Handling the Imbalance Problem of IVF Implantation Prediction
Asli Uyar, Ayşe Bener, Haydar Nadir Ciray, Mustafa Bahçeci · 2010
Predicting implantation outcomes of in- vitro fertilization (IVF) embryos is critical for the success of the treatment. We have applied the Naive Bayes classifler to an original IVF dataset in order to discriminate embryos according to the implanta- tion potentials. The dataset we analyzed represents an imbalanced distribution of positive and negative instances. In order to deal with the problem of im- balance, we examined the efiects of oversampling the minority class, undersampling the majority class and the adjustment of the decision threshold on the clas- siflcation performance. We have used features of Re- ceiver Operating Characteristics (ROC) curves in the evaluation of experiments. Our results revealed that it is possible to obtain optimum True Positive and False Positive Rates simply by adjusting the decision threshold. Under-sampling experiments show that we can achieve the same prediction performance with less data as well as 736 embryo samples.