Classifying the modes of Cesarean Section using Machine Learning Techniques

Abstract

Machine learning techniques provide a learning method that can be used to motivate knowledge from data. There are some studies on the use of machine learning techniques for medical cesarean data. In this study, we evaluate different machine learning techniques for the general reasons for the cesarean section (emergency C-section or preplanned). Data on cesarean section is a collection from different hospitals of city Lahore and different medical factors are identified. A cesarean classification model is built using a Random Forest classifier, and K-Nearest Neighbor classifier. It can classify the cesarean into emergency C-section or preplanned C-section with an average accuracy, precision, and recall of 67% and 65% respectively. Chi_square test of association is used to extract disease patterns from the collection. It highlights the significant medical covariates that are associated with doctors’ advice and the association among pre-birth covariates.