ROC based evaluation and comparison of classifiers for IVF implantation prediction

Abstract

Determination of the best performing classification method for a specific application domain is important for the applicability of machine learning systems. We have compared six classifiers for predicting implantation potentials of IVF embryos. We have constructed an embryo based dataset which represents an imbalanced distribution of positive and negative samples as in most of the medical datasets. Since it is shown that accuracy is not an appropriate measure for imbalanced class distributions, ROC analysis have been used for performance evaluation. Our experimental results reveal that Naive Bayes and Radial Basis Function methods produced significantly better performance with (0.739 ± 0.036) and (0.712 ± 0.036) area under the curve measures respectively. © 2010 Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering.