Current Issue

Volume 11, Number 3, Oct-Dec 2017 Pages: 184-190

Predicting Implantation Outcome of In Vitro Fertilization and Intracytoplasmic Sperm Injection Using Data Mining Techniques


Pegah Hafiz, M.Sc, 1, Mohtaram Nematollahi, Ph.D, 2, *, Reza Boostani, Ph.D, 3, Bahia Namavar Jahromi, M.D, 4, 5,
Department of Medical Informatics, School of Management and Medical Informatics, Shiraz University of Medical Sciences, Shiraz, Iran
Anesthesiology and Critical Care Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
Department of Computer Science and Engineering and Information Technology, School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran
Department of Obstetrics and Gynecology, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran
Infertility Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
*Corresponding Address: P.O.Box: 7187687599 Anesthesiology and Critical Care Research Center Shiraz University of Medical Sci- ences 5thFloor Mohammad Rasool Allah Research Tower Khalili Avenue Shiraz Iran Email:mnemat@sums.ac.ir

Abstract

Background

In vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) are two important subsets of the assisted reproductive techniques, used for the treatment of infertility. Predicting implantation outcome of IVF/ICSI or the chance of pregnancy is essential for infertile couples, since these treatments are complex and expensive with a low probability of conception.

Materials and Methods

In this cross-sectional study, the data of 486 patients were collected using census method. The IVF/ICSI dataset contains 29 variables along with an identifier for each patient that is either negative or positive. Mean accuracy and mean area under the receiver operating characteristic (ROC) curve are calculated for the classifiers. Sensitivity, specificity, positive and negative predictive values, and likelihood ratios of classifiers are employed as indicators of performance. The state-of-art classifiers which are candidates for this study include support vector machines, recursive partitioning (RPART), random forest (RF), adaptive boosting, and one-nearest neighbor.

Results

RF and RPART outperform the other comparable methods. The results revealed the areas under the ROC curve (AUC) as 84.23 and 82.05%, respectively. The importance of IVF/ICSI features was extracted from the output of RPART. Our findings demonstrate that the probability of pregnancy is low for women aged above 38.

Conclusion

Classifiers RF and RPART are better at predicting IVF/ICSI cases compared to other decision makers that were tested in our study. Elicited decision rules of RPART determine useful predictive features of IVF/ICSI. Out of 20 factors, the age of woman, number of developed embryos, and serum estradiol level on the day of human chorionic gonadotropin administration are the three best features for such prediction.