Vaginal Power Doppler Parameters as New Predictors of Intra-Cytoplasmic Sperm Injection Outcome

Abstract

Intra-Cytoplasmic Sperm Injection (ICSI) represents the best chance to have a baby for couples that have an infertility problem. ICSI treatment is expensive, and there are a number of factors affecting the success of the treatment. This work is mainly aimed to classify and predict the ICSI treatment results using (1) the classical statistical study, (i.e. logistic regression) and (2) the artificial intelligence (i.e. Neural Networks). For this purpose, data are extracted from real patients. The data contain parameters such as the age, the endometrial receptivity, the endometrial and myometrial vascularity index, number of embryo transfer, the day of transfer, and the quality of embryo transferred. These parameters may affect the result of the ICSI treatment. Overall, the logistic regression predicts the output of the ICSI outcome with an accuracy of 75%. In other parts, the neural network managed to achieve an accuracy of 79.5% with all parameters and 75% with only the significant parameters.