(1) Background: Fetal growth restriction is a relatively common disorder in pregnant patients with thrombophilia. New artificial intelligence algorithms are a promising option for the prediction of adverse obstetrical outcomes. The aim of this study was to evaluate the predictive performance of a Feed-Forward Back Propagation Network (FFBPN) for the prediction of small for gestational age (SGA) newborns in a cohort of pregnant patients with thrombophilia. (2) Methods: This observational retrospective study included all pregnancies in women with thrombophilia who attended two tertiary maternity hospitals in Romania between January 2013 and December 2020. Bivariate associations of SGA and each predictor variable were evaluated. Clinical and paraclinical predictors were further included in a FFBPN, and its predictive performance was assessed. (3) Results: The model had an area under the curve (AUC) of 0.95, with a true positive rate of 86.7%, and a false discovery rate of 10.5%. The overall accuracy of our model was 90%. (4) Conclusion: This is the first study in the literature that evaluated the performance of a FFBPN for the prediction of pregnant patients with thrombophilia at a high risk of giving birth to SGA newborns, and its promising results could lead to a tailored prenatal management.

Background: Pregnancy in women with systemic lupus erythematosus (SLE) is accompanied by adverse pregnancy outcomes (APOs). We aimed to investigate the association between clinical, sonographic, and laboratory parameters and APOs (preeclampsia, intrauterine growth restriction, premature birth, and maternal mortality). Methods: This observational retrospective study included all pregnancies in women with SLE who attended two tertiary maternity hospitals from Romania between January 2013 and December 2020. Clinical, sonographic, and laboratory variables were examined. Bivariate associations of APO status and each predictor variable were evaluated, and significant predictors were further included in a classification model based on discriminant analysis. Results: Predictors of APOs included BMI > 25 kg/m², personal history of lupus nephritis or chronic hypertension, proteinuria, low C3, SLE Disease Activity Index 2000 (SLEDAI-2k score ≥ 4 and physician’s global-assessment (PGA) score ≥ 1 throughout pregnancy, increased mean uterine arteries pulsatility index in the first and second trimesters, cerebroplacental ratio < 1 in the second and third trimesters, and small fetal abdominal circumference in the third trimester. Glucocorticoids, methyldopa, and aspirin use appeared to be protective against APOs. Conclusions: This study provides a comprehensive analysis of the most important predictors for APOs in pregnant patients with SLE, which could constitute a basis for further research.

(1) Background: Neonatal cerebral sinovenous thrombosis (CSVT) is a rare disorder, associated with long-term neurological sequelae. The aim of this study was to retrospectively evaluate the most commonly encountered perinatal risk factors for this disease in a cohort of newborns from Romania. (2) Methods: The medical records of neonatal CSVT patients treated between January 2017 and December 2021 were descriptively assessed. (3) Results: The study included nine neonates, five males (55.56%) and four females (44.44%), who were born at term. The most commonly presented clinical manifestations were feeding difficulties, lethargy, respiratory distress, loss of consciousness, and seizures. Maternal-inherited thrombophilia, male sex, complicated delivery, perinatal asphyxia, and mechanical ventilation were frequently identified as potential risk factors for developing CSVT. The lesions were more frequently localized in the superior sagittal sinus (n = 7; 77.78%), followed by the transverse (n = 4; 44.44%), sigmoid (n = 2; 22.22%), and cavernous (n = 1; 11.11%) sinuses. Low-molecular-weight heparin was administered to all patients, and two of them died from thrombotic complications. (4) Conclusions: Recognition of potential risk factors and a prompt diagnosis of neonatal CSVT could lead to better patient management and to a reduction of severe complications.

Background/Objectives: The diagnostic performance of CINtec^® PLUS can be influenced by numerous patient characteristics and risk factors. The aim of this retrospective study was to evaluate and model the risk factors associated with CINtec^® PLUS test positivity in patients undergoing cervical cancer screening and to assess their predictive performance for the prediction of cervical intraepithelial neoplasia (CIN) 2/3 using an unsupervised machine learning-based model. Methods: Medical data of 134 patients with human papillomavirus (HPV) infection who underwent CINtec^® PLUS testing were used to model the impact of risk factors on dual-stain cytology positivity and to evaluate the predictive performance for CIN2/3. Results: The gradient boosting classifier for the prediction of CINtec^® PLUS positivity using clinical risk factors had a precision of 75%, an overall accuracy of 0.62, and an area under the curve (AUC) value of 0.77. Body mass index and age were the most important variables in this model. HSIL, ASC-US, and other high-risk HPV strains increased the likelihood of a positive outcome. Overall AUC values for a positive test alone were 0.74 and 0.69 for CIN2 and CIN3 prediction, respectively. For CIN2 prediction, the XGBoost model performed well, with 71% sensitivity, 85% specificity, and an AUC value of 0.90. However, the model had 96% sensitivity, 25% specificity, and 0.58 AUC for CIN3 prediction. Conclusions: Patient characteristics and risk factors can influence CINtec^® PLUS positivity rates and they need to be carefully considered before choosing a specific management.

Background/Objectives: In Romania, where cervical cancer incidence remains among the highest in the European Union, a risk-based management strategy could support more precise allocation of limited resources. The aim of this study was to test the prognostic utility of immediate pre-treatment and post-treatment risk predictions, derived from the American Society of Colposcopy and Cervical Pathology (ASCCP) risk-based management guidelines for the prediction of progression, regression or persistence of high-grade cervical dysplasia. Methods: In this prospective cohort study, we included 223 patients aged over 30 years who underwent self-referred or targeted screening with or without histologically confirmed cervical intraepithelial neoplasia (CIN) of any grade. We employed Fine and Gray’s subdistribution hazard model that evaluated the cumulative incidence function for each specific outcome, treating other outcomes as competing events. These outcomes were further stratified depending on the type of high-grade dysplasia. Results: The immediate post-treatment risk was significantly associated with subsequent progression of cervical dysplasia. For a cut-off of 60%, the immediate post-treatment risk was able to significantly predict the progression of both CIN2+ and CIN3+. On the other hand, the immediate pre-treatment risk > 60% was significantly associated with progression of CIN3+, but not of CIN2+. Also, the immediate pre-treatment risk was significantly associated with regression, but this observation did not persist at the >60% threshold. Both pre- and post-treatment risk > 60% were strongly associated with persistence across histologic subgroups. Conclusions: The ASCCP-derived immediate risk estimates, especially post-treatment risk > 60%, proved effective in predicting progression and persistence of high-grade cervical dysplasia.

(1) Background: Neonatal early-onset sepsis (EOS) is associated with important mortality and morbidity. The aims of this study were to evaluate the association between serum biomarkers with early onset neonatal sepsis in a cohort of patients with prolonged rupture of membranes (PROM), and to calculate their diagnostic accuracy. (2) Methods: A retrospective cohort study was conducted on 1355 newborns with PROM admitted between January 2017 and March 2020, who were divided in two groups: group A, with PROM ≥ 18 hours and group B, with PROM < 18 hours. Both groups were further split into subgroups: proven sepsis, probable sepsis and no sepsis. Descriptive statistics, ANOVA analysis, and a Random Effects Generalized Least Squares (GLS) regression were used to evaluate the data. (3) Results: The statistically significant predictors of neonatal sepsis were the high white blood cells count from the first (p = 0.005) and third day (p = 0.028), and high CRP values from the first day (p = 0.004). Procalcitonin (area under the curve - AUC = 0.78) and CRP (AUC = 0.76) measured on the first day had the best predictive performance for early onset neonatal sepsis. (4) Conclusions: Further studies are needed to explore other bi-omarkers of sepsis in both pregnant women and newborns to better predict EOS.