The Impact of Cesarean Section Trends and Associated Complications in the Current World: A Comprehensive Analysis Using Machine Learning Techniques

The accurate prediction of the correct mode of delivery is crucial for the safety and well-being of both mother and child. Currently, this decision heavily relies on the subjective judgement of the attending physician, which can introduce risks if an incorrect method is chosen. Many expectant mothers may opt for a cesarean section without fully understanding whether it is the most suitable option for them. Particularly in developing countries, complications during delivery pose significant challenges. This study aims to address these concerns by identifying key features for determining the delivery mode and applying various machine learning algorithms to predict it accurately. The analysis involved five machine learning models, namely K-nearest neighbours (KNN), random forest, decision tree, support vector machine (SVM), and AdaBoost. The dataset utilized in this study consists of 6157 birth records from four different hospitals in Spain, encompassing 161 distinct features. By leveraging regression analysis-based machine learning methods, we strive to enhance the decision-making process and ultimately improve the safety outcomes for mothers and infants.