Dataset Information

Predicting adverse pregnancy outcomes of pregnant mothers with syphilis based on a logistic regression model: a retrospective study.

ABSTRACT:

Objective

Maternal syphilis could cause serious consequences. The aim of this study was to identify risk factors for maternal syphilis in order to predict an individual's risk of developing adverse pregnancy outcomes (APOs).

Methods

A retrospective study was conducted on 768 pregnant women with syphilis. A questionnaire was completed and data analyzed. The data was divided into a training set and a testing set. Using logistic regression to establish predictive models in the training set, and its predictive performance was evaluated in the testing set. The probability of APOs occurrence is presented through a nomogram.

Results

Compared with the APOs group, pregnant women in the non-APOs group participated in a longer treatment course. Course, time of the first antenatal care, gestation week at syphilis diagnosis, and gestation age at delivery in weeks were independent predictors of APOs, and they were used to establish the nomogram.

Conclusions

Our study investigated the impact of various characteristics of syphilis pregnant women on pregnancy outcomes and established a prediction model of APOs in Suzhou. The incidence of APOs can be reduced by controlling for these risk factors.

SUBMITTER: Zhang YW

PROVIDER: S-EPMC10538632 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting adverse pregnancy outcomes of pregnant mothers with syphilis based on a logistic regression model: a retrospective study.

Zhang Yu-Wei YW Liu Man-Yu MY Yu Xing-Hao XH He Xiu-Yu XY Song Wei W Liu Xiao X Ma Ya-Na YN

Frontiers in public health 20230914

<h4>Objective</h4>Maternal syphilis could cause serious consequences. The aim of this study was to identify risk factors for maternal syphilis in order to predict an individual's risk of developing adverse pregnancy outcomes (APOs).<h4>Methods</h4>A retrospective study was conducted on 768 pregnant women with syphilis. A questionnaire was completed and data analyzed. The data was divided into a training set and a testing set. Using logistic regression to establish predictive models in the traini ...[more]

PMID: 37780444

Similar Datasets

Project description:ObjectiveTo evaluate the association between marijuana use and a composite adverse pregnancy outcome using biological sampling.DesignRetrospective cohort study.SettingSingle tertiary center.PopulationYoung women (13-22 years old) with singleton, non-anomalous pregnancies delivered from September 2011 to May 2017.MethodsExposure was defined as marijuana detected on universal urine toxicology testing or by self-report. Multivariable logistic regression modelling was used to estimate the effect of any marijuana use on the primary composite outcome. The effect of marijuana exposure was also estimated for self-reported use, toxicology-detected use, and multiple use detected by toxicology.Main outcome measureThe primary composite outcome included spontaneous preterm birth, hypertensive disorders of pregnancy, stillbirth, or small for gestational age.ResultsOf 1206 pregnant young women, 17.5% (n = 211) used marijuana. Among the women who used marijuana, 8.5% (n = 18) were identified by self-report alone, 63% (n = 133) by urine toxicology alone, and 28.4% (n = 60) by both. Urine toxicology testing results were available for 1092 (90.5%) births. The composite outcome occurred more frequently in pregnancies exposed to marijuana (46 versus 34%, P < 0.001). This remained significant after adjusting for race/ethnicity and tobacco in the multivariable model (adjusted OR 1.50, 95% CI 1.09-2.05). When marijuana exposure was defined by self-report only, the association with adverse pregnancy outcome became non-significant (adjusted OR 1.01, 95% CI 0.62-1.64).ConclusionIn a population of young women with nearly universal biological sampling, marijuana exposure was associated with adverse pregnancy outcomes. The heterogeneity of findings in existing studies evaluating the impact of marijuana on mothers and neonates may result from the incomplete ascertainment of exposure.Tweetable abstractMarijuana use, as detected by universal urine testing, was associated with a composite adverse pregnancy outcome among young mothers.

Project description:IntroductionPreeclampsia, one of the leading causes of maternal and fetal morbidity and mortality, demands accurate predictive models for the lack of effective treatment. Predictive models based on machine learning algorithms demonstrate promising potential, while there is a controversial discussion about whether machine learning methods should be recommended preferably, compared to traditional statistical models.MethodsWe employed both logistic regression and six machine learning methods as binary predictive models for a dataset containing 733 women diagnosed with preeclampsia. Participants were grouped by four different pregnancy outcomes. After the imputation of missing values, statistical description and comparison were conducted preliminarily to explore the characteristics of documented 73 variables. Sequentially, correlation analysis and feature selection were performed as preprocessing steps to filter contributing variables for developing models. The models were evaluated by multiple criteria.ResultsWe first figured out that the influential variables screened by preprocessing steps did not overlap with those determined by statistical differences. Secondly, the most accurate imputation method is K-Nearest Neighbor, and the imputation process did not affect the performance of the developed models much. Finally, the performance of models was investigated. The random forest classifier, multi-layer perceptron, and support vector machine demonstrated better discriminative power for prediction evaluated by the area under the receiver operating characteristic curve, while the decision tree classifier, random forest, and logistic regression yielded better calibration ability verified, as by the calibration curve.ConclusionMachine learning algorithms can accomplish prediction modeling and demonstrate superior discrimination, while Logistic Regression can be calibrated well. Statistical analysis and machine learning are two scientific domains sharing similar themes. The predictive abilities of such developed models vary according to the characteristics of datasets, which still need larger sample sizes and more influential predictors to accumulate evidence.

Project description:BackgroundPregnant people are particularly vulnerable to SARS-CoV-2 infection and to ensuing severe illness. Predicting adverse maternal and perinatal outcomes could aid clinicians in deciding on hospital admission and early initiation of treatment in affected individuals, streamlining the triaging processes.MethodsAn international repository of 1501 SARS-CoV-2-positive cases in pregnancy was created, consisting of demographic variables, patient comorbidities, laboratory markers, respiratory parameters, and COVID-19-related symptoms. Data were filtered, preprocessed, and feature selection methods were used to obtain the optimal feature subset for training a variety of machine learning models to predict maternal or fetal/neonatal death or critical illness.ResultsThe Random Forest model demonstrated the best performance among the trained models, correctly identifying 83.3% of the high-risk patients and 92.5% of the low-risk patients, with an overall accuracy of 89.0%, an AUC of 0.90 (95% Confidence Interval 0.83 to 0.95), and a recall, precision, and F1 score of 0.85, 0.94, and 0.89, respectively. This was achieved using a feature subset of 25 features containing patient characteristics, symptoms, clinical signs, and laboratory markers. These included maternal BMI, gravidity, parity, existence of pre-existing conditions, nicotine exposure, anti-hypertensive medication administration, fetal malformations, antenatal corticosteroid administration, presence of dyspnea, sore throat, fever, fatigue, duration of symptom phase, existence of COVID-19-related pneumonia, need for maternal oxygen administration, disease-related inpatient treatment, and lab markers including sFLT-1/PlGF ratio, platelet count, and LDH.ConclusionsWe present the first COVID-19 prognostication pipeline specifically for pregnant patients while utilizing a large SARS-CoV-2 in pregnancy data repository. Our model accurately identifies those at risk of severe illness or clinical deterioration, presenting a promising tool for advancing personalized medicine in pregnant patients with COVID-19.

Project description:BackgroundThe World Health Organization initiative to eliminate mother-to-child transmission of syphilis aims for ? 90% of pregnant women to be tested for syphilis and ? 90% to receive treatment by 2015. We calculated global and regional estimates of syphilis in pregnancy and associated adverse outcomes for 2008, as well as antenatal care (ANC) coverage for women with syphilis.Methods and findingsEstimates were based upon a health service delivery model. National syphilis seropositivity data from 97 of 193 countries and ANC coverage from 147 countries were obtained from World Health Organization databases. Proportions of adverse outcomes and effectiveness of screening and treatment were from published literature. Regional estimates of ANC syphilis testing and treatment were examined through sensitivity analysis. In 2008, approximately 1.36 million (range: 1.16 to 1.56 million) pregnant women globally were estimated to have probable active syphilis; of these, 80% had attended ANC. Globally, 520,905 (best case: 425,847; worst case: 615,963) adverse outcomes were estimated to be caused by maternal syphilis, including approximately 212,327 (174,938; 249,716) stillbirths (>28 wk) or early fetal deaths (22 to 28 wk), 91,764 (76,141; 107,397) neonatal deaths, 65,267 (56,929; 73,605) preterm or low birth weight infants, and 151,547 (117,848; 185,245) infected newborns. Approximately 66% of adverse outcomes occurred in ANC attendees who were not tested or were not treated for syphilis. In 2008, based on the middle case scenario, clinical services likely averted 26% of all adverse outcomes. Limitations include missing syphilis seropositivity data for many countries in Europe, the Mediterranean, and North America, and use of estimates for the proportion of syphilis that was "probable active," and for testing and treatment coverage.ConclusionsSyphilis continues to affect large numbers of pregnant women, causing substantial perinatal morbidity and mortality that could be prevented by early testing and treatment. In this analysis, most adverse outcomes occurred among women who attended ANC but were not tested or treated for syphilis, highlighting the need to improve the quality of ANC as well as ANC coverage. In addition, improved ANC data on syphilis testing coverage, positivity, and treatment are needed. Please see later in the article for the Editors' Summary.

Dataset Information

Predicting adverse pregnancy outcomes of pregnant mothers with syphilis based on a logistic regression model: a retrospective study.

Objective

Methods

Results

Conclusions

Publications

Predicting adverse pregnancy outcomes of pregnant mothers with syphilis based on a logistic regression model: a retrospective study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets