Performance Assessment of Supervised Learning Techniques for Caesarean Rate Prediction

Abstract

Machine learning techniques automate the decision making process. These techniques, when applied to the healthcare industry, improve the health conditions of the patient and offers a reduction of the cost of healthcare services. The current study used machine learning classification techniques to predict the chances of caesarean. The dataset used in the study includes 80 instances of pregnant women with six health attributes. In this study, 14 classification techniques are applied to the dataset using ten cross-fold validation training methods. The results obtained from the prediction conclude that the Naïve Bayes algorithm provides more accurate results as compared to other models applied onto the dataset.

Keywords: Machine Learning, Classification Techniques, C-Section Prediction, Caesarean Prediction