Prenatal risk assessment of Trisomy 21 by probabilistic classifiers

This study proposes a probabilistic approach to evaluate prenatal risk of Down syndrome. In this study, we address the decision-making problem in diagnosing Down syndrome from the machine learning perspective aiming to decrease invasive tests. We employ Naive Bayes and Bayesian Networks classification algorithms as probabilistic methods. This probabilistic classification approach is one of the leading work in medical domain. We use George Washington University dataset in our study. We also benchmark our probabilistic classifiers with widely used non-probabilistic classifiers in machine learning literature. Finally the results of the experiments show that probabilistic classifiers enable acceptable prediction of Trisomy 21 case and the classification performance can be improved by using the proposed techniques in this study.