Predicting Maternal Health Risk Using Machine Learning Models and Comparing The Performance Of Percentage Split And K-Fold Cross Validation

This paper presents a comprehensive study on predicting maternal health risk using advanced machine learning models. We explore the effectiveness of different model architectures and evaluate their performance using two common techniques: percentage split and K-Fold cross-validation. Our research highlights the significance of accurate risk prediction in maternal healthcare, emphasizing the need for robust model evaluation methods. Through extensive comparative analysis, this study provides valuable insights into the optimal approach for predicting maternal health outcomes, contributing to the advancement of healthcare technologies and ensuring better maternal well-being.