Multifactor Prediction of Embryo Transfer Outcomes Based on a Machine Learning Algorithm.

Ran Liu,Bo Xu,Ying Wang,Lihua Luo,Xiaohua Jiang,Shun Bai,Shengxia Zheng,Xianhong Tong

doi:10.3389/fendo.2021.745039

Ran Liu, Bo Xu + Show 6 more

Open Access

https://doi.org/10.3389/fendo.2021.745039

Copy DOI

Abstract

In vitro fertilization-embryo transfer (IVF-ET) technology make it possible for infertile couples to conceive a baby successfully. Nevertheless, IVF-ET does not guarantee success. Frozen embryo transfer (FET) is an important supplement to IVF-ET. Many factors are correlated with the outcome of FET which is unpredictable. Machine learning is a field of study that predict various outcomes by defining data attributes and using relevant data and calculation algorithms. Machine learning algorithm has been widely used in clinical research. The present study focuses on making predictions of early pregnancy outcomes in FET through clinical characters, including age, body mass index (BMI), endometrial thickness (EMT) on the day of progesterone treatment, good-quality embryo rate (GQR), and type of infertility (primary or secondary), serum estradiol level (E2) on the day of embryo transfer, and serum progesterone level (P) on the day of embryo transfer. We applied four representative machine learning algorithms, including logistic regression (LR), conditional inference tree, random forest (RF) and support vector machine (SVM) to build prediction models and identify the predictive factors. We found no significant difference among the models in the sensitivity, specificity, positive predictive rate, negative predictive rate or accuracy in predicting the pregnancy outcome of FET. For example, the positive/negative predictive rate of the SVM (gamma = 1, cost = 100, 10-fold cross validation) is 0.56 and 0.55. This approach could provide a reference for couples considering FET. The prediction accuracy of the present study is limited, which suggests that there may be some other more effective predictors to be developed in future work.

Highlights

Frozen embryo transfer (FET) can avoid the occurrence of ovarian hyperstimulation syndrome and avoid the adverse effects of superphysiological estrogen and early elevated progesterone on embryo implantation [1]
There was no significant difference between the two groups regarding some baseline characteristics (e.g., body mass index (BMI), endometrial preparation protocol, number of transferred embryos per transferred cycle, number of good-quality embryos per transferred cycle, type of embryos transferred, serum estradiol level on the day of ET, serum progesterone level on the day of ET and endometrial morphology) except for age, endometrial thickness (EMT), good-quality embryo rate (GQR) and type of infertility
Machine learning algorithms were used to establish four models to predict the pregnancy outcomes of patients preparing for FET with hormone replacement cycles

Summary

Introduction

Frozen embryo transfer (FET) can avoid the occurrence of ovarian hyperstimulation syndrome and avoid the adverse effects of superphysiological estrogen and early elevated progesterone on embryo implantation [1]. It is difficult to predict the success rate objectively during the FET cycle [2]. Identifying factors that can accurately predict the success rate would be clinically significant. A large number of studies have found that endometrial receptivity is one of the main factors affecting the pregnancy outcome. Golbasi et al did not demonstrate any significant relationship between EMT changes and clinical pregnancy rates during FET cycles [7]. The quality of the embryo and maternal age are major factors affecting pregnancy outcomes. Until now, it is still uncertain which factors have the best ability to predict pregnancy outcomes during hormone replacement FET cycles

Methods

Results

Discussion

Conclusion