Chu R, Chen W, Song G, et al. - To predict adverse events risk in pregnant women with congenital heart disease, two prediction models for mothers and their offspring were created in this study with a development cohort and a validation cohort, both comprising pregnant women with congenital heart disease (n = 318). Validation followed predictor selection, and thereafter, model was built applying multivariate logistic regression analysis. An accuracy of 0.76 to 0.86 [AUC (area under the receiver operating characteristic curve) = 0.74–0.87] in the development cohort, and 0.72 to 0.86 (AUC = 0.68–0.80) in the validation cohort was displayed by the maternal model, as shown by the machine learning–based algorithms. The neonatal model displayed an accuracy of 0.75 to 0.80 (AUC = 0.71–0.77) and 0.72 to 0.79 (AUC = 0.69–0.76) in the development and validation cohorts, respectively, as per machine learning–based algorithms. For adverse maternal as well as neonatal events, two prenatal risk evaluation models were established in this study. The likely utility of these models was suggested as an aid to clinicians in tailoring precise management as well as therapy in pregnant women suffering from congenital heart disease.