scholarly journals Machine learning approaches to predict gestational age in normal and complicated pregnancies via urinary metabolomics analysis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Takafumi Yamauchi ◽  
Daisuke Ochi ◽  
Naomi Matsukawa ◽  
Daisuke Saigusa ◽  
Mami Ishikuro ◽  
...  

AbstractThe elucidation of dynamic metabolomic changes during gestation is particularly important for the development of methods to evaluate pregnancy status or achieve earlier detection of pregnancy-related complications. Some studies have constructed models to evaluate pregnancy status and predict gestational age using omics data from blood biospecimens; however, less invasive methods are desired. Here we propose a model to predict gestational age, using urinary metabolite information. In our prospective cohort study, we collected 2741 urine samples from 187 healthy pregnant women, 23 patients with hypertensive disorders of pregnancy, and 14 patients with spontaneous preterm birth. Using gas chromatography-tandem mass spectrometry, we identified 184 urinary metabolites that showed dynamic systematic changes in healthy pregnant women according to gestational age. A model to predict gestational age during normal pregnancy progression was constructed; the correlation coefficient between actual and predicted weeks of gestation was 0.86. The predicted gestational ages of cases with hypertensive disorders of pregnancy exhibited significant progression, compared with actual gestational ages. This is the first study to predict gestational age in normal and complicated pregnancies by using urinary metabolite information. Minimally invasive urinary metabolomics might facilitate changes in the prediction of gestational age in various clinical settings.

2021 ◽  
Author(s):  
Takafumi Yamauchi ◽  
Daisuke Ochi ◽  
Naomi Matsukawa ◽  
Daisuke Saigusa ◽  
Mami Ishikuro ◽  
...  

Abstract The elucidation of dynamic metabolomic changes during gestation is particularly important for the development of methods to evaluate pregnancy status or achieve earlier detection of pregnancy-related complications. Some studies have constructed models to evaluate pregnancy status and predict gestational age using omics data from blood biospecimens; however, less invasive methods are desired. Here we propose a model to predict gestational age, using urinary metabolite information. In our prospective cohort study, we collected 2,741 urine samples from 187 healthy pregnant women, 23 patients with hypertensive disorders of pregnancy, and 14 patients with spontaneous preterm birth. Using gas chromatography-tandem mass spectrometry, we identified 184 urinary metabolites that showed dynamic systematic changes in healthy pregnant women according to gestational age. A model to predict gestational age during normal pregnancy progression was constructed; the correlation coefficient between actual and predicted weeks of gestation was 0.86. The predicted gestational ages of cases with hypertensive disorders of pregnancy exhibited significant progression, compared with actual gestational ages. This is the first study to predict gestational age in normal and complicated pregnancies by using urinary metabolite information. Minimally invasive urinary metabolomics might facilitate changes in the prediction of gestational age in various clinical settings.


2021 ◽  
Vol 15 (10) ◽  
pp. 3420-3422
Author(s):  
Kalsoom Essa Bhattani ◽  
Shumaila Khawaja Khail ◽  
Kashif Ali Samin ◽  
Zubaida Khanum Wazir ◽  
Mobashara Ghulam Muhammad ◽  
...  

Background and Aim: Globally, hypertension disorder is the most common disorder in pregnancy. It complicates 6–10% of pregnancies with a major contribution to the worldwide maternal mortality rate. The aim of the current study was to evaluate the pregnancy outcomes in women with Hypertension disorders. Materials and Methods: This cross-sectional study was carried out on women with hypertension disorders enrolled in the department of Gynecology, Mardan Women Hospital, Sheikh Maltoon Town, Mardan and Family Health Centre, Peshawar from March 2021 to August 2021. Demographic details such as age, gestational age, parity, intrapartum, early postpartum complications such as perinatal outcomes and mode of delivery, and antepartum were recorded from each individual. Chi-square test was used for comparing the composite adverse outcomes such as preterm birth, postpartum hemorrhage, abrupt placenta, and mortality rate. SPSS version 20 was used for data analysis. Results: Of the total 2357 pregnant women, about 146 (6.2%) women had hypertensive disorders of pregnancy. The mean age of 146 pregnant women was 29.45±4.67 years with an age range from 17 to 43 years. About 37 (25.3%) women had no perinatal and maternal complications. Out of 109 pregnant women, the prevalence of eclampsia, preeclampsia, and pregnancy-induced hypertension were 8 (7.3%), 44 (40.4%), and 57 (52.3%) respectively. Based on gestational age, preterm (24-36 weeks) and term (>37 weeks) were 35 (32.1%) and 74 (67.9%) respectively. Other maternal complications were Abruption Placentae, Postpartum hemorrhage (PPH), Renal Failure., Pulmonary Edema, Disseminated intravascular coagulation (DIC), and Maternal Death. Conclusion: Our study found hypertension disorders as a significant medical disorder in pregnant women. However, neonatal outcomes and pregnancy outcomes were significantly smooth in more than 50% of pregnant women. Keywords: Hypertensive disorders of pregnancy, Pre-eclampsia, Eclampsia.


2021 ◽  
Author(s):  
Shiyu Zeng ◽  
Ling Yu ◽  
Yiling Ding ◽  
Mengyuan Yang

Abstract Background This study aims to explore whether plasma endocrine gland-derived vascular endothelial growth factor (EG-VEGF) in the first trimester can be used as a predictor of hypertensive disorders of pregnancy (HDP), and compare it with placental growth factor (PlGF) and soluble fms-like tyrosine kinase-1 (sFlt-1) to evaluate its prediction of HDP value. Methods This is a prospective cohort study that records the medical history of the pregnant women included in the study at 11–13 weeks’ gestation, and analyzes serum biochemical markers including EG-VEGF, PIGF, sFlt-1 and sFlt-1/PIGF. The predictive values of these tests were determined. We used the receiver operating characteristic (ROC) curve to find the optimal cut-off value for each biomarker and compare the operating characteristics (sensitivity, specificity). Logistic regression analysis was used to create a prediction model for HDP based on maternal characteristics and maternal biochemistry. Results Data were obtained from 205 pregnant women. 17 cases were diagnosed with HDP, the incidence rate was 8.2% (17/205). Women who developed HDP had a significantly higher body mass index (BMI) and mean arterial pressure (MAP). Serum EG-VEGF levels in the first trimester are significantly higher in pregnant women with HDP. The sensitivity, specificity, positive predictive value (PPV) and negative predictive value(NPV) of serum EG-VEGF levels more than 227.83 pg/ml for predicting HDP were 43%, 93%, 86% and 62%, respectively. We established a prediction model in the first trimester include maternal BMI, MAP, and EG-VEGF, with an AUC of 0.8861 (95%CI: 0.7905–0.9818), which is better than using EG-VEGF alone (AUC: 0.66). Conclusion This study demonstrated that serum EG-VEGF is a promising biomarker for predicting HDP in the first trimester. It has better predictive performance compared with the currently used biomarkers like PIGF and sFlt-1. Combining maternal clinical characteristics and biochemical tests at 11–13 weeks can effectively identify women at high risk of HDP.


Hypertension ◽  
2021 ◽  
Vol 78 (Suppl_1) ◽  
Author(s):  
Takao Kato ◽  
Eri Muta ◽  
Moriaki Inoko

Background: Cardiovascular functions and hemodynamics dramatically change during pregnancy such as cardiac output, expanded blood volume, reduced systematic vascular resistance, and heart chamber enlargement. Hypertensive disorders of pregnancy (HDP) may affect the cardiac load during pregnancy; however, the data about plasma concentration of cardiac troponin in pregnant women with HDP is very limited. Methods: We prospectively collected data of 751 pregnant women between 2012 and 2013 in Japanese general hospital. We analyzed laboratory data and echocardiographic findings after delivery. The elevated cTnI was defined as >0.015 ng/mL because the normal population have serum cTnI of less than 0.015 ng/mL in this assay. Results: The HDP were observed in 32 patients; the elevated cTnI was observed 40 patients. The age of patients with HDP (33.7 ±4.3 years) was not different from that of those without HDP (33.3 ± 5.0 years). The brain natriuretic peptides levels were not different between those with and without HDP. The proportion of elevated cTnI was higher in those with HDP (21.8%) than those without (3.6%, P<0.0001). After adjusting for confounders, the risk of elevated cTnI in those with HDP relative to those without HDP remained significant (odds ratio 4.52, 95% confidence interval 1.45-14.5). There were no women with reduced left ventricular ejection fraction. Conclusions: HDP was associated with elevated cTni, suggesting myocardial microinjury might occur more frequently in those with HDP.


2021 ◽  
Vol 8 ◽  
Author(s):  
Wendy N. Phoswa

Purpose of the Review: The main objective of this study is to investigate mechanisms associated with gestational diabetes mellitus (GDM) and hypertensive disorders of pregnancy (HDP) in HIV infected pregnant women by looking how placental hormones such as (progesterone and prolactin) and basic haemostatic parameters are regulated in HIV infected pregnancies.Recent Findings: HIV/AIDS are a major global obstetric health burden that lead to increased rate of morbidity and mortality. HIV/AIDS has been associated with the pathophysiology of GDM and HDP. Increased risk of GDM due to highly active antiretroviral therapy (HAART) usage has been reported in HIV infected pregnancies, which causes insulin resistance in both pregnant and non-pregnant individuals. HAART is a medication used for lowering maternal antepartum viral load and pre-exposure and post-exposure prophylaxis of the infant. In pregnant women, HAART induces diabetogenic effect by causing dysregulation of placental hormones such as (progesterone and prolactin) and predispose HIV infected women to GDM. In addition to HIV/AIDS and GDM, Studies have indicated that HIV infection causes haemostatic abnormalities such as hematological disorder, deregulated haematopoiesis process and the coagulation process which results in HDP.Summary: This study will help on improving therapeutic management and understanding of the pathophysiology of GDM and HDP in the absence as well as in the presence of HIV infection by reviewing studies reporting on these mechanism.


Hypertension ◽  
2020 ◽  
Vol 76 (5) ◽  
pp. 1506-1513 ◽  
Author(s):  
Michael C. Honigberg ◽  
Hilde Kristin Refvik Riise ◽  
Anne Kjersti Daltveit ◽  
Grethe S. Tell ◽  
Gerhard Sulo ◽  
...  

Hypertensive disorders of pregnancy (HDP) have been associated with heart failure (HF). It is unknown whether concurrent pregnancy complications (small-for-gestational-age or preterm delivery) or recurrent HDP modify HDP-associated HF risk. In this cohort study, we included Norwegian women with a first birth between 1980 and 2004. Follow-up occurred through 2009. Cox models examined gestational hypertension and preeclampsia in the first pregnancy as predictors of a composite of HF-related hospitalization or HF-related death, with assessment of effect modification by concurrent small-for-gestational-age or preterm delivery. Additional models were stratified by final parity (1 versus ≥2 births) and tested associations with recurrent HDP. Among 508 422 women, 565 experienced incident HF over a median 11.8 years of follow-up. After multivariable adjustment, gestational hypertension in the first birth was not significantly associated with HF (hazard ratio, 1.41 [95% CI, 0.84–2.35], P =0.19), whereas preeclampsia was associated with a hazard ratio of 2.00 (95% CI, 1.50–2.68, P <0.001). Among women with HDP, risks were not modified by concurrent small-for-gestational-age or preterm delivery ( P interaction =0.42). Largest hazards of HF were observed in women whose only lifetime birth was complicated by preeclampsia and women with recurrent preeclampsia. HF risks were similar after excluding women with coronary artery disease. In summary, women with preeclampsia, especially those with one lifetime birth and those with recurrent preeclampsia, experienced increased HF risk compared to women without HDP. Further research is needed to clarify causal mechanisms.


2020 ◽  
Vol 37 (08) ◽  
pp. 837-844 ◽  
Author(s):  
John R. Barton ◽  
George R. Saade ◽  
Baha M. Sibai

Hypertensive disorders are the most common medical complications of pregnancy and a major cause of maternal and perinatal morbidity and death. The detection of elevated blood pressure during pregnancy is one of the cardinal aspects of optimal antenatal care. With the outbreak of novel coronavirus disease 2019 (COVID-19) and the risk for person-to-person spread of the virus, there is a desire to minimize unnecessary visits to health care facilities. Women should be classified as low risk or high risk for hypertensive disorders of pregnancy and adjustments can be accordingly made in the frequency of maternal and fetal surveillance. During this pandemic, all pregnant women should be encouraged to obtain a sphygmomanometer. Patients monitored for hypertension as an outpatient should receive written instructions on the important signs and symptoms of disease progression and provided contact information to report the development of any concern for change in status. As the clinical management of gestational hypertension and preeclampsia is the same, assessment of urinary protein is unnecessary in the management once a diagnosis of a hypertensive disorder of pregnancy is made. Pregnant women with suspected hypertensive disorders of pregnancy and signs and symptoms associated with the severe end of the disease spectrum (e.g., headaches, visual symptoms, epigastric pain, and pulmonary edema) should have an evaluation including complete blood count, serum creatinine level, and liver transaminases (aspartate aminotransferase and alanine aminotransferase). Further, if there is any evidence of disease progression or if acute severe hypertension develops, prompt hospitalization is suggested. Current guidelines from the American College of Obstetricians and Gynecologists (ACOG) and The Society for Maternal-Fetal Medicine (SMFM) for management of preeclampsia with severe features suggest delivery after 34 0/7 weeks of gestation. With the outbreak of COVID-19, however, adjustments to this algorithm should be considered including delivery by 30 0/7 weeks of gestation in the setting of preeclampsia with severe features. Key Points


2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Amanual Getnet Mersha ◽  
Tadesse Melaku Abegaz ◽  
Mohammed Assen Seid

Abstract Background Hypertensive disorders of pregnancy complicate around 6% of pregnancies and accounts for 19% of maternal death in Ethiopia. The current review aimed to assess maternal and perinatal outcomes of pregnancies complicated by hypertension in Ethiopia. Methods A systematic review and meta-analysis was done on the outcome of hypertensive disorder among pregnant women in Ethiopia. Literature search was made in five databases and Statistical analyses were carried out by using Stata 14 software. The pooled prevalence of maternal death, HELLP syndrome, perinatal death, and low birth weight was calculated using a random-effects model. Egger’s test and funnel plot were used to evaluate publication bias. The Cochran Q test and I2 test statistics were used to test the heterogeneity of studies. Result Thirteen studies included in the review, with an overall sample size of 5894 women diagnosed to have hypertensive disorder of pregnancy. The pooled prevalence of maternal death was estimated to be 4% (95% CI: 2, 6%). The pooled prevalence of HELLP syndrome was 13% (95% CI: 10, 16%). Other complications such as pulmonary edema, kidney injury, hepatic injury, placental abruption, and aspiration pneumonia were also reported. Perinatal death was observed in one-fourth of women with HDP 25% (95% CI: 18, 32%). The pooled prevalence of low birth weight neonate in a woman with HDP is 37% (95% CI, 27, 48%). Conclusions In Ethiopia, the prevalence of perinatal and maternal mortality among pregnant women with one of the hypertensive disorders were found to be higher than rates reported from high income as well as most of the low and middle income countries. For instance, one in four of pregnancies complicated by hypertensive disorder end up in perinatal death in Ethiopia. HELLP syndrome, placental abruption, pulmonary edema, renal damage, prematurity, perinatal asphyxia, and low birth weight were also commonly reported. To improve the health outcomes of hypertensive disorders of pregnancy, it is recommended to improve utilization of maternal health service; early detection and early referral of pregnant women with hypertensive disorder; advocating policies and strategies that improves the quality of health care that a pregnant woman and her newborn receive.


2019 ◽  
Vol 37 (01) ◽  
pp. 008-013 ◽  
Author(s):  
Lydia L. Shook ◽  
Mark A. Clapp ◽  
Penelope S. Roberts ◽  
Sarah N. Bernstein ◽  
Ilona T. Goldfarb

Abstract Objective To test the hypothesis that high fetal fraction (FF) on first trimester cell-free deoxyribonucleic acid (cfDNA) aneuploidy screening is associated with adverse perinatal outcomes. Study Design This is a single-institution retrospective cohort study of women who underwent cfDNA screening at <14 weeks' gestation and delivered a singleton infant between July 2016 and June 2018. Women with abnormal results were excluded. Women with high FF (≥95th percentile) were compared with women with normal FF (5th–95th percentiles). Outcomes investigated were preterm birth, small for gestational age, and hypertensive disorders of pregnancy. Results A total of 2,033 women met inclusion criteria. The mean FF was 10.0%, and FF >16.5% was considered high (n = 102). Women with high FF had a greater chance of delivering a small for gestational age infant <fifth percentile, with an adjusted odds ratio of 2.4 (95% confidence interval: 1.1–4.8, p = 0.039). There was no significant association between high FF and either preterm birth or hypertensive disorders of pregnancy. Conclusion Women with a high FF in the first trimester are at increased risk of delivering a small for gestational age infant <fifth percentile. Further investigation into the clinical implications of a high FF is warranted.


Sign in / Sign up

Export Citation Format

Share Document