Prediction of child birth delivery mode using hybrid-boosting ensemble machine learning model

Abstract

Maternal health is a critical aspect of public health that affects the well-being of both mother and infant. Despite the medical breakthroughs, maternal mortality rates remain high, particularly in developing countries. AI- based models provide new ways to analyze and interpret medical data, which can ultimately improve maternal and fetal health outcomes. The present study proposes a hybrid model for the maternal mode of delivery classification in pregnancy, which utilizes the strength of Ada Boost, Gradient Boost, and XG Boost algorithms. The proposed model culminates the three algorithms to improve the accuracy and efficiency of childbirth delivery classification method in pregnant women. The dataset used in this study consists of features such as age, systolic and diastolic blood pressure, blood sugar, body temperature, heart rate, placenta previa, and gravida. The dataset is divided into training and testing sets, where 70% of the data is used for training and the rest 30% for testing. The output of the Ada Boost, Gradient Boost, and XG Boost classifier is considered, and a maximum probability voting system selects the output with the highest probability as the most correct one. Performance is evaluated using various metrics, such as accuracy, precision, recall, and F1 score as an outcome where the XG Boost showed an accuracy of 97.07%, the Ada Boost showed 85.02%, and the Gradient Boost showed 92.51% respectively. Results also conspicuously showed that the proposed model achieves the highest accuracy of t98.05%, with 97.9% precision, 97.9% recall, and an F1 score of 97.9% on the testing dataset. The hybrid model proposed in this study has the potentiality to improve the accuracy and efficiency of the maternal mode of delivery classification in pregnancy, leading to better health outcomes for pregnant women and their babies.