A comparative study on mode of delivery and analyzing the risk factors of cesarean delivery using K-nearest neighbor, SVM and C5.0 Classification Techniques

This paper depicts human services in decision making by applying machine learning algorithms on medical data. Health care industry produces huge amount of data that controls complex information relating to patients and their medical conditions. Data mining techniques have the effectiveness to determine relationships or hidden patterns among the objects in the medical data. Most supervised machine learning classification and advancement methods are employed for making decisions. This work focuses on predicting the mode of birth at an early stage by diagnosing the various risk factors. The modes of delivery are vaginal and cesarean. This analyzing helps to predict the birth mode and reduce the cesarean delivery. We examine this system on the collected data and find the best prediction. The physicians can apply this system for making better decisions in emergency cases. In this work, machine learning algorithms are applied for diagnosing the mode of delivery.