, with AdaBoost and XGBoost achieving nearly identical top scores across most metrics: ROC-AUC (90 %), accuracy (89 %), PR-AUC (83 %), and F1 score (88 %) Feature importance analysis highlighted the most predictive factors for mode of delivery. Maternal age demonstrated the highest importance, followed by gravida and maternal height. Additional key contributors included weeks of gestation, - 2-hour plasma glucose level following an oral glucose tolerance test (OGTT), number of previous cesarean sections, and parity.

CONCLUSION

The findings validate the potential of AI algorithms not only to accurately predict the mode of delivery using antepartum data but also to identify key contributing factors. Integrating such models into clinical decision support systems could enhance prenatal counseling and risk stratification, ultimately contributing to more informed delivery planning and improved maternal and neonatal outcomes.

Advancing Obstetric Care Through Artificial Intelligence-Enhanced Clinical Decision Support Systems: A Systematic Review

Although artificial intelligence (AI) has grown over the past 10 years and clinical decision support systems (CDSS) have begun to be used in obstetric care, little is known about how AI functions in obstetric care-specific CDSS. We conducted a systematic review based on research studies that looked at AI-augmented CDSS in obstetric care to identify and synthesize CDSS functionality, AI techniques, clinical implementation, and AI-augmented CDSS in obstetric care. We searched four different databases (Scopus, PubMed, Web of Science, and IEEE Xplore) for relevant studies, and we found 354 studies. The studies were evaluated for eligibility based on predefined inclusion and exclusion criteria. The systematic review incorporated 30 studies after conducting an eligibility assessment of all studies. We used the Newcastle Ottawa Scale for risk bias assessment of all included studies. Medical prediction, therapeutic recommendations, diagnostic support, and knowledge dissemination constitute the key features of CDSS service offerings. The current research on CDSS included findings about early fetal anomaly detection, economical surveillance, prenatal ultrasonography assistance, and ontology development methodologies according to our study findings.

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.

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.

Predicting vaginal delivery after labor induction using machine learning: Development of a multivariable prediction model

INTRODUCTION

Induction of labor, often used for pregnancy termination, has globally rising rates, especially in high-income countries where pregnant women present with more comorbidities. Consequently, concerns on a potential rise in cesarean section (CS) rates after induction of labor (IOL) demand for improved counseling on delivery mode within this context.

MATERIAL AND METHODS

We aim to develop a prognostic model for predicting vaginal delivery after labor induction using computational learning. Secondary aims include elaborating a prognostic model for CS due to abnormal fetal heart rate and labor dystocia, and evaluation of these models' feature importance, using maternal clinical predictors at IOL admission. The best performing model was assessed in an independent validation data using the area under the receiver operating curve (AUROC). Internal model validation was performed using 10-fold cross-validation. Feature importance was calculated using SHAP (SHapley Additive exPlanation) values to interpret the importance of influential features. Our main outcome measures were mode of delivery after induction of labor, dichotomized as vaginal or cesarean delivery and CS indications, dichotomized as abnormal fetal heart rate and labor dystocia.

RESULTS

Our sample comprised singleton term pregnant women (n = 2434) referred for IOL to a tertiary Obstetrics center between January 2018 and December 2021. Prediction of vaginal delivery obtained good discrimination in the independent validation data (AUROC = 0.794, 95% CI 0.783-0.805), showing high positive and negative predictive values (PPV and NPV) of 0.752 and 0.793, respectively, high specificity (0.910) and sensitivity (0.766). The CS model showed an AUROC of 0.590 (95% CI 0.565-0.615) and high specificity (0.893). Sensitivity, PPV and NVP values were 0.665, 0.617, and 0.7, respectively. Labor features associated with vaginal delivery were by order of importance: Bishop score, number of previous term deliveries, maternal height, interpregnancy time interval, and previous eutocic delivery.

CONCLUSIONS

This prognostic model produced a 0.794 AUROC for predicting vaginal delivery. This, coupled with knowing the features influencing this outcome, may aid providers in assessing an individual's risk of CS after IOL and provide personalized counseling.

Artificial Intelligence-Augmented Clinical Decision Support Systems for Pregnancy Care: Systematic Review

BACKGROUND

Despite the emerging application of clinical decision support systems (CDSS) in pregnancy care and the proliferation of artificial intelligence (AI) over the last decade, it remains understudied regarding the role of AI in CDSS specialized for pregnancy care.

OBJECTIVE

To identify and synthesize AI-augmented CDSS in pregnancy care, CDSS functionality, AI methodologies, and clinical implementation, we reported a systematic review based on empirical studies that examined AI-augmented CDSS in pregnancy care.

METHODS

We retrieved studies that examined AI-augmented CDSS in pregnancy care using database queries involved with titles, abstracts, keywords, and MeSH (Medical Subject Headings) terms. Bibliographic records from their inception to 2022 were retrieved from PubMed/MEDLINE (n=206), Embase (n=101), and ACM Digital Library (n=377), followed by eligibility screening and literature review. The eligibility criteria include empirical studies that (1) developed or tested AI methods, (2) developed or tested CDSS or CDSS components, and (3) focused on pregnancy care. Data of studies used for review and appraisal include title, abstract, keywords, MeSH terms, full text, and supplements. Publications with ancillary information or overlapping outcomes were synthesized as one single study. Reviewers independently reviewed and assessed the quality of selected studies.

RESULTS

We identified 30 distinct studies of 684 studies from their inception to 2022. Topics of clinical applications covered AI-augmented CDSS from prenatal, early pregnancy, obstetric care, and postpartum care. Topics of CDSS functions include diagnostic support, clinical prediction, therapeutics recommendation, and knowledge base.

CONCLUSIONS

Our review acknowledged recent advances in CDSS studies including early diagnosis of prenatal abnormalities, cost-effective surveillance, prenatal ultrasound support, and ontology development. To recommend future directions, we also noted key gaps from existing studies, including (1) decision support in current childbirth deliveries without using observational data from consequential fetal or maternal outcomes in future pregnancies; (2) scarcity of studies in identifying several high-profile biases from CDSS, including social determinants of health highlighted by the American College of Obstetricians and Gynecologists; and (3) chasm between internally validated CDSS models, external validity, and clinical implementation.

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.

Fast Healthcare Interoperability Resources-Based Support System for Predicting Delivery Type: Model Development and Evaluation Study

BACKGROUND

The escalating prevalence of cesarean delivery globally poses significant health impacts on mothers and newborns. Despite this trend, the underlying reasons for increased cesarean delivery rates, which have risen to 36.3% in Portugal as of 2020, remain unclear. This study delves into these issues within the Portuguese health care context, where national efforts are underway to reduce cesarean delivery occurrences.

OBJECTIVE

This paper aims to introduce a machine learning, algorithm-based support system designed to assist clinical teams in identifying potentially unnecessary cesarean deliveries. Key objectives include developing clinical decision support systems for cesarean deliveries using interoperability standards, identifying predictive factors influencing delivery type, assessing the economic impact of implementing this tool, and comparing system outputs with clinicians' decisions.

METHODS

This study used retrospective data collected from 9 public Portuguese hospitals, encompassing maternal and fetal data and delivery methods from 2019 to 2020. We used various machine learning algorithms for model development, with light gradient-boosting machine (LightGBM) selected for deployment due to its efficiency. The model's performance was compared with clinician assessments through questionnaires. Additionally, an economic simulation was conducted to evaluate the financial impact on Portuguese public hospitals.

RESULTS

The deployed model, based on LightGBM, achieved an area under the receiver operating characteristic curve of 88%. In the trial deployment phase at a single hospital, 3.8% (123/3231) of cases triggered alarms for potentially unnecessary cesarean deliveries. Financial simulation results indicated potential benefits for 30% (15/48) of Portuguese public hospitals with the implementation of our tool. However, this study acknowledges biases in the model, such as combining different vaginal delivery types and focusing on potentially unwarranted cesarean deliveries.

CONCLUSIONS

This study presents a promising system capable of identifying potentially incorrect cesarean delivery decisions, with potentially positive implications for medical practice and health care economics. However, it also highlights the challenges and considerations necessary for real-world application, including further evaluation of clinical decision-making impacts and understanding the diverse reasons behind delivery type choices. This study underscores the need for careful implementation and further robust analysis to realize the full potential and real-world applicability of such clinical support systems.

Current status of the position on labor progress prediction for contemporary pregnant women using Friedman curves: An updated review

AIM

Prediction of labor progression is important for maternal and fetal health, as improved accuracy can lead to more timely intervention and improved outcomes. This review aims to outline the importance of predicting the progression of spontaneous parturition, detail the various methods employed to enhance this prediction and provide recommendations for future research.

METHODS

We searched articles relating to labor progression and systematic review articles on Artificial Inteligence (AI) in childbirth management using PubMed. To supplement, Google Scholar was used to find recent guidelines and related documents.

RESULTS

Traditional methods like vaginal examinations, criticized for subjectivity and inaccuracy, are gradually being replaced by ultrasound, considered a more objective and accurate approach. Further advancements have been observed with machine learning and artificial intelligence techniques, which promise to surpass the accuracies of conventional methods. The Friedman curve, developed in 1954, is the standard for assessing labor progress, but its application to Asian women, in particular, remains controversial, and various studies have reported that the actual rate of labor was slower than that indicated by the Friedman curve.

CONCLUSION

There is a need to innovate methodologies for predicting delivery tailored to modern pregnant women, especially when they have different genetic and cultural backgrounds than their Western counterparts, such as Asians. Future research should develop predictive models of labor progression that aim to enhance medical intervention and improve the safety and well-being of both mother and child.

Artificial intelligence as a new answer to old challenges in maternal-fetal medicine and obstetrics

BACKGROUND

Following the latest trends in the development of artificial intelligence (AI), the possibility of processing an immense amount of data has created a breakthrough in the medical field. Practitioners can now utilize AI tools to advance diagnostic protocols and improve patient care.

OBJECTIVE

The aim of this article is to present the importance and modalities of AI in maternal-fetal medicine and obstetrics and its usefulness in daily clinical work and decision-making process.

METHODS

A comprehensive literature review was performed by searching PubMed for articles published from inception up until August 2023, including the search terms "artificial intelligence in obstetrics", "maternal-fetal medicine", and "machine learning" combined through Boolean operators. In addition, references lists of identified articles were further reviewed for inclusion.

RESULTS

According to recent research, AI has demonstrated remarkable potential in improving the accuracy and timeliness of diagnoses in maternal-fetal medicine and obstetrics, e.g., advancing perinatal ultrasound technique, monitoring fetal heart rate during labor, or predicting mode of delivery. The combination of AI and obstetric ultrasound can help optimize fetal ultrasound assessment by reducing examination time and improving diagnostic accuracy while reducing physician workload.

CONCLUSION

The integration of AI in maternal-fetal medicine and obstetrics has the potential to significantly improve patient outcomes, enhance healthcare efficiency, and individualized care plans. As technology evolves, AI algorithms are likely to become even more sophisticated. However, the successful implementation of AI in maternal-fetal medicine and obstetrics needs to address challenges related to interpretability and reliability.

A multimodal model in the prediction of the delivery mode using data from a digital twin-empowered labor monitoring system

Objective

This study aims to address the limitations of current clinical methods in predicting delivery mode by constructing a multimodal neural network-based model. The model utilizes data from a digital twin-empowered labor monitoring system, including computerized cardiotocography (cCTG), ultrasound (US) examination data, and electronic health records (EHRs) of pregnant women.

Methods

The model integrates three modalities of data from 105 pregnant women (76 vaginal deliveries and 29 cesarean deliveries) at the Department of Obstetrics and Gynecology of The First Affiliated Hospital of Jinan University, Guangzhou, China. It employs a hybrid architecture of a convolutional neural network (CNN) and bi-directional long short-term memory (BiLSTM) to compress the data into a single feature vector for each patient.

Results

The designed model achieves a cross-validation accuracy of 93.33%, an F1-score of 86.26%, an area under the receiver operating characteristic curve of 97.10%, and a Brier Score of 6.67%. Importantly, while cCTG and EHRs are crucial for labor management, the integration of US imaging data significantly enhances prediction accuracy.

Conclusion

The findings of this study suggest that the developed multimodal model is a promising tool for predicting delivery mode and provides a comprehensive approach to intrapartum maternal and fetal health monitoring. The integration of multi-source data, including real-time information, holds potential for further improving the algorithm's predictive accuracy as the volume of analyzed data increases. This could be highly beneficial for dynamically fusing data from different sources throughout the maternal and fetal health lifecycle, from pregnancy to delivery.

Use of artificial intelligence in obstetrics: not quite ready for prime time

Artificial intelligence is finding several applications in healthcare settings. This study aimed to report evidence on the effectiveness of artificial intelligence application in obstetrics. Through a narrative review of literature, we described artificial intelligence use in different obstetrical areas as follows: prenatal diagnosis, fetal heart monitoring, prediction and management of pregnancy-related complications (preeclampsia, preterm birth, gestational diabetes mellitus, and placenta accreta spectrum), and labor. Artificial intelligence seems to be a promising tool to help clinicians in daily clinical activity. The main advantages that emerged from this review are related to the reduction of inter- and intraoperator variability, time reduction of procedures, and improvement of overall diagnostic performance. However, nowadays, the diffusion of these systems in routine clinical practice raises several issues. Reported evidence is still very limited, and further studies are needed to confirm the clinical applicability of artificial intelligence. Moreover, better training of clinicians designed to use these systems should be ensured, and evidence-based guidelines regarding this topic should be produced to enhance the strengths of artificial systems and minimize their limits.