scholarly journals Machine learning from fetal flow waveforms to predict adverse perinatal outcomes: a study protocol

2018 ◽  
Vol 2 ◽  
pp. 8
Author(s):  
Zahra Hoodbhoy ◽  
Babar Hasan ◽  
Fyezah Jehan ◽  
Bart Bijnens ◽  
Devyani Chowdhury

Background: In Pakistan, stillbirth rates and early neonatal mortality rates are amongst the highest in the world. The aim of this study is to provide proof of concept for using a computational model of fetal haemodynamics, combined with machine learning. This model will be based on Doppler patterns of the fetal cardiovascular, cerebral and placental flows with the goal to identify those fetuses at increased risk of adverse perinatal outcomes such as stillbirth, perinatal mortality and other neonatal morbidities. Methods: This will be prospective one group cohort study which will be conducted in Ibrahim Hyderi, a peri-urban settlement in south east of Karachi. The eligibility criteria include pregnant women between 22-34 weeks who reside in the study area. Once enrolled, in addition to the performing fetal ultrasound to obtain Dopplers, data on socio-demographic, maternal anthropometry, haemoglobin and cardiotocography will be obtained on the pregnant women. Discussion: The machine learning approach for predicting adverse perinatal outcomes obtained from the current study will be validated in a larger population at the next stage. The data will allow for early interventions to improve perinatal outcomes.

Viruses ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 853
Author(s):  
Sara Cruz Melguizo ◽  
María Luisa de la Cruz Conty ◽  
Paola Carmona Payán ◽  
Alejandra Abascal-Saiz ◽  
Pilar Pintando Recarte ◽  
...  

Pregnant women who are infected with SARS-CoV-2 are at an increased risk of adverse perinatal outcomes. With this study, we aimed to better understand the relationship between maternal infection and perinatal outcomes, especially preterm births, and the underlying medical and interventionist factors. This was a prospective observational study carried out in 78 centers (Spanish Obstetric Emergency Group) with a cohort of 1347 SARS-CoV-2 PCR-positive pregnant women registered consecutively between 26 February and 5 November 2020, and a concurrent sample of PCR-negative mothers. The patients’ information was collected from their medical records, and the association of SARS-CoV-2 and perinatal outcomes was evaluated by univariable and multivariate analyses. The data from 1347 SARS-CoV-2-positive pregnancies were compared with those from 1607 SARS-CoV-2-negative pregnancies. Differences were observed between both groups in premature rupture of membranes (15.5% vs. 11.1%, p < 0.001); venous thrombotic events (1.5% vs. 0.2%, p < 0.001); and severe pre-eclampsia incidence (40.6 vs. 15.6%, p = 0.001), which could have been overestimated in the infected cohort due to the shared analytical signs between this hypertensive disorder and COVID-19. In addition, more preterm deliveries were observed in infected patients (11.1% vs. 5.8%, p < 0.001) mainly due to an increase in iatrogenic preterm births. The prematurity in SARS-CoV-2-affected pregnancies results from a predisposition to end the pregnancy because of maternal disease (pneumonia and pre-eclampsia, with or without COVID-19 symptoms).


2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
L F Christensen ◽  
S Heuckendorff ◽  
K Fonager ◽  
C Overgaard

Abstract Background Mounting evidence suggests that mental health problems in pregnant women may negatively affect the intra- and extrauterine health and development of the child. This is especially of concern as the prevalence of mental health problems in pregnant women is high and believed to be increasing. We set out to quantify the effect of maternal mental health status on the risk of adverse perinatal outcomes for the infant. Methods We undertook a nationwide register-based cohort study including children born alive in Denmark between 2000 and 2016. The exposed cohort was children born to mothers with mental health problems in the two years prior to childbirth that had been cared for in primary care settings only (Group 1, minor problems, n = 71 759) or had required psychiatric intervention (Group 2, moderate-severe problems, n = 41 099). All non-exposed children served as comparison group (n = 908 268). We calculated risk ratios (RRs) with 95% confidence intervals (CI) for each perinatal outcome of interest. Results Infants in Group 1 as well as Group 2 were at higher risk of neonatal death than infants born to unaffected mothers, although for Group 2 the trend was non-significant (Group 1: adjusted RR (aRR) 1.34, 95% CI 1.17-1.52; Group 2: aRR 1.11, 95% CI 0.94-1.32). Both exposure groups were furthermore at significantly increased risk of 5-minute Apgar scores &lt;7 (Group 1: aRR 1.27, 95% CI 1.17-1.37; Group 2: aRR 1.52, 95% CI 0.94-1.32) and &lt;4 (Group 1: aRR 1.26, 95% CI 1.10-1.44; Group 2: aRR 1.28, 95% CI 1.08-1.52) and of hospital admission in the neonatal period (Group 1: aRR 1.22, 95% CI 1.19-1.24; Group 2: 1.29, 95% CI 1.26-1.32), paralleled by a significantly higher risk of preterm birth and several neonatal morbidities. Conclusions Infants born to mothers with moderate-severe as well as minor mental health problems were at increased risk of multiple adverse perinatal outcomes, thus calling for effective preventive strategies to improve outcomes in both groups.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shigeki Koshida ◽  
Shinsuke Tokoro ◽  
Daisuke Katsura ◽  
Shunichiro Tsuji ◽  
Takashi Murakami ◽  
...  

AbstractMaternal perception of decreased fetal movement is associated with adverse perinatal outcomes. Although there have been several studies on interventions related to the fetal movements count, most focused on adverse perinatal outcomes, and little is known about the impact of the fetal movement count on maternal behavior after the perception of decreased fetal movement. We investigated the impact of the daily fetal movement count on maternal behavior after the perception of decreased fetal movement and on the stillbirth rate in this prospective population-based study. Pregnant women in Shiga prefecture of Japan were asked to count the time of 10 fetal movements from 34 weeks of gestation. We analyzed 101 stillbirths after the intervention compared to 121 stillbirths before the intervention. In multivariable analysis, maternal delayed visit to a health care provider after the perception of decreased fetal movement significantly reduced after the intervention (aOR 0.31, 95% CI 0.11–0.83). Our regional stillbirth rates in the pre-intervention and post-intervention periods were 3.06 and 2.70 per 1000 births, respectively. Informing pregnant women about the fetal movement count was associated with a reduction in delayed maternal reaction after the perception of decreased fetal movement, which might reduce stillbirths.


2020 ◽  
Vol 48 (9) ◽  
pp. 900-911 ◽  
Author(s):  
Ernesto Antonio Figueiro-Filho ◽  
Mark Yudin ◽  
Dan Farine

AbstractThe objective of this review was to identify the most significant studies reporting on COVID-19 during pregnancy and to provide an overview of SARS-CoV-2 infection in pregnant women and perinatal outcomes. Eligibility criteria included all reports, reviews; case series with more than 100 individuals and that reported at least three of the following: maternal characteristics, maternal COVID-19 clinical presentation, pregnancy outcomes, maternal outcomes and/or neonatal/perinatal outcomes. We included eight studies that met the inclusion criteria, representing 10,966 cases distributed in 15 countries around the world until July 20, 2020. The results of our review demonstrate that the maternal characteristics, clinical symptoms, maternal and neonatal outcomes almost 11,000 cases of COVID-19 and pregnancy described in 15 different countries are not worse or different from the general population. We suggest that pregnant women are not more affected by the respiratory complications of COVID-19, when compared to the outcomes described in the general population. We also suggest that the important gestational shift Th1-Th2 immune response, known as a potential contributor to the severity in cases of viral infections during pregnancy, are counter-regulated by the enhanced-pregnancy-induced ACE2-Ang-(1–7) axis. Moreover, the relatively small number of reported cases during pregnancy does not allow us to affirm that COVID-19 is more aggressive during pregnancy. Conversely, we also suggest, that down-regulation of ACE2 receptors induced by SARS-CoV-2 cell entry might have been detrimental in subjects with pre-existing ACE2 deficiency associated with pregnancy. This association might explain the worse perinatal outcomes described in the literature.


Author(s):  
Elizabeth Norton ◽  
Frances Shofer ◽  
Hannah Schwartz ◽  
Lorraine Dugoff

Objective To determine if women who newly met criteria for stage 1 hypertension in early pregnancy were at increased risk for adverse perinatal outcomes compared with normotensive women. Study Design We conducted a retrospective cohort study of women who had prenatal care at a single institution and subsequently delivered a live infant between December 2017 and August 2019. Women with a singleton gestation who had at least two prenatal visits prior to 20 weeks of gestation were included. We excluded women with known chronic hypertension or other major maternal illness. Two groups were identified: (1) women newly diagnosed with stage 1 hypertension before 20 weeks of gestation (blood pressure [BP] 130–139/80–89 on at least two occasions) and (2) women with no known history of hypertension and normal BP (<130/80 mm Hg) before 20 weeks of gestation. The primary outcome was any hypertensive disorder of pregnancy; secondary outcomes were indicated preterm birth and small for gestational age. Generalized linear models were used to compare risk of adverse outcomes between the groups. Results Of the 1,630 women included in the analysis, 1,443 women were normotensive prior to 20 weeks of gestation and 187 women (11.5%) identified with stage 1 hypertension. Women with stage 1 hypertension were at significantly increased risk for any hypertensive disorder of pregnancy (adjusted risk ratio [aRR]: 1.86, 95% confidence interval [CI]: 1.12–3.04) and indicated preterm birth (aRR: 1.83, 95% CI: 1.12–3.02). Black women and obese women with stage 1 hypertension were at increased for hypertensive disorder of pregnancy compared with white women and nonobese women, respectively (aRR: 1.32, 95% CI: 1.11–1.57; aRR: 1.69, 95% CI: 1.39–2.06). Conclusion These results provide insight about the prevalence of stage 1 hypertension and inform future guidelines for diagnosis and management of hypertension in pregnancy. Future research is needed to assess potential interventions to mitigate risk. Key Points


2021 ◽  
Vol 29 (3) ◽  
pp. 255-265
Author(s):  
İbrahim Ömeroğlu ◽  
Didem Dereli Akdeniz ◽  
Hakan Gölbaşı ◽  
Ceren Gölbaşı ◽  
Atalay Ekin

Objective Our study aimed to evaluate the perinatal and neonatal outcomes of hypertensive pregnant women with or without proteinuria. We compared the predictivity of spot urinary protein to creatinine (P/C) ratio and 24-hour protein excretions on outcomes. Methods We retrospectively enrolled 230 pregnant women with a new diagnosis of hypertension between 20 and 37 weeks of gestation. We divided the patients into two groups according to the protein level determined by 24-hour urine collection and P/C ratio. The presence and level of proteinuria, its relationship with the P/C ratio, and the relationship between these findings and perinatal outcomes were evaluated. Results Gestational age at delivery weeks and latency period (duration between diagnosis of hypertension and delivery) were significantly earlier in pregnant women with ≥300 mg/24-h and P/C ratio ≥0.3. Adverse neonatal outcomes were significant in patients with proteinuria ≥300 mg/24-hour and P/C ratio ≥0.3. Urinary protein levels in 24-hour urine were significantly higher in pregnant women with P/C ratio ≥0.3 and a significantly positive correlation was found between 24-h proteinuria and P/C (r=0.382, p<0.001). Conclusion Our study demonstrated that a protein loss of ≥300 mg in 24-h and a P/C ratio in spot urine ≥0.3 in hypertensive pregnant women is associated with adverse perinatal outcomes. Furthermore, we have identified that proteinuria ≥300 mg/day and spot urine P/C ratio ≥0.3 in hypertensive pregnant women make them prone to early delivery risk.


2018 ◽  
Vol 39 (01) ◽  
pp. 029-035 ◽  
Author(s):  
Michael Schatz ◽  
Jennifer Namazy

AbstractPregnancy may be complicated by new onset or preexisting asthma. This article reviews diagnosis and management of asthma in the pregnant patient. Special attention is paid to the challenges in diagnosis and management of this condition during pregnancy. Asthma is one of the most common potentially serious medical problems to complicate pregnancy, and asthma may adversely affect both maternal quality of life and perinatal outcomes. Asthma may adversely affect both maternal quality of life and, perinatal outcomes. Pregnant asthmatics have been shown to be at an increased risk of adverse perinatal outcomes. Optimal management of asthma during pregnancy is thus important for both mother and baby. This article provides an update on the available literature regarding the safety of commonly used asthma medications during pregnancy.


Nutrients ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 2179
Author(s):  
Dubravka Havaš Auguštin ◽  
Jelena Šarac ◽  
Mario Lovrić ◽  
Jelena Živković ◽  
Olga Malev ◽  
...  

Maternal nutrition and lifestyle in pregnancy are important modifiable factors for both maternal and offspring’s health. Although the Mediterranean diet has beneficial effects on health, recent studies have shown low adherence in Europe. This study aimed to assess the Mediterranean diet adherence in 266 pregnant women from Dalmatia, Croatia and to investigate their lifestyle habits and regional differences. Adherence to the Mediterranean diet was assessed through two Mediterranean diet scores. Differences in maternal characteristics (diet, education, income, parity, smoking, pre-pregnancy body mass index (BMI), physical activity, contraception) with regards to location and dietary habits were analyzed using the non-parametric Mann–Whitney U test. The machine learning approach was used to reveal other potential non-linear relationships. The results showed that adherence to the Mediterranean diet was low to moderate among the pregnant women in this study, with no significant mainland–island differences. The highest adherence was observed among wealthier women with generally healthier lifestyle choices. The most significant mainland–island differences were observed for lifestyle and socioeconomic factors (income, education, physical activity). The machine learning approach confirmed the findings of the conventional statistical method. We can conclude that adverse socioeconomic and lifestyle conditions were more pronounced in the island population, which, together with the observed non-Mediterranean dietary pattern, calls for more effective intervention strategies.


Medicina ◽  
2019 ◽  
Vol 55 (9) ◽  
pp. 550
Author(s):  
Carolina Scala ◽  
Umberto Leone Roberti Maggiore ◽  
Fabio Barra ◽  
Matteo Tantari ◽  
Simone Ferrero

Background and objective: Previous studies did not draw a definitive conclusion about the influence of the role of deep endometriosis (DE) and ovarian endometrioma (OE) as risk factor for developing adverse perinatal outcomes in patients affected by endometriosis. This study aimed to investigate if adverse fetal and maternal outcomes, and in particular the incidence of small for gestational age (SGA) infants, are different in pregnant women with OE versus pregnant women with DE without OE. Material and methods: This study was based on a retrospective analysis of a database collected prospectively. The population included in the study was divided into three groups: patients with OE, patients with DE without concomitant OE, and patients without endometriosis (controls). The controls were matched on the basis of age and parity. Demographic data at baseline and pregnancy outcomes were recorded. Results: There was no statistically significant difference in first trimester levels of PAPP-A, first and mid-pregnancy trimester mean Uterine Artery Doppler pulsatile index, estimated fetal weight centile, and SGA fetuses’ prevalence for patients with OE, and those with DE without OE in comparison to health women; moreover, there was no statistically significant difference with regard to SGA birth prevalence, prevalence of preeclampsia, and five-minute Apgar score between these three groups. Conclusions: The specific presence of OE or DE in pregnant women does not seem to be associated with an increased risk of delivering an SGA infant. These data seem to suggest that patients with endometriosis should be treated in pregnancy as the general population, thus not needing a closer monitoring.


Sign in / Sign up

Export Citation Format

Share Document