RESUMO
Diabetes mellitus during pregnancy and gestational diabetes are major concerns worldwide. These conditions may lead to the development of severe diabetic retinopathy during pregnancy or worsen pre-existing cases. Gestational diabetes also increases the risk of diabetes for both the mother and the fetus in the future. Understanding the prevalence, evaluating risk factors contributing to pathogenesis, and identifying treatment challenges related to diabetic retinopathy in expectant mothers are all of utmost importance. Pregnancy-related physiological changes, including those in metabolism, blood flow, immunity, and hormones, can contribute to the development or worsening of diabetic retinopathy. If left untreated, this condition may eventually result in irreversible vision loss. Treatment options such as laser therapy, intravitreal anti-vascular endothelial growth factor drugs, and intravitreal steroids pose challenges in managing these patients without endangering the developing baby and mother. This narrative review describes the management of diabetic retinopathy during pregnancy, highlights its risk factors, pathophysiology, and diagnostic methods, and offers recommendations based on findings from previous literature.
RESUMO
(1) Background: Prenatal care providers face a continuous challenge in screening for intrauterine growth restriction (IUGR) and preeclampsia (PE). In this study, we aimed to assess and compare the predictive accuracy of four machine learning algorithms in predicting the occurrence of PE, IUGR, and their associations in a group of singleton pregnancies; (2) Methods: This observational prospective study included 210 singleton pregnancies that underwent first trimester screenings at our institution. We computed the predictive performance of four machine learning-based methods, namely decision tree (DT), naïve Bayes (NB), support vector machine (SVM), and random forest (RF), by incorporating clinical and paraclinical data; (3) Results: The RF algorithm showed superior performance for the prediction of PE (accuracy: 96.3%), IUGR (accuracy: 95.9%), and its subtypes (early onset IUGR, accuracy: 96.2%, and late-onset IUGR, accuracy: 95.2%), as well as their association (accuracy: 95.1%). Both SVM and NB similarly predicted IUGR (accuracy: 95.3%), while SVM outperformed NB (accuracy: 95.8 vs. 94.7%) in predicting PE; (4) Conclusions: The integration of machine learning-based algorithms in the first-trimester screening of PE and IUGR could improve the overall detection rate of these disorders, but this hypothesis should be confirmed in larger cohorts of pregnant patients from various geographical areas.
RESUMO
BACKGROUND: Cardiovascular diseases are a leading cause of mortality and morbidity worldwide. Pregnancy imposes unique physiological changes on a woman's cardiovascular system. MATERIALS AND METHODS: A cohort of 68 participants, comprising 30 pregnant women with cardiovascular risk and 38 without cardiovascular risk, was recruited for this study. These participants were prospectively followed during their pregnancies from 2020 to 2022 at the Obstetrics and Gynecology Department of the "Pius Brînzeu" Emergency County Clinical Hospital in Timisoara, Romania. All women included in this study underwent cesarean section deliveries at the same medical facility. Data regarding the gestational weeks at delivery, birth weight, and Apgar scores assessed by neonatologists were collected for each participant. Statistical analyses were performed to compare the neonatal effects between the two groups. RESULTS: The results of this study revealed significant differences between the groups in terms of Apgar scores (p = 0.0055), gestational weeks (p = 0.0471), and baby birth weight (p = 0.0392). CONCLUSION: The findings underscore the importance of considering maternal cardiovascular health as a potential determinant of neonatal outcomes. Further research is needed to elucidate the underlying mechanisms and develop strategies for optimizing neonatal outcomes in high-risk pregnancies.
