Dataset Information

Prediction of Adverse Outcomes in De Novo Hypertensive Disorders of Pregnancy: Development and Validation of Maternal and Neonatal Prognostic Models.

ABSTRACT: Effectively identifying high-risk patients with de novo hypertensive disorder of pregnancy (HDP) is required to enable timely intervention and to reduce adverse maternal and perinatal outcomes. Electronic medical record of pregnant women with de novo HDP were extracted from a birth cohort in Beijing, China. The adverse outcomes included maternal and fetal morbidities, mortality, or any other adverse complications. A multitude of machine learning statistical methods were employed to develop two prediction models, one for maternal complications and the other for perinatal deteriorations. The maternal model using the random forest algorithm produced an AUC of 0.984 (95% CI (0.978, 0.991)). The strongest predictors variables selected by the model were platelet count, fetal head/abdominal circumference ratio, and gestational age at the diagnosis of de novo HDP; The perinatal model using the boosted tree algorithm yielded an AUC of 0.925 (95% CI (0.907, 0.945]). The strongest predictor variables chosen were gestational age at the diagnosis of de novo HDP, fetal femur length, and fetal head/abdominal circumference ratio. These prediction models can help identify de novo HDP patients at increased risk of complications who might need intense maternal or perinatal care.

SUBMITTER: Chen J

PROVIDER: S-EPMC9690621 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of Adverse Outcomes in De Novo Hypertensive Disorders of Pregnancy: Development and Validation of Maternal and Neonatal Prognostic Models.

Chen Junjun J Ji Yuelong Y Su Tao T Jin Ma M Yuan Zhichao Z Peng Yuanzhou Y Zhou Shuang S Bao Heling H Luo Shusheng S Wang Hui H Liu Jue J Han Na N Wang Hai-Jun HJ

Healthcare (Basel, Switzerland) 20221118 11

Effectively identifying high-risk patients with de novo hypertensive disorder of pregnancy (HDP) is required to enable timely intervention and to reduce adverse maternal and perinatal outcomes. Electronic medical record of pregnant women with de novo HDP were extracted from a birth cohort in Beijing, China. The adverse outcomes included maternal and fetal morbidities, mortality, or any other adverse complications. A multitude of machine learning statistical methods were employed to develop two p ...[more]

PMID: 36421631

Similar Datasets

Project description:IntroductionHypertensive disorders of pregnancy (HDP) are a leading cause of global perinatal (fetal and neonatal) and maternal morbidity and mortality. We sought to describe HDP and determine the magnitude and risk factors for adverse perinatal and maternal outcomes among women with HDP in southwestern Uganda.MethodsWe prospectively enrolled pregnant women admitted for delivery and diagnosed with HDP at a tertiary referral hospital in southwestern Uganda from January 2019 to November 2019, excluding women with pre-existing hypertension. The participants were observed and adverse perinatal and maternal outcomes were documented. We used multivariable logistic regression models to determine independent risk factors associated with adverse perinatal and maternal outcomes.ResultsA total of 103 pregnant women with a new-onset HDP were enrolled. Almost all women, 93.2% (n = 96) had either pre-eclampsia with severe features or eclampsia. The majority, 58% (n = 60) of the participants had an adverse perinatal outcome (36.9% admitted to the neonatal intensive care unit (ICU), 20.3% stillbirths, and 1.1% neonatal deaths). Fewer participants, 19.4% (n = 20) had an adverse maternal outcome HELLP syndrome (7.8%), ICU admission (3%), and postpartum hemorrhage (3%). In adjusted analyses, gestational age of < 34 weeks at delivery and birth weight <2.5kg were independent risk factors for adverse perinatal outcomes while referral from another health facility and eclampsia were independent risk factors for adverse maternal outcomes.ConclusionAmong women with HDP at our institution, majority had preeclampsia with severe symptoms or eclampsia and an unacceptably high rate of adverse perinatal and maternal outcomes; over a fifth of the mothers experiencing stillbirth. This calls for improved antenatal surveillance of women with HDP and in particular improved neonatal and maternal critical care expertise at delivering facilities. Earlier detection and referral, as well as improvement in initial management at lower level health units and on arrival at the referral site is imperative.

Project description:The relationship between first-trimester GWG ( T1GWG) and risk of hypertensive disorders of pregnancy (HDP) remained uncertain. This study aimed to investigate the association between T1GWG and risk of de novo HDP. Meanwhile, we explored the mediated effect and constructed an early GWG category to evaluate the predictive capacity for HDP. T1GWG was defined as the weight difference between 13 ± 1 gestational weeks and pre-conception. HDP group was defined as having diagnosis of de novo HDP, including gestational hypertension or de novo pre-eclampsia (PE) during the current pregnancy. Early GWG category was constructed according to the risk of HDP within each pre-pregnancy body mass index (BMI) group. Cox regression model was utilized to check the association between the T1GWG and HDP. Serial mediation model was adopted to evaluate the potential mediators including mean arterial pressure (MAP) at 13th and 20th week. The logistic regression model with bootstrap was performed to assess the predictive capacity of Early GWG category and MAP for the risk of HDP. A total of 17,901 pregnant women (mean age, 29.0 years) were recruited from 2013 to 2017 at the Tongzhou Maternal and Child Health Hospital in Beijing, China. Compared to women in Class 1 of early GWG category, women in the Class 2, 3, 4 have increased risks of HDP by 1.42, 4.27, and 4.62 times, respectively (hazard ratio [HR] = 2.42, 95% CI: 2.11-2.77; HR = 5.27, 95% CI: 4.05-6.86; HR = 5.62, 95% CI: 4.05-7.79). The MAP measured at 13th and 20th week totally mediated 33.1 and 26.7% of association between T1GWG GWG and HDP in total participants and overweight/obesity pregnancies, respectively. The area under receiver operator characteristic curve for predictive model utilizing early GWG category and MAP measured at 13th and 20th week for the risk of HDP is 0.760 (95% CI: 0.739-0.777). The T1GWG was associated with de novo HDP, which was partially mediated by MAP measured at 13th and 20th week. Early GWG category showed a better predictive capacity for the risk of HDP compared to the National Academy of Medicine criteria for T1GWG.

Dataset Information

Prediction of Adverse Outcomes in De Novo Hypertensive Disorders of Pregnancy: Development and Validation of Maternal and Neonatal Prognostic Models.

Publications

Prediction of Adverse Outcomes in De Novo Hypertensive Disorders of Pregnancy: Development and Validation of Maternal and Neonatal Prognostic Models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets