C-section birth data classification using ensemble modelling techniques and their performance analysis

Abstract: Data mining and machine learning techniques have a wide range of applications in businesses, healthcare, organizations, and academia, to name a few. Machinelearning has been used by several academics to construct decision support systems, analyse major clinical features, extract useful information from trends in historical data, generate predictions, and classify diseases. Successful research gave doctors the ability to make the best decisions at the correct moment. We plan to use the learning potential of machine learning methods to classify birth data utilizing bagging, boosting, and stacking classification algorithms in the current work. Diversity in living styles, medical aid, religious connotations, and the place you live in all have an impact on the people who live in that culture. The current study is a complete comparison of the bagging, boosting, and stacking classification algorithms used on the government hospital's birth data. The caret library in R, which is regarded as an encompassing framework for developing machine learning models, is used for the experiments. Different evaluation measures are used to offer accuracy-based results. Boosting features with regard to, sensitivity, and specificity, the Gradient Boosting Machine (GBM) performed somewhat better.