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.

The 2009 Institute of Medicine (IOM) guidelines for gestational weight gain (GWG) are intended for use among women in the United States. Little data are available on whether the 2009 IOM recommendations can be applied to Asian women. This study aimed to evaluate whether the recommendations are related to adverse pregnancy outcomes in Korean pregnant women. A retrospective cohort study was conducted for all singleton-pregnant women at a university hospital in Korea. After classifying the enrolled women into four Korean pre-pregnancy body mass index (BMI) categories, the risk of adverse pregnancy outcomes were analyzed for women who gained inadequate or excessive GWG based on 2009 IOM recommendations. Of 7,843 pregnancies, 64.0% of women had normal pre-pregnancy BMI and 42.7% achieved optimal GWG. Across all BMI categories, adverse pregnancies outcomes such as small for gestational age (SGA), large for gestational age (LGA), preterm birth, preeclampsia, and cesarean due to dystocia were significantly associated with GWG (all P ≤ 0.001).Women with normal BMI who gained inadequate weight were more likely to develop SGA and preterm birth and less likely to develop LGA (adjusted odds ratio (aOR) 2.21, 1.33, and 0.54, respectively). Whereas, women with normal BMI who gained excessive weight were more likely to develop LGA, preterm birth, preeclampsia, and cesarean section due to dystocia (aOR 2.10, 1.33, 1.37, and 1.37, respectively) and less likely to develop SGA (aOR 0.60). It is tolerable for Korean women to follow recommended GWG from the 2009 IOM guidelines to decrease adverse pregnancy outcomes. This will be helpful for antenatal care on GWG not only for Korean pregnant women, but also other Asian women who have lower BMI criteria than Caucasian women.

To investigate pertussis vaccination rates during pregnancy and the routine recommendation rates by maternity healthcare professionals (HCPs), including influencing factors, in Korea. Two different questionnaires were developed and conducted anonymously for pregnant or postpartum women and maternity HCPs in 30 multi-centers. Maternal pertussis vaccination rates and maternity HCPs' recommendation rates were analyzed. Independent influencing factors were analyzed using multivariate logistic regression analysis, respectively. The rate of pertussis vaccination during pregnancy among 466 women was 67%. Among 164 multiparous women, 35.5% received pertussis vaccinations during every pregnancy. However, 27.9% among all pregnant women did not receive information about pertussis and vaccination. The independent influencing factors for maternal pertussis vaccination, given as the tetanus, diphtheria and acellular pertussis (Tdap), were "getting informed" (OR 18.597, 95% CI 11.206-30.861), "informed by OBGYN doctors" (OR 4.426, 95% CI 2.144-9.267), and "metropolitan residence" (OR 3.048, 95% CI 1.419-6.548). Among a total of 373 maternity HCPs, 210 (56.3%) routinely recommended pertussis vaccination, but 21.7% of the total maternity HCP participants did not know the maternal Tdap guideline. The independent factors affecting routine recommendation were the awareness of guideline (OR 9.771, 95% CI 5.227-18.265, p < 0.001) and personal pertussis vaccination within 10 years (OR 3.108, 95% CI 2.377-10.329, p < 0.001). The barriers for routine recommendation were the lack of informational materials (29%), time (25%), and knowledge (23%). To increase pertussis vaccination coverage in pregnant women, more education for maternity HCPs, increase the personal pertussis vaccination rates of HCPs, and informational materials, are needed.

Kim WJ, et al. Obstet Gynecol Sci. 2018 Jan;61(1):7-13. https://doi.org/10.5468/ogs.2018.61.1.7

Ko HS, et al. J Korean Med Sci. 2018 Jan;33(10):e80. https://doi.org/10.3346/jkms.2018.33.e80