Prediction the success rate of intracytoplasmic sperm injection (ICSI) using logistic regression model

Background: Intra cytoplasmic sperm injection (ICSI) is a main option in infertile men. Unfortunately, despite of high cost of doing ICSI the rate of success is not acceptable, and failing pregnancy put a heavy anxiety to couples. Recently many research have been done upon various models for classification of IVF (invitro fertilization), ICSI, ET (embryo transfer), but none of these models can predict the success rate of infertility up to 100%. If the predictive method has been used as second supervisor beside embryologist, it can improve the success rate and prevent from unimportant treatment.Methods: This study is aimed to use logistic regression model for predicting the success rate of ICSI. Our database with concluded 345 patients received ICSI treatment, and each of them constructed 54 numerical and nominal records. This database was randomly divided into the estimation (n= 276) and validation (n= 69) data set. The models were used based on binary logistic regression (BLR) feature selection tools.Result: Finally, the model were evaluated using important criteria such as accuracy, sensitivity and specificity. The best output of the BLR model by using 54 variables revealed accuracy (97%) and sensitivity (93%).Conclusion: Our result demonstrated that BLR model outperformed highlighting the great power of BLR in success rate of ICSI prediction while using binary output.

Keywords:

ET , ICSI , Infertility , IVF , Pregnancy , Logistic regression