Background and Objectives: Polycystic ovary syndrome (PCOS) is a complex disorder that can negatively impact the obstetrical outcomes. The aim of this study was to determine the predictive performance of four machine learning (ML)-based algorithms for the prediction of adverse pregnancy outcomes in pregnant patients diagnosed with PCOS. Materials and Methods: A total of 174 patients equally divided into 2 groups depending on the PCOS diagnosis were included in this prospective study. We used the Mantel–Haenszel test to evaluate the risk of adverse pregnancy outcomes for the PCOS patients and reported the results as a crude and adjusted odds ratio (OR) with a 95% confidence interval (CI). A generalized linear model was used to identify the predictors of adverse pregnancy outcomes in PCOS patients, quantifying their impact as risk ratios (RR) with 95% CIs. Significant predictors were included in four machine learning-based algorithms and a sensitivity analysis was employed to quantify their performance. Results: Our crude estimates suggested that PCOS patients had a higher risk of developing gestational diabetes and had a higher chance of giving birth prematurely or through cesarean section in comparison to patients without PCOS. When adjusting for confounders, only the odds of delivery via cesarean section remained significantly higher for PCOS patients. Obesity was outlined as a significant predictor for gestational diabetes and fetal macrosomia, while a personal history of diabetes demonstrated a significant impact on the occurrence of all evaluated outcomes. Random forest (RF) performed the best when used to predict the occurrence of gestational diabetes (area under the curve, AUC value: 0.782), fetal macrosomia (AUC value: 0.897), and preterm birth (AUC value: 0.901) in PCOS patients. Conclusions: Complex ML algorithms could be used to predict adverse obstetrical outcomes in PCOS patients, but larger datasets should be analyzed for their validation.

(1) Background: Cervical elastography is a new concept that could allow clinicians to assess cervical consistency in various clinical scenarios. We aimed to evaluate the predictive performance of the strain ratio (SR) at the level of the internal os, either individually or in combination with other parameters, in the prediction of spontaneous preterm birth (PTB) at various gestational ages. (2) Methods: This prospective study included 114 pregnant patients with a high-risk profile for PTB who underwent cervical elastography during the second trimester. Clinical and paraclinical data were assessed using univariate analysis, logistic regression, and sensitivity analysis. (3) Results: The SR achieved an area under the receiver operating curve (AUROC) value of 0.850, a sensitivity of 85.71%, and a specificity of 84.31% in the prediction of PTB before 37 weeks of gestation. The combined model showed superior results in terms of accuracy (AUROC = 0.938), sensitivity (92.31%), and specificity (95.16%). When considering PTB subtypes, the highest AUROC value (0.80) and accuracy (95.61%) of this marker were achieved in the prediction of extremely preterm birth, before 28 weeks of gestation. (4) Conclusions: The SR achieved an overall good predictive performance in the prediction of PTB and could be further evaluated in various cohorts of patients.

(1) Background: Trial of labor after cesarean (TOLAC) can be associated with significant maternal and neonatal complications, and the aim of this retrospective study was to calculate the risks and probabilities of these complications in two tertiary maternity centers in Romania. (2) Methods: A total of 216 patients who attempted TOLAC were included in the study and were segregated into two groups, depending on TOLAC success. Medical records were assessed, and clinical data were used to determine the maternal and neonatal risks and complications, using multinomial logistic regression and postestimation predictions. (3) Results: Our data indicated that patients who had a failed TOLAC had significantly higher risks and probabilities of uterine rupture, either complete or incomplete; intensive care unit (ICU) admission; and emergency hysterectomy. The newborns of these mothers had significantly higher risks and probabilities of low Apgar score at birth, neonatal intensive care unit (NICU) admission, and invasive ventilation. (4) Conclusions: Failed TOLAC could lead to significant maternal and neonatal complications, and women who attempt this procedure should be monitored in a tertiary center where a multidisciplinary team and an emergency operating room are available.

Latency antibiotic therapy is an established component of expectant management after preterm prelabour rupture of membranes (PPROMs). Pooled randomised evidence from 22 trials involving 6872 women and infants shows that antibiotics prolong pregnancy, reduce chorioamnionitis (risk ratio 0.66) and reduce neonatal infection (risk ratio 0.67), without a significant reduction in perinatal mortality. The evidence supporting the therapeutic principle is stronger than the evidence defining how the therapy should be configured. This narrative review examines the three decisions an obstetrician makes at the bedside, namely, which agent, at which dose and route, and for how long, and the comparative evidence behind each. Contemporary practice descends from two protocols: the ampicillin–erythromycin regimen of the NICHD Maternal–Fetal Medicine Units Network trial and the erythromycin arm of ORACLE I. Neither was designed to identify an optimal regimen. Substitution of azithromycin for erythromycin rests predominantly on observational cohorts together with one small open-label randomised comparison that pre-specified no non-inferiority margin and is therefore pragmatic and guideline-permitted rather than confirmed by an adequately powered randomised trial. No randomised dose comparison using clinical endpoints has been performed in PPROM, although randomised pharmacokinetic data exist for azithromycin. The seven-day course derives from a trial protocol rather than from a duration-ranging study, and the two randomised duration comparisons published since 2023 point in opposite directions. Guideline agreement reflects shared historical ancestry rather than independent confirmation of optimality. Adequately powered pragmatic trials, stratified by gestational age, remain the principal unmet need.

Molecular classification underpins prognostic assessment in endometrial carcinoma, but heterogeneity persists within molecular classes. This narrative review examines whether tissue-based, circulating and emerging biomarkers add prognostic information beyond molecular class and clinicopathological factors. We distinguish four evidentiary levels: prognostic association, independence after adjustment for molecular class, within-class stratification and incremental predictive performance. Clinical utility is considered separately. Estrogen receptor (ER) status now contributes to risk stratification of no specific molecular profile (NSMP) tumors in the 2025 European guidelines, primarily on within-class prognostic evidence. Its incremental predictive performance has been demonstrated only in high-risk disease, with internal validation. Clinical utility remains unproven, and findings within mismatch repair-deficient disease are discordant. CTNNB1 mutation has shown inconsistent associations with recurrence, mainly in early-stage disease. Chromosome 1q32.1 amplification was associated with recurrence within NSMP in two cohorts. Neither marker has been formally assessed for incremental predictive performance. Where model comparisons were performed, gains in discrimination were generally modest. Larger gains arose from small samples or models without external validation, and external validation remained uncommon. No individual biomarker examined has demonstrated prospective clinical utility on its own.

Among uterus-preserving treatments for presumed fibroids, only myomectomy yields a specimen. Occult uterine sarcoma is uncommon, but leiomyosarcoma is clinically aggressive and seldom recognised before treatment. This narrative review examines what pretreatment assessment can and cannot establish. Literature from PubMed/MEDLINE, Scopus, Web of Science, Embase, and the Cochrane Library was synthesised narratively. Reported frequencies of unexpected sarcoma differ between clinical populations, mostly from 0.1% to 0.4%, and rise with age. Other predisposing factors are imprecisely quantified; genome-wide association data do not discriminate sarcoma from leiomyoma. Separate meta-analyses, largely of retrospective, enriched studies, report higher accuracy for magnetic resonance imaging (MRI), including diffusion-weighted sequences, than for ultrasound, by indirect comparison. Serum markers, composite scores and circulating nucleic acids remain supportive or investigational; directed biopsy lacks validation in unselected populations. In all-sarcoma scenarios, published likelihood ratios indicate that a negative MRI lowers, but does not eliminate, the probability of sarcoma; an exploratory, assumption-dependent reconstruction from a consecutive cohort illustrates their uncertain transportability. No available test reliably excludes sarcoma; after specimen-free therapy, a missed sarcoma may remain unrecognised until reassessment. We propose a conceptual framework, not a validated decision rule, that considers absolute residual risk alongside the specimen status of the chosen treatment.