Prediction of vaginal birth after cesarean deliveries using machine learning

Applying Automated Machine Learning to Predict Mode of Delivery Using Ongoing Intrapartum Data in Laboring Patients

OBJECTIVE

 This study aimed to develop and validate a machine learning (ML) model to predict the probability of a vaginal delivery (Partometer) using data iteratively obtained during labor from the electronic health record.

STUDY DESIGN

 A retrospective cohort study of deliveries at an academic, tertiary care hospital was conducted from 2013 to 2019 who had at least two cervical examinations. The population was divided into those delivered by physicians with nulliparous term singleton vertex (NTSV) cesarean delivery rates <23.9% (Partometer cohort) and the remainder (control cohort). The cesarean rate among this population of lower risk patients is a standard metric by which to compare provider rates; <23.9% was the Healthy People 2020 goal. A supervised automated ML approach was applied to generate a model for each population. The primary outcome was accuracy of the model developed on the Partometer cohort at 4 hours from admission to labor and delivery. Secondary outcomes included discrimination ability (receiver operating characteristics-area under the curve [ROC-AUC]), precision-recall AUC, and calibration of the Partometer. To assess generalizability, we compared the performance and clinical predictors identified by the Partometer to the control model.

RESULTS

 There were 37,932 deliveries during the study period; after exclusions, 9,385 deliveries were included in the Partometer cohort and 19,683 in the control cohort. Accuracy of predicting vaginal delivery at 4 hours was 87.1% for the Partometer (ROC-AUC: 0.82). Clinical predictors of greatest importance in the stacked Intrapartum Partometer Model included the Admission Model prediction and ongoing measures of dilatation and station which mirrored those found in the control population.

CONCLUSION

 Using automated ML and intrapartum factors improved the accuracy of prediction of probability of a vaginal delivery over both previously published models based on logistic regression. Harnessing real-time data and ML could represent the bridge to generating a truly prescriptive tool to augment clinical decision-making, predict labor outcomes, and reduce maternal and neonatal morbidity.

KEY POINTS

· Our ML-based model yielded accurate predictions of mode of delivery early in labor.. · Predictors for models created on populations with high and low cesarean rates were the same.. · A ML-based model may provide meaningful guidance to clinicians managing labor..

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.

Women's preference for a vaginal birth in Brazilian private hospitals: effects of a quality improvement project

BACKGROUND

In 2015, a quality improvement project called "Adequate Childbirth Project" (PPA) was implemented in Brazilian private hospitals in order to reduce cesarean sections without clinical indication. The PPA is structured in four components, one of which is directed at women and families. The objective of this study is to evaluate the effects of PPA on women's preference for vaginal birth (VB) at the end of pregnancy.

METHODS

Evaluative research conducted in 12 private hospitals participating in the PPA. Interviews were carried out in the immediate postpartum period and medical record data were collected at hospital discharge. The implementation of PPA activities and women's preference for type of birth at the beginning and end of pregnancy were compared in women assisted in the PPA model of care and in the standard of care model, using a chi-square statistical test. To estimate the effect of PPA on women's preference for VB at the end of pregnancy, multiple logistic regression was performed with selection of variables using a causal diagram.

RESULTS

Four thousand seven hundred ninety-eight women were interviewed. The implementation of the planned activities of PPA was less than 50%, but were significantly more frequent among women assisted in the PPA model of care. Women in this group also showed a greater preference for VB at the beginning and end of pregnancy. The PPA showed an association with greater preference for VB at the end of pregnancy in primiparous (OR 2.54 95% CI 1.99-3.24) and multiparous women (OR 1.44 95% CI 0.97-2.12), although in multiparous this association was not significant. The main factor associated with the preference for VB at the end of pregnancy was the preference for this type of birth at the beginning of pregnancy, both in primiparous (OR 18.67 95% CI 14.22-24.50) and in multiparous women (OR 53.11 95% CI 37.31-75.60).

CONCLUSIONS

The PPA had a positive effect on women's preference for VB at the end of pregnancy. It is plausible that more intense effects are observed with the expansion of the implementation of the planned activities. Special attention should be given to information on the benefits of VB in early pregnancy.

Trial of labor after cesarean, vaginal birth after cesarean, and the risk of uterine rupture: an expert review

The decision to pursue a trial of labor after cesarean delivery is complex and depends on patient preference, the likelihood of successful vaginal birth after cesarean delivery, assessment of the risks vs benefits of trial of labor after cesarean delivery, and available resources to support safe trial of labor after cesarean delivery at the planned birthing center. The most feared complication of trial of labor after cesarean delivery is uterine rupture, which can have catastrophic consequences, including substantial maternal and perinatal morbidity and mortality. Although the absolute risk of uterine rupture is low, several clinical, historical, obstetrical, and intrapartum factors have been associated with increased risk. It is therefore critical for clinicians managing patients during trial of labor after cesarean delivery to be aware of these risk factors to appropriately select candidates for trial of labor after cesarean delivery and maximize the safety and benefits while minimizing the risks. Caution is advised when considering labor augmentation and induction in patients with a previous cesarean delivery. With established hospital safety protocols that dictate close maternal and fetal monitoring, avoidance of prostaglandins, and careful titration of oxytocin infusion when induction agents are needed, spontaneous and induced trial of labor after cesarean delivery are safe and should be offered to most patients with 1 previous low transverse, low vertical, or unknown uterine incision after appropriate evaluation, counseling, planning, and shared decision-making. Future research should focus on clarifying true risk factors and identifying the optimal approach to intrapartum and induction management, tools for antenatal prediction, and strategies for prevention of uterine rupture during trial of labor after cesarean delivery. A better understanding will facilitate patient counseling, support efforts to improve trial of labor after cesarean delivery and vaginal birth after cesarean delivery rates, and reduce the morbidity and mortality associated with uterine rupture during trial of labor after cesarean delivery.

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

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 improvements in screening as well as in the prediction of the disease in high-risk women. This is due to, among other things, the introduction of biomarkers such as the sFlt-1/PlGF ratio. Recently, the traditional definition of preeclampsia has been expanded based on new insights into the pathophysiology and conclusive evidence on the ability of angiogenic biomarkers to improve detection of preeclampsia-associated maternal and fetal adverse events.However, with the widespread availability of digital solutions, such as decision support algorithms and remote monitoring devices, a chance for a further improvement of care arises. Two lines of research and application are promising: First, on the patient side, home monitoring has the potential to transform the traditional care pathway. The importance of the ability to input and access data remotely is a key learning from the COVID-19 pandemic. Second, on the physician side, machine-learning-based decision support algorithms have been shown to improve precision in clinical decision-making. The integration of signals from patient-side remote monitoring devices into predictive algorithms that power physician-side decision support tools offers a chance to further improve care.The purpose of this review is to summarize the recent advances in prediction, diagnosis and monitoring of preeclampsia and its associated adverse outcomes. We will review the potential impact of the ability to access to clinical data via remote monitoring. In the combination of advanced, machine learning-based risk calculation and remote monitoring lies an unused potential that allows for a truly patient-centered care.

Development of a multivariate predictive nomogram among women with antepartum fetal death diagnosed at ≥ 34 weeks of gestation for outcome of TOLAC

OBJECTIVE

The present study was planned to develop a nomogram that will give a priori estimate on the probability of vaginal birth from maternal features in women with antepartum fetal death diagnosed at ≥ 34 week's gestation and previous one low transverse cesarean section (LTCS). This will help to reduce maternal complications and increase confidence when planning a trial of labor after cesarean section (TOLAC).

METHODS

A prospective observational study was planned where participants underwent induction of labor with Foley's catheter (unless already in spontaneous labor) within 24 h of enrolment. Participants with absent or inadequate contractions, oxytocin infusion as an additional agent was used. Data was collected on maternal predelivery features. Outcome of participants was categorized into two classes-vaginal and cesarean delivery. Classifiers were trained with data on maternal features and the accuracy of predicting outcome class determined. The classifier with maximum accuracy was used to develop a nomogram.

RESULT

Three hundred and one women underwent treatment as per protocol. Two hundred and twenty women attained successful vaginal delivery and eighty-one women underwent caesarean section. Factors having a significant impact on outcome were maternal body mass index (BMI), bishop score, duration of augmentation, estimated foetal weight, interval from previous LTCS, admission to active labor interval, vaginal delivery after LTCS and gestational age. The Naïve -Bayes model gave the highest prediction accuracy (0.88).

CONCLUSION

Non-linear classifiers by using selective features could predict the outcome of TOLAC among women with intra-uterine fetal death attempting vaginal birth at or beyond 34 weeks gestation with high accuracy.

Construction and evaluation of nursing-sensitive quality indicators for vaginal birth after cesarean: A Delphi study based on Chinese population

Aim

To develop scientific, systematic and clinically applicable nursing-sensitive quality indicators for vaginal birth after cesarean in obstetrics, which provide a theoretical and clinical basis for monitoring and improving the nursing quality of vaginal birth after cesarean in China.

Methods

A modified Delphi-consensus technique was used in this study. Based on literature retrieval published between January 2012 and December 2022 and group discussion, the preliminary nursing-sensitive quality indicators were selected using a structural-process-outcome model. Then a questionnaire was designed on the preliminary indicators. The modified Delphi method was used to conduct two rounds of expert consultation among 26 hospitals in China. The survey data of experts' opinions were collected and analyzed to determine the final nursing-sensitive quality indicators. The importance of indicators, rationality of calculation formula and operability of data collection were analyzed and discussed.

Results

A total of 33 nursing-sensitive quality indicators were determined. The indicators were composed of 3-level ones, including 3 first-level indicators (structural, process and outcome indicators), 9 s-level ones and 33 third-level ones. The positive coefficients in the two rounds of expert consultation were 95.56 % and 97.67 %, respectively, and the authoritative coefficients were 0.88 and 0.94. The coefficients of variation ranged from 0.05 to 0.28.

Conclusion

The nursing-sensitive quality indicators were successfully developed using the modified Delphi method. The indicators are scientific, systematic and clinically operable, and play an important role in improving the nursing quality for pregnant women with vaginal birth after cesarean.

Predictors of Uterine Rupture After One Previous Cesarean Section: An Unmatched Case-Control Study

Background

Uterine rupture is a rare occurrence but has catastrophic complications during pregnancy. The incidence is relatively higher in scarred uteri because there is a promotion of labor after cesarean section. There is a scarcity of evidence from low-income countries regarding the predictors of uterine rupture after trial labor.

Objective

To assess factors determining uterine rupture during labor after the previous cesarean section among mothers delivered at Hawassa University Comprehensive Specialized Hospital from September 2017 to September 2022.

Methods

A facility-based unmatched case-control study was done by reviewing 105 patients, which included 35 cases and 70 controls in a 1:2 case-to-control ratio. The association between dependent and independent variables was sought with running binary and multivariate analyses by using the cut point of a p value < 0.05 and 95% CI.

Results

The prevalence of uterine rupture is 1.6%. The factors significantly associated with uterine rupture after trial of labor are fetal weight >3.8 kg (AOR: 5.21), antenatal care 4 (AOR: 3.6), labor duration >15 hours (AOR: 10.7), and previous successful vaginal delivery (AOR: 3.4). Poor fetal-maternal outcomes like 91.4% fetal death, 29 hysterectomies, 22 blood transfusions, and 1 death.

Conclusion

The prevalence is relatively higher than in developed countries. The number of antenatal care, labor duration, and lower fetal weight are not common findings associated with uterine rupture after trial of labor across the literature, so large-scale studies are needed to develop guidelines for the Ethiopian setup. Improving the quality of obstetrics care given in each level of health system.

Identifying risk of stillbirth using machine learning

BACKGROUND

Previous predictive models using logistic regression for stillbirth do not leverage the advanced and nuanced techniques involved in sophisticated machine learning methods, such as modeling nonlinear relationships between outcomes.

OBJECTIVE

This study aimed to create and refine machine learning models for predicting stillbirth using data available before viability (22-24 weeks) and throughout pregnancy, as well as demographic, medical, and prenatal visit data, including ultrasound and fetal genetics.

STUDY DESIGN

This is a secondary analysis of the Stillbirth Collaborative Research Network, which included data from pregnancies resulting in stillborn and live-born infants delivered at 59 hospitals in 5 diverse regions across the United States from 2006 to 2009. The primary aim was the creation of a model for predicting stillbirth using data available before viability. Secondary aims included refining models with variables available throughout pregnancy and determining variable importance.

RESULTS

Among 3000 live births and 982 stillbirths, 101 variables of interest were identified. Of the models incorporating data available before viability, the random forests model had 85.1% accuracy (area under the curve) and high sensitivity (88.6%), specificity (85.3%), positive predictive value (85.3%), and negative predictive value (84.8%). A random forests model using data collected throughout pregnancy resulted in accuracy of 85.0%; this model had 92.2% sensitivity, 77.9% specificity, 84.7% positive predictive value, and 88.3% negative predictive value. Important variables in the previability model included previous stillbirth, minority race, gestational age at the earliest prenatal visit and ultrasound, and second-trimester serum screening.

CONCLUSION

Applying advanced machine learning techniques to a comprehensive database of stillbirths and live births with unique and clinically relevant variables resulted in an algorithm that could accurately identify 85% of pregnancies that would result in stillbirth, before they reached viability. Once validated in representative databases reflective of the US birthing population and then prospectively, these models may provide effective risk stratification and clinical decision-making support to better identify and monitor those at risk of stillbirth.

An idiosyncratic MIMBO-NBRF based automated system for child birth mode prediction

Predicting the mode of child birth is still remains one of the most complex and challenging tasks in ancient times. Also, there is no such strong methodologies are developed in the conventional works for birth mode prediction. Therefore, the proposed work objects to develop a novel and distinct optimization based machine learning technique for creating the child birth mode prediction system. This framework includes the modules of data imputation, feature selection, classification, and prediction. Initially, the data imputation process is performed to improve the quality of dataset by normalizing the attributes and filling the missed fields. Then, the Multivariate Intensified Mine Blast Optimization (MIMBO) technique is implemented to choose the best set of features by estimating the optimal function. After that, an integrated Naïve Bayes - Random Forest (NBRF) technique is developed by incorporating the functions of conventional NB and RF techniques. The novel contribution of this technique, a Bird Mating (BM) optimization technique is used in NBRF classifier for estimating the likelihood parameter to generate the Bayesian rules. The main idea of this paper is to develop a simple as well as efficient automated system with the use of hybrid machine learning model for predicting the mode of child birth. For this purpose, advanced algorithms such as MIMBO based feature selection, and NBRF based classification are implemented in this work. Due to the inclusion of MIMBO and BM optimization techniques, the performance of classifier is greatly improved with low computational burden and increased prediction accuracy. Moreover, the combination of proposed MIMBO-NBRF technique outperforms the existing child birth prediction methods with superior results in terms of average accuracy up to 99 %. In addition, some other parameters are also estimated and compared with the existing techniques for proving the overall superiority of the proposed framework.

Prediction of cesarean delivery in class III obese nulliparous women: An externally validated model using machine learning

BACKGROUND

class III obese women, are at a higher risk of cesarean section during labor, and cesarean section is responsible for increased maternal and neonatal morbidity in this population.

OBJECTIVE

the objective of this project was to develop a method with which to quantify cesarean section risk before labor.

METHODS

this is a multicentric retrospective cohort study conducted on 410 nulliparous class III obese pregnant women who attempted vaginal delivery in two French university hospitals. We developed two predictive algorithms (a logistic regression and a random forest models) and assessed performance levels and compared them.

RESULTS

the logistic regression model found that only initial weight and labor induction were significant in the prediction of unplanned cesarean section. The probability forest was able to predict cesarean section probability using only two pre-labor characteristics: initial weight and labor induction. Its performances were higher and were calculated for a cut-point of 49.5% risk and the results were (with 95% confidence intervals): area under the curve 0.70 (0.62,0.78), accuracy 0.66 (0.58, 0.73), specificity 0.87 (0.77, 0.93), and sensitivity 0.44 (0.32, 0.55).

CONCLUSIONS

this is an innovative and effective approach to predicting unplanned CS risk in this population and could play a role in the choice of a trial of labor versus planned cesarean section. Further studies are needed, especially a prospective clinical trial.

FUNDING

French state funds "Plan Investissements d'Avenir" and Agence Nationale de la Recherche.

Middle eastern college of obstetricians and gynecologists (MCOG) practice guidelines: Role of prediction models in management of trial of labor after cesarean section. Practice guideline no. 05-O-22✰,✰✰,★,★★

Cesarean delivery rates have been steadily rising since the beginning of the 21st century. The growing incidence is even more prominent in developing countries owing to lack of evidence-based guidance and audit, and the expansion of private practice. The uprise in Cesarean delivery rate has been associated with considerable financial burden and has increased the risk otherwise uncommon serious complications such as placenta accreta disorders and uterine rupture. In addition to primary prevention of Cesarean delivery, trial of labor after cesarean section is one of the most successful strategies to reduce Cesarean deliveries and minimize risks associated with higher order Cesarean deliveries. This guideline appraises patient selection strategies and use of prediction model to promote counseling and enhance safety in women considering vaginal birth after Cesarean.

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

Introduction

Machine learning (ML) corresponds to a wide variety of methods that use mathematics, statistics and computational science to learn from multiple variables simultaneously. By means of pattern recognition, ML methods are able to find hidden correlations and accomplish accurate predictions regarding different conditions. ML has been successfully used to solve varied problems in different areas of science, such as psychology, economics, biology and chemistry. Therefore, we wondered how far it has penetrated into the field of obstetrics and gynecology.

Aim

To describe the state of art regarding the use of ML in the context of pregnancy diseases and complications.

Methodology

Publications were searched in PubMed, Web of Science and Google Scholar. Seven subjects of interest were considered: gestational diabetes mellitus, preeclampsia, perinatal death, spontaneous abortion, preterm birth, cesarean section, and fetal malformations.

Current state

ML has been widely applied in all the included subjects. Its uses are varied, the most common being the prediction of perinatal disorders. Other ML applications include (but are not restricted to) biomarker discovery, risk estimation, correlation assessment, pharmacological treatment prediction, drug screening, data acquisition and data extraction. Most of the reviewed articles were published in the last five years. The most employed ML methods in the field are non-linear. Except for logistic regression, linear methods are rarely used.

Future challenges

To improve data recording, storage and update in medical and research settings from different realities. To develop more accurate and understandable ML models using data from cutting-edge instruments. To carry out validation and impact analysis studies of currently existing high-accuracy ML models.

Conclusion

The use of ML in pregnancy diseases and complications is quite recent, and has increased over the last few years. The applications are varied and point not only to the diagnosis, but also to the management, treatment, and pathophysiological understanding of perinatal alterations. Facing the challenges that come with working with different types of data, the handling of increasingly large amounts of information, the development of emerging technologies, and the need of translational studies, it is expected that the use of ML continue growing in the field of obstetrics and gynecology.

Analysis of Publication Activity and Research Trends in the Field of AI Medical Applications: Network Approach

Artificial intelligence (AI) has revolutionized numerous industries, including medicine. In recent years, the integration of AI into medical practices has shown great promise in enhancing the accuracy and efficiency of diagnosing diseases, predicting patient outcomes, and personalizing treatment plans. This paper aims at the exploration of the AI-based medicine research using network approach and analysis of existing trends based on PubMed. Our findings are based on the results of PubMed search queries and analysis of the number of papers obtained by the different search queries. Our goal is to explore how are the AI-based methods used in healthcare research, which approaches and techniques are the most popular, and to discuss the potential reasoning behind the obtained results. Using analysis of the co-occurrence network constructed using VOSviewer software, we detected the main clusters of interest in AI-based healthcare research. Then, we proceeded with the thorough analysis of publication activity in various categories of medical AI research, including research on different AI-based methods applied to different types of medical data. We analyzed the results of query processing in the PubMed database over the past 5 years obtained via a specifically designed strategy for generating search queries based on the thorough selection of keywords from different categories of interest. We provide a comprehensive analysis of existing applications of AI-based methods to medical data of different modalities, including the context of various medical fields and specific diseases that carry the greatest danger to the human population.

Prior childbirth experience and attitude towards subsequent vaginal birth after one caesarean delivery in Lagos, Nigeria: a cross-sectional study

BACKGROUND

Prior caesarean delivery (CD) impacts CD rates in many parts of the world. In low and middle-income countries, few women attempt a trial of labour after caesarean delivery (TOLAC) due to inadequate resources for safe vaginal birth after caesarean delivery (VBAC). The CD rates continue to rise as more women undergo repeat CD. In Nigeria, VBAC rate is low and the contribution of women's prior childbirth experiences and delivery wishes to this situation deserves further investigation. This study examined the parturient factor in the low VBAC rate to recommend strategies for change.

OBJECTIVE

To describe prior caesarean-related childbirth experiences and attitudes towards subsequent vaginal birth in pregnant women with one previous CD.

METHOD

This cross-sectional study of antenatal clinic attendees in a tertiary hospital employed the convenience sampling method to recruit 216 consenting women with one previous CD. Structured questionnaires were used to collect information on participants' prior caesarean-related birth experiences, attitudes to vaginal birth in the index pregnancy, future delivery intentions and eventual delivery route. Univariate and bivariate analyses compared delivery wishes based on CD type. SPSS version 22.0 was used for data analysis.

RESULTS

The modal maternal and gestational age groups were 30-39 years (68.1%) and 29-34 weeks (49.1%) respectively; majorities (60.6%) were secundigravida; 61.6% experienced labour before their CDs while 76.9% had emergency CDs. Complications were documented in 1.4% and 11.1% of mothers and babies respectively. Ninety percent reported a satisfactory overall childbirth experience. A majority (83.3%) preferred TOLAC in the index pregnancy because they desired natural childbirth while 16.7% wanted a repeat CD due to the fear of fetal-maternal complications. The previous CD type and desire for more babies were significantly associated with respondents' preferred mode of delivery (p = 0.001 and 0.023 respectively). Women with previous emergency CD were more likely to prefer vaginal delivery.

CONCLUSIONS

Antenatal women prefer TOLAC in subsequent pregnancies despite prior satisfactory caesarean-related birth experiences. Adoption of TOLAC in appropriately selected cases will impact women's psyche positively and reduce CD rate.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 2-Data From Nonwearables

OBJECTIVES

Despite the increasing interest in applying machine learning (ML) methods in health economics and outcomes research (HEOR), stakeholders face uncertainties in when and how ML can be used. We reviewed the recent applications of ML in HEOR.

METHODS

We searched PubMed for studies published between January 2020 and March 2021 and randomly chose 20% of the identified studies for the sake of manageability. Studies that were in HEOR and applied an ML technique were included. Studies related to wearable devices were excluded. We abstracted information on the ML applications, data types, and ML methods and analyzed it using descriptive statistics.

RESULTS

We retrieved 805 articles, of which 161 (20%) were randomly chosen. Ninety-two of the random sample met the eligibility criteria. We found that ML was primarily used for predicting future events (86%) rather than current events (14%). The most common response variables were clinical events or disease incidence (42%) and treatment outcomes (22%). ML was less used to predict economic outcomes such as health resource utilization (16%) or costs (3%). Although electronic medical records (35%) were frequently used for model development, claims data were used less frequently (9%). Tree-based methods (eg, random forests and boosting) were the most commonly used ML methods (31%).

CONCLUSIONS

The use of ML techniques in HEOR is growing rapidly, but there remain opportunities to apply them to predict economic outcomes, especially using claims databases, which could inform the development of cost-effectiveness models.

Simplifying the prediction of vaginal birth after cesarean delivery: role of the cervical exam

OBJECTIVE

Predicting likelihood of vaginal birth after cesarean (VBAC) is a cornerstone in counseling patients considering a trial of labor after cesarean (TOLAC). Yet, the simplified Bishop score (SBS), a score comprised cervical dilation, station, and effacement assessment used to predict successful vaginal delivery, has not been applied to the TOLAC population. We evaluated the relationship between admission SBS and likelihood of successful VBAC. We also determined the predictive characteristics of SBS, compared to cervical dilation alone, for successful VBAC.

METHODS

This is a secondary analysis of a prospective cohort study of patients with a singleton gestation, ≥37 0/7 weeks gestation, and prior cesarean admitted to Labor & Delivery between 2010 and 2014. The primary outcome of successful VBAC was compared between those with a favorable (score >5) and unfavorable (score ≤5) admission SBS. Secondary outcomes were select maternal and neonatal outcomes. Adjusted risk ratios were estimated using multivariable logistic regression analyses. Receiver-operating characteristic curves compared predictive capabilities of cervical dilation alone to SBS for successful VBAC.

RESULTS

Of the 656 patients who underwent a TOLAC during the study period, 421 (64%) had a successful VBAC. 203 (31%) and 453 (69%) had a favorable and an unfavorable admission SBS, respectively. After adjusting for body mass index and prior vaginal delivery, patients with a favorable admission SBS had a 30% greater likelihood of successful VBAC compared to those with an unfavorable SBS (aRR 1.30, 95% CI 1.16-1.40). Admission cervical dilation alone performed similarly to SBS as a predictor of successful VBAC, with a receiver-operator characteristic curve area under the curve (AUC) of 0.68 (95% CI 0.64-0.72) versus an AUC 0.66 (95% CI 0.62-0.70), respectively (p = .07). There were no differences in adverse maternal or neonatal outcomes between those with an unfavorable and favorable SBS.

CONCLUSIONS

A favorable admission SBS is associated with an increased likelihood of VBAC. Although both admission SBS and cervical dilation alone are only modest predictors of VBAC, admission cervical dilation performs overall similarly to current models for VBAC prediction and is an objective, reproducible, and generalizable measure. Our study highlights the value of waiting until end of pregnancy (rather than the first prenatal visit) to conclude patient counseling on the decision to TOLAC in order to consider admission cervical assessment, particularly cervical dilation.

Diversity in Machine Learning: A Systematic Review of Text-Based Diagnostic Applications

OBJECTIVE

 As the storage of clinical data has transitioned into electronic formats, medical informatics has become increasingly relevant in providing diagnostic aid. The purpose of this review is to evaluate machine learning models that use text data for diagnosis and to assess the diversity of the included study populations.

METHODS

 We conducted a systematic literature review on three public databases. Two authors reviewed every abstract for inclusion. Articles were included if they used or developed machine learning algorithms to aid in diagnosis. Articles focusing on imaging informatics were excluded.

RESULTS

 From 2,260 identified papers, we included 78. Of the machine learning models used, neural networks were relied upon most frequently (44.9%). Studies had a median population of 661.5 patients, and diseases and disorders of 10 different body systems were studied. Of the 35.9% (N = 28) of papers that included race data, 57.1% (N = 16) of study populations were majority White, 14.3% were majority Asian, and 7.1% were majority Black. In 75% (N = 21) of papers, White was the largest racial group represented. Of the papers included, 43.6% (N = 34) included the sex ratio of the patient population.

DISCUSSION

 With the power to build robust algorithms supported by massive quantities of clinical data, machine learning is shaping the future of diagnostics. Limitations of the underlying data create potential biases, especially if patient demographics are unknown or not included in the training.

CONCLUSION

 As the movement toward clinical reliance on machine learning accelerates, both recording demographic information and using diverse training sets should be emphasized. Extrapolating algorithms to demographics beyond the original study population leaves large gaps for potential biases.

Machine learning to predict pregnancy outcomes: a systematic review, synthesizing framework and future research agenda

Machine Learning (ML) has been widely used in predicting the mode of childbirth and assessing the potential maternal risks during pregnancy. The primary aim of this review study is to explore current research and development perspectives that utilizes the ML techniques to predict the optimal mode of childbirth and to detect various complications during childbirth. A total of 26 articles (published between 2000 and 2020) from an initial set of 241 articles were selected and reviewed following a Systematic Literature Review (SLR) approach. As outcomes, this review study highlighted the objectives or focuses of the recent studies conducted on pregnancy outcomes using ML; explored the adopted ML algorithms along with their performances; and provided a synthesized view of features used, types of features, data sources and its characteristics. Besides, the review investigated and depicted how the objectives of the prior studies have changed with time being; and the association among the objectives of the studies, uses of algorithms, and the features. The study also delineated future research opportunities to facilitate the existing initiatives for reducing maternal complacent and mortality rates, such as: utilizing unsupervised and deep learning algorithms for prediction, revealing the unknown reasons of maternal complications, developing usable and useful ML-based clinical decision support systems to be used by the expecting mothers and health professionals, enhancing dataset and its accessibility, and exploring the potentiality of surgical robotic tools. Finally, the findings of this review study contributed to the development of a conceptual framework for advancing the ML-based maternal healthcare system. All together, this review will provide a state-of-the-art paradigm of ML-based maternal healthcare that will aid in clinical decision-making, anticipating pregnancy problems and delivery mode, and medical diagnosis and treatment.

Prediction of Emergency Cesarean Section Using Machine Learning Methods: Development and External Validation of a Nationwide Multicenter Dataset in Republic of Korea

This study was a multicenter retrospective cohort study of term nulliparous women who underwent labor, and was conducted to develop an automated machine learning model for prediction of emergent cesarean section (CS) before onset of labor. Nine machine learning methods of logistic regression, random forest, Support Vector Machine (SVM), gradient boosting, extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), k-nearest neighbors (KNN), Voting, and Stacking were applied and compared for prediction of emergent CS during active labor. External validation was performed using a nationwide multicenter dataset for Korean fetal growth. A total of 6549 term nulliparous women was included in the analysis, and the emergent CS rate was 16.1%. The C-statistics values for KNN, Voting, XGBoost, Stacking, gradient boosting, random forest, LGBM, logistic regression, and SVM were 0.6, 0.69, 0.64, 0.59, 0.66, 0.68, 0.68, 0.7, and 0.69, respectively. The logistic regression model showed the best predictive performance with an accuracy of 0.78. The machine learning model identified nine significant variables of maternal age, height, weight at pre-pregnancy, pregnancy-associated hypertension, gestational age, and fetal sonographic findings. The C-statistic value for the logistic regression machine learning model in the external validation set (1391 term nulliparous women) was 0.69, with an overall accuracy of 0.68, a specificity of 0.83, and a sensitivity of 0.41. Machine learning algorithms with clinical and sonographic parameters at near term could be useful tools to predict individual risk of emergent CS during active labor in nulliparous women.

A new index for obstetrics safety and quality of care: integrating cesarean delivery rates with maternal and neonatal outcomes

BACKGROUND

Cesarean delivery rates have been used as obstetrical quality indicators. However, these approaches do not consider the accompanying maternal and neonatal morbidities. A challenge in the field of obstetrics has been to establish a valid outcomes quality measure that encompasses preexisting high-risk maternal factors and associated maternal and neonatal morbidities and is universally acceptable to all stakeholders, including patients, healthcare providers, payers, and governmental agencies.

OBJECTIVE

This study aimed to (1) establish a new single metric for obstetrical quality improvement among nulliparous patients with term singleton vertex-presenting fetus, integrating cesarean delivery rates adjusted for preexisting high-risk maternal factors with associated maternal and neonatal morbidities, and (2) determine whether obstetrician quality ranking by this new metric is different compared with the rating based on individual crude and/or risk-adjusted cesarean delivery rates. The single metric has been termed obstetrical safety and quality index.

STUDY DESIGN

This was a cross-sectional study of all nulliparous patients with term singleton vertex-presenting fetuses delivered by 12 randomly chosen obstetricians in a single institution. A review of all records was performed, including a review of maternal high-risk factors and maternal and neonatal outcomes. Maternal and neonatal medical records were reviewed to determine crude and adjusted cesarean delivery rates by obstetricians and quantify maternal and neonatal complications. We estimated the obstetrician-specific crude cesarean delivery rates and rates adjusted for obstetrician-specific maternal and neonatal complications from logistic regression models. From this model, we derived the obstetrical safety and quality index for each obstetrician. The final ranking based on the obstetrical safety and quality index was compared with the initial ranking by crude cesarean delivery rates. Maternal and neonatal morbidities were analyzed as ≥1 and ≥2 maternal and/or neonatal complications.

RESULTS

These 12 obstetricians delivered a total of 535 women; thus, 1070 (535 maternal and 535 neonatal) medical records were reviewed to determine crude and adjusted cesarean delivery rates by obstetricians and quantify maternal and neonatal complications. The ranking of crude cesarean delivery rates was not correlated (rho=0.05; 95% confidence interval, -0.54 to 0.60) to the final ranking based on the obstetrical safety and quality index. Of note, 8 of 12 obstetricians shifted their rank quartiles after adjustments for high-risk maternal conditions and maternal and neonatal outcomes. There was a strong correlation between the ranking based on ≥1 maternal and/or neonatal complication and ranking based on ≥2 maternal and/or neonatal complications (rho=0.63; 95% confidence interval, 0.08-0.88).

CONCLUSION

Ranking based on crude cesarean delivery rates varied significantly after considering high-risk maternal conditions and associated maternal and neonatal outcomes. Therefore, the obstetrical safety and quality index, a single metric, was developed to identify ways to improve clinician practice standards within an institution. Use of this novel quality measure may help to change initiatives geared toward patient safety, balancing cesarean delivery rates with optimal maternal and neonatal outcomes. This metric could be used to compare obstetrical quality not only among individual obstetricians but also among hospitals that practice obstetrics.

Predicting vaginal birth after caesarean section: Validation of the Grobman model in a New Zealand population

BACKGROUND

The decision regarding mode of birth following a primary caesarean section is important. Women may choose an elective repeat caesarean section or a trial of labour in an attempt to achieve a vaginal birth after caesarean (VBAC). The highest morbidity and mortality is associated with those who have an emergency caesarean section following a trial of labour. Therefore, the ability to accurately predict successful VBAC is important in antenatal counselling.

AIMS

To test the validity of the Grobman prediction nomogram in a New Zealand (NZ) population.

MATERIALS AND METHODS

A retrospective cohort study was performed of women carrying a singleton, cephalic pregnancy at term and who had one previous lower segment caesarean section in Northland, NZ. The probabilities of successful VBAC were calculated using the variables in the Grobman model and compared with observed VBAC rates using a calibration curve. The predictive ability of the model was assessed using area under the receiver operating characteristic curve (AUC).

RESULTS

Of the 421 eligible women, 354 elected to undergo a trial of labour, of whom 69.5% had a successful VBAC. The AUC for the Grobman model was 0.72 (95% CI 0.67-0.78) with predicted and actual outcomes being similar when predicted success was over 50%. The predictive ability of the model appeared more accurate for Māori and Pacifika women compared to the NZ European population.

CONCLUSIONS

The Grobman model predicts successful VBAC reasonably well in a NZ population and can be used as an antenatal counselling aid.

Contributions of artificial intelligence reported in Obstetrics and Gynecology journals: a systematic review

Background

The applications of artificial intelligence (AI) processes have grown significantly in all medical disciplines during the last decades. Two main types of AI have been applied in medicine: symbolic AI (eg, knowledge base and ontologies) and nonsymbolic AI (eg, machine learning and artificial neural networks). Consequently, AI has also been applied across most obstetrics and gynecology (OB/GYN) domains, including general obstetrics, gynecology surgery, fetal ultrasound, and assisted reproductive medicine, among others.

Objective

The aim of this study was to provide a systematic review to establish the actual contributions of AI reported in OB/GYN discipline journals.

Methods

The PubMed database was searched for citations indexed with “artificial intelligence” and at least one of the following medical subject heading (MeSH) terms between January 1, 2000, and April 30, 2020: “obstetrics”; “gynecology”; “reproductive techniques, assisted”; or “pregnancy.” All publications in OB/GYN core disciplines journals were considered. The selection of journals was based on disciplines defined in Web of Science. The publications were excluded if no AI process was used in the study. Review, editorial, and commentary articles were also excluded. The study analysis comprised (1) classification of publications into OB/GYN domains, (2) description of AI methods, (3) description of AI algorithms, (4) description of data sets, (5) description of AI contributions, and (6) description of the validation of the AI process.

Results

The PubMed search retrieved 579 citations and 66 publications met the selection criteria. All OB/GYN subdomains were covered: obstetrics (41%, 27/66), gynecology (3%, 2/66), assisted reproductive medicine (33%, 22/66), early pregnancy (2%, 1/66), and fetal medicine (21%, 14/66). Both machine learning methods (39/66) and knowledge base methods (25/66) were represented. Machine learning used imaging, numerical, and clinical data sets. Knowledge base methods used mostly omics data sets. The actual contributions of AI were method/algorithm development (53%, 35/66), hypothesis generation (42%, 28/66), or software development (3%, 2/66). Validation was performed on one data set (86%, 57/66) and no external validation was reported. We observed a general rising trend in publications related to AI in OB/GYN over the last two decades. Most of these publications (82%, 54/66) remain out of the scope of the usual OB/GYN journals.

Conclusions

In OB/GYN discipline journals, mostly preliminary work (eg, proof-of-concept algorithm or method) in AI applied to this discipline is reported and clinical validation remains an unmet prerequisite. Improvement driven by new AI research guidelines is expected. However, these guidelines are covering only a part of AI approaches (nonsymbolic) reported in this review; hence, updates need to be considered.

Early Warning Model of Placenta Accreta Spectrum Disorders Complicated with Cervical Implantation: A Single-Center Retrospective Study

Background

Placenta accreta spectrum (PAS) disorders seriously threaten the safety of the mother and infant in the perinatal period. Moreover, PAS is associated with poor maternal and perinatal outcomes once complicated with cervical implantation. Dismally, there are few reports about PAS complicated with cervical involvement currently, and the early warning models are also rarely reported. To screen the risk factors of PAS complicated with cervical implantation and construct an early risk warning model, we performed the analysis of clinical indicators and images of PAS patients by artificial intelligence (AI) data processing methods.

Methods

The clinical data of 166 patients with PAS in our hospital from January 2016 to September 2020 were retrospectively analyzed. The patients were divided into cervical implantation group and lower uterine implantation group according to the position of placenta implantation. Then, we compared the pregnancy outcomes of the two groups, screened the possible related factors of PAS complicated with cervical implantation by univariate analysis, and established the early warning model by logistic regression analysis.

Results

The maternal outcome of PAS complicated with cervical implantation was worse than that of the lower uterine implantation group. Through univariate analysis and logistic regression analysis, we found that the cervical width, abundant cervical blood flow, and bladder line interruption were all risk factors of PAS complicated with cervical implantation, and their contribution to the establishment of the regression model was statistically significant.

Conclusion

PAS complicated with cervical implantation was extremely severe. Early identification of risk factors and establishment of a risk warning model have certain guiding significance for clinical formulation of a reasonable treatment plan.

Primary risk stratification for neonatal jaundice among term neonates using machine learning algorithm

BACKGROUND

Neonatal jaundice occurs in approximately 60% of term newborns. Although risk factors for neonatal jaundice have been studied, all the suggested strategies are based on various newborn tests for bilirubin levels. We aim to stratify neonates into risk groups for clinically significant neonatal jaundice using a combined data analysis approach, without serum bilirubin evaluation.

STUDY DESIGN

Term (gestational week 37-42) neonates born in a single medical center, 2005-2018 were identified. Anonymized data were analyzed using machine learning. Thresholds for stratification into risk groups were established. Associations were evaluated statistically using neonates with and without clinically significant neonatal jaundice from the study population.

RESULTS

A total of 147,667 consecutive term live neonates were included. The machine learning diagnostic ability to evaluate the risk for neonatal jaundice was 0.748; 95% CI 0.743-0.754 (AUC). The most important factors were (in order of importance) maternal blood type, maternal age, gestational age at delivery, estimated birth weight, parity, CBC at admission, and maternal blood pressure at admission. Neonates were then stratified by risk: 61% (n = 90,140) were classed as low-risk, 39% (n = 57,527) as higher-risk. Prevalence of jaundice was 4.14% in the full cohort, and 1.47% and 8.29% in the low- and high-risk cohorts, respectively; OR 6.06 (CI: 5.7-6.45) for neonatal jaundice in high-risk group.

CONCLUSION

A population tailored "first step" screening policy using machine learning model presents potential of neonatal jaundice risk stratification for term neonates. Future development and validation of this computational model are warranted.

Using Machine Learning to Predict Complications in Pregnancy: A Systematic Review

Introduction: Artificial intelligence is widely used in medical field, and machine learning has been increasingly used in health care, prediction, and diagnosis and as a method of determining priority. Machine learning methods have been features of several tools in the fields of obstetrics and childcare. This present review aims to summarize the machine learning techniques to predict perinatal complications.

Objective: To identify the applicability and performance of machine learning methods used to identify pregnancy complications.

Methods: A total of 98 articles were obtained with the keywords “machine learning,” “deep learning,” “artificial intelligence,” and accordingly as they related to perinatal complications (“complications in pregnancy,” “pregnancy complications”) from three scientific databases: PubMed, Scopus, and Web of Science. These were managed on the Mendeley platform and classified using the PRISMA method.

Results: A total of 31 articles were selected after elimination according to inclusion and exclusion criteria. The features used to predict perinatal complications were primarily electronic medical records (48%), medical images (29%), and biological markers (19%), while 4% were based on other types of features, such as sensors and fetal heart rate. The main perinatal complications considered in the application of machine learning thus far are pre-eclampsia and prematurity. In the 31 studies, a total of sixteen complications were predicted. The main precision metric used is the AUC. The machine learning methods with the best results were the prediction of prematurity from medical images using the support vector machine technique, with an accuracy of 95.7%, and the prediction of neonatal mortality with the XGBoost technique, with 99.7% accuracy.

Conclusion: It is important to continue promoting this area of research and promote solutions with multicenter clinical applicability through machine learning to reduce perinatal complications. This systematic review contributes significantly to the specialized literature on artificial intelligence and women’s health.

Intelligent systems in obstetrics and midwifery: Applications of machine learning

INTRODUCTION

Machine learning is increasingly utilized over recent years in order to develop models that represent and solve problems in a variety of domains, including those of obstetrics and midwifery. The aim of this systematic review was to analyze research studies on machine learning and intelligent systems applications in midwifery and obstetrics.

METHODS

A thorough literature review was performed in four electronic databases (PubMed, APA PsycINFO, SCOPUS, ScienceDirect). Only articles that discussed machine learning and intelligent systems applications in midwifery and obstetrics, were considered in this review. Selected articles were critically evaluated as for their relevance and a contextual synthesis was conducted.

RESULTS

Thirty-two articles were included in this systematic review as they met the inclusion and methodological criteria specified in this study. The results suggest that machine learning and intelligent systems have produced successful models and systems in a broad list of midwifery and obstetrics topics, such as diagnosis, pregnancy risk assessment, fetal monitoring, bladder tumor, etc.

CONCLUSIONS

This systematic review suggests that machine learning represents a very promising area of artificial intelligence for the development of practical and highly effective applications that can support human experts, as well the investigation of a wide range of exciting opportunities for further research.

A Retrospective Study of the Association of Repeated Attempts at Trial of Labor After Cesarean Birth on Maternal and Neonatal Outcomes

Purpose

To assess the maternal and neonatal outcomes of repeated trials of labor after one previous cesarean section.

Materials and Methods

We identified and reviewed the records of all women who had had a trial of labor after cesarean section at a tertiary care center in Saudi Arabia between January 1, 2011, and December 30, 2018. The inclusion criteria were women with singleton vertex pregnancies between 24 and 42 weeks of gestation and a trial of labor after one cesarean section. The exclusion criteria were two or more previous cesarean sections, intrauterine fetal demise, breech presentation, labor induction, estimated fetal weight >4 kg, and classical or low vertical uterine incision. The pregnancy outcomes of these women were compared according to the number of trials of labor after cesarean section.

Results

During the study period, 1139 women met the inclusion criteria. The number of women with previous zero, one, two, or three or more trials of labor after cesarean section were 669 (58.7%), 237 (20.8%), 132 (11.6%), and 101 (8.9%), respectively. There were statistically significant trends between the four groups in age, nationality, gravidity, and parity but not in the booking status, BMI, or the hemoglobin level before a trial of labor after cesarean section. The rate of vaginal birth after cesarean section increased significantly (p<0.001) from 72.9% with zero to 93.3% with one, 93.9% with two, and 94.1% with three or more trials of labor after cesarean section.

Conclusion

Previously successful vaginal births after cesarean delivery are associated with improved maternal and neonatal outcomes in the subsequent trials of labor after cesarean delivery.

Trial of labor after cesarean in primiparous women with fetal macrosomia

KEY MESSAGE

Spontaneous labor onset, epidural anesthesia and prior cesarean for non-arrest disorders are strong predictors of successful vaginal birth after cesarean in women delivering a macrosomic fetus.

PURPOSE

Lower rates of successful vaginal birth after cesarean in association with increasing birthweight were previously reported. We aimed to determine the factors associated with successful trial of labor after cesarean (TOLAC) among primiparous women with fetal macrosomia.

METHODS

A retrospective cohort study conducted during 2005-2019 at two university hospitals, including all primiparous women delivering a singleton fetus weighing ≥ 4000 g, after cesarean delivery at their first delivery. A multivariate analysis was performed to evaluate the characteristics associated with TOLAC success (primary outcome).

RESULTS

Of 551 primiparous women who met the inclusion criteria, 50.1% (n = 276) attempted a TOLAC and 174 (63.0%) successfully delivered vaginally. In a multivariate analysis, spontaneous onset of labor (aOR [95% CI] 3.68 (2.05, 6.61), P < 0.001), epidural anesthesia (aOR [95% CI] 2.38 (1.35, 4.20), P = 0.003) and history of cesarean delivery due to non-arrest disorder (aOR [95% CI] 2.25 (1.32, 3.85), P = 0.003) were the only independent factors associated with TOLAC success. Successful TOLAC was achieved in 82.0% (82/100) in the presence of all three favorable factors, 61.3% (65/106) in the presence of two factors and 38.6% (27/70) in the presence of one or less of these three factors (P < 0.001).

CONCLUSION

Spontaneous onset of labor, epidural anesthesia and prior cesarean delivery due to non-arrest disorders were independently associated with higher vaginal birth after cesarean rate among women with fetal macrosomia, with an overall favorable success rate in the presence of these factors. These findings should be implemented in patient counseling in those contemplating a vaginal birth in this setting.

Prediction of vaginal birth after cesarean for labor dystocia by sonographic estimated fetal weight

OBJECTIVE

To estimate the association of the weight difference between the index trial of labor after cesarean (TOLAC) sonographic estimated fetal weight (sEFW) and prior delivery birth weight with TOLAC success rate among women with previous labor dystocia and no prior vaginal delivery.

METHODS

A retrospective cohort study including all women with prior cesarean for labor dystocia and no prior vaginal delivery undergoing TOLAC during between March 2011 and June 2020 with a sEFW within 1 week from delivery.

RESULTS

Overall, 168 women were included, of those 107 (63.7%) successfully delivered vaginally. The mean sEFW and mean birth weight were lower in the TOLAC success group (P = 0.010 and P = 0.013, respectively). The rate of higher sEFW in the current delivery compared with the previous delivery did not differ between study groups. The rate of higher TOLAC birth weight was lower in the TOLAC success group (odds ratio 0.30; 95% confidence interval 0.15-0.58). In multivariable regression analysis, maternal age older than 30 years, induction of labor, and higher birth weight were independently negatively associated with TOLAC success (adjusted odds ratio [95% confidence interval]: 0.27 [0.10-0.70], 0.27 [0.08-0.90], and 0.43 [0.19-0.94]; P = 0.008, P = 0.034, and P = 0.035, respectively).

CONCLUSIONS

sEFW characteristics did not predict the success or failure of TOLAC among women with prior labor dystocia and no previous vaginal delivery.

Risk management of vaginal birth after cesarean section (Review)

The increasing number of patients who desire to experience vaginal birth after cesarean (VBAC) and the optimized protocols for trial of labor after cesarean (TOLAC) has led to a shift of old obstetrical paradigms. The VBAC trend is accompanied with numerous challenges for healthcare professionals, from establishing suitability of each pregnant patient profile for TOLAC to active labor management, and ethical or legal issues, which occasionally are not included in specific guidelines. That is why an individualized risk assessment and management can serve obstetricians as a useful tool for improving outcomes of patients, satisfaction, and also for avoiding legal or moral liabilities. The risk management concept aims to reduce foreseen risks and to emulate strategies for prediction and prevention of unwanted events. In obstetrics, and particularly for the VBAC topic, this concept is relatively new and undefined, and thus its features are disparate between guideline recommendations and clinical studies. This narrative review intends to offer a new and organic perspective over clinical aspects of TOLAC and VBAC risk management.

The urological complications of vaginal birth after cesarean (VBAC) - a literature review

The appearance of urological complications is a major problem in obstetrics and gynecologic surgery; the bladder is the most common damaged organ. Due to a continuous increase in the rate of cesareans, the incidence of urologic complications will be potentially higher. We reviewed the most important risk factors for urinary tract injury and analyzed the strategies necessary to avoid these situations during vaginal birth after cesarean (VBAC). The risks and benefits of VBAC should be balanced before deciding the mode of delivery.

Reliable Prediction Models Based on Enriched Data for Identifying the Mode of Childbirth by Using Machine Learning Methods: Development Study

Background

The use of artificial intelligence has revolutionized every area of life such as business and trade, social and electronic media, education and learning, manufacturing industries, medicine and sciences, and every other sector. The new reforms and advanced technologies of artificial intelligence have enabled data analysts to transmute raw data generated by these sectors into meaningful insights for an effective decision-making process. Health care is one of the integral sectors where a large amount of data is generated daily, and making effective decisions based on these data is therefore a challenge. In this study, cases related to childbirth either by the traditional method of vaginal delivery or cesarean delivery were investigated. Cesarean delivery is performed to save both the mother and the fetus when complications related to vaginal birth arise.

Objective

The aim of this study was to develop reliable prediction models for a maternity care decision support system to predict the mode of delivery before childbirth.

Methods

This study was conducted in 2 parts for identifying the mode of childbirth: first, the existing data set was enriched and second, previous medical records about the mode of delivery were investigated using machine learning algorithms and by extracting meaningful insights from unseen cases. Several prediction models were trained to achieve this objective, such as decision tree, random forest, AdaBoostM1, bagging, and k-nearest neighbor, based on original and enriched data sets.

Results

The prediction models based on enriched data performed well in terms of accuracy, sensitivity, specificity, F-measure, and receiver operating characteristic curves in the outcomes. Specifically, the accuracy of k-nearest neighbor was 84.38%, that of bagging was 83.75%, that of random forest was 83.13%, that of decision tree was 81.25%, and that of AdaBoostM1 was 80.63%. Enrichment of the data set had a good impact on improving the accuracy of the prediction process, which supports maternity care practitioners in making decisions in critical cases.

Conclusions

Our study shows that enriching the data set improves the accuracy of the prediction process, thereby supporting maternity care practitioners in making informed decisions in critical cases. The enriched data set used in this study yields good results, but this data set can become even better if the records are increased with real clinical data.

Clinical Effects of Form-Based Management of Forceps Delivery under Intelligent Medical Model

Background

Forceps delivery is one of the most important measures to facilitate vaginal delivery. It can reduce the rate of first cesarean delivery. Frustratingly, adverse maternal and neonatal outcomes associated with forceps delivery have been frequently reported in recent years. There are two major reasons: one is that the abilities of doctors and midwives in forceps delivery vary from hospital to hospital and the other one is lack of regulations in the management of forceps delivery. In order to improve the success rate of forceps delivery and reduce the incidence of maternal and neonatal complications, we applied form-based management to forceps delivery under an intelligent medical model. The aim of this work is to explore the clinical effects of form-based management of forceps delivery.

Methods

Patients with forceps delivery in Maternal and Child Health Hospital Affiliated to Nanchang University were divided into two groups: form-based patients from January 1, 2019, to December 31, 2020, were selected as the study group, while traditional protocol patients from January 1, 2017, to December 31, 2018, were chosen as the control group. Then, we compared the maternal and neonatal outcomes of these two groups.

Results

There were significant differences in the maternal and neonatal adverse outcomes such as rate of postpartum hemorrhage, degree of perineal laceration, and incidence of neonatal facial skin abrasions between the two groups, whereas differences in the incidence of asphyxia and intracranial hemorrhage were not significant.

Conclusions

Form-based management could help us assess the security of forceps delivery comprehensively, as it could not only improve the success rate of the one-time forceps traction scheme but also reduce the incidence of maternal and neonatal adverse outcomes effectively.

Fetal Head Station at Second-Stage Dystocia and Subsequent Trial of Labor After Cesarean Delivery Success Rate

OBJECTIVE

To investigate whether fetal head station at the index cesarean delivery is associated with a subsequent trial of labor success rate among primiparous women.

METHODS

A retrospective cohort study conducted at two tertiary medical centers included all primiparous women with subsequent delivery after cesarean delivery for second-stage dystocia during 2009-2019, identified from the electronic medical record databases. Univariate and multivariate analyses were performed to assess the factors associated with successful trial of labor after cesarean (TOLAC) (primary outcome). Additionally, all women with failed TOLAC were matched one-to-one to women with successful TOLAC, according to factors identified in the univariate analysis.

RESULTS

Of 481 primiparous women with prior cesarean delivery for second-stage dystocia, 64.4% (n=310) attempted TOLAC, and 222 (71.6%) successfully delivered vaginally. The rate of successful TOLAC was significantly higher in those with fetal head station below the ischial spines at the index cesarean delivery, as compared with those with higher head station (79.0% vs 60.5%, odds ratio [OR] 2.46, 95% CI 1.49-4.08). The proportion of neonates weighing more than 3,500 g in the subsequent delivery was lower in those with successful TOLAC compared with failed TOLAC (29.7% vs 43.2%, OR 0.56, 95% CI 0.33-0.93). In a multivariable analysis, lower fetal head station at the index cesarean delivery was the only independent factor associated with TOLAC success (adjusted OR 2.38, 95% CI 1.43-3.96). Matching all women with failed TOLAC one-to-one to women with successful TOLAC, according to birth weight and second-stage duration at the subsequent delivery, lower fetal head station at the index cesarean delivery remained the only factor associated with successful TOLAC.

CONCLUSION

Lower fetal head station at the index cesarean delivery for second-stage dystocia was independently associated with a higher vaginal birth after cesarean rate, with an overall acceptable success rate. These findings should improve patient counseling and reassure those who wish to deliver vaginally after prior second-stage arrest.

Artificial intelligence (AI) in the detection of rectosigmoid deep endometriosis

OBJECTIVES

The aim of this study was to compare the accuracy of seven classical Machine Learning (ML) models trained with ultrasound (US) soft markers to raise suspicion of endometriotic bowel involvement.

MATERIALS AND METHODS

Input data to the models was retrieved from a database of a previously published study on bowel endometriosis performed on 333 patients. The following models have been tested: k-nearest neighbors algorithm (k-NN), Naive Bayes, Neural Networks (NNET-neuralnet), Support Vector Machine (SVM), Decision Tree, Random Forest, and Logistic Regression. The data driven strategy has been to split randomly the complete dataset in two different datasets. The training dataset and the test dataset with a 67 % and 33 % of the original cases respectively. All models were trained on the training dataset and the predictions have been evaluated using the test dataset. The best model was chosen based on the accuracy demonstrated on the test dataset. The information used in all the models were: age; presence of US signs of uterine adenomyosis; presence of an endometrioma; adhesions of the ovary to the uterus; presence of "kissing ovaries"; absence of sliding sign. All models have been trained using CARET package in R with ten repeated 10-fold cross-validation. Accuracy, Sensitivity, Specificity, positive (PPV) and negative (NPV) predictive value were calculated using a 50 % threshold. Presence of intestinal involvement was defined in all cases in the test dataset with an estimated probability greater than 0.5.

RESULTS

In our previous study from where the inputs were retrieved, 106 women had a final expert US diagnosis of rectosigmoid endometriosis. In term of diagnostic accuracy the best model was the Neural Net (Accuracy, 0.73; sensitivity, 0.72; specificity 0.73; PPV 0.52; and NPV 0.86) but without significant difference with the others.

CONCLUSIONS

The accuracy of ultrasound soft markers in raising suspicion of rectosigmoid endometriosis using Artificial Intelligence (AI) models showed similar results to the logistic model.

Prediction of severe adverse neonatal outcomes at the second stage of labour using machine learning: a retrospective cohort study

OBJECTIVE

To create a personalised machine learning model for prediction of severe adverse neonatal outcomes (SANO) during the second stage of labour.

DESIGN

Retrospective Electronic-Medical-Record (EMR) -based study.

POPULATION

A cohort of 73 868 singleton, term deliveries that reached the second stage of labour, including 1346 (1.8%) deliveries with SANO.

METHODS

A gradient boosting model was created, analysing 21 million data points from antepartum features (e.g. gravidity and parity) gathered at admission to the delivery unit, and intrapartum data (e.g. cervical dilatation and effacement) gathered during the first stage of labour. Deliveries were allocated to high-risk and low-risk groups based on the Youden index to maximise sensitivity and specificity.

MAIN OUTCOME MEASURES

SANO was defined as either umbilical cord pH levels ≤7.1 or 1-minute or 5-minute Apgar score ≤7.

RESULTS

The model for prediction of SANO yielded an area under the receiver operating curve (AUC) of 0.761 (95% CI 0.748-0.774). A third of the cohort (33.5%, n = 24 721) were allocated to a high-risk group for SANO, which captured up to 72.1% of these cases (odds ratio 5.3, 95% CI 4.7-6.0; high-risk versus low-risk groups).

CONCLUSIONS

Data acquired throughout the first stage of labour can be used to predict SANO during the second stage of labour using a machine learning model. Stratifying parturients at the beginning of the second stage of labour in a 'time out' session, can direct a personalised approach to management of this challenging aspect of labour, as well as improve allocation of staff and resources.

TWEETABLE ABSTRACT

Personalised prediction score for severe adverse neonatal outcomes in labour using machine learning model.

Maternal age at first cesarean delivery related to adverse pregnancy outcomes in a second cesarean delivery: a multicenter, historical, cross-sectional cohort study

Background

To determine the effects of maternal age at first cesarean on maternal complications and adverse outcomes of pregnancy with the second cesarean.

Methods

This was a multicenter, historical, cross-sectional cohort study involving singleton pregnancies ≥28 gestational weeks, with a history of 1 cesarean delivery, and who underwent a second cesarean between January and December 2017 at 11 public tertiary hospitals in 7 provinces of China. We analyzed the effects of maternal age at first cesarean on adverse outcomes of pregnancy in the second cesarean using multivariate logistic regression analysis.

Results

The study consisted of 10,206 singleton pregnancies. Women were at first cesarean between 18 and 24, 25–29, 30–34, and ≥ 35 years of age; and numbered 2711, 5524, 1751, and 220 cases, respectively. Maternal age between 18 and 24 years at first cesarean increased the risk of placenta accreta spectrum (aOR, 1.499; 95% CI, 1.12–2.01), placenta previa (aOR, 1.349; 95% CI, 1.07–1.70), intrahepatic cholestasis of pregnancy (aOR, 1.947; 95% CI, 1.24–3.07), postpartum hemorrhage (aOR, 1.505; 95% CI, 1.05–2.16), and blood transfusion (aOR, 1.517; 95% CI, 1.21–1.91) in the second cesarean compared with the reference group (aged 25–29 years). In addition, maternal age ≥ 35 years at first cesarean was a risk factor for premature rupture of membranes (aOR, 1.556; 95% CI, 1.08–2.24), placental abruption (aOR, 6.464, 95% CI, 1.33–31.51), uterine rupture (aOR, 7.952; 95% CI, 1.43–44.10), puerperal infection (aOR, 6.864; 95% CI, 1.95–24.22), neonatal mild asphyxia (aOR, 4.339; 95% CI, 1.53–12.32), severe asphyxia (aOR, 18.439; 95% CI, 1.54–220.95), and admission to a neonatal intensive care unit (aOR, 2.825; 95% CI, 1.54–5.17) compared with the reference group (aged 25–29 years).

Conclusions

Maternal age between 18 and 24 years or advanced maternal age at first cesarean was an independent risk factor for adverse maternal outcomes with the second cesarean. Advanced maternal age at the first cesarean specifically increased adverse neonatal outcomes with the second. Therefore, decisions as to whether to perform a first cesarean at a young or advanced maternal age must be critically evaluated.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12884-021-03608-9.

Implementation of a calculator to predict cesarean delivery during labor induction: a qualitative evaluation of the clinician perspective

BACKGROUND

We previously conducted a prospective cohort study (n=1610) demonstrating that the implementation of a validated calculator to predict likelihood of cesarean delivery during labor induction was associated with reduced maternal morbidity, reduced cesarean delivery rate, and improved birth satisfaction.

OBJECTIVE

To optimize future implementation, we used qualitative interviews to understand the clinician perspective on: (1) the cesarean delivery risk calculator implementation and (2) the mechanisms by which the use of the calculator resulted in the observed improved outcomes.

STUDY DESIGN

After completion of the prospective study (June 30, 2019), 20 trainees and attending clinicians (including nurse-midwives, obstetrical physicians, and family medicine physicians) at the study site participated in a single, brief semistructured interview from March 1, 2020, to June 30, 2020. Transcriptions were coded using a systematic approach.

RESULTS

Overall, clinicians had favorable perspectives regarding the cesarean delivery risk calculator. Clinicians described the calculator as offering "objective data" and a "standardized snapshot of the labor trajectory." Concerns were raised regarding "overreliance" on calculator output. Barriers to use included time for patient counseling and "awkwardness" around the interactions and perceived patient misunderstanding of the calculator result. Although most senior clinicians (n=8) reported that the calculator did not impact patient management, trainee clinicians (n=12) more often felt that the calculator influenced care at the extremes of cesarean delivery risk. Furthermore, more senior clinicians felt "neutral" regarding any impact of counseling patients on cesarean delivery risk compared with trainee clinicians, who felt that the counseling "built [patient-clinician] trust."

CONCLUSION

This qualitative evaluation characterized the generally positive clinician perspective around the cesarean delivery risk calculator, while identifying specific facilitators and barriers to implementation. In addition, we elucidated potential mechanisms by which the calculator may have been related to clinician decision making and patient-clinician interactions, leading to reduced maternal morbidity and improved patient birth satisfaction. This information is important as widespread implementation of the cesarean delivery risk calculator begins.

Development and Validation of Predictive Models for Vaginal Birth After Cesarean Delivery in China

Background

The rate of delivery by cesarean section is rising in China, where vaginal birth after cesarean (VBAC) is in its early stages. There are no validated screening tools to predict VBAC success in China. The objective of this study was to identify the variables predicting the likelihood of successful VBAC to create a predictive model.

Material/Methods

This multicenter, retrospective study included 1013 women at ≥28 gestational weeks with a vertex singleton gestation and 1 prior low-transverse cesarean from January 2017 to December 2017 in 11 public tertiary hospitals within 7 provinces of China. Two multivariable logistic regression models were developed: (1) at a first-trimester visit and (2) at the pre-labor admission to hospital. The models were evaluated with the area under the receiver operating characteristic curve (AUC) and internally validated using k-fold cross-validation. The pre-labor model was calibrated and a graphic nomogram and clinical impact curve were created.

Results

A total of 87.3% (884/1013) of women had successful VBAC, and 12.7% (129/1013) underwent unplanned cesarean delivery after a failed trial of labor. The AUC of the first-trimester model was 0.661 (95% confidence interval [CI]: 0.61–0.712), which increased to 0.758 (95% CI: 0.715–0.801) in the pre-labor model. The pre-labor model showed good internal validity, with AUC 0.743 (95% CI: 0.694–0.785), and was well calibrated.

Conclusions

VBAC provides women the chance to experience a vaginal delivery. Using a pre-labor model to predict successful VBAC is feasible and may help choose mode of birth and contribute to a reduction in cesarean delivery rate.

Successful vaginal birth after cesarean in the second delivery is not associated with the stage of labor of the primary unplanned cesarean delivery

BACKGROUND

Candidates for trial of labor after cesarean must be carefully screened to maximize success and minimize morbidity. Demographic and obstetric characteristics affecting success rates must be delineated.

OBJECTIVE

We examined whether the labor stage of the primary delivery in which a woman underwent an unplanned cesarean delivery would affect the likelihood that she could achieve a subsequent vaginal birth.

STUDY DESIGN

Electronic medical records-based study of 676 parturients. Trial of labor rates and outcomes were compared between women whose primary cesarean delivery was performed in the first vs. the second stage of labor.

SETTING

Hadassah Medical Center, Israel POPULATION: Women in their second pregnancies, with singleton fetuses, who underwent unplanned cesarean delivery in their first pregnancy and elected trial of labor in the second delivery. The main outcome measures were maternal and neonatal complications and vaginal birth rates in first vs. second stage of labor groups.

RESULTS

In our population, 76 % of women attempt trial of labor after cesarean. Rates of successful vaginal delivery did not differ significantly between those who underwent primary cesarean in the first vs. second stage of labor: 67.4 % vs. 70.2 %, p = 0.483, respectively. Among women whose primary UCD was in the second stage, only 18.2 % (35/192) required a UCD in the second stage in the subsequent delivery, while 58.9 % (113/192) underwent UCD in the first stage in both deliveries.

CONCLUSION

Labor stage of the primary unplanned cesarean delivery, should not dissuade women from a trial of labor after cesarean in their second delivery.

Prediction of vaginal birth after cesarean delivery in Southeast China: a retrospective cohort study

BACKGROUND

We aimed to develop and validate a nomogram for effective prediction of vaginal birth after cesarean (VBAC) and guide future clinical application.

METHODS

We retrospectively analyzed data from hospitalized pregnant women who underwent trial of labor after cesarean (TOLAC), at the Fujian Provincial Maternity and Children's Hospital, between October 2015 and October 2017. Briefly, we included singleton pregnant women, at a gestational age above 37 weeks who underwent a primary cesarean section, in the study. We then extracted their sociodemographic data and clinical characteristics, and randomly divided the samples into training and validation sets. We employed the least absolute shrinkage and selection operator (LASSO) regression to select variables and construct VBAC success rate in the training set. Thereafter, we validated the nomogram using the concordance index (C-index), decision curve analysis (DCA), and calibration curves. Finally, we adopted the Grobman's model to perform comparisons with published VBAC prediction models.

RESULTS

Among the 708 pregnant women included according to inclusion criteria, 586 (82.77%) patients were successfully for VBAC. Multivariate logistic regression models revealed that maternal height (OR, 1.11; 95% CI, 1.04 to 1.19), maternal BMI at delivery (OR, 0.89; 95% CI, 0.79 to 1.00), fundal height (OR, 0.71; 95% CI, 0.58 to 0.88), cervix Bishop score (OR, 3.27; 95% CI, 2.49 to 4.45), maternal age at delivery (OR, 0.90; 95% CI, 0.82 to 0.98), gestational age (OR, 0.33; 95% CI, 0.17 to 0.62) and history of vaginal delivery (OR, 2.92; 95% CI, 1.42 to 6.48) were independently associated with successful VBAC. The constructed predictive model showed better discrimination than that from the Grobman's model in the validation series (c-index 0.906 VS 0.694, respectively). On the other hand, decision curve analysis revealed that the new model had better clinical net benefits than the Grobman's model.

CONCLUSIONS

VBAC will aid in reducing the rate of cesarean sections in China. In clinical practice, the TOLAC prediction model will help improve VBAC's success rate, owing to its contribution to reducing secondary cesarean section.