Objective: This study aimed to evaluate and compare maternal and fetal outcomes between pregnancies in women aged 40 and over and those in women under 40 years of age at a tertiary care hospital. Methods: A retrospective cohort study was conducted at Necmettin Erbakan University Medical Faculty Hospital, analyzing data from 345 women aged 40 and over and 366 women under 40 who delivered between January 2015 and December 2024. Maternal and perinatal outcomes—including mode of delivery, gestational age, birth weight, and complications such as gestational diabetes, preeclampsia, and postpartum hemorrhage—were compared between the two groups. Results: Women aged 40 and over had significantly higher rates of cesarean section (73% vs. 36.1%, p < 0.0001), preterm delivery (27.8% vs. 18%, p = 0.002), and gestational diabetes (14.8% vs. 7.7%, p = 0.002). Additionally, these women had a higher incidence of preeclampsia (13% vs. 5.7%, p = 0.001) and postpartum hemorrhage (18% vs. 10.5%, p = 0.003). Despite these increased risks, the 5 min APGAR score was significantly higher in the ≥40 age group (median 8 vs. 7, p < 0.0001). The incidence of chromosomal abnormalities was significantly higher in patients≥ 40 years, with 5 cases (1.4%) reported, compared to no cases (0%) in the <40 age group (p = 0.025). Conclusions: This study shows that pregnancies in women aged 40 and above carry higher maternal and fetal risks compared to younger women. Complications such as preterm labor, cesarean delivery, gestational diabetes, and preeclampsia occur more frequently in this group. However, with careful prenatal care, positive neonatal outcomes are often achievable, highlighting the need for age-specific management and early risk detection.

This study aimed to create a risk prediction model with artificial intelligence (AI) to identify patients at higher risk of postpartum hemorrhage using perinatal characteristics that may be associated with later postpartum hemorrhage (PPH) in twin pregnancies that underwent cesarean section. The study was planned as a retrospective cohort study at University Hospital. All twin cesarean deliveries were categorized into two groups: those with and without PPH. Using the perinatal characteristics of the cases, four different machine learning classifiers were created: Logistic regression (LR), support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP). LR, RF, and SVM models were created a second time by including class weights to manage the underlying imbalances in the data. A total of 615 twin pregnancies were included in the study. There were 150 twin pregnancies with PPH and 465 without PPH. Dichorionity, PAS, and placenta previa were significantly higher in the PPH-positive group (p = .045, p = .004, p = .001 respectively). In our model, LR with class weight was the best model with the highest negative predictive value. The AUC in our LR with class weight model was %75.12 with an accuracy of 70.73%, a PPV of 47.92%, and an NPV of 85.33% in our data. Although the application of machine learning to create predictive models using clinical risk factors and our model’s 70% accuracy rate are encouraging, it is not sufficient. Machine learning modeling needs further study and validation before being incorporated into clinical use.

Background and Objectives: This study aims to evaluate the predictive value of comprehensive data obtained in obstetric clinics for the detection of stillbirth and the predictive ability set of machine learning models for stillbirth. Material and Method: The study retrospectively included all stillbirths followed up at a hospital between January 2015 and March 2024 and randomly selected pregnancies that resulted in a live birth. The electronic record system accessed pregnant women’s maternal, fetal, and obstetric characteristics. Based on the perinatal characteristics of the cases, four distinct machine learning classifiers were developed: logistic regression (LR), Support Vector Machine (SVM), Random Forest (RF), and multilayer perceptron (MLP). Results: The study included a total of 951 patients, 499 of whom had live births and 452 of whom had stillbirths. The consanguinity rate, fetal anomalies, history of previous stillbirth, maternal thrombosis, oligohydramnios, and abruption of the placenta were significantly higher in the stillbirth group (p = 0.001). Previous stillbirth histories resulted in a higher rate of stillbirth (OR: 7.31, 95%CI: 2.76–19.31, p = 0.001). Previous thrombosis histories resulted in a higher rate of stillbirth (OR: 14.13, 95%CI: 5.08–39.31, p = 0.001). According to the accuracy estimates of the machine learning models, RF is the most successful model with 96.8% accuracy, 96.3% sensitivity, and 97.2% specificity. Conclusions: The RF machine learning approach employed to predict stillbirths had an accuracy rate of 96.8%. We believe that the elevated success rate of stillbirth prediction using maternal, neonatal, and obstetric risk factors will assist healthcare providers in reducing stillbirth rates through prenatal care interventions.

Objective This study aims to compare the perinatal outcomes of pregnant women with heart disease and a healthy pregnant control group, as well as the maternal and newborn outcomes of pregnant women with congenital heart disease and acquired heart disease. Material method Pregnant women with heart disease and healthy control pregnant women were included in this retrospective study. Sociodemographic data of all patients included in the study were obtained from electronic records. Perinatal outcomes of all patients were compared. Results A total of 258 pregnant women were included in the study. While 129 pregnant women were diagnosed with heart disease, 129 patients were low-risk pregnant women. Preeclampsia (p=0.004) and cesarean section (p=0.01) rates were higher in pregnant women with heart disease compared to healthy pregnant women. Compared with healthy pregnant women, pregnant women with heart disease had a lower birth weight (p=0.003), a higher fetal growth restriction (FGR) rate (p=0.036), lower birth percentiles (p=0.002), a lower 5-minute APGAR (p=0.0001), a higher neonatal intensive care unit (NICU) admission rate (p=0.001), and a longer NICU stay rate (p=0.001). The mean gestational age at birth of pregnant women with congenital heart disease was higher than that of those with acquired heart disease (p=0.017). Conclusion It was observed that all maternal heart diseases were associated with adverse perinatal outcomes compared to healthy pregnant women. In this series, perinatal adverse outcomes of pregnant women with congenital and acquired heart disease did not differ. Keywords: acquired heart disease, congenital heart disease, pregnancy

This study examined the impact of blood glucose‐regulated gestational diabetes (GDM) on fetal pulmonary artery Doppler parameters. This prospective case–control study was performed at a tertiary university hospital. The study cohort comprised GDM patients with controlled blood glucose levels and a healthy control group. Acceleration time/ejection time (At/Et) of the main pulmonary artery, right pulmonary artery, and left pulmonary artery Doppler parameters were assessed and contrasted between the two groups. The study comprised 90 patients, with 30 in the gestational diabetes mellitus group focused on blood sugar regulation and 60 in the healthy control group. No statistically significant difference was observed between the two groups regarding the common main pulmonary artery At/Et ( p = 0.465), right pulmonary artery At/Et ( p = 0.237), and left pulmonary artery At/Et ( p = 0.283). No statistically significant difference was noted between the two groups regarding APGAR scores and blood gas parameters of the newborns ( p < 0.05). No statistically significant difference was observed in fetal pulmonary artery Doppler parameters ( p < 0.05) when gestational diabetes mellitus cases were classified based on the utilization of diet and insulin for blood sugar regulation. The pulmonary artery Doppler parameters in fetuses of pregnant women with gestational diabetes mellitus and controlled blood sugar levels are comparable to those of healthy controls. Moreover, dietary habits and insulin administration for glycemic control did not alter pulmonary artery Doppler metrics. The findings suggest that well‐managed gestational diabetes mellitus, irrespective of the treatment modality, do not substantially influence the fetal pulmonary artery dynamics.

OBJECTIVE: This study aimed to investigate the predictive value of the Delta Neutrophil Index (DNI) in detecting placenta accreta spectrum (PAS) in patients with placenta previa (PP). STUDY DESIGN: A retrospective study was conducted on 735 patients diagnosed with PP. Demographic characteristics, laboratory results, and maternal and fetal outcomes were obtained from electronic medical records. DNI levels were assessed with other inflammatory markers, and logistic regression analysis was performed to identify predictors of the PAS. Receiver operating characteristic (ROC) analysis was used to determine the diagnostic accuracy of DNI in distinguishing PAS cases from non-PAS cases. RESULTS: Logistic regression analysis revealed that the number of previous cesarean sections and DNI levels were significant predictors of the development of PAS (p=0.07). Elevated DNI levels were independently associated with an increased risk of PAS (p<0.05). The optimal cut-off value of DNI for diagnosing PAS was determined as 0.07 with a sensitivity of 67.5% and a specificity of 56.26%. The area under the ROC curve (AUC) for DNI was calculated as 0.639, indicating moderate diagnostic accuracy. CONCLUSION: This study demonstrates that DNI is a potential predictor of PAS development in cases of PP. Integrating DNI assessment into routine prenatal care protocols in PP patients may facilitate early risk identification and inform clinical management strategies. Further research is needed to confirm these findings and explore the broader applicability of DNI in obstetric practice.