Search

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.

Objective: This study aims to evaluate the perinatal outcomes of triplet pregnancies reduced from triplets to twins with fetal reduction (FR), followed expectantly without FR, and reduced to triplets from higher-order multiple pregnancies (HOMP) with FR., Materials and Methods: Multifetal pregnancies followed at the university hospital in the last 8 years were evaluated retrospectively. The study group was composed of three groups. The first group was those who started as trichorionic-triamniotic (TCTA) triplets and were followed by triplets. The second group consisted of HOMPs reduced to TCTA triplets with FR. The third group consisted of pregnant women who started as TCTA triplets and were reduced to dichorionic-diamniotic (DCDA) twins with FR., Results: A total of 69 multifetal pregnancies were included in the study. No statistical difference was observed between miscarriage rates in all groups ( p  = 0.190). Birth rates below 32 weeks were similar between groups ( p  = 0.158). The birth rates below 34 weeks were statistically significantly lower in the group in which DCDA was reduced by TCTA compared to the other two groups ( p  = 0.001). The first and second fetus weights in the group reduced to DCDA twins from TCTA were higher than the group followed expectantly, they were similar to the triplets reduced from HOMP. Stillbirth rates were similar in all groups ( p  = 0.057)., Conclusion: In TCTA pregnancies, when the priority is three live-born babies, expectant management seems to be a reasonable choice, considering the low rate of miscarriage and high rate of survivor neonates in this group.

Objective: The aim was to compare neonatal outcomes according to cell phone specific absorption rate (SAR) levels and daily time spent on cell phones by pregnant women., Material and Methods: Women who gave birth at Konya City Hospital between September 2020 and February 2021 were included in this retrospective study. Gestational ages, birth weight, birth length, head circumference, sex, 5-minute APGAR scores, neonate postpartum resuscitation requirement, delivery type, the model of phone used by the pregnant women, and the average time spent on the phone during a day were recorded. To determine the relation between the SAR values of the phones used and delivering a small for gestational age (SGA) baby, receiver operating characteristic curve analysis was performed., Results: In total 1495 pregnant women were included. The rate of delivering a SGA fetus was significantly higher in women who used phones with higher SAR values (p=0.001). The cut-off value for the SAR level was 1.23 W/kg with 69.3% sensitivity and 73.0% specificity (area under the curve: 0.685; 95% confidence interval: 0.643-0.726). No correlation was found between time spent on the phone and SGA birth rate. Although both phone SAR values and time spent on the phone were higher in the symmetrical SGA group compared to the asymmetrical SGA group, the difference was not significant (p>0.05). Although the women who had preterm delivery had higher phone SAR values and had spent more time on the phone compared to those who had term deliveries, the difference was again not significant (p>0.05)., Conclusion: As the SAR values of cell phones used during pregnancy increased, there was a trend towards delivering a SGA baby., Competing Interests: Conflict of Interest: No conflict of interest is declared by the authors., (Copyright© 2024 The Author. Published by Galenos Publishing House on behalf of Turkish-German Gynecological Association.)