Roles of estradiol levels on the day of human chorionic gonadotrophin administration in the live birth of patients with frozen embryo transfer

Construction of the machine learning-based live birth prediction models for the first in vitro fertilization pregnant women

BACKGROUND

This study was to conduct prediction models based on parameters before and after the first cycle, respectively, to predict live births in women who received fresh or frozen in vitro fertilization (IVF) or intracytoplasmic sperm injection (ICSI) for the first time.

METHODS

This retrospective cohort study population consisted of 1,857 women undergoing the IVF cycle from 2019 to 2021 at Huizhou Municipal Central Hospital. The data between 2019 and 2020 were completely randomly divided into a training set and a validation set (8:2). The data from 2021 was used as the testing set, and the bootstrap validation was carried out by extracting 30% of the data for 200 times on the total data set. In the training set, variables are divided into those before the first cycle and after the first cycle. Then, predictive factors before the first cycle and after the first cycle were screened. Based on the predictive factors, four supervised machine learning algorithms were respectively considered to build the predictive models: logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), and light gradient boosting machine (LGBM). The performances of the prediction models were evaluated by the area under the receiver operator characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy.

RESULTS

Totally, 851 women (45.83%) had a live birth. The LGBM model showed a robust performance in predicting live birth before the first cycle, with AUC being 0.678 [95% confidence interval (CI): 0.651 to 0.706] in the training set, 0.612 (95% CI: 0.553 to 0.670) in the validation set, 0.634 (95% CI: 0.511 to 0.758) in the testing set, and 0.670 (95% CI: 0.626 to 0.715) in the bootstrap validation. The AUC value in the training set, validation set, testing set, and bootstrap of LGBM to predict live birth after the first cycle was 0.841 (95% CI: 0.821 to 0.861), 0.816 (95% CI: 0.773 to 0.859), 0.835 (95% CI: 0.743 to 0.926), and 0.839 (95% CI: 0.806 to 0.871), respectively.

CONCLUSION

The LGBM model based on the predictive factors before and after the first cycle for live birth in women showed a good predictive performance. Therefore, it may assist fertility specialists and patients to adjust the appropriate treatment strategy.

A validated model for individualized prediction of pregnancy outcome in woman after fresh cycle of Day 5 single blastocyst transfer

The association between the embryo quality, clinical characteristics, miRNAs (secreted by blastocysts in the culture medium) and pregnancy outcomes has been well-established. Studies on prediction models for pregnancy outcome, using clinical characteristics and miRNA expression, are limited. We aimed to establish the prediction model for prediction of pregnancy outcome of woman after a fresh cycle of Day 5 single blastocyst transfer (Day 5 SBT) based on clinical data and miRNA expression. A total of 86 women, 50 with successful pregnancy and 36 with pregnancy failure after fresh cycle of Day 5 SBT, were enrolled in this study. All samples were divided into training set and test set (3:1). Based on clinical index statistics of enrolled population and miRNA expression, the prediction model was constructed, followed by validation of the prediction model. Four clinical indicators, female age, sperm DNA fragmentation index, anti-mullerian hormone, estradiol, can be used as independent predictors of pregnancy failure after fresh cycle of Day 5 SBT. Three miRNAs (hsa-miR-199a-3p, hsa-miR-199a-5p and hsa-miR-99a-5p) had a potential diagnostic value for pregnancy failure after Day 5 SBT. The predictive effect of model combining 4 clinical indicators and 3 miRNAs (area under the receiver operating characteristic curve, AUC = 0.853) was better than models combining single 4 clinical indicators (AUC = 0.755) or 3 miRNAs (AUC = 0.713). Based on 4 clinical indicators and 3 miRNAs, a novel model to predict pregnancy outcome in woman after fresh cycle of Day 5 SBT has been developed and validated. The predictive model may be valuable for clinicians to make the optimal clinical decision and patient selection.

Roles of estradiol levels on the day of human chorionic gonadotrophin administration in the live birth of patients with frozen embryo transfer

Background

Estradiol (E₂) is an important hormone in women. Changes of serum E₂ levels may affect the endometrial receptivity for embryo implantation and thus affect pregnancy outcomes. This study was to assess the association between serum E₂ levels on the day of human chorionic gonadotrophin (HCG) administration and live‐birth rates in patients with frozen embryo transfer (FET).

Methods

Totally 2071 women receiving long protocols of long‐acting gonadotropin‐releasing hormone (GnRH) agonists were enrolled. According to the E₂ levels on the day of HCG administration, these patients were divided into four groups: 676 cases of E₂ ≤ 3051 pg/mL in Q₁ group, 676 cases of 3051 pg/mL < E₂ ≤ 4558 pg/mL in Q₂ group, 675 cases of 4558 pg/mL < E₂ ≤ 6718 pg/mL in Q₃ group, and 674 cases of E₂ > 6718 pg/mL in Q₄ group. The clinical indicators including female age, body mass index (BMI), duration of infertility, infertility styles, treatment protocols, hormone levels, total antral follicle count, endometrial thickness, top‐level embryos, and live‐birth rates were analyzed, and multivariable logistic model was conducted to select significant variables.

Results

Significant differences were observed for the female age (OR = 0.965, 95% CI: 0.946‐0.985, P < .001), total antral follicle counts (OR = 1.025, 95% CI: 1.008‐1.043, P = .004), transferring what day of embryos (OR = 1.242, 95% CI: 1.137‐1.356, P < .001), endometrial thickness (OR = 1.058, 95% CI: 1.004‐1.115, P = .035), top‐level embryos (OR = 1.416, 95% CI: 1.157‐1.731, P = .001), and E₂ levels on HCG day >6781 pg/mL (OR = 1.344, 95% CI: 1.069‐1.690, P = .011) between live‐birth and non‐live‐birth groups. The area under the curve (AUC) for E₂ levels on HCG day was 0.558, the sensitivity was 54.75%, and the specificity was 55.10%.

Conclusion

Serum E₂ level on HCG day was an independent predictor of live‐birth achievement in patients with FET.