Dataset Information

Prediction of Adverse Maternal Outcomes in Preeclampsia Using a Risk Prediction Model.

ABSTRACT:

Background

This study was conducted to evaluate how the preeclampsia integrated estimate of risk (fullPIERS) model performs in the prediction of adverse maternal outcomes when the predictor variables are all obtained within 24-h of admission for preeclampsia.

Methods

A prospective cohort study on 323 women who fulfilled definite inclusion and exclusion criteria was conducted. Subjects were monitored for clinical symptoms of preeclampsia, biochemical parameters, and adverse maternal and neonatal outcomes. A risk prediction score was calculated using the fullPIERS calculator. Statistical analysis of rates and ratios was carried out by assessing ? (2) test and odds ratio.

Results

18.3 % (n = 60) had adverse maternal outcome and 42.8 % (n = 138) had adverse fetal outcome, and 43 (13.35 %) had combined adverse maternal and perinatal outcome. Dyspnea, visual disturbances, epigastric pain, and [Formula: see text] appeared to be highly significant risk factors. In the biochemical variables studied, serum creatinine and serum uric acid were found to have a significant association. The association between adverse perinatal outcome and vaginal delivery was highly significant (OR 0.35, 95 % CI 0.19, 0.63), and the P value was 0.0005. The likelihood ratio associated with the highest risk group (predicted probability of the outcome ?30 %) showed excellent performance (i.e., 17.5) of fullPIERS model as a rule in test.

Conclusion

The fullPIERS model performed well in the prediction of adverse maternal outcomes in women with preeclampsia. It is easy to use. The model is based on the use of few important clinical and biochemical parameters and does not require extensive laboratory testing. Although it might be of limited use in a well-equipped tertiary care facility, this model can be utilized in the setting of district or sub-district level hospitals to identify patients who are at risk of complications due to preeclampsia. Timely referral to a higher center will help in reducing the morbidity and mortality associated with this condition.

SUBMITTER: Agrawal S

PROVIDER: S-EPMC5016414 | biostudies-literature | 2016 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of Adverse Maternal Outcomes in Preeclampsia Using a Risk Prediction Model.

Agrawal Shruti S Maitra Nandita N

Journal of obstetrics and gynaecology of India 20151111 Suppl 1

<h4>Background</h4>This study was conducted to evaluate how the preeclampsia integrated estimate of risk (fullPIERS) model performs in the prediction of adverse maternal outcomes when the predictor variables are all obtained within 24-h of admission for preeclampsia.<h4>Methods</h4>A prospective cohort study on 323 women who fulfilled definite inclusion and exclusion criteria was conducted. Subjects were monitored for clinical symptoms of preeclampsia, biochemical parameters, and adverse materna ...[more]

PMID: 27651587

Similar Datasets

Project description:ImportanceWomen with disabilities have a higher risk of preterm birth, gestational diabetes, preeclampsia, and cesarean delivery; however, their risk of other obstetric interventions, adverse maternal outcomes, and clinical indications for increased cesarean delivery is unclear.ObjectiveTo evaluate risk of a range of obstetric interventions and adverse maternal outcomes, including severe maternal morbidities (SMM) and mortality, among women with and without disabilities.Design, setting, and participantsThe Consortium on Safe Labor was a retrospective cohort that included comprehensive medical chart review for deliveries between January 2002 and January 2008. Data were collected from 12 clinical sites, which included 19 hospitals across the United States. This secondary analysis was conducted in February to July 2021.ExposuresUsing International Classification of Diseases, Ninth Revision, codes and a validated algorithm to define disability, participants were classified as having physical, intellectual, sensory, or any disability, and compared with women with no documented disability.Main outcomes and measuresThe relative risk (RR) of 23 obstetric interventions and adverse maternal outcomes, including SMM and mortality, was evaluated.ResultsOf the 223 385 women in the study, 9206 (4.1%) were Asian or Pacific Islander, 50 235 (22.5%) were Black, 39 039 (17.5%) were Hispanic, and 110 443 (49.4%) were White, with a mean (SD) age of 27.6 (6.2) years. There were 2074 (0.9%) women with disability and 221 311 (99.1%) without. Among women with disabilities, 1733 (83.5%) were physical, 91 (4.4%) were intellectual, and 250 (12.1%) were sensory. Compared with women with no disability, women with disabilities had higher risk of gestational diabetes, placenta previa, premature rupture of membranes, preterm premature rupture of membranes, and postpartum fever as well as maternal death (adjusted relative risk [aRR], 11.19; 95% CI, 2.40-52.19) and individual SMMs: severe preeclampsia/eclampsia (aRR, 2.15; 95% CI, 1.80-2.56), hemorrhage (aRR, 1.27; 95% CI, 1.09-1.49), and fever (aRR, 1.32; 95% CI, 1.03-1.67), with the highest risk observed for thromboembolism (aRR, 6.08; 95% CI, 4.03-9.16), cardiovascular events (aRR, 4.02; 95% CI, 2.87-5.63), and infection (aRR, 2.69; 95% CI, 1.97-3.67). Women with any disability also had higher risk of interventions, including oxytocin augmentation, operative vaginal delivery, and cesarean delivery (aRR, 1.33; 95% CI, 1.25-1.42), with the cesarean indication less likely to be medically indicated (aRR, 0.79; 95% CI, 0.70-0.89). Risk of adverse outcomes and interventions remained consistent across disability categories.Conclusions and relevanceIn this study, women with physical, intellectual, and sensory disability during pregnancy were at higher risk of adverse outcomes, including a broad range of SMM and maternal mortality.

Project description:BackgroundRacial and ethnic diversification of the physician and nurse workforce is recommended as a leverage point to address the impact of structural racism in maternal care, but empirical evidence supporting this recommendation is currently lacking.ObjectiveThis study aimed to assess the association between state-level registered nurse workforce racial and ethnic diversity and severe adverse maternal outcomes during childbirth.Study designThis population-based cross-sectional study analyzed 2017 US birth certificate data. Severe adverse maternal outcomes included eclampsia, blood transfusion, hysterectomy, or intensive care unit admission. Proportions of minoritized racial and ethnic registered nurses in each state were abstracted from the American Community Survey (5-year estimate, 2013-2017). This proportion was categorized into 3 terciles, with the first tercile corresponding to the lowest proportion and the third tercile corresponding to the highest proportion. Crude and adjusted odds ratios and 95% confidence intervals of severe adverse maternal outcomes associated with terciles of the state proportion of minoritized racial and ethnic nurses were estimated using logistic regression models.ResultsOf the 3,668,813 birth certificates studied, 29,174 recorded severe adverse maternal outcomes (79.5 per 10,000; 95% confidence interval, 78.6-80.4). The mean state proportion of minoritized racial and ethnic nurses was 22.1%, ranging from 3.3% in Maine to 68.2% in Hawaii. For White mothers, the incidence of severe adverse outcomes was 85.3 per 10,000 for those who gave births in states in the first tercile of the proportion of minoritized racial and ethnic nurses and 53.9 per 10,000 for those who gave birth in states in the third tercile (risk difference, -31.4 per 10,000; 95% confidence interval, -34.4 to -28.5). It corresponds to a 37% decreased risk of severe adverse maternal outcomes associated with giving birth in a state in the third tercile (crude odds ratio, 0.63; 95% confidence interval, 0.60-0.66). A decreased risk of severe adverse maternal outcomes was observed for Black mothers (crude odds ratio, 0.65; 95% confidence interval, 0.61-0.70), Hispanic mothers (crude odds ratio, 0.51; 95% confidence interval, 0.48-0.54), and Asian and Pacific Islander mothers (crude odds ratio, 0.65; 95% confidence interval, 0.58-0.72) but not for Native American mothers (crude odds ratio, 0.89; 95% confidence interval, 0.72-1.09) or mothers with >1 race (crude odds ratio, 1.44; 95% confidence interval, 0.72-1.09). After adjustment for patients and hospital characteristics, giving birth in states in the third tercile was associated with a reduced risk of severe adverse outcomes as follows: 32% for White mothers (adjusted odds ratio, 0.68; 95% confidence interval, 0.59-0.77), 20% for Black mothers (adjusted odds ratio, 0.80; 95% confidence interval, 0.65-0.99), 31% for Hispanic mothers (adjusted odds ratio, 0.69; 95% confidence interval, 0.58-0.82), and 50% for Asian and Pacific Islander mothers (adjusted odds ratio, 0.50; 95% confidence interval, 0.38-0.65). The associations of the proportion of minoritized racial and ethnic nurses with the risk of severe adverse maternal outcomes were not statistically significant for Native American mothers and more than 1 race mothers. Results were similar when blood transfusion was excluded from the outcome measure.ConclusionA diverse state registered nurse workforce was associated with a reduced risk of severe adverse maternal outcomes during childbirth.

Project description:Preeclampsia is one of the leading causes of maternal and fetal morbidity and mortality. Due to the lack of effective preventive measures, its prediction is essential to its prompt management. This study aimed to develop models using machine learning to predict late-onset preeclampsia using hospital electronic medical record data. The performance of the machine learning based models and models using conventional statistical methods were also compared. A total of 11,006 pregnant women who received antenatal care at Yonsei University Hospital were included. Maternal data were retrieved from electronic medical records during the early second trimester to 34 weeks. The prediction outcome was late-onset preeclampsia occurrence after 34 weeks' gestation. Pattern recognition and cluster analysis were used to select the parameters included in the prediction models. Logistic regression, decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, and stochastic gradient boosting method were used to construct the prediction models. C-statistics was used to assess the performance of each model. The overall preeclampsia development rate was 4.7% (474 patients). Systolic blood pressure, serum blood urea nitrogen and creatinine levels, platelet counts, serum potassium level, white blood cell count, serum calcium level, and urinary protein were the most influential variables included in the prediction models. C-statistics for the decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, stochastic gradient boosting method, and logistic regression models were 0.857, 0.776, 0.573, 0.894, 0.924, and 0.806, respectively. The stochastic gradient boosting model had the best prediction performance with an accuracy and false positive rate of 0.973 and 0.009, respectively. The combined use of maternal factors and common antenatal laboratory data of the early second trimester through early third trimester could effectively predict late-onset preeclampsia using machine learning algorithms. Future prospective studies are needed to verify the clinical applicability algorithms.

Project description:Background: Globally, 10–15% of maternal deaths are statistically attributable to preeclampsia. Compared with late-onset PE, the severity of early-onset PE remains more harmful with higher morbidity and mortality. Objective: To establish an early-onset preeclampsia prediction model by clinical characteristics, risk factors and routine laboratory indicators were investigated from pregnant women at 6 to 10 gestational weeks. Methods: The clinical characteristics, risk factors, and 38 routine laboratory indicators (6–10 weeks of gestation) including blood lipids, liver and kidney function, coagulation, blood count, and other indicators of 91 early-onset preeclampsia patients and 709 normal controls without early-onset preeclampsia from January 2010 to May 2021 in Peking University Third Hospital (PUTH) were retrospectively analyzed. A logistic regression, decision tree model, and support vector machine (SVM) model were applied for establishing prediction models, respectively. ROC curves were drawn; area under curve (AUCROC), sensitivity, and specificity were calculated and compared. Results: There were statistically significant differences in the rates of diabetes, antiphospholipid syndrome (APS), kidney disease, obstructive sleep apnea (OSAHS), primipara, history of preeclampsia, and assisted reproductive technology (ART) (p < 0.05). Among the 38 routine laboratory indicators, there were no significant differences in the levels of PLT/LYM, NEU/LYM, TT, D-Dimer, FDP, TBA, ALP, TP, ALB, GLB, UREA, Cr, P, Cystatin C, HDL-C, Apo-A1, and Lp(a) between the two groups (p > 0.05). The levels of the rest indicators were all statistically different between the two groups (p < 0.05). If only 12 risk factors of PE were analyzed with the logistic regression, decision tree model, and support vector machine (SVM), and the AUCROC were 0.78, 0.74, and 0.66, respectively, while 12 risk factors of PE and 38 routine laboratory indicators were analyzed with the logistic regression, decision tree model, and support vector machine (SVM), and the AUCROC were 0.86, 0.77, and 0.93, respectively. Conclusions: The efficacy of clinical risk factors alone in predicting early-onset preeclampsia is not high while the efficacy increased significantly when PE risk factors combined with routine laboratory indicators. The SVM model was better than logistic regression model and decision tree model in early prediction of early-onset preeclampsia incidence.

Dataset Information

Prediction of Adverse Maternal Outcomes in Preeclampsia Using a Risk Prediction Model.

Background

Methods

Results

Conclusion

Publications

Prediction of Adverse Maternal Outcomes in Preeclampsia Using a Risk Prediction Model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets