Search

This study aimed to develop an early pregnancy risk scoring model for pregnancy-associated hypertension (PAH) based on maternal pre-pregnancy characteristics, such as mean arterial pressure (MAP), pregnancy-associated plasma protein-A (PAPP-A) or neither. The perinatal databases of seven hospitals from January 2009 to December 2020 were randomly divided into a training set and a test set at a ratio of 70:30. The data of a total pregnant restricted population (women not taking aspirin during pregnancy) were analyzed separately. Three models (model 1, pre-pregnancy factors only; model 2, adding MAP; model 3, adding MAP and PAPP-A) and the American College of Obstetricians and Gynecologists (ACOG) risk factors model were compared. A total of 2840 (8.11%) and 1550 (3.3%) women subsequently developed PAH and preterm PAH, respectively. Performances of models 2 and 3 with areas under the curve (AUC) over 0.82 in both total population and restricted population were superior to those of model 1 (with AUCs of 0.75 and 0.748, respectively) and the ACOG risk model (with AUCs of 0.66 and 0.66) for predicting PAH and preterm PAH. The final scoring system with model 2 for predicting PAH and preterm PAH showed moderate to good performance (AUCs of 0.78 and 0.79, respectively) in the test set. "A risk scoring model for PAH and preterm PAH with pre-pregnancy factors and MAP showed moderate to high performances. Further prospective studies for validating this scoring model with biomarkers and uterine artery Doppler or without them might be required". [ABSTRACT FROM AUTHOR]

This study was a multicenter retrospective cohort study of term nulliparous women who underwent labor, and was conducted to develop an automated machine learning model for prediction of emergent cesarean section (CS) before onset of labor. Nine machine learning methods of logistic regression, random forest, Support Vector Machine (SVM), gradient boosting, extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), k-nearest neighbors (KNN), Voting, and Stacking were applied and compared for prediction of emergent CS during active labor. External validation was performed using a nationwide multicenter dataset for Korean fetal growth. A total of 6549 term nulliparous women was included in the analysis, and the emergent CS rate was 16.1%. The C-statistics values for KNN, Voting, XGBoost, Stacking, gradient boosting, random forest, LGBM, logistic regression, and SVM were 0.6, 0.69, 0.64, 0.59, 0.66, 0.68, 0.68, 0.7, and 0.69, respectively. The logistic regression model showed the best predictive performance with an accuracy of 0.78. The machine learning model identified nine significant variables of maternal age, height, weight at pre-pregnancy, pregnancy-associated hypertension, gestational age, and fetal sonographic findings. The C-statistic value for the logistic regression machine learning model in the external validation set (1391 term nulliparous women) was 0.69, with an overall accuracy of 0.68, a specificity of 0.83, and a sensitivity of 0.41. Machine learning algorithms with clinical and sonographic parameters at near term could be useful tools to predict individual risk of emergent CS during active labor in nulliparous women. [ABSTRACT FROM AUTHOR]