Exploring Machine Learning Algorithms to Find the Best Features for Predicting Modes of Childbirth

The mode of delivery is a crucial determinant for ensuring the safety both mother and child. current practice predicting generally opinion physician in charge, but choosing wrong method can cause different short-term long-term health issues baby. purpose this study was twofold: first, to reveal possible features determining childbirth, second, explore machine learning algorithms by considering best childbirth (vaginal birth, cesarean emergency cesarean, vacuum extraction, or forceps delivery). An empirical conducted, which included literature review, interviews, structured survey relevant while five were explored identify most significant algorithm prediction based on 6157 birth records minimum set features. research revealed 32 that suitable modes categorized into groups their importance. Various models developed, with stacking classification (SC) producing highest f1 score (97.9%) random forest (RF) performing almost as well (f1-score = 97.3%), followed k-nearest neighbors (KNN; f1-score 95.8%), decision tree (DT; 93.2%), support vector (SVM; 88.6%) techniques, all (n 32)