Search

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. [ABSTRACT FROM AUTHOR]

Objectives: Abnormal fetal tongue size is a phenotypic feature of various syndromes including Beckwith‐Wiedemann, Pierre‐Robin, oromandibular limb hypoplasia, chromosomal aberrations, etc. Current data regarding normal fetal tongue size are limited. Hence, micro/macroglossia are subjectively determined. The aim of the study was to construct a contemporary fetal tongue nomogram and to assess its clinical contribution. Methods: A prospective cross‐sectional study was performed in well dated, low risk, singleton pregnancies. Fetal tongues were measured by 5 trained sonographers. Highest quality images were selected. Intra‐ and interobserver variability was assessed. Tongue length, width, area, and circumference 1st to 99th centiles were calculated for each gestational week. Based on the normal tongue size charts, we created a Tongue Centile Calculator. Results: Over 18 months, 664 tongue measurements were performed. A cubic polynomial regression model best described the correlation between tongue size and gestational age. The correlation coefficient (r2) was 0.934, 0.932, 0.925, and 0.953 for tongue length, width, area, and circumference, respectively (P <.001). Intra‐ and interobserver variability had high interclass correlation coefficients (>0.9). Using the new charts, we were able to identify 2 cases of macroglossia, subsequently diagnosed with Beckwith‐Wiedemann, and 4 cases of microglossia, 3 associated with Pierre‐Robin sequence, and 1 associated with persistent buccopharyngeal membrane. Conclusions: We present novel fetal tongue size charts from 13 to 40 weeks of gestation. Clinical application of these nomograms may be beneficial in the prenatal diagnosis of syndromes or malformations associated with abnormal fetal tongue size. [ABSTRACT FROM AUTHOR]

Objective: To evaluate the intra-observer variability of the middle cerebral artery (MCA) and umbilical artery (UA) Doppler measurement taken under optimal conditions in term, uncomplicated pregnancies. Methods: A prospective study on uncomplicated singleton term pregnancies was performed. Multiple Doppler measurements were taken in the MCA and the UA by one examiner. Intra-rater agreement was calculated. Doppler indices were correlated to fetal biometric parameters and to gestational age. Results: One hundred patients were recruited. MCA indices were found to have the highest strength of intra-rater/observer agreement (K = 0.888) versus only a "good" agreement for UA pulsatility index (PI) (K = 0.755).The MCA-PI was significantly correlated with BPD (r = −0.198, p =.047), EFW (r = −0.241, p =.01) and birthweight (r = −0.208, p =.03). A statistically significant decrease was found in the MCA PI (r = −.422, p <.001) and in the CPR (r = −0.444, p <.001) with advancing pregnancy, between 37 and 42 weeks gestation. The UA PI did not change significantly (p =.099) during this period. Conclusions: MCA PI measured at term is reproducible with a high ICC. MCA PI significantly decreases with advancing gestation at term. No correlation was found between Doppler measurements and time to delivery. [ABSTRACT FROM AUTHOR]

Objective: The aim of this study was to describe the prenatal diagnosis of Major Aortopulmonary Collateral Arteries (MAPCAs), and to present a systematic ultrasound method for evaluating lung vascularity in fetuses with pulmonary atresia with ventricular septal defect (PAVSD) and agenesis of ductus arteriosus (DA). Method: This retrospective study evaluated fetuses diagnosed with PAVSD with agenesis of DA, for the presence of the MAPCAs anomaly. Fetal pulmonary vasculature was investigated by 2D and 4D Spatio Temporal Image Correlation (STIC) technology using High Definition Color Doppler. Results: Over a 10 year period, six fetuses were diagnosed with MAPCAs. Prenatal diagnosis was made between 17 w 6 d and 28 w 4 d in five fetuses, with the sixth diagnosed at 37 w 6 d. All six had PAVSD with agenesis DA, four exhibited pulmonic atresia without any arterial outflow, while two fetuses presented with absent left pulmonary artery, and a miniscule right pulmonary artery. In five cases, the parents elected to terminate the pregnancy and the last, although born alive, did not survive an attempt at restorative surgery and died at the age of 5 months. Postnatal CT angiography imaging of this case revealed the subclavian origin of the MAPCAs. Chromosomal micro array analysis of the amniotic fluid revealed that five of the six fetuses were normal and one was lost to follow up. Conclusion: MAPCAs should be investigated in cases of PAVSD with agenesis DA. A meticulous ultrasound evaluation using 2D and 4D STIC can permit the prenatal diagnosis of this anomaly and provide the parents with the opportunity for prenatal consultation. [ABSTRACT FROM AUTHOR]