Deep learning prediction of renal anomalies for prenatal ultrasound diagnosis.

Deep learning algorithms have demonstrated remarkable potential in clinical diagnostics, particularly in the field of medical imaging. In this study, we investigated the application of deep learning models in early detection of fetal kidney anomalies. To provide an enhanced interpretation of those models' predictions, we proposed an adapted two-class representation and developed a multi-class model interpretation approach for problems with more than two labels and variable hierarchical grouping of labels. Additionally, we employed the explainable AI (XAI) visualization tools Grad-CAM and HiResCAM, to gain insights into model predictions and identify reasons for misclassifications. The study dataset consisted of 969 ultrasound images from unique patients; 646 control images and 323 cases of kidney anomalies, including 259 cases of unilateral urinary tract dilation and 64 cases of unilateral multicystic dysplastic kidney. The best performing model achieved a cross-validated area under the ROC curve of 91.28% ± 0.52%, with an overall accuracy of 84.03% ± 0.76%, sensitivity of 77.39% ± 1.99%, and specificity of 87.35% ± 1.28%. Our findings emphasize the potential of deep learning models in predicting kidney anomalies from limited prenatal ultrasound imagery. The proposed adaptations in model representation and interpretation represent a novel solution to multi-class prediction problems.

Persisting risk factors for preeclampsia among high-risk pregnancies already using prophylactic aspirin: a multi-country retrospective investigation.

BACKGROUND: Low-dose aspirin is recommended for pregnant individuals at high-risk of developing preeclampsia, but less is known about those that develop preeclampsia even while using prophylactic aspirin for preeclampsia prevention as the best course of treatment. OBJECTIVES: The objective of this study is to investigate the risk factors with the highest risk of developing preeclampsia among pregnant individuals already using aspirin from high-risk obstetrical centers across five countries. DESIGN: This is a secondary analysis of pregnant individuals from the Folic Acid Clinical Trial (FACT) who were using prophylactic aspirin before 16 weeks gestation. The FACT randomized control trial took place in 70 high risk obstetrical centers in Canada, United Kingdom, Australia, Jamaica, and Argentina between 2011-2015. Participants were included if they had any of the risk factors for preeclampsia: diabetes, chronic hypertension, twin pregnancy, history of preeclampsia, and/or obesity (Body Mass Index ≥35). The outcomes of interest were preeclampsia and preterm preeclampsia (<37 weeks). Log binomial regressions assessed factors significantly associated with any preeclampsia or preterm-preeclampsia (<37 weeks) using adjusted risk ratios (ARR) and 95% confidence intervals (CI). RESULTS: There were 2296 pregnant individuals with complete information on aspirin included in this study. At baseline, all patients were at high risk of preeclampsia and were eligible for aspirin prophylaxis, however, only 660 (28.7%) were taking aspirin. Among the 660 pregnant individuals taking aspirin, 132 (20%) developed preeclampsia and 60 (9.09%) preterm preeclampsia. Among pregnant individuals using aspirin, the risks of preeclampsia were highest for twins (ARR:2.62, 95% CI: 1.68-4.11), history of preeclampsia (ARR: 2.42, 95% CI: 1.74-3.38), and hypertension (ARR:1.92, 95% CI: 1.37-2.69). Similar trends were found for preterm-preeclampsia for twins (ARR:4.10, 95% CI:2.15-7.82), history of preeclampsia (ARR:2.75, 95% CI:1.62-4.67), and hypertension (ARR:2.18, 95% CI:1.28-3.72). No significant differences were found for obesity or diabetes. CONCLUSION: These findings suggest that individuals with twin pregnancies, a history of preeclampsia, or hypertension may not benefit from aspirin to the same extent as those with other complications such as obesity or diabetes. Careful clinical monitoring for these risks factors is recommended and future research into the effectiveness in these populations would increase our understanding of the current best practice of prophylactic aspirin use to prevent preeclampsia. TRIAL REGISTRATION: Current Controlled Trials ISRCTN23781770 and ClinicalTrials.gov NCT01355159.

Gestational Folate and Folic Acid Intake among Women in Canada at Higher Risk of Pre-Eclampsia.

BACKGROUND: Periconceptional folic acid (FA) supplementation is recommended to prevent neural tube defects; however, the extent to which recommendations are met through dietary sources and supplements is not clear. OBJECTIVES: Our objective was to evaluate the dietary and supplemental intakes of FA in a Canadian pregnancy cohort and to determine the proportions of pregnant women exceeding the Estimated Average Requirement (EAR) and Tolerable Upper Intake Level (UL). METHODS: FACT (the Folic Acid Clinical Trial) was an international multicenter, randomized, double-blinded, placebo-controlled, phase III trial investigating FA for the prevention of pre-eclampsia in high-risk pregnancies. Participants were enrolled from Canadian sites at 8-16 weeks of gestation. Dietary and supplemental FA intake data were collected through participant interviews and FFQs at the time of FACT enrollment. Categorical data were summarized as n (%) and continuous data as median (IQR). RESULTS: This study included 1198 participants. Participants consumed 485 µg dietary folate equivalents (DFE)/d (IQR: 370-630 µg DFE/d) from dietary sources of folate and FA. Through diet alone, 43.4% of participants consumed ≥520 µg DFE/d, the EAR for pregnant individuals. Of the 91.9% of participants who consumed daily FA supplements, 0.4% consumed <400 µg FA/d and 96.0% consumed ≥1000 µg/d, the UL for FA. Median (IQR) total folate intake was 2167 µg DFE/d (2032-2325 µg DFE/d); 95.3% of participants met or exceeded the EAR from all sources, but 1069 (89.2%) participants exceeded the UL. CONCLUSIONS: The majority of participants in this Canadian pregnancy cohort did not consume the recommended amount of folate from dietary sources. However, most prenatal supplements contained 1000 µg FA, resulting in the majority of women exceeding the UL. With no additional benefit associated with FA intakes beyond the UL for most women, modification of prenatal supplement formulations may be warranted to ensure women meet but do not exceed recommended FA intakes.FACT was registered at clinicaltrials.gov as NCT01355159 and at isrctn.com as ISRCTN23781770.

The determinants of maternal homocysteine in pregnancy: findings from the Ottawa and Kingston Birth Cohort.

OBJECTIVE: Observational studies have linked elevated homocysteine to vascular conditions. Folate intake has been associated with lower homocysteine concentration, although randomised controlled trials of folic acid supplementation to decrease the incidence of vascular conditions have been inconclusive. We investigated determinants of maternal homocysteine during pregnancy, particularly in a folic acid-fortified population. DESIGN: Data were from the Ottawa and Kingston Birth Cohort of 8085 participants. We used multivariable regression analyses to identify factors associated with maternal homocysteine, adjusted for gestational age at bloodwork. Continuous factors were modelled using restricted cubic splines. A subgroup analysis examined the modifying effect of MTHFR 677C>T genotype on folate, in determining homocysteine concentration. SETTING: Participants were recruited in Ottawa and Kingston, Canada, from 2002 to 2009. PARTICIPANTS: Women were recruited when presenting for prenatal care in the early second trimester. RESULTS: In 7587 participants, factors significantly associated with higher homocysteine concentration were nulliparous, smoking and chronic hypertension, while factors significantly associated with lower homocysteine concentration were non-Caucasian race, history of a placenta-mediated complication and folic acid supplementation. Maternal age and BMI demonstrated U-shaped associations. Folic acid supplementation of >1 mg/d during pregnancy did not substantially increase folate concentration. In the subgroup analysis, MTHFR 677C>T modified the effect of folate status on homocysteine concentration. CONCLUSIONS: We identified determinants of maternal homocysteine relevant to the lowering of homocysteine in the post-folic acid fortification era, characterised by folate-replete populations. A focus on periconceptional folic acid supplementation and improving health status may form an effective approach to lower homocysteine.

Effect of folic acid supplementation in pregnancy on preeclampsia: the folic acid clinical trial study.

Preeclampsia (PE) is hypertension with proteinuria that develops during pregnancy and affects at least 5% of pregnancies. The Effect of Folic Acid Supplementation in Pregnancy on Preeclampsia: the Folic Acid Clinical Trial (FACT) aims to recruit 3,656 high risk women to evaluate a new prevention strategy for PE: supplementation of folic acid throughout pregnancy. Pregnant women with increased risk of developing PE presenting to a trial participating center between 8(0/7) and 16(6/7) weeks of gestation are randomized in a 1 : 1 ratio to folic acid 4.0 mg or placebo after written consent is obtained. Intent-to-treat population will be analyzed. The FACT study was funded by the Canadian Institutes of Health Research in 2009, and regulatory approval from Health Canada was obtained in 2010. A web-based randomization system and electronic data collection system provide the platform for participating centers to randomize their eligible participants and enter data in real time. To date we have twenty participating Canadian centers, of which eighteen are actively recruiting, and seven participating Australian centers, of which two are actively recruiting. Recruitment in Argentina, UK, Netherlands, Brazil, West Indies, and United States is expected to begin by the second or third quarter of 2013. This trial is registered with NCT01355159.

The Ottawa and Kingston (OaK) Birth Cohort: development and achievements.

OBJECTIVE: The Ottawa and Kingston (OaK) Birth Cohort collected data on maternal and infant genetic and epidemiologic variables in order to (1) explore the association between folate supplementation or thrombophilias and adverse, placenta-mediated pregnancy outcomes; (2) create a biobank of maternal and infant biological and genetic samples; and (3) stimulate future research using this cohort data. METHODS: A prospective cohort design was used to collect mother and infant data. Women were recruited at 12 to 20 weeks' gestation, during prenatal care visits at The Ottawa Hospital and Kingston General Hospital from October 2002 to April 2009. Data on maternal and infant demographics, maternal health, obstetrical history, and pregnancy outcomes were collected. Testing was done for biological/serological markers associated with adverse pregnancy outcomes. Maternal and cord blood samples were biobanked. RESULTS: A total of 8085 mothers were recruited to the OaK Birth Cohort. Analysis of the cohort data showed that taking multivitamin supplements containing folic acid was associated with a reduced risk of preeclampsia (aOR 0.37; 95% CI 0.18 to 0.75). The majority of participants agreed to have their genetic/biological samples biobanked (samples collected for n = 7241 mothers, n = 2175 infants) and to be re-contacted regarding future research opportunities. CONCLUSION: Birth cohorts are a useful tool in determining associations between risk factors and adverse maternal and fetal outcomes, and can serve as a repository of data for future research. Creating strong research partnerships helped enhance financial resources and increase participant recruitment potential. Epidemiological and biobanked data and samples from the OaK Birth Cohort are available for use by other investigators.

Comparison of carbetocin and oxytocin for the prevention of postpartum hemorrhage following vaginal delivery:a double-blind randomized trial.

OBJECTIVES: To compare the efficacy of a single 100 micro g intramuscular (IM) carbetocin injection, a long-acting oxytocin agonist, to a 2-hour 10 IU oxytocin intravenous (IV) infusion, in reducing the incidence and severity of postpartum hemorrhage (PPH) in women at risk for this condition. METHODS: A randomized, double-blind, placebo-controlled study was conducted at 2 hospital centres, including 160 women with at least 1 risk factor for PPH. Eighty-three women received 100 microg carbetocin IM and an IV placebo immediately after placental delivery, while 77 women received placebo IM and oxytocin IV infusion. Complete blood count was collected at entry and 24 hours postpartum. All outcome measures, including the need for additional uterotonic agents or uterine massage, blood loss, and drop in hemoglobin and hematocrit, were analyzed using chi-square, Fisher exact, and Student t tests. RESULTS: Population profile and risk factors for PPH were similar for each group. No significant difference was observed in the number of women requiring additional uterotonic medication (12 in each group). However, in the carbetocin group, 36 of the 83 women (43.4%) required at least 1 uterine massage compared to 48 of the 77 women (62.3%) in the oxytocin group (P <.02). Overall, uterotonic intervention was clinically indicated in 37 of the women (44.6%) receiving carbetocin compared to 49 of the women (63.6%) given an IV oxytocin infusion (P <.02). There were no differences in laboratory PPH indicators between the 2 groups.