Predicting vaginal birth after previous cesarean: Using machine-learning models and a population-based cohort in Sweden.
Ontology highlight
ABSTRACT: Introduction
Predicting a woman's probability of vaginal birth after cesarean could facilitate the antenatal decision-making process. Having a previous vaginal birth strongly predicts vaginal birth after cesarean. Delivery outcome in women with only a cesarean delivery is more unpredictable. Therefore, to better predict vaginal birth in women with only one prior cesarean delivery and no vaginal deliveries would greatly benefit clinical practice and fill a key evidence gap in research. Our aim was to predict vaginal birth in women with one prior cesarean and no vaginal deliveries using machine-learning methods, and compare with a US prediction model and its further developed model for a Swedish setting.Material and methods
A population-based cohort study with a cohort of 3116 women with only one prior birth, a cesarean, and a subsequent trial of labor during 2008-2014 in the Stockholm-Gotland region, Sweden. Three machine-learning methods (conditional inference tree, conditional random forest and lasso binary regression) were used to predict vaginal birth after cesarean among women with one previous birth. Performance of the new models was compared with two existing models developed by Grobman et al (USA) and Fagerberg et al (Sweden). Our main outcome measures were area under the receiver-operating curve (AUROC), overall accuracy, sensitivity and specificity of prediction of vaginal birth after previous cesarean delivery.Results
The AUROC ranged from 0.61 to 0.69 for all models, sensitivity was above 91% and specificity below 22%. The majority of women with an unplanned repeat cesarean had a predicted probability of vaginal birth after cesarean >60%.Conclusions
Both classical regression models and machine-learning models had a high sensitivity in predicting vaginal birth after cesarean in women without a previous vaginal delivery. The majority of women with an unplanned repeat cesarean delivery were predicted to succeed with a vaginal birth (ie specificity was low). Additional covariates combined with machine-learning techniques did not outperform classical regression models in this study.
SUBMITTER: Lindblad Wollmann C
PROVIDER: S-EPMC8048592 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:An association between the vaginal microbiome and preterm birth has been reported. However, in practice, it is difficult to predict premature birth using the microbiome because the vaginal microbial community varies highly among samples depending on the individual, and the prediction rate is very low. The purpose of this study was to select markers that improve predictive power through machine learning among various vaginal microbiota and develop a prediction algorithm with better predictive power that combines clinical information. As a multicenter case-control study with 150 Korean pregnant women with 54 preterm delivery group and 96 full-term delivery group, cervicovaginal fluid was collected from pregnant women during mid-pregnancy. Their demographic profiles (age, BMI, education level, and PTB history), white blood cell count, and cervical length were recorded, and the microbiome profiles of the cervicovaginal fluid were analyzed. The subjects were randomly divided into a training (n = 101) and a test set (n = 49) in a two-to-one ratio. When training ML models using selected markers, five-fold cross-validation was performed on the training set. A univariate analysis was performed to select markers using seven statistical tests, including the Wilcoxon rank-sum test. Using the selected markers, including Lactobacillus spp., Gardnerella vaginalis, Ureaplasma parvum, Atopobium vaginae, Prevotella timonensis, and Peptoniphilus grossensis, machine learning models (logistic regression, random forest, extreme gradient boosting, support vector machine, and GUIDE) were used to build prediction models. The test area under the curve of the logistic regression model was 0.72 when it was trained with the 17 selected markers. When analyzed by combining white blood cell count and cervical length with the seven vaginal microbiome markers, the random forest model showed the highest test area under the curve of 0.84. The GUIDE, the single tree model, provided a more reasonable biological interpretation, using the 10 selected markers (A. vaginae, G. vaginalis, Lactobacillus crispatus, Lactobacillus fornicalis, Lactobacillus gasseri, Lactobacillus iners, Lactobacillus jensenii, Peptoniphilus grossensis, P. timonensis, and U. parvum), and the covariates produced a tree with a test area under the curve of 0.77. It was confirmed that the association with preterm birth increased when P. timonensis and U. parvum increased (AUC = 0.77), which could also be explained by the fact that as the number of Peptoniphilus lacrimalis increased, the association with preterm birth was high (AUC = 0.77). Our study demonstrates that several candidate bacteria could be used as potential predictors for preterm birth, and that the predictive rate can be increased through a machine learning model employing a combination of cervical length and white blood cell count information.
| S-EPMC9378785 | biostudies-literature
Project description:Postpartum hemorrhage is the leading cause of maternal morbidity. Clinical prediction of postpartum hemorrhage remains challenging, particularly in the case of a vaginal birth. We studied machine learning models to predict postpartum hemorrhage. Women who underwent vaginal birth at the Tokyo Women Medical University East Center between 1995 and 2020 were included. We used 11 clinical variables to predict a postpartum hemorrhage defined as a blood loss of > 1000 mL. We constructed five machine learning models and a deep learning model consisting of neural networks with two layers after applying the ensemble learning of five machine learning classifiers, namely, logistic regression, a support vector machine, random forest, boosting trees, and decision tree. For an evaluation of the performance, we applied the area under the curve of the receiver operating characteristic (AUC), the accuracy, false positive rate (FPR) and false negative rate (FNR). The importance of each variable was evaluated through a comparison of the feature importance calculated using a Boosted tree. A total of 9,894 patients who underwent vaginal birth were enrolled in the study, including 188 cases (1.9%) with blood loss of > 1000 mL. The best learning model predicted postpartum hemorrhage with an AUC of 0.708, an accuracy of 0.686, FPR of 0.312, and FNR of 0.398. The analysis of the importance of the variables showed that pregnant gestation of labor, the maternal weight upon admission of labor, and the maternal weight before pregnancy were considered to be weighted factors. Machine learning model can predict postpartum hemorrhage during vaginal delivery. Further research should be conducted to analyze appropriate variables and prepare big data, such as hundreds of thousands of cases.
| S-EPMC8604915 | biostudies-literature
Project description:BackgroundBirth weight is a significant determinant of the likelihood of survival of an infant. Babies born at low birth weight are 25 times more likely to die than at normal birth weight. Low birth weight (LBW) affects one out of every seven newborns, accounting for about 14.6 percent of the babies born worldwide. Moreover, the prevalence of LBW varies substantially by region, with 7.2 per cent in the developed regions and 13.7 per cent in Africa, respectively. Ethiopia has a large burden of LBW, around half of Africa. These newborns were more likely to die within the first month of birth or to have long-term implications. These are stunted growth, low IQ, overweight or obesity, developing heart disease, diabetes, and early death. Therefore, the ability to predict the LBW is the better preventive measure and indicator of infant health risks.MethodThis study implemented predictive LBW models based on the data obtained from the Ethiopia Demographic and Health Survey 2016. This study was employed to compare and identify the best-suited classifier for predictive classification among Logistic Regression, Decision Tree, Naive Bayes, K-Nearest Neighbor, Random Forest (RF), Support Vector Machine, Gradient Boosting, and Extreme Gradient Boosting.ResultsData preprocessing is conducted, including data cleaning. The Normal and LBW are the binary target category in this study. The study reveals that RF was the best classifier and predicts LBW with 91.60 percent accuracy, 91.60 percent Recall, 96.80 percent ROC-AUC, 91.60 percent F1 Score, 1.05 percent Hamming loss, and 81.86 percent Jaccard score.ConclusionThe RF predicted the occurrence of LBW more accurately and effectively than other classifiers in Ethiopia Demographic Health Survey. Gender of the child, marriage to birth interval, mother's occupation and mother's age were Ethiopia's top four critical predictors of low birth weight in Ethiopia.
| S-EPMC9443037 | biostudies-literature
Project description:BACKGROUND:Metabolic syndrome is a cluster of disorders that significantly influence the development and deterioration of numerous diseases. FibroScan is an ultrasound device that was recently shown to predict metabolic syndrome with moderate accuracy. However, previous research regarding prediction of metabolic syndrome in subjects examined with FibroScan has been mainly based on conventional statistical models. Alternatively, machine learning, whereby a computer algorithm learns from prior experience, has better predictive performance over conventional statistical modeling. OBJECTIVE:We aimed to evaluate the accuracy of different decision tree machine learning algorithms to predict the state of metabolic syndrome in self-paid health examination subjects who were examined with FibroScan. METHODS:Multivariate logistic regression was conducted for every known risk factor of metabolic syndrome. Principal components analysis was used to visualize the distribution of metabolic syndrome patients. We further applied various statistical machine learning techniques to visualize and investigate the pattern and relationship between metabolic syndrome and several risk variables. RESULTS:Obesity, serum glutamic-oxalocetic transaminase, serum glutamic pyruvic transaminase, controlled attenuation parameter score, and glycated hemoglobin emerged as significant risk factors in multivariate logistic regression. The area under the receiver operating characteristic curve values for classification and regression trees and for the random forest were 0.831 and 0.904, respectively. CONCLUSIONS:Machine learning technology facilitates the identification of metabolic syndrome in self-paid health examination subjects with high accuracy.
| S-EPMC7136841 | biostudies-literature
Project description:The COVID-19 pandemic has had a significant impact on public life and health worldwide, putting the world's healthcare systems at risk. The first step in stopping this outbreak is to detect the infection in its early stages, which will relieve the risk, control the outbreak's spread, and restore full functionality to the world's healthcare systems. Currently, PCR is the most prevalent diagnosis tool for COVID-19. However, chest X-ray images may play an essential role in detecting this disease, as they are successful for many other viral pneumonia diseases. Unfortunately, there are common features between COVID-19 and other viral pneumonia, and hence manual differentiation between them seems to be a critical problem and needs the aid of artificial intelligence. This research employs deep- and transfer-learning techniques to develop accurate, general, and robust models for detecting COVID-19. The developed models utilize either convolutional neural networks or transfer-learning models or hybridize them with powerful machine-learning techniques to exploit their full potential. For experimentation, we applied the proposed models to two data sets: the COVID-19 Radiography Database from Kaggle and a local data set from Asir Hospital, Abha, Saudi Arabia. The proposed models achieved promising results in detecting COVID-19 cases and discriminating them from normal and other viral pneumonia with excellent accuracy. The hybrid models extracted features from the flatten layer or the first hidden layer of the neural network and then fed these features into a classification algorithm. This approach enhanced the results further to full accuracy for binary COVID-19 classification and 97.8% for multiclass classification.
| S-EPMC8357494 | biostudies-literature
Project description:PURPOSE: To determine the maternal and fetal outcomes of successful external cephalic version (ECV) as well as factors predicting vaginal birth. METHODS: The ECV data over a period of three years at Universiti Kebangsaan Malaysia Medical Centre (UKMMC) between 1 September 2008 and 30 September 2010 was reviewed. Sixty-seven patients who had successful ECV were studied and reviewed for maternal, fetal, and labour outcomes. The control group comprised patients with cephalic singletons of matching parity who delivered following the index cases. RESULTS: The mean gestational age at ECV was 263 ± 6.52 days (37.5 weeks ± 6.52 days). Spontaneous labour and transient cardiotocographic (CTG) changes were the commonest early adverse effects following ECV. The reversion rate was 7.46%. The mean gestational age at delivery of the two groups was significantly different (P = 0.000) with 277.9 ± 8.91 days and 269.9 ± 9.68 days in the study group and control groups, respectively. The study group needed significantly more inductions of labour. They required more operative deliveries, had more blood loss at delivery, a higher incidence of meconium-stained liquor, and more cord around the neck. Previous flexed breeches had a threefold increase in caesarean section rate compared to previous extended breeches (44.1% versus 15.2%, P = 0.010). On the contrary, an amniotic fluid index (AFI) of 13 or more is significantly associated with a higher rate of vaginal birth (86.8% versus 48.3%, P = 0.001). CONCLUSIONS: Patients with successful ECV were at higher risk of carrying the pregnancy beyond 40 weeks and needing induction of labour, with a higher rate of caesarean section and higher rates of obstetrics complications. Extended breech and AFI 13 or more were significantly more likely to deliver vaginally postsuccessful ECV. This additional information may be useful to caution a patient with breech that ECV does not bring them to behave exactly like a normal cephalic, so that they have more realistic expectations. However, these predictive factors needed further confirmation and hopefully, in the future, they would be able to further enhance counselling prior to ECV.
| S-EPMC3919060 | biostudies-other
Project description:BACKGROUND:Rates of cesarean deliveries have been increasing, and contributes to the rising number of elective cesarean deliveries in subsequent pregnancies with associated maternal and neonatal risks. Multiple guidelines recommend that women be offered a trial of labor after a cesarean (TOLAC). The objective of the study is to systematically review the literature on adjunct clinical interventions that influence vaginal birth after cesarean (VBAC) rates. METHODS:We searched Ovid Medline, Ovid Embase, Wiley Cochrane Library, CINAHL via EBSCOhost; and Ovid PsycINFO. Additional studies were identified by searching for clinical trial records, conference proceedings and dissertations. Limits were applied for language (English and French) and year of publication (1985 to present). Two reviewers independently screened comparative studies (randomized or non-randomized controlled trials, and observational designs) according to a priori eligibility criteria: women with prior cesarean sections; any adjunct clinical intervention or exposure intended to increase the VBAC rate; any comparator; and, outcomes reporting changes in TOLAC or VBAC rates. One reviewer extracted data and a second reviewer verified for accuracy. Two reviewers independently conducted methodological quality assessments using the Mixed Methods Appraisal Tool (MMAT). RESULTS:Twenty-three studies of overall moderate to good methodological quality examined adjunct clinical interventions affecting TOLAC and/or VBAC rates: system-level interventions (three studies), provider-level interventions (three studies), guidelines or information for providers (seven studies), provider characteristics (four studies), and patient-level interventions (six studies). Provider-level interventions (opinion leader education, laborist, and obstetrician second opinion for cesarean sections) and provider characteristics (midwifery antenatal care, physicians on night float call schedules, and deliveries by family physicians) were associated with increased rates of VBAC. Few studies employing heterogeneous designs, sample sizes, interventions and comparators limited confidence in the effects. Studies of system-level and patient-level interventions, and guidelines/information for providers reported mixed findings. CONCLUSIONS:Limited evidence indicates some provider-level interventions and provider characteristics may increase rates of attempted and successful TOLACs and/or VBACs, whereas other adjunct clinical interventions such as system-level interventions, patient-level interventions, and guidelines/information for healthcare providers show mixed findings.
| S-EPMC6249876 | biostudies-other
Project description:BackgroundThe ability to accurately predict survival in older adults is crucial as it guides clinical decision making. The added value of using health care usage for predicting mortality remains unexplored. The aim of this study was to investigate if temporal patterns of healthcare expenditures, can improve the predictive performance for mortality, in spousal bereaved older adults, next to other widely used sociodemographic variables.MethodsThis is a population-based cohort study of 48,944 Danish citizens 65 years of age and older suffering bereavement within 2013-2016. Individuals were followed from date of spousal loss until death from all causes or 31st of December 2016, whichever came first. Healthcare expenditures were available on weekly basis for each person during the follow-up and used as predictors for mortality risk in Extreme Gradient Boosting models. The extent to which medical spending trajectories improved mortality predictions compared to models with sociodemographics, was assessed with respect to discrimination (AUC), overall prediction error (Brier score), calibration, and clinical benefit (decision curve analysis).ResultsThe AUC of age and sex for mortality the year after spousal loss was 70.8% [95% CI 68.8, 72.8]. The addition of sociodemographic variables led to an increase of AUC ranging from 0.9% to 3.1% but did not significantly reduce the overall prediction error. The AUC of the model combining the variables above plus medical spending usage was 80.8% [79.3, 82.4] also exhibiting smaller Brier score and better calibration. Overall, patterns of healthcare expenditures improved mortality predictions the most, also exhibiting the highest clinical benefit among the rest of the models.ConclusionTemporal patterns of medical spending have the potential to significantly improve our assessment on who is at high risk of dying after suffering spousal loss. The proposed methodology can assist in a more efficient risk profiling and prognosis of bereaved individuals.
| S-EPMC10406307 | biostudies-literature
Project description:ObjectiveWe aimed to determine the key predictors of perinatal deaths using machine learning models compared with the logistic regression model.DesignA secondary data analysis using the Kilimanjaro Christian Medical Centre (KCMC) Medical Birth Registry cohort from 2000 to 2015. We assessed the discriminative ability of models using the area under the receiver operating characteristics curve (AUC) and the net benefit using decision curve analysis.SettingThe KCMC is a zonal referral hospital located in Moshi Municipality, Kilimanjaro region, Northern Tanzania. The Medical Birth Registry is within the hospital grounds at the Reproductive and Child Health Centre.ParticipantsSingleton deliveries (n=42 319) with complete records from 2000 to 2015.Primary outcome measuresPerinatal death (composite of stillbirths and early neonatal deaths). These outcomes were only captured before mothers were discharged from the hospital.ResultsThe proportion of perinatal deaths was 3.7%. There were no statistically significant differences in the predictive performance of four machine learning models except for bagging, which had a significantly lower performance (AUC 0.76, 95% CI 0.74 to 0.79, p=0.006) compared with the logistic regression model (AUC 0.78, 95% CI 0.76 to 0.81). However, in the decision curve analysis, the machine learning models had a higher net benefit (ie, the correct classification of perinatal deaths considering a trade-off between false-negatives and false-positives)-over the logistic regression model across a range of threshold probability values.ConclusionsIn this cohort, there was no significant difference in the prediction of perinatal deaths between machine learning and logistic regression models, except for bagging. The machine learning models had a higher net benefit, as its predictive ability of perinatal death was considerably superior over the logistic regression model. The machine learning models, as demonstrated by our study, can be used to improve the prediction of perinatal deaths and triage for women at risk.
| S-EPMC7574940 | biostudies-literature
Project description:BackgroundIn the absence of effective measures to predict steroid responsiveness, patients with nonhereditary steroid-resistant nephrotic syndrome (SRNS) have a significantly increased risk of progression to end-stage renal disease. In view of the poor outcomes of SRNS, it is urgent to identify the steroid responsiveness of idiopathic nephrotic syndrome (INS) early.MethodsTo build a prediction model for SRNS, we collected 91 subjects; 57 of them had steroid-sensitive nephrotic syndrome, and the others had SRNS. For each subject, 87 clinical variables were measured. In general, only a small part of these variables is informative to SRNS. Thus, we proposed a new variable selection framework including a penalized regression approach (named MLR+TLP) to select variables having a linear effect on the SRNS and a nonparametric screening method (MAC) to select variables having a nonlinear marginal (joint) effect on the SRNS. Thereafter, considering the correlation between selected clinical variables, we used a stepwise method to build our final model for predicting SRNS. In addition, a statistical testing procedure is proposed to test the overfitting of the proposed model.ResultsTwenty-six clinical variables were selected to be informative to SRNS, and an SVM model was built to predict SRNS with a leave-one-out cross-validation (LOO-CV) accuracy of 95.2% (overfitting p value<0.005). To make the model more useful, we incorporate prior medical information into the model and consider the correlation between selected variables. Then, a reduced SVM model including only eight clinical variables (erythrocyte sedimentation rate, urine occult blood, percentage of neutrophils, immunoglobulin A, cholesterol, vinculin autoantibody, aspartate aminotransferase, and prolonged prothrombin time) was built to have a LOO-CV accuracy of 92.8% (overfitting p value<0.005). The validation cohort showed that the reduced model obtained an accuracy of 94.0% (overfitting p value<0.005), with a sensitivity of 90.0% and a specificity of 96.7%. Notably, vinculin autoantibody is the only podocyte autoantibody included in this model. It is linearly related to steroid responsiveness. Finally, our model is freely available as a user-friendly web tool at https://datalinkx.shinyapps.io/srns/.ConclusionThe SRNS prediction model constructed in this study comprehensively and objectively evaluates the internal conditions and disease status of INS patients and will provide scientific guidance for selecting treatment methods for children with nonhereditary SRNS.
| S-EPMC9911108 | biostudies-literature