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.

Ahn TG, et al. J Korean Med Sci. 2024 Apr;39(13):e131. https://doi.org/10.3346/jkms.2024.39.e131

Recently, conventional interviews have been replaced with the multiple mini-interviews (MMI) for medical student selection in Korea. We first introduced the MMI as a new admissions tool in Korea. The aim of this study is to determine whether the MMI accurately predicts academic achievement on both written and performance-based examinations during the first 2 years of medical school. The original scores of each station were standardized to T-scores in the candidates group. Three cohorts of students were included depending upon the year they entered medical school. Pearson’s correlations were calculated to estimate the correlations between MMI scores and academic achievements. Additional correlated factors were run through multiple stepwise linear regression analysis to estimate predictive validity. There were no differences between T-scores or grade point averages (GPA) among the cohorts. The correlation coefficients between total MMI scores and academic achievement in Year 1 and the Year 2 performance-based examinations ranged from 0.17 to 0.43. Station 1 significantly predicted academic achievement over the second year. Station 3 significantly predicted only performance-based examination performance over the second year. MMI is a useful tool to assist with medical student selection. In particular, critical thinking, professionalism, and presentation and communication skills may be meaningful topics for predicting academic achievements, especially in performance-based subjects.

Pregnant women were excluded from vaccination against Coronavirus 2019 (COVID-19) until September 2021 in South Korea. Although vaccination for pregnant women started in October 2021, vaccine acceptance in pregnant women is yet unknown. This cross-sectional study aimed to investigate COVID-19 vaccine acceptance during pregnancy and influencing factors. An anonymous survey was distributed in obstetrics departments to all pregnant or postpartum women, during the prenatal or postpartum visit. The proportion of self-reported COVID-19 vaccination during pregnancy among 436 women was 26.6%. Pregnancy-related independent factors influencing maternal COVID-19 vaccination were “received vaccine information about from obstetrics and gynecology (OBGYN) doctors” (OR 3.41, 95% CI 2.05–5.65), “cohabitant COVID-19 vaccination” (OR 2.43, 95% CI 1.06–5.59), and “second trimester” (OR 7.35, 95% CI 1.54–35.15). In women who did not want to get vaccinated, the most common reason for COVID-19 vaccination hesitancy was concern that COVID-19 vaccine might affect the fetus (91.7%, 243/266), followed by distrust in COVID-19 vaccine effectiveness (42.6%, 113/266). This study showed that providing information about maternal COVID-19 vaccination, especially by OBGYN doctors, is crucial for increasing vaccination coverage in pregnant women. Providing updated evidence of COVID-19 vaccine efficacy and safety in pregnant women may be also helpful for increasing vaccine acceptance.

Jeon J, et al. Obstet Gynecol Sci. 2017 Nov;60(6):499-505. https://doi.org/10.5468/ogs.2017.60.6.499