Objective: Shoulder dystocia (ShD) is a rare but serious obstetric emergency associated with significant neonatal morbidity. This study aimed to evaluate the predictive performance of machine learning (ML) models based on fetal biometric ratios and clinical characteristics for the identification of ShD in pregnancies without clinical suspicion of macrosomia. Methods: We conducted a retrospective case-control study including 284 women (84 ShD cases and 200 controls) who underwent spontaneous vaginal delivery between 37 and 42 weeks of gestation. All participants had an estimated fetal weight (EFW) below the 90th percentile according to Hadlock reference curves. Univariate and multivariate logistic regression analyses were performed on maternal and neonatal parameters, and statistically significant variables (p < 0.05) were used to construct adjusted odds ratio (aOR) models. Supervised ML models—Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGB)—were trained and tested to assess predictive accuracy. Performance metrics included AUC-ROC, sensitivity, specificity, accuracy, and F1-score. Results: The BPD/AC ratio and AC/FL ratio markedly enhanced the prediction of ShD. When added to other features in RF models, the BPD/AC ratio got an AUC of 0.884 (95% CI: 0.802–0.957), a sensitivity of 68%, and a specificity of 83%. On the other hand, the AC/FL ratio, along with other factors, led to an AUC of 0.896 (95% CI: 0.805–0.972), 68% sensitivity, and 90% specificity. Conclusions: In pregnancies without clinical suspicion of macrosomia, ML models integrating fetal biometric ratios with maternal and labor-related factors significantly improved the prediction of ShD. These models may support clinical decision-making in low-risk deliveries where ShD is often unexpected.
28 July 2025 in International Journal of Gynecology & Obstetrics
To evaluate maternal serum Elabela (ELA) levels in pregnancies complicated by placenta accreta spectrum (PAS) and to assess their association with disease
Infectious complications at the surgical site complicates 1–4% of cesarean deliveries. Strict aseptic technique, hand hygiene and the use of sterile surgical gloves are essential to reduce the risk of surgical site contamination. Glove perforations are observed in almost 30% of all procedures and represent an underestimated potential risk factor for postoperative infections. The aim of this prospective study was to investigate glove perforation rates in cesarean deliveries and to analyze the impact of unrecognized glove perforations during surgery on surgical site infection rates after cesarean delivery. Surgical gloves from cesarean section were collected prospectively. All gloves were inspected for perforation holes. Cases in which surgical gloves had visible (macro) perforations were excluded from the study. Remaining gloves were examined using a water-fill test. Gloves with a positive water filling test were defined as the study group and negative gloves as the control group. Superficial Surgical Site Infections (SSI) were analyzed for the groups. A total of 1,779 pairs of used surgical gloves were collected and examined for perforations across 593 cesarean operations. Macro perforation were observed in 56 (9.4%) operations. The remaining 1,611 pairs of gloves underwent water-fill testing. Of these, 505 operations had completely intact gloves, while in 32 (5.4%) cases, micro-perforations were identified. SSI occurred in 18 women (3.3%): 7 in the perforation group (21.8%) and 11 in the control group (2.2%) (p < 0.001). In multivariable logistic regression analysis, glove micro-perforation was found to be a significant independent predictor of SSI (adjusted odds ratio: 12.705; 95% CI: 4.244–38.039; p < 0.001), even after adjusting for potential confounders including diabetes, obesity, emergency cesarean, operative duration, and intraoperative blood loss. Our data show that glove perforation is unexpectedly common and underestimated in terms of unfavorable surgical outcomes. The rate of surgical site infections is increasing and we suggest that unrecognized glove perforation must be considered as a risk factor for surgical site infection after cesarean section.
Background: Gestational hypertension (GHT) is associated with adverse maternal and perinatal outcomes, and reliable biomarkers for risk stratification remain limited. Thrombospondin-4 (TSP-4), a matricellular glycoprotein implicated in vascular remodeling, may play a role in hypertensive disorders of pregnancy. This study aimed to investigate maternal serum TSP-4 levels in GHT and their associations with obstetric and neonatal outcomes. Methods: This prospective cohort study included 44 women with GHT and 44 normotensive controls. Maternal serum TSP-4 levels were measured between 20–30 weeks’ gestation, and demographic, obstetric, and neonatal data were recorded. The development of preeclampsia (PE) and composite adverse perinatal outcomes (CAPO) was subsequently compared between the groups. Results: TSP-4 levels were significantly higher in the GHT group compared with controls (9.50 vs. 7.92 ng/mL, p < 0.001). Women with GHT had lower gestational age at delivery and birth weight, with higher rates of preterm delivery, fetal distress, NICU admission, and composite adverse perinatal outcomes (all p < 0.01). Within the GHT group, patients who developed PE had notably higher TSP-4 levels (13.45 vs. 9.33 ng/mL, p < 0.001). Conclusions: Elevated maternal serum TSP-4 is independently associated with GHT and progression to PE. TSP-4 may serve as a novel biomarker for risk assessment in hypertensive disorders of pregnancy.
4 February 2026 in Journal of the Turkish-German Gynecological Association
Comparative analysis of hormonal and metabolic indices in phenotypic subgroups of polycystic ovary syndrome - Journal of the Turkish-German Gynecological Association