Accurate prediction of vaginal birth after cesarean is crucial for selecting women suitable for a trial of labor after cesarean (TOLAC). We sought to develop a machine learning (ML) model for predi...

COVID-19 infection imposes a risk for pregnant individuals and may lead to adverse maternal and obstetric outcomes. This is a retrospective cohort study of all women giving birth between March and July 2021 at a single tertiary center. Obstetric and neonatal outcomes were compared between vaccinated and non-vaccinated pregnant women with singleton pregnancies. Women with prior COVID-19 infection, multiple gestations and stillbirth were excluded from the study. Of 4708 women who delivered during the study period, 3700 met the eligibility criteria, of whom 3240 were vaccinated during pregnancy. Compared with the non-vaccinated group, the vaccinated group was characterized by a lower rate of smoking (3.70% vs. 6.67%, p = 0.0028), whereasother maternal characteristics were not significantly different. Multivariable analysis demonstrated that COVID-19 mRNA vaccination was not significantly associated with increased risk of preterm birth as well as other adverse obstetric outcomes including hypertensive diseases of pregnancy, cesarean delivery and small for gestational age. However, a significantly lower risk for meconium-stained amniotic fluid was observed among the vaccinated group (adjusted odds ratio 0.63; 95% confidence interval, 0.46–0.86, p = 0.0039). Moreover, the vaccine was not significantly associated with increased risk of neonatal adverse outcomes including respiratory complications and NICU hospitalization. In conclusion, BNT162b2 messenger RNA vaccination during pregnancy was not associated with an increased rate of adverse obstetric and neonatal outcomes. Therefore, in view of its safety on one hand, and the risk associated with COVID-19 disease in pregnancy on the other hand, BNT 162b2 COVID-19 vaccine should be recommended for pregnant women.

Objective: To develop a comprehensive machine learning (ML) model predicting unplanned cesarean delivery (uCD) among singleton pregnancies based on features available at admission to labor.Methods: A retrospective cohort study from a tertiary medical center. Women with singleton vertex pregnancy of 34 weeks or more admitted for vaginal delivery between March 2011 and May 2019 were included. The cohort was divided into training (80%) and validation (20%) data sets. A separate cohort between June 2019 and April 2021 served as a test data set. Features selection was performed using a Random Forest ML algorithm.Results: The study population included 73 667 women, of which 4125 (6.33%) underwent uCD. The final model consisted of 13 features, based on prediction importance. The XGBoost model performed best with areas under the curve for the training, validation, and test data sets of 0.874, 0.839, and 0.840, respectively. The model showed a 65% positive predictive value for uCD among women in the 100th centile group, and a 99% or more negative predictive value in the less than 50th centile group. Positive and negative predictive values remained high among subgroups with high pretest probability of uCD.Conclusion: An ML model for the prediction of uCD provides clinically useful risk stratification that remains accurate across gestational weeks 34–42 and among clinical risk groups. The model may be clinically useful for physicians and women admitted for labor.Synopsis: A machine learning model predicts unplanned cesarean delivery and can inform women's individualized decision making.

Background: Management of pilonidal sinus (PNS) disease has changed notably in the past decade, with the introduction of novel surgical techniques and technological innovation. In this study, we summarized our initial experience with sinus laser-assisted closure (SiLaC) of pilonidal disease. Methods: A retrospective analysis of a prospective database of all patients who underwent minimally invasive surgery combined with laser therapy for PNS between September 2018 and December 2020 was performed. Patients' demographics, clinical and perioperative data, as well postoperative outcomes were recorded and analyzed. Results: A total of 92 patients (86 males, 93.4%) underwent SiLaC surgery for pilonidal sinus disease during the study period. Patients' median age was 22 (range 16–62 years), and 60.8% of them previously underwent abscess drainage due to PNS. SiLaC was performed under local anesthesia in 85.7% of cases (78 patients) with a median energy of 1081 J (range 13–5035 J). One patient was lost to follow-up, leaving 91 patients for final analysis. The primary outcome was complete healing rate, standing at 81.3% (74/91 patients). In 8 patients (8.8%), there was minor incomplete healing that did not require reintervention. Recurrent/nonhealing disease was seen in 9 patients (9.9%), requiring reoperation in 7 patients (8.4%). Of those, 4 patients underwent repeat SiLaC and 3 patients underwent wide excision. Analysis of risk factors for PNS recurrence demonstrated that general anesthesia (P = .02) was associated with increased risk for recurrence along with a trend for increased risk in patients with significant hairiness (P = .078). No differences were seen in age (P = .621), gender (P = .475), median sinus length (P = .397), and energy used (P = .904). Conclusion: Primary healing rate after SiLaC surgery for chronic PNS was >80% in our series. Ten percent of patients did not achieve complete healing but did not require surgery due to lack of symptoms.