Applications of Logistic Regression and Artificial
Neural Network for ICSI Prediction
Zeinab Abbas1,
Ali Saad1, Mohammad Ayache1, and Chadi Fakih2
1Department of Biomedical Engineering, Islamic
University of Lebanon, Lebanon
2Department
of medicine, Lebanese University and Saint Joseph University, Lebanon
Abstract: The third most serious
disease estimated by Word Wide Organization after cancer and cardiovascular
disease is the infertility. The advanced treatment techniques is the Intra-Cytoplasmic Sperm Injection (ICSI) procedure, it
represents the best chance to have a baby for couples having an infertility
problem. ICSI treatment is expensive, and there are many factors affecting the
success of the treatment, including male and female factors. The paper aims to
classify and predict the ICSI treatment results using logistic regression and
artificial neural network. For this purpose, data are extracted from real
patients and contain parameters such as age, endometrial receptivity,
endometrial and myometrial vascularity index, number of embryo transfer, day of
transfer, and quality of embryo transferred. 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.
Keywords: Artificial Neural Network (ANN), Assisted
Reproductive Treatment (ART), In-Vitro Fertilization (IVF), ICSI, logistic
regression.