Adjusting decision threshold in Naive Bayes based IVF embryo selection

In this study, IVF embryo selection has been considered as a binary classification problem and predictibality of implantation outcome of individual embryos has been tested using Naive Bayes method. First, in order to perform classification experiments, an embryo based dataset has been constructed from database of Bahccedileci IVF Centre. Since the class distribution of dataset is highly imbalanced (11% Pozitive and 89% Negative implantation outcomes) the decision threshold of Naive Bayes classifier has been optimized using the features of ROC analysis. Experimental results show that classification with optimized threshold performs better than classification with default threshold.