A comparative study of classification algorithms for predicting gestational risks in pregnant women

Pregnant women must be protected from complications during the period of gestation which is a stage every woman undergoes many physiological changes, sometimes inducing complications that may turn severe and lead to death of both mother and fetus. Classification methods are popularly used method whose algorithms are best suitable in medical diagnosis. Among them C4.5 Decision Tree algorithm and Naïve Bayes algorithm are effectively used for classifying medical data. Both algorithms are most capable to classify the pregnancy data of present research study. The main aim of this paper is to highlight concept of standardization of parameters selected for data collection in study to achieve elevated results of classification by selected classification algorithms. The paper also presents how efficiently risk levels can be predicted by the selected algorithms to protect pregnant women from complications in pregnant women health. Pregnancy data of present research study is considered for classifying and predicting complications leading to different risk levels during pregnancy. The best algorithm among selected two algorithms namely C4.5 and Naïve Bayes Classifier is identified in the paper for further improving the efficiency of selected classifier. By identifying the risks in pregnancy, present maternal and fetal mortality rate can be efficiently reduced to lower rates thus providing a safe pregnancy period, post natal period and a healthy baby to pregnant mothers.