Early Prediction and Analysis of Caesarian Section Delivery for Better Healthcare Operational Decisions

Abstract

The objective of this research work is to anticipate Caesarian-Section Deliveries using machine learning classifier models furthermore the accuracy of various machine learning classifier models is also compared in predicting Caesarian Section Deliveries. These predictions are useful in health care operational decision making. For experimentation the data set is collected from the UCI machine learning repository. The main attributes represented in this data set are age, delivery number, delivery time, blood pressure, heart status. The class attribute is Caesarian. All these parameters influence the mode of delivery. The given data set is divided into two parts one is training set and the other is test set, 80% of which is considered as a training set and the remaining 20% is considered as a test set. Three machine learning classifier models are implemented using WEKA3.8.3 and by observing the results it is clear that BayesNetwork classifier model does the correct prediction with accuracy of 87.5%.